TranscEngram Research

Generative Structure from Motion with Native 3D Diffusion

Generative Structure from Motion with Native 3D Diffusion

Haobin Duan, Binbin Huang, Mochu Xiang, Yiqun Zhao, Zibo Zhao, Yi Ma, Shenghua Gao

GenSfM uses a few uncalibrated images to estimate camera poses and object shape together. A 3D diffusion model infers surfaces outside the observed views.

GenSfM 从少量未标定图像中联合估计相机位姿和物体形状，并用三维扩散模型推断未观测到的表面。

Information-Theoretic Scaling Laws for Generative Diffusion Training

Druv Pai, Dejan Stancevic, Yi Ma, Luca Ambrogioni

从信息论角度刻画扩散模型对特定训练集的依赖，研究数据规模与样本记忆、生成质量的关系。

Nested Sparsity for Scalable Pretraining and Continual Learning

Tianzhe Chu, Druv Pai, Yi Ma

使注意力计算按输入选择稀疏子结构，研究嵌套稀疏性在模型预训练与持续学习中的作用。

Embodied Playground: A Long-Horizon Agentic Robotics Benchmark for Physical, Strategic, and Spatial Reasoning

Feng Chen, Pei Zhou, Lixuan He, Yunchao Yao, Li Sun, Shenghua Gao, Mingyu Ding, Kaifeng Zhang, Kaichen Zhou, Yi Ma

用 410 个任务环境评估具身智能体跨多个阶段完成操作、推理和规划的能力，并提供统一的任务完成与规则检查。

GazeAct: A Human-Gaze-Annotated Manipulation Dataset for Attention-Regularized Policies

Anupam Pani, Wang Yuan, Qifan Wang, Yanchao Yang

在 40 项真实机器人操作任务中同步记录操作者视线与动作，形成 12,000 条示范，并用视线监督训练视觉语言动作策略。

FlexPart: Text-Controlled Semantics-Aware 3D Part Segmentation at Flexible Granularity

Yiqun Zhao, Jiachen Xu, Yihao Zhi, Yunfei Zhao, Zibo Zhao, Xintong Han, Chunchao Guo, Shenghua Gao

根据文本指定部件和粒度，对三维网格进行语义分割。

Rethinking Routing Exploration in Modern Mixture-of-Experts

Bingcong Li, Hao Ma, Michael Muehlebach, Niao He, Yi Ma

分析共享专家如何影响混合专家模型的路由探索，并研究按输入调节专家选择的方法。

Seeing Both the Forest and the Trees: Reusing Holistic 3D Priors for Part-Decomposed Generation

Yiqun Zhao, Binbin Huang, Haobin Duan, Zibo Zhao, Shenghua Gao

利用整体三维生成先验，同时生成可区分的对象部件，保留对象的整体形状与部件关系。

SPEAR: Selective Preference Elicitation with Adaptive Rewards for VLM-Guided Robotic Manipulation

Zewen Wu, Ruizhe Liu, Pei Zhou, Feng Chen, Yanchao Yang

让视觉语言模型有选择地比较机器人动作，并将偏好反馈用于训练操作策略。

SituHOI: Scalable Capture of Scene-Situated Full-Body Human-Object Interaction

Qifan Wang, Qihang Fang, Boao Shi, Yushi Du, Pei Zhou, Siyan Dong, Yanchao Yang

研究如何规模化采集真实场景中全身人体与物体的交互动作。

ScenePlacer: Reformulating Scene-Level Object Pose Estimation as Visibility Field Learning

Ken Deng, Jiarui Liu, Guibiao Liao, Kunming Luo, Mochu Xiang, Hongyu Yan, Yebin Liu, Shenghua Gao, Yizhou Yu, Ping Tan

学习物体的可见性场，再将生成的三维物体对齐到场景观测中。

From Pixel to Poses: Object-centric Tool Manipulation Learning from Human Demonstrations

Bangjun Wang, Longyan Wu, Yukun Wei, Shenghe Shao, Chaoyi Huang, Wenze Cui, Zetong Xu, Hanlin Wu, Long Chen, Yi Ma, Hongyang Li

从人类示范视频中学习以物体位姿为中心的工具操作策略，降低对成对人机示范数据的依赖。

Scaling Versatile 3D Assets Editing with a Million-Scale Dataset

Badi Li, Tianxin Huang, Yu Zhou, Wei-Shi Zheng, Yi Ma, Shenghua Gao

构建百万规模的三维资产编辑数据集，并提供用于训练和评估多种三维编辑任务的框架。

Uni-VLaT: Whole-Body Tactile Adaptation of VLA Policies for Humanoid Loco-Manipulation

Zihao Wang, Shutong Liu, Siqi Zheng, Liu Cao, Ruoqu Chen, Rundong Liu, Yanchao Yang, Mengdi Xu

将全身分布式触觉输入视觉语言动作策略，以支持人形机器人的移动和接触操作。

SlackDrive: Reclaiming Runtime Slack for Adaptive Driving Inference

Xiaohuan Pei, Hengguang Zhou, Yuanhao Ban, Justin Cui, Jiaqi Feng, Haoyu Xie, Tao Huang, Pichao Wang, Yanchao Yang, Cho-Jui Hsieh

根据车辆计算资源的实时余量调整驾驶模型推理预算，平衡延迟与规划质量。

Grounding Generated Video Plans in Simulation Towards Versatile Dexterous Controllers

Tianyue Wu, Boyuan An, Shuqi Zhao, Heyu Guo, Wanli Xing, Yi Ma, Kaifeng Zhang, Ruihai Wu, Masayoshi Tomizuka

把生成视频中的手与物体运动转为仿真中的可执行参考轨迹，用于训练灵巧控制器。

Mesh BDF: Barycentric Dominance Field for 3D Native Mesh Generation

Gaochao Song, Haohan Weng, Luo Zhang, Zibo Zhao, Shenghua Gao

用重心支配场表示三维形状，支持原生网格生成。

FORGE: Fragment-Oriented Ranking and Generation for Context-Aware Molecular Optimization

Qingchuan Zhang, He Cao, Hao Li, Yanjun Shao, Zhiyuan Liu, Shihang Wang, Shufang Xie, Shenghua Gao, Xinwu Ye

通过分子片段排序与生成，在给定上下文中优化候选分子。

Pushing Biomolecular Utility-Diversity Frontiers with Supergroup Relative Policy Optimization

Xinwu Ye, He CAO, Li Hao, Bin Feng, Zijing Liu, Robert Tang, Yu Li, Shenghua Gao

以强化学习兼顾生成生物分子的功能效用与候选分子多样性。

DeepTutor: Towards Agentic Personalized Tutoring

Bingxi Zhao, Jiahao Zhang, Xubin Ren, Zirui Guo, Tianzhe Chu, Yi Ma, Chao Huang

研究教学智能体如何根据学习者的问题和学习进度提供个性化辅导。

Gaze-Regularized Vision-Language-Action Models for Robotic Manipulation

Anupam Pani, Yanchao Yang

将人的注视区域用于约束视觉语言动作模型的注意力，研究机器人对操作目标的定位。

Hierarchical Action Learning for Weakly-Supervised Action Segmentation

Junxian Huang, Ruichu Cai, Juntao Fang, Hao Zhu, Boyan Xu, Weilin Chen, Zijian Li, Shenghua Gao

用分层动作学习在弱监督条件下划分视频中的动作片段。

LatentChem: From Textual CoT to Latent Thinking in Chemical Reasoning

Xinwu Ye, Yicheng Mao, Yuxuan Liao, Jia Zhang, Yimeng (Yoyo) Liu, Hao Li, Fang Wu, Zhiwei Li, Zehong Wang, Zhiyuan Liu, Zhenfei Yin, Li Yuan, Phil Torr, Huan Sun, xiangxiang Zeng, Mengdi Wang, Le Cong, Shenghua Gao, Robert Tang

将化学推理从文字思维链转移到连续的隐空间。

Coordinated Humanoid Manipulation with Choice Policies

Haozhi Qi, Yen-Jen Wang, Toru Lin, Brent Yi, Yi Ma, Koushil Sreenath, Jitendra Malik

将分模块遥操作采集与候选动作评分结合，学习人形机器人手眼、双臂和行走的全身协调。

COLA: Learning Human-Humanoid Coordination for Collaborative Object Carrying

Yushi Du, Yixuan Li, Baoxiong Jia, Yutang Lin, Pei Zhou, Wei Liang, Yanchao Yang, Siyuan Huang

研究人和人形机器人如何协调步态与施力，共同搬运物体。

CodePlot-CoT: Mathematical Visual Reasoning by Thinking with Code-Driven Images

Chengqi Duan, Kaiyue Sun, Rongyao Fang, Manyuan Zhang, Yan Feng, Ying Luo, Yufang Liu, Ke Wang, Peng Pei, Xunliang Cai, Hongsheng Li, Yi Ma, Xihui Liu

让模型编写代码绘制数学图形，再利用图形推理需要辅助线或函数图像的数学问题。

PROFusion: Robust and Accurate Dense Reconstruction via Camera Pose Regression and Optimization

Siyan Dong, Zijun Wang, Lulu Cai, Yi Ma, Yanchao Yang

结合学习式相机位姿初始化与后续优化，在快速运动或视角大幅变化时进行稠密场景重建。

VB-Com: Learning Vision-Blind Composite Humanoid Locomotion Against Deficient Perception

Junli Ren, Tao Huang, Huayi Wang, Zirui Wang, Qingwei Ben, Junfeng Long, Yanchao Yang, Jiangmiao Pang, Ping Luo

融合视觉与不依赖视觉的运动策略，研究人形机器人在感知受限时如何行走。

AbSpecAlign: Specificity Reward Alignment for Antigen-Conditioned Antibody Generation

Jingbo Zeng, Yang Xiao, Shenghua Gao

研究如何用反映抗原特异性的奖励来指导抗体生成，使生成过程针对给定抗原。

AffordVLA: Implicit Affordance Representation Alignment for Vision-Language-Action Models

Weijie Kong, Yi Ma

将物体可供机器人执行的动作编码为隐式表示，并与视觉、语言和动作模型的表征对齐。

Intelligent Robot Manipulation Requires Self-Directed Learning

Li Chen, Chonghao Sima, Kashyap Chitta, Antonio Loquercio, Ping Luo, Yi Ma, Hongyang Li

讨论机器人如何从自主交互中识别目标、学习操作技能并评估能力，尤其关注缺少显式奖励的场景。

On-Policy Adaptation Mitigates Hyperparameter-Sensitive Forgetting in Vision-Language Models

Doyoon Kim, Ziyang Wu, Jingfeng Yang, Yi Ma

研究视觉语言模型在微调中对超参数敏感的遗忘现象，并检验基于当前策略的适配能否缓解遗忘。

PhenoModel: A multimodal phenotypic drug design foundation model for discovering novel potential inhibitors of multiple cancer cells

Shihang Wang, Qilei Han, Weichen Qin, Lin Wang, Junhong Yuan, Fengyu Cai, Yiqun Zhao, Pengxuan Ren, Yunze Zhang, Yilin Tang, Ruifeng Li, Zongquan Li, Wenchao Zhang, Shenghua Gao, Fang Bai

结合细胞表型和分子信息，筛选针对不同癌细胞的潜在抑制剂。

PSMa: Learning Protein Surface Representations with Physicochemical Masked Autoencoders

Qianyu Chen, Xinyue Ma, Hao Yang, Shenghua Gao, Fang Bai

以理化特征为监督信号，通过掩码自编码学习蛋白质表面表示。

Scaling Optimization-Oriented Hypernetworks for Implicit Neural Representations

Scaling Optimization-Oriented Hypernetworks for Implicit Neural Representations

Lulu Cai, Hanxiang Ren, Siyan Dong, Li Sun, Jiefeng Wu, Youyi Zheng, Yi Ma, Yanchao Yang

An attention-based hypernetwork generates the weights of an implicit neural representation in one forward pass, avoiding per-instance weight fitting at inference.

研究如何扩大优化导向超网络的规模，使网络能够直接生成隐式神经表示模型的参数。

YOCO: You Only Calibrate Once! Fast Mocap Calibration for Dexterous Teleoperation

YOCO: You Only Calibrate Once! Fast Mocap Calibration for Dexterous Teleoperation

Yu Zhang, Yunqi Li, Yushi Du, Yi Ma, Yanchao Yang

用少量配对手部姿态快速校准动捕手套或无标记跟踪器，减少不同操作者、穿戴方式造成的偏差。

Video-Conditioned Generative Joint 2D-3D Hand Motion Recovery

Video-Conditioned Generative Joint 2D-3D Hand Motion Recovery

Chen Xu, Yunqi Li, Binbin Huang, Brent Yi, Shenghua Gao, Yi Ma

从视频直接联合生成对齐的二维和三维手部姿态序列，以处理遮挡和逐帧估计的不连续问题。

SPOON: Towards Coherent Compositional 3D Scene Generation from Uncalibrated Multi-view Images

SPOON: Towards Coherent Compositional 3D Scene Generation from Uncalibrated Multi-view Images

Guibiao Liao, Mochu Xiang, Heng Li, Ken Deng, Zijie Wang, Guanbin Li, Ping Tan, Shenghua Gao, Yizhou Yu

从未经标定的多视图图像生成空间关系一致的组合式三维场景。

TraceFlow: Guiding Frozen Flow-Matching Robot Policies with Success and Failure Traces

TraceFlow: Guiding Frozen Flow-Matching Robot Policies with Success and Failure Traces

Jiaxuan Zhang, Ruizhe Liu, Yu Zhang, Yanchao Yang

从成功和失败的机器人执行记录提取引导信号，在推理时调整已有策略的动作。

The Imitator Game: Benchmarking Robot Imitative Ability Beyond Action Prediction

The Imitator Game: Benchmarking Robot Imitative Ability Beyond Action Prediction

Xunzhe Zhou, Yiyang Cai, Fengyi Wang, Ran Ju, Hanxiang Ren, Ruizhe Liu, Yu Zhang, Qian Luo, Feng Chen, Pei Zhou, Yi Ma, Yanchao Yang

用人类示范视频测试机器人能否理解示范意图，并在工具、物体或布局发生变化时完成任务。

DexVerse: A Modular Benchmark for Multi-Task, Multi-Embodiment Dexterous Manipulation

DexVerse: A Modular Benchmark for Multi-Task, Multi-Embodiment Dexterous Manipulation

Yunchao Yao, Zhuxiu Xu, Tianqi Zhang, Zixian Liu, Sikai Li, Zhenyu Wei, Feng Chen, Dihong Huang, Kechang Wan, Chenyang Ma, Shuqi Zhao, Shenghua Gao, Masayoshi Tomizuka, Yi Ma, Mingyu Ding

建立模块化灵巧操作基准，比较策略在多种任务、传感条件和机器人硬件之间的泛化能力。

GeoMoLa: Geometry-Aware Motion Latents for Learning Robust Manipulation Policies

GeoMoLa: Geometry-Aware Motion Latents for Learning Robust Manipulation Policies

Yunchao Zhang, Yijia Weng, Ruizhe Liu, Ming Hu, Leonidas Guibas, Yanchao Yang

从运动中学习反映物体几何关系的隐表示，用来训练更稳健的机器人操作策略。

Pointer-CAD v2: Plan-Then-Construct CAD Generation with Dimension-Aware Parametric Precision

Pointer-CAD v2: Plan-Then-Construct CAD Generation with Dimension-Aware Parametric Precision

Dacheng Qi, Chenyu Wang, Jingwei Xu, Yi Ma, Shenghua Gao

将 CAD 生成分为先规划、再构造两个阶段，重点评估几何参数及物理尺寸的准确性。

RoboLineage: Agent-Native Data Lifecycle Governance Across Robot Policy Iterations

RoboLineage: Agent-Native Data Lifecycle Governance Across Robot Policy Iterations

Qian Luo, Wentao Guo, Zhennan Qin, Nanchun Guo, Yunhan Zhao, Yi Ma, Yanchao Yang

追踪机器人策略迭代中的数据采集、审核、训练与评估记录，使部署和下一轮采集决策可追溯。

Geometric Entropy: When Trajectory Diversity Helps and Hurts in Imitation Learning

Geometric Entropy: When Trajectory Diversity Helps and Hurts in Imitation Learning

Qian Luo, Ruizhe Liu, Pei Zhou, Xunzhe Zhou, Yanchao Yang

提出轨迹几何熵指标，分析模仿学习中示范轨迹多样性与任务表现的关系。

Tri-Info: Generalizable, Interpretable Failure Prediction for VLA Models via Information Theory

Tri-Info: Generalizable, Interpretable Failure Prediction for VLA Models via Information Theory

Jinghan Yang, Yunchao Zhang, Wang Yuan, Haolun Wan, Jiaming Zhang, Zhengyang Hu, Yanchao Yang

利用信息论指标预测视觉语言动作模型何时可能失败，并分析预测依据。

InfoAtlas: A Foundation Model for Zero-Shot Statistical Dependence Estimate

InfoAtlas: A Foundation Model for Zero-Shot Statistical Dependence Estimate

Zhengyang Hu, Yanzhi Chen, Hanxiang Ren, Qunsong Zeng, Youyi Zheng, Adrian Weller, Kaibin Huang, Yanchao Yang

在合成数据上预训练模型，以零样本方式估计新数据中变量之间的统计依赖。

Beyond 3D VQAs: Injecting 3D Spatial Priors into Vision-Language Models for Enhanced Geometric Reasoning

Beyond 3D VQAs: Injecting 3D Spatial Priors into Vision-Language Models for Enhanced Geometric Reasoning

Chun-Hsiao Yeh, Shengyi Qian, Manchen Wang, Yi Ma, Joseph Tighe, Fanyi Xiao

把三维几何先验引入视觉语言模型，研究模型如何推理物体的位置和空间关系。

DISC: Decoupling Instruction from State-Conditioned Control via Policy Generation

DISC: Decoupling Instruction from State-Conditioned Control via Policy Generation

Hanxiang Ren, Pei Zhou, Xunzhe Zhou, Yanchao Yang

A hypernetwork turns a language instruction into a task-specific control policy. The resulting policy uses observations to choose the robot’s actions.

用语言指令生成任务专用策略，使机器人在执行时根据当前状态控制动作。

DexHoldem: An Agentic Robotics Benchmark for Dexterous Manipulation in Texas Hold'em

DexHoldem: An Agentic Robotics Benchmark for Dexterous Manipulation in Texas Hold'em

Feng Chen, Tianzhe Chu, Li Sun, Pei Zhou, Zhuxiu Xu, Shenghua Gao, Yuexiang Zhai, Yanchao Yang, Yi Ma

以真实灵巧手执行德州扑克任务，评估机器人在多轮游戏中的视觉感知、策略判断和精细操作。

OpenSearch-VL: An Open Recipe for Frontier Multimodal Search Agents

OpenSearch-VL: An Open Recipe for Frontier Multimodal Search Agents

Shuang Chen, Kaituo Feng, Hangting Chen, Wenxuan Huang, Dasen Dai, Quanxin Shou, Yunlong lin, Xiangyu Yue, Shenghua Gao, Tianyu Pang

公开训练多模态搜索智能体的方法，使模型能结合视觉信息开展检索。

Gaze-Regularized VLMs for Ego-Centric Behavior Understanding

Gaze-Regularized VLMs for Ego-Centric Behavior Understanding

Anupam Pani, Yanchao Yang

在训练时引入眼动注视信号，研究视觉语言模型如何从第一视角视频预测人的后续动作。

Pointer-CAD: Unifying B-Rep and Command Sequences via Pointer-based Edges & Faces Selection

Pointer-CAD: Unifying B-Rep and Command Sequences via Pointer-based Edges & Faces Selection

Dacheng Qi, Chenyu Wang, Jingwei Xu, Tianzhe Chu, Zibo Zhao, Wen Liu, Wenrui Ding, Yi Ma, Shenghua Gao

通过指针机制选择边和面，将 CAD 边界表示与建模命令序列统一起来。

Flow Policy Gradients for Robot Control

Flow Policy Gradients for Robot Control

Brent Yi, Hongsuk Choi, Himanshu Gaurav Singh, Xiaoyu Huang, Takara E. Truong, Carmelo Sferrazza, Yi Ma, Rocky Duan, Pieter Abbeel, Guanya Shi, Karen Liu, Angjoo Kanazawa

研究如何利用策略梯度训练基于流模型的连续控制策略，并在机器人控制任务上评估。

CUPID: Generative 3D Reconstruction via Joint Object and Pose Modeling

CUPID: Generative 3D Reconstruction via Joint Object and Pose Modeling

Binbin Huang, Haobin Duan, Yiqun Zhao, Zibo Zhao, Yi Ma, Shenghua Gao

From a single image, CUPID jointly estimates an object’s geometry, texture and camera pose, keeping the reconstructed object aligned with the input view.

联合建模物体三维形状与相机姿态，再利用与像素对齐的图像特征细化重建结果。

SRUM: Fine-Grained Self-Rewarding for Unified Multimodal Models

SRUM: Fine-Grained Self-Rewarding for Unified Multimodal Models

Weiyang Jin, Yuwei Niu, Jiaqi Liao, Chengqi Duan, Aoxue Li, Shenghua Gao, Xihui Liu

为统一多模态模型提供细粒度自奖励信号。

Viser: Imperative, Web-based 3D Visualization for Python

Viser: Imperative, Web-based 3D Visualization for Python

Brent Yi, Chung Min Kim, Justin Kerr, Gina Wu, Rebecca Feng, Anthony Zhang, Jonas Kulhanek, Hongsuk Choi, Yi Ma, Matthew Tancik, Angjoo Kanazawa

面向机器人和计算机视觉的 Python 三维可视化工具，支持在浏览器中交互展示三维场景。

LongSplat: Online Generalizable 3D Gaussian Splatting from Long Sequence Images

LongSplat: Online Generalizable 3D Gaussian Splatting from Long Sequence Images

Guichen Huang, Ruoyu Wang, Xiangjun Gao, Che Sun, Yuwei Wu, Shenghua Gao, Yunde Jia

从长序列图像在线生成可泛化的三维高斯场景表示。

Beyond Simple Edits: X-Planner for Complex Instruction-Based Image Editing

Beyond Simple Edits: X-Planner for Complex Instruction-Based Image Editing

Chun-Hsiao Yeh, Yilin Wang, Nanxuan Zhao, Richard Zhang, Yuheng Li, Yi Ma, Krishna Kumar Singh

利用多模态语言模型将复杂或间接的图像编辑指令拆成可执行的编辑步骤。

Topology-Preserved Auto-regressive Mesh Generation in the Manner of Weaving Silk

Topology-Preserved Auto-regressive Mesh Generation in the Manner of Weaving Silk

Gaochao Song, Zibo Zhao, Haohan Weng, Jingbo Zeng, Rongfei Jia, Shenghua Gao

以自回归方式生成三维网格，并在生成过程中保持拓扑结构。

Seeing from Another Perspective: Evaluating Multi-View Understanding in MLLMs

Seeing from Another Perspective: Evaluating Multi-View Understanding in MLLMs

Chun-Hsiao Yeh, Chenyu Wang, Shengbang Tong, Ta Ying Cheng, Ruoyu Wang, Tianzhe Chu, Yuexiang Zhai, Yubei Chen, Shenghua Gao, Yi Ma

评估多模态大模型能否在多个视角之间匹配同一对象，并保持对场景几何关系的一致理解。

Breaking the Curse of Dimensionality: Diffusion Models Efficiently Learn Low-Dimensional Distributions

Breaking the Curse of Dimensionality: Diffusion Models Efficiently Learn Low-Dimensional Distributions

Peng Wang, Huijie Zhang, Zekai Zhang, Siyi Chen, Yi Ma, Qing Qu

在低秩高斯混合模型下，将扩散模型训练与子空间聚类联系起来，分析学习低维分布所需的样本量。

GAUSS: Benchmarking Structured Mathematical Skills for Large Language Models

Yue Zhang, Jiaxin Zhang, Qiuyu Ren, Tahsin Saffat, Xiaoxuan Liu, Zitong Yang, Banghua Zhu, Yi Ma

将数学能力拆成十二个维度，评测大语言模型在知识理解、问题求解、表达与创造等方面的表现。

SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training

Tianzhe Chu, Yuexiang Zhai, Jihan Yang, Shengbang Tong, Saining Xie, Dale Schuurmans, Quoc V. Le, Sergey Levine, Yi Ma

通过算术卡牌和导航任务比较监督微调与强化学习对规则变化、视觉变化的适应能力。

From Simple to Complex Skills: The Case of In-Hand Object Reorientation

Haozhi Qi, Brent Yi, Mike Lambeta, Yi Ma, Roberto Calandra, Jitendra Malik

以已训练的基础技能作为分层策略的组成部分，学习在手中将物体转到目标朝向。

Implementing batch normalization-like algorithm with a single spintronic neuron

Zhuo Xu, Yue Xin, Zhengping Yuan, Kang Zhou, Yumeng Yang, Shenghua Gao, Zhifeng Zhu

用单个自旋电子神经元实现类批量归一化，通过脉冲宽度和磁各向异性调节激活函数。

Diffusion Models Learn Low-Dimensional Distributions VIA Subspace Clustering

Peng Wang, Huijie Zhang, Zekai Zhang, Siyi Chen, Yi Ma, Qing Qu

以子空间聚类解释扩散模型从具有低维结构的数据中学习分布的过程。

Flexible protein-ligand docking with diffusion-based side-chain packing

Runze Zhang, Xinyu Jiang, Duanhua Cao, Zhaokun Wang, Jie Yu, Mingan Chen, Zhehuan Fan, Xiangtai Kong, Jiacheng Xiong, Zimei Zhang, Wei Zhang, Shengkun Ni, Yitian Wang, Minda Liao, Shenghua Gao, Sulin Zhang, Mingyue Zheng

通过扩散模型预测氨基酸侧链构象，处理蛋白质与配体对接时的柔性。

Improving Neuron-level Interpretability with White-box Language Models

Hao Bai, Yi Ma

在白盒语言模型中研究单个神经元的可解释性，分析其激活与模型行为之间的联系。

Hyper-GoalNet: Goal-Conditioned Manipulation Policy Learning with HyperNetworks

Hyper-GoalNet: Goal-Conditioned Manipulation Policy Learning with HyperNetworks

Pei Zhou, Wanting Yao, Qian Luo, Xunzhe Zhou, Yanchao Yang

在给定任务目标的条件下，用超网络生成机器人操作策略。

GenDexHand: Generative Simulation for Dexterous Hands

GenDexHand: Generative Simulation for Dexterous Hands

Feng Chen, Zhuxiu Xu, Tianzhe Chu, Xunzhe Zhou, Li Sun, Zewen Wu, Shenghua Gao, Zhongyu Li, Yanchao Yang, Yi Ma

构建生成式灵巧手仿真流程，结合任务分解和运动规划，生成可执行的任务及示范轨迹。

Gaze-VLM: Bridging Gaze and VLMs through Attention Regularization for Egocentric Understanding

Gaze-VLM: Bridging Gaze and VLMs through Attention Regularization for Egocentric Understanding

Anupam Pani, Yanchao Yang

用人的注视位置约束模型注意力，从第一视角视频预测事件并理解人的行为。

HiMaCon: Discovering Hierarchical Manipulation Concepts from Unlabeled Multi-Modal Data

HiMaCon: Discovering Hierarchical Manipulation Concepts from Unlabeled Multi-Modal Data

Ruizhe Liu, Pei Zhou, Qian Luo, Li Sun, Jun Cen, Yibing Song, Yanchao Yang

从无标注多模态示范中发现分层的机器人操作概念。

HyperTASR: Hypernetwork-Driven Task-Aware Scene Representations for Robust Manipulation

HyperTASR: Hypernetwork-Driven Task-Aware Scene Representations for Robust Manipulation

Li Sun, Jiefeng Wu, Feng Chen, Ruizhe Liu, Yanchao Yang

让超网络根据任务和执行阶段调整场景表示，帮助机器人关注当前操作所需的信息。

On the Edge of Memorization in Diffusion Models

On the Edge of Memorization in Diffusion Models

Sam Buchanan, Druv Pai, Yi Ma, Valentin De Bortoli

区分扩散模型复现训练样本与生成新样本的条件，研究记忆与泛化之间的边界。

Cameras as Relative Positional Encoding

Cameras as Relative Positional Encoding

Ruilong Li, Brent Yi, Junchen Liu, Hang Gao, Yi Ma, Angjoo Kanazawa

将相机内外参与相对位姿引入多视角 Transformer，并比较不同几何位置编码方案。

Attention-Only Transformers via Unrolled Subspace Denoising

Attention-Only Transformers via Unrolled Subspace Denoising

Peng Wang, Yifu Lu, Yaodong Yu, Druv Pai, Qing Qu, Yi Ma

从低维子空间去噪的迭代过程推导仅含注意力的 Transformer，分析其结构为何能学习表征。

Language-Image Alignment with Fixed Text Encoders

Language-Image Alignment with Fixed Text Encoders

Jingfeng Yang, Ziyang Wu, Yue Zhao, Yi Ma

固定预训练语言模型的文本编码器，仅训练图像编码器来学习图文对齐。

HuMoCon: Concept Discovery for Human Motion Understanding

HuMoCon: Concept Discovery for Human Motion Understanding

Qihang Fang, Chengcheng Tang, Bugra Tekin, Shugao Ma, Yanchao Yang

从人体运动数据中发现可用于理解动作的概念。

Recollection from Pensieve: Novel View Synthesis via Learning from Uncalibrated Videos

Recollection from Pensieve: Novel View Synthesis via Learning from Uncalibrated Videos

Ruoyu Wang, Yi Ma, Shenghua Gao

直接从未标定的视频或多视角图像中自监督学习，使模型能够合成新的观察视角。

PyRoki: A Modular Toolkit for Robot Kinematic Optimization

PyRoki: A Modular Toolkit for Robot Kinematic Optimization

Chung Min Kim, Brent Yi, Hongsuk Choi, Yi Ma, Ken Goldberg, Angjoo Kanazawa

用模块化 Python 工具描述姿态、速度、避碰等优化目标，并求解机器人运动学问题。

Simplifying DINO via Coding Rate Regularization

Simplifying DINO via Coding Rate Regularization

Ziyang Wu, Jingyuan Zhang, Druv Pai, Xudong Wang, Chandan Singh, Jianwei Yang, Jianfeng Gao, Yi Ma

A coding-rate regularizer helps prevent collapse when training vision models with self-distillation, simplifying the DINO training procedure.

将编码率正则化引入 DINO 自监督视觉训练，研究如何控制表征坍缩并简化训练流程。

Multi-Sensor Object Anomaly Detection: Unifying Appearance, Geometry, and Internal Properties

Multi-Sensor Object Anomaly Detection: Unifying Appearance, Geometry, and Internal Properties

Wenqiao Li, Bozhong Zheng, Xiaohao Xu, Jinye Gan, Fading Lu, Xiang Li, Na Ni, Zheng Tian, Xiaonan Huang, Shenghua Gao, Yingna Wu

融合多种传感器观测，利用外观、几何与内部属性检测物体异常。

FreeSplatter: Pose-free Gaussian Splatting for Sparse-view 3D Reconstruction

FreeSplatter: Pose-free Gaussian Splatting for Sparse-view 3D Reconstruction

Jiale Xu, Shenghua Gao, Ying Shan

从稀疏视图重建三维场景，无需预先给定相机位姿。

SLAM3R: Real-Time Dense Scene Reconstruction from Monocular RGB Videos

SLAM3R: Real-Time Dense Scene Reconstruction from Monocular RGB Videos

Yuzheng Liu, Siyan Dong, Shuzhe Wang, Yingda Yin, Yanchao Yang, Qingnan Fan, Baoquan Chen

由单目彩色视频实时重建稠密三维场景。

Reloc3r: Large-Scale Training of Relative Camera Pose Regression for Generalizable, Fast, and Accurate Visual Localization

Reloc3r: Large-Scale Training of Relative Camera Pose Regression for Generalizable, Fast, and Accurate Visual Localization

Siyan Dong, Shuzhe Wang, Shaohui Liu, Lulu Cai, Qingnan Fan, Juho Kannala, Yanchao Yang

用大规模图像对训练相对相机位姿回归模型，支持跨场景视觉定位。

Scaling Mesh Generation via Compressive Tokenization

Scaling Mesh Generation via Compressive Tokenization

Haohan Weng, Zibo Zhao, Biwen Lei, Xianghui Yang, Jian Liu, Zeqiang Lai, Zhuo Chen, Yuhong Liu, Jie Jiang, Chunchao Guo, Tong Zhang, Shenghua Gao, C. L. Philip Chen

用压缩式词元表示提高三维网格生成的可扩展性。

Surfel-Based Gaussian Inverse Rendering for Fast and Relightable Dynamic Human Reconstruction From Monocular Videos

Surfel-Based Gaussian Inverse Rendering for Fast and Relightable Dynamic Human Reconstruction From Monocular Videos

Yiqun Zhao, Chenming Wu, Binbin Huang, Yihao Zhi, Chen Zhao, Jingdong Wang, Shenghua Gao

从单目视频重建动态人体，并支持通过高斯逆渲染调整照明。

InfoGS: Efficient Structure-Aware 3D Gaussians via Lightweight Information Shaping

InfoGS: Efficient Structure-Aware 3D Gaussians via Lightweight Information Shaping

Yunchao Zhang, Guandao Yang, Leonidas Guibas, Yanchao Yang

通过信息约束使三维高斯表示反映场景结构。

3D StreetUnveiler with Semantic-aware 2DGS - a simple baseline

3D StreetUnveiler with Semantic-aware 2DGS - a simple baseline

Jingwei Xu, Yikai Wang, Yiqun Zhao, Yanwei Fu, Shenghua Gao

用带语义信息的二维高斯泼溅表示和重建街景。

HERA: Hybrid Explicit Representation for Ultra-Realistic Head Avatars

HERA: Hybrid Explicit Representation for Ultra-Realistic Head Avatars

Hongrui Cai, Yuting Xiao, Xuan Wang, Jiafei Li, Yudong Guo, Yanbo Fan, Shenghua Gao, Juyong Zhang

用混合显式三维表示构建逼真的数字人头部化身。

MLLM-Tool: A Multimodal Large Language Model for Tool Agent Learning

MLLM-Tool: A Multimodal Large Language Model for Tool Agent Learning

Chenyu Wang, Weixin Luo, Sixun Dong, Xiaohua Xuan, Zhengxin Li, Lin Ma, Shenghua Gao

通过多模态大语言模型学习调用工具。

Pseudo-Plane Regularized Signed Distance Field for Neural Indoor Scene Reconstruction

Pseudo-Plane Regularized Signed Distance Field for Neural Indoor Scene Reconstruction

Jing Li, Jinpeng Yu, Ruoyu Wang, Shenghua Gao

用伪平面约束符号距离场，重建室内场景几何。

AutoCGP: Closed-Loop Concept-Guided Policies from Unlabeled Demonstrations

AutoCGP: Closed-Loop Concept-Guided Policies from Unlabeled Demonstrations

Pei Zhou, Ruizhe Liu, Qian Luo, Fan Wang, Yibing Song, Yanchao Yang

从无标注示范中发现操作概念，并用这些概念训练闭环机器人操作策略。

Estimating Body and Hand Motion in an Ego-sensed World

Estimating Body and Hand Motion in an Ego-sensed World

Brent Yi, Vickie Ye, Maya Zheng, Yunqi Li, Lea Müller, Georgios Pavlakos, Yi Ma, Jitendra Malik, Angjoo Kanazawa

利用穿戴式第一视角传感数据，估计人在真实场景中的身体和手部运动。

Gen4Gen: Generative Data Pipeline for Generative Multi-Concept Composition

Gen4Gen: Generative Data Pipeline for Generative Multi-Concept Composition

Chun-Hsiao Yeh, Ta Ying Cheng, He-Yen Hsieh, David Chuan-En Lin, Yi Ma, Andrew Markham, Niki Trigoni, H. T. Kung, Yubei Chen

生成多概念组合的训练数据，研究图像生成模型如何在同一场景中呈现多个指定概念。

HyPoGen: Optimization-Biased Hypernetworks for Generalizable Policy Generation

HyPoGen: Optimization-Biased Hypernetworks for Generalizable Policy Generation

Hanxiang Ren, Li Sun, Xulong Wang, Pei Zhou, Zewen Wu, Siyan Dong, Difan Zou, Youyi Zheng, Yanchao Yang

研究如何把优化偏好写入超网络，以生成可迁移的操作策略。

Intra- and Cross-View Enhancement for OCTA Imaging

Intra- and Cross-View Enhancement for OCTA Imaging

Jingbo Zeng, Bingyao Tan, Zaiwang Gu, Shenghua Gao, Leopold Schmetterer, Jun Cheng

结合视图内与跨视图信息增强光学相干断层血管成像。

NesT-NABind: a Nested Transformer for Nucleic Acid-Binding Site Prediction on Protein Surface

NesT-NABind: a Nested Transformer for Nucleic Acid-Binding Site Prediction on Protein Surface

Xinyue Ma, Fenglei Li, Qianyu Chen, Shenghua Gao, Fang Bai

用嵌套 Transformer 预测蛋白质表面的核酸结合位点。

Token Statistics Transformer: Linear-Time Attention via Variational Rate Reduction

Token Statistics Transformer: Linear-Time Attention via Variational Rate Reduction

Ziyang Wu, Tianjiao Ding, Yifu Lu, Druv Pai, Jingyuan Zhang, Weida Wang, Yaodong Yu, Yi Ma, Benjamin Haeffele

The attention mechanism uses token statistics to keep attention cost linear as the sequence grows.

从变分编码率约减推导基于词元统计量的注意力机制，将计算量降至随序列长度线性增长。

CigTime: Corrective Instruction Generation Through Inverse Motion Editing

Qihang Fang, Chengcheng Tang, Bugra Tekin, Yanchao Yang

通过逆向编辑人体动作生成纠正指令，描述如何修正既有动作。

On the Evaluation of Generative Robotic Simulations

Feng Chen, Botian Xu, Pu Hua, Peiqi Duan, Yanchao Yang, Yi Ma, Huazhe Xu

研究如何评估生成式方法构建的机器人仿真任务。

Space-time 2D Gaussian Splatting for Accurate Surface Reconstruction under Complex Dynamic Scenes

Shuo Wang, Binbin Huang, Ruoyu Wang, Shenghua Gao

用时空二维高斯泼溅重建复杂动态场景的表面。

Closed-Loop Visuomotor Control with Generative Expectation for Robotic Manipulation

Qingwen Bu, Jia Zeng, Li Chen, Yanchao Yang, Guyue Zhou, Junchi Yan, Ping Luo, Heming Cui, Yi Ma, Hongyang Li

让机器人比较预期与实际观察，闭环调整长时程操作动作。

GeoFormer: Learning Point Cloud Completion with Tri-Plane Integrated Transformer

Jinpeng Yu, Binbin Huang, Yuxuan Zhang, Huaxia Li, Xu Tang, Shenghua Gao

用整合三平面表示的 Transformer 补全三维点云。

MaxMI: A Maximal Mutual Information Criterion for Manipulation Concept Discovery

Pei Zhou, Yanchao Yang

以最大互信息为标准从未标注示范中发现关键操作状态。

DISCO: Embodied Navigation and Interaction via Differentiable Scene Semantics and Dual-Level Control

Xinyu Xu, Shengcheng Luo, Yanchao Yang, Yong-Lu Li, Cewu Lu

利用可微场景语义与双层控制，研究具身智能体的导航和交互。

MeshSegmenter: Zero-Shot Mesh Semantic Segmentation via Texture Synthesis

Ziming Zhong, Yanyu Xu, Jing Li, Jiale Xu, Zhengxin Li, Chaohui Yu, Shenghua Gao

通过纹理合成，对三维网格做零样本语义分割。

InfoNorm: Mutual Information Shaping of Normals for Sparse-View Reconstruction

Xulong Wang, Siyan Dong, Youyi Zheng, Yanchao Yang

用互信息约束表面法向，研究稀疏视角条件下的三维重建。

SG-NeRF: Neural Surface Reconstruction with Scene Graph Optimization

Yiyang Chen, Siyan Dong, Xulong Wang, Lulu Cai, Youyi Zheng, Yanchao Yang

将场景图优化与神经表面重建结合，恢复多视角图像中的场景几何。

FCA-RAC: First Cycle Annotated Repetitive Action Counting

Jiada Lu, WeiWei Zhou, Xiang Qian, Dongze Lian, Yanyu Xu, Weifeng Wang, Lina Cao, Shenghua Gao

利用第一个动作周期的标注，统计视频中的重复动作。

InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models

Jiale Xu, Weihao Cheng, Yiming Gao, Xintao Wang, Shenghua Gao, Ying Shan

从单张图像通过稀疏视图重建模型生成三维网格。

InfoCon: Concept Discovery with Generative and Discriminative Informativeness

Ruizhe Liu, Qian Luo, Yanchao Yang

基于操作概念对物理状态的生成和判别能力，从示范中自动发现技能结构。

BID: Boundary-Interior Decoding for Unsupervised Temporal Action Localization Pre-Trainin

Qihang Fang, Chengcheng Tang, Shugao Ma, Yanchao Yang

从无标注骨骼运动序列学习动作内部结构与时间边界，用于动作定位。

InfoNet: Neural Estimation of Mutual Information without Test-Time Optimization

Zhengyang Hu, Song Kang, Qunsong Zeng, Kaibin Huang, Yanchao Yang

训练神经网络在测试时直接估计变量间互信息。

Revisit Human-Scene Interaction via Space Occupancy

Xinpeng Liu, Haowen Hou, Yanchao Yang, Yong-Lu Li, Cewu Lu

通过空间占用关系描述人体与周围场景的交互。

Towards Scalable 3D Anomaly Detection and Localization: A Benchmark via 3D Anomaly Synthesis and A Self-Supervised Learning Network

Wenqiao Li, Xiaohao Xu, Yao Gu, Bozhong Zheng, Shenghua Gao, Yingna Wu

通过合成三维异常建立数据基准，训练自监督异常检测与定位网络。

TSP-Transformer: Task-Specific Prompts Boosted Transformer for Holistic Scene Understanding

Shuo Wang, Jing Li, Zibo Zhao, Dongze Lian, Binbin Huang, Xiaomei Wang, Zhengxin Li, Shenghua Gao

为不同任务设计提示，联合理解场景的多种视觉属性。

RoomDesigner: Encoding Anchor-latents for Style-consistent and Shape-compatible Indoor Scene Generation

Yiqun Zhao, Zibo Zhao, Jing Li, Sixun Dong, Shenghua Gao

用锚点潜变量生成风格一致、形状相容的室内布局。

Text2Reward: Reward Shaping with Language Models for Reinforcement Learning

Tianbao Xie, Siheng Zhao, Chen Henry Wu, Yitao Liu, Qian Luo, Victor Zhong, Yanchao Yang, Tao Yu

让语言模型为强化学习任务生成稠密奖励函数。

DebSDF: Delving Into the Details and Bias of Neural Indoor Scene Reconstruction

Yuting Xiao, Jingwei Xu, Zehao Yu, Shenghua Gao

分析神经隐式方法在室内几何细节重建中的偏差。

High-Level Feature Guided Decoding for Semantic Segmentation

Ye Huang, Di Kang, Shenghua Gao, Wen Li, Lixin Duan

用高层语义特征引导分割模型的解码。

Anatomical Prior and Inter-Slice Consistency for Semi-Supervised Vertebral Structure Detection in 3D Ultrasound Volume

Hongye Zeng, Kang Zhou, Songhan Ge, Yuchong Gao, Jianhao Zhao, Shenghua Gao, Rui Zheng

结合解剖先验和切片间一致性，在三维超声中半监督检测脊椎结构。

Closed-Loop Transcription via Convolutional Sparse Coding

Xili Dai, Ke Chen, Shengbang Tong, Jingyuan Zhang, Xingjian Gao, Mingyang Li, Druv Pai, Yuexiang Zhai, Xiaojun Yuan, Heung-Yeung Shum, Lionel M. Ni, Yi Ma

通过卷积稀疏编码实现闭环表征转录。

Ctrl123: Consistent Novel View Synthesis via Closed-Loop Transcription

Hongxiang Zhao, Xili Dai, Jianan Wang, Shengbang Tong, Jingyuan Zhang, Weida Wang, Lei Zhang, Yi Ma

通过闭环转录合成与已有观察一致的新视角图像。

Differentially Private Representation Learning via Image Captioning

Tom Sander, Yaodong Yu, Maziar Sanjabi, Alain Oliviero Durmus, Yi Ma, Kamalika Chaudhuri, Chuan Guo

借助图像描述任务学习满足差分隐私要求的表征。

Emergence of Segmentation with Minimalistic White-Box Transformers

Yaodong Yu, Tianzhe Chu, Shengbang Tong, Ziyang Wu, Druv Pai, Sam Buchanan, Yi Ma

研究极简白盒 Transformer 如何自发形成图像分割能力。

Feature Re-Representation and Reliable Pseudo Label Retraining for Cross-Domain Semantic Segmentation

Jing Li, Kang Zhou, Shenhan Qian, Wen Li, Lixin Duan, Shenghua Gao

通过特征重表示与可靠伪标签再训练，改善跨域语义分割。

Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning

Simon Zhai, Hao Bai, Zipeng Lin, Jiayi Pan, Peter Tong, Yifei Zhou, Alane Suhr, Saining Xie, Yann LeCun, Yi Ma, Sergey Levine

以强化学习微调大型视觉语言模型，使其能够作出行动决策。

HeroMaker: Human-centric Video Editing with Motion Priors

Shiyu Liu, Zibo Zhao, Yihao Zhi, Yiqun Zhao, Binbin Huang, Shuo Wang, Ruoyu Wang, Michael Xuan, Zhengxin Li, Shenghua Gao

利用运动先验编辑以人为主体的视频。

Image Clustering via the Principle of Rate Reduction in the Age of Pretrained Models

Tianzhe Chu, Shengbang Tong, Tianjiao Ding, Xili Dai, Benjamin David Haeffele, René Vidal, Yi Ma

在预训练模型的表征上应用编码率约减原理进行图像聚类。

Insight: A Multi-modal Diagnostic Pipeline Using LLMs for Ocular Surface Disease Diagnosis

Chun-Hsiao Yeh, Jiayun Wang, Andrew D. Graham, Andrea J. Liu, Bo Tan, Yubei Chen, Yi Ma, Meng C. Lin

结合多模态信息和大语言模型，构建眼表疾病诊断流程。

Investigating the Catastrophic Forgetting in Multimodal Large Language Model Fine-Tuning

Yuexiang Zhai, Shengbang Tong, Xiao Li, Mu Cai, Qing Qu, Yong Jae Lee, Yi Ma

研究多模态大语言模型在微调过程中遗忘原有能力的问题。

Learning a Diffusion Model Policy from Rewards via Q-Score Matching

Michael Psenka, Alejandro Escontrela, Pieter Abbeel, Yi Ma

通过 Q 分数匹配，从奖励信号学习基于扩散模型的策略。

Lessons from Learning to Spin "Pens"

Jun Wang, Ying Yuan, Haichuan Che, Haozhi Qi, Yi Ma, Jitendra Malik, Xiaolong Wang

研究机器人如何学习转笔，以及这类灵巧操作的学习难点。

Masked Completion via Structured Diffusion with White-Box Transformers

Druv Pai, Sam Buchanan, Ziyang Wu, Yaodong Yu, Yi Ma

用白盒 Transformer 和结构化扩散模型补全被遮蔽的内容。

OLAT Gaussians for Generic Relightable Appearance Acquisition

Zhiyi Kuang, Yanchao Yang, Siyan Dong, Jiayue Ma, Hongbo Fu, Youyi Zheng

用三维高斯表示单灯照明下采集的物体外观，以支持重新打光。

Point As Gaussian: Forward Point Cloud Rendering

Zibo Zhao, Wen Liu, Xin Chen, Xianfang Zeng, Shiyu Liu, Gang Yu, Shenghua Gao

把点表示为高斯分布，减少前向点云渲染中的孔洞与模糊。

Representation Learning via Manifold Flattening and Reconstruction

Michael Psenka, Druv Pai, Vishal Raman, Shankar Sastry, Yi Ma

通过展平并重建数据流形学习表征。

RLIF: Interactive Imitation Learning as Reinforcement Learning

Jianlan Luo, Perry Dong, Yuexiang Zhai, Yi Ma, Sergey Levine

将交互式模仿学习表述为强化学习问题。

ViP: A Differentially Private Foundation Model for Computer Vision

Yaodong Yu, Maziar Sanjabi, Yi Ma, Kamalika Chaudhuri, Chuan Guo

构建面向计算机视觉、满足差分隐私要求的基础模型。

xDDPM: Explainable Denoising Diffusion Probabilistic Model for Scientific Modeling

Qianru Zhang, Chenglei Yu, Yudong Yan, Xiangyu Kuang, Yi Ma, Yuansheng Cao, Siu Ming Yiu, Tailin Wu

为科学建模构建可解释的去噪扩散概率模型。

CAD-MLLM: Unifying Multimodality-Conditioned CAD Generation With MLLM

CAD-MLLM: Unifying Multimodality-Conditioned CAD Generation With MLLM

Jingwei Xu, Chenyu Wang, Zibo Zhao, Wen Liu, Yi Ma, Shenghua Gao

用多模态大语言模型统一处理不同条件下的 CAD 生成。

2D Gaussian Splatting for Geometrically Accurate Radiance Fields

2D Gaussian Splatting for Geometrically Accurate Radiance Fields

Binbin Huang, Zehao Yu, Anpei Chen, Andreas Geiger, Shenghua Gao

以二维高斯泼溅学习几何准确的辐射场。

BBSEA: An Exploration of Brain-Body Synchronization for Embodied Agents

BBSEA: An Exploration of Brain-Body Synchronization for Embodied Agents

Sizhe Yang, Qian Luo, Anumpam Pani, Yanchao Yang

研究如何让基础模型生成任务，并结合机器人身体可执行的技能在仿真中训练具身智能体。

A Global Geometric Analysis of Maximal Coding Rate Reduction

A Global Geometric Analysis of Maximal Coding Rate Reduction

Peng Wang, Huikang Liu, Druv Pai, Yaodong Yu, Zhihui Zhu, Qing Qu, Yi Ma

从全局几何角度分析最大编码率约减目标的性质。

Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs

Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs

Shengbang Tong, Zhuang Liu, Yuexiang Zhai, Yi Ma, Yann LeCun, Saining Xie

评测多模态大语言模型的视觉感知局限。

Scaling White-Box Transformers for Vision

Scaling White-Box Transformers for Vision

Jinrui Yang, Xianhang Li, Druv Pai, Yuyin Zhou, Yi Ma, Yaodong Yu, Cihang Xie

The authors scale up CRATE on visual recognition tasks and study how changes to its architecture and training affect accuracy.

研究如何扩展用于视觉任务的白盒 Transformer。

Unsupervised Learning of Structured Representation via Closed-Loop Transcription

Unsupervised Learning of Structured Representation via Closed-Loop Transcription

Shengbang Tong, Xili Dai, Yubei Chen, Mingyang Li, Zengyi Li, Brent Yi, Yann LeCun, Yi Ma

A closed-loop training objective learns features from unlabeled images that can support both classification and image generation.

通过闭环转录，在无监督条件下学习具有结构的表征。

White-Box Transformers via Sparse Rate Reduction: Compression Is All There Is?

White-Box Transformers via Sparse Rate Reduction: Compression Is All There Is?

Yaodong Yu, Sam Buchanan, Druv Pai, Tianzhe Chu, Ziyang Wu, Shengbang Tong, Hao Bai, Yuexiang Zhai, Benjamin D. Haeffele, Yi Ma

The expanded journal study develops the theory behind CRATE and tests the architecture in both encoding and decoding tasks across images and text.

从稀疏编码率约减出发推导可解释的白盒 Transformer。

Towards Learning Geometric Eigen-Lengths Crucial for Fitting Tasks

Yijia Weng, Kaichun Mo, Ruoxi Shi, Yanchao Yang, Leonidas J. Guibas

学习判断物体能否穿过开口或放入指定空间所需的关键几何尺寸。

LivelySpeaker: Towards Semantic-Aware Co-Speech Gesture Generation

Yihao Zhi, Xiaodong Cun, Xuelin Chen, Xi Shen, Wen Guo, Shaoli Huang, Shenghua Gao

根据语音语义生成伴随说话的手势。

Revisiting Event-Based Video Frame Interpolation

Jiaben Chen, Yichen Zhu, Dongze Lian, Jiaqi Yang, Yifu Wang, Renrui Zhang, Xinhang Liu, Shenhan Qian, Laurent Kneip, Shenghua Gao

研究利用事件相机信息插入视频中间帧的方法。

Michelangelo: Conditional 3D Shape Generation based on Shape-Image-Text Aligned Latent Representation

Zibo Zhao, Wen Liu, Xin Chen, Xianfang Zeng, Rui Wang, Pei Cheng, Bin Fu, Tao Chen, Gang Yu, Shenghua Gao

对齐形状、图像与文本的隐空间，用条件输入生成三维形状。

InstructP2P: Learning to Edit 3D Point Clouds with Text Instructions

Jiale Xu, Xintao Wang, Yan-Pei Cao, Weihao Cheng, Ying Shan, Shenghua Gao

根据文字指令编辑三维点云。

Omni-Line-of-Sight Imaging for Holistic Shape Reconstruction

Binbin Huang, Xingyue Peng, Siyuan Shen, Suan Xia, Ruiqian Li, Yanhua Yu, Yuehan Wang, Shenghua Gao, Wenzheng Chen, Shiying Li, Jingyi Yu

通过全视线成像重建物体的完整形状。

Divided Attention: Unsupervised Multi-Object Discovery with Contextually Separated Slots

Dong Lao, Zhengyang Hu, Francesco Locatello, Yanchao Yang, Stefano Soatto

借助上下文分离的对象表示，从无标注视频中发现多个独立运动的对象。

JacobiNeRF: NeRF Shaping with Mutual Information Gradients

Xiaomeng Xu, Yanchao Yang, Kaichun Mo, Boxiao Pan, Li Yi, Leonidas J. Guibas

用互信息梯度调整神经辐射场的表示，使其反映场景中的结构关系。

VDN-NeRF: Resolving Shape-Radiance Ambiguity via View-Dependence Normalization

Bingfan Zhu, Yanchao Yang, Xulong Wang, Youyi Zheng, Leonidas J. Guibas

归一化神经辐射场中的视角依赖，缓解几何形状与辐射外观的歧义。

Weakly Supervised Video Representation Learning with Unaligned Text for Sequential Videos

Sixun Dong, Huazhang Hu, Dongze Lian, Weixin Luo, Yicheng Qian, Shenghua Gao

利用与画面未逐帧对齐的文本，弱监督学习时序视频表示。

Dream3D: Zero-Shot Text-to-3D Synthesis Using 3D Shape Prior and Text-to-Image Diffusion Models

Jiale Xu, Xintao Wang, Weihao Cheng, Yan-Pei Cao, Ying Shan, Xiaohu Qie, Shenghua Gao

结合三维形状先验和文生图扩散模型，从文字生成三维形状。

Lifelong Person Re-identification via Knowledge Refreshing and Consolidation

Chunlin Yu, Ye Shi, Zimo Liu, Shenghua Gao, Jingya Wang

通过更新和巩固已有知识，持续学习不同数据域的行人重识别。

COPILOT: Human-Environment Collision Prediction and Localization from Egocentric Videos

Boxiao Pan, Bokui Shen, Davis Rempe, Despoina Paschalidou, Kaichun Mo, Yanchao Yang, Leonidas J. Guibas

从第一视角视频预测人与环境发生碰撞的可能性及其位置。

PlaneDepth: Self-Supervised Depth Estimation via Orthogonal Planes

Ruoyu Wang, Zehao Yu, Shenghua Gao

用正交平面结构约束自监督深度估计。

Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning

Mitsuhiko Nakamoto, Simon Zhai, Anikait Singh, Max Sobol Mark, Yi Ma, Chelsea Finn, Aviral Kumar, Sergey Levine

校准离线强化学习的预训练过程，以提高在线微调效率。

Canonical Factors for Hybrid Neural Fields

Brent Yi, Weijia Zeng, Sam Buchanan, Yi Ma

研究混合神经场表示中的规范因子分解。

EMP-SSL: Towards Self-Supervised Learning in One Training Epoch

Shengbang Tong, Yubei Chen, Yi Ma, Yann LeCun

探索用一个训练轮次完成自监督表征学习。

General In-hand Object Rotation with Vision and Touch

Haozhi Qi, Brent Yi, Sudharshan Suresh, Mike Lambeta, Yi Ma, Roberto Calandra, Jitendra Malik

结合视觉与触觉，使机器人在手中转动不同物体。

Magic Tailor: a Latent-Anchor based Diffusion Model for 3D Clothes Generation

Zibo Zhao, Wen Liu, Xin Chen, Gang Yu, Shenghua Gao

用带隐空间锚点的条件扩散模型生成三维服装。

Minimalistic Unsupervised Representation Learning with the Sparse Manifold Transform

Yubei Chen, Zeyu Yun, Yi Ma, Bruno A. Olshausen, Yann LeCun

利用稀疏流形变换构建极简的无监督表征学习方法。

Pursuit of a discriminative representation for multiple subspaces via sequential games

Druv Pai, Michael Psenka, Chih-Yuan Chiu, Manxi Wu, Edgar Dobriban, Yi Ma

将多个子空间的判别性表征学习建模为序贯博弈。

Role of Uncertainty in Anticipatory Trajectory Prediction for a Ping-Pong Playing Robot

Nima Rahmanian, Michael Gupta, Renzo Soatto, Srisai Nachuri, Michael Psenka, Yi Ma, S. Shankar Sastry

分析预测不确定性在乒乓球机器人预判球路中的作用。

SCAFF-PD: Communication Efficient Fair and Robust Federated Learning

Yaodong Yu, Sai Praneeth Karimireddy, Yi Ma, Michael Jordan

在公平性与鲁棒性约束下提高联邦学习的通信效率。

Structure-Aware Surface Reconstruction via Primitive Assembly

Jingen Jiang, Mingyang Zhao, Shiqing Xin, Yanchao Yang, Hanxiao Wang, Xiaohong Jia, Dong-Ming Yan

通过组合几何基元进行结构感知的三维表面重建。

Understanding the Complexity Gains of Single-Task RL with a Curriculum

Qiyang Li, Yuexiang Zhai, Yi Ma, Sergey Levine

分析采用课程式训练如何影响单任务强化学习的复杂度。

Unsupervised Manifold Linearizing and Clustering

Tianjiao Ding, Shengbang Tong, Kwan Ho Ryan Chan, Xili Dai, Yi Ma, Benjamin D. Haeffele

在无监督条件下将数据流形线性化并进行聚类。

Incremental Learning of Structured Memory via Closed-Loop Transcription

Incremental Learning of Structured Memory via Closed-Loop Transcription

Shengbang Tong, Xili Dai, Ziyang Wu, Mingyang Li, Brent Yi, Yi Ma

The model adds new classes while using its encoder and decoder to preserve previously learned representations, reducing forgetting during incremental learning.

通过闭环转录增量学习有结构的记忆表征。

White-Box Transformers via Sparse Rate Reduction

White-Box Transformers via Sparse Rate Reduction

Yaodong Yu, Sam Buchanan, Druv Pai, Tianzhe Chu, Ziyang Wu, Shengbang Tong, Benjamin D. Haeffele, Yi Ma

Alternating compression and sparsification steps yield a transformer-like block and a mathematical interpretation of its attention and feed-forward operations.

依据稀疏编码率约减原理构建白盒 Transformer。

ResNeRF: Geometry-Guided Residual Neural Radiance Field for Indoor Scene Novel View Synthesis

Yuting Xiao, Yiqun Zhao, Yanyu Xu, Shenghua Gao

以几何约束残差辐射场，生成室内场景新视角。

Dual-Space NeRF: Learning Animatable Avatars and Scene Lighting in Separate Spaces

Yihao Zhi, Shenhan Qian, Xinhao Yan, Shenghua Gao

在独立空间学习可动画人体和场景光照。

UNIF: United Neural Implicit Functions for Clothed Human Reconstruction and Animation

Shenhan Qian, Jiale Xu, Ziwei Liu, Liqian Ma, Shenghua Gao

用联合神经隐式函数重建穿衣人体并驱动其动画。

6D Camera Relocalization in Visually Ambiguous Extreme Environments

Yang Zheng, Tolga Birdal, Fei Xia, Yanchao Yang, Yueqi Duan, Leonidas J. Guibas

研究在外观高度相似、视觉线索有限的环境中如何恢复相机的六自由度位姿。

SpOT: Spatiotemporal Modeling for 3D Object Tracking

Colton Stearns, Davis Rempe, Jie Li, Rares Ambrus, Sergey Zakharov, Vitor Guizilini, Yanchao Yang, Leonidas J. Guibas

对目标的时空变化进行建模，用于三维多目标跟踪。

PREF: Phasorial Embedding Fields for Compact Neural Representations

Binbin Huang, Xinhao Yan, Anpei Chen, Shenghua Gao, Jingyi Yu

用相量嵌入场紧凑表示连续神经场。

DearKD: Data-Efficient Early Knowledge Distillation for Vision Transformers

Xianing Chen, Qiong Cao, Yujie Zhong, Jing Zhang, Shenghua Gao, Dacheng Tao

通过早期知识蒸馏降低视觉 Transformer 对训练数据的需求。

GIMO: Gaze-Informed Human Motion Prediction in Context

Yang Zheng, Yanchao Yang, Kaichun Mo, Jiaman Li, Tao Yu, Yebin Liu, C. Karen Liu, Leonidas J. Guibas

结合眼动注视与场景几何，预测人在环境中的运动。

TransRAC: Encoding Multi-scale Temporal Correlation with Transformers for Repetitive Action Counting

Huazhang Hu, Sixun Dong, Yiqun Zhao, Dongze Lian, Zhengxin Li, Shenghua Gao

用多尺度时序相关性统计视频中的重复动作次数。

Taylor3DNet: Fast 3D Shape Inference With Landmark Points Based Taylor Series

Yuting Xiao, Jiale Xu, Shenghua Gao

利用地标点与泰勒展开快速推断三维形状。

Domain Adaptation on Point Clouds via Geometry-Aware Implicits

Yuefan Shen, Yanchao Yang, Mi Yan, He Wang, Youyi Zheng, Leonidas J. Guibas

借助隐式几何表示缓解不同点云数据域之间的差异。

Object Pursuit: Building a Space of Objects via Discriminative Weight Generation

Chuanyu Pan, Yanchao Yang, Kaichun Mo, Yueqi Duan, Leonidas J. Guibas

用判别式权重生成方法学习和扩充以物体为中心的表示。

SVIP: Sequence VerIfication for Procedures in Videos

Yicheng Qian, Weixin Luo, Dongze Lian, Xu Tang, Peilin Zhao, Shenghua Gao

验证视频中操作步骤的顺序。

IFR-Explore: Learning Inter-object Functional Relationships in 3D Indoor Scenes

Qi Li, Kaichun Mo, Yanchao Yang, Hang Zhao, Leonidas J. Guibas

研究机器人如何通过探索发现三维室内场景中物体之间的功能关系。

Cross-domain Trajectory Prediction with CTP-Net

Pingxuan Huang, Zhenhua Cui, Jing Li, Shenghua Gao, Bo Hu, Yanyan Fang

利用 CTP-Net 进行跨域运动轨迹预测。

Proxy-Bridged Image Reconstruction Network for Anomaly Detection in Medical Images

Kang Zhou, Jing Li, Weixin Luo, Zhengxin Li, Jianlong Yang, Huazhu Fu, Jun Cheng, Jiang Liu, Shenghua Gao

借助代理桥接的图像重建网络检测医学图像异常。

ADeLA: Automatic Dense Labeling with Attention for Viewpoint Shift in Semantic Segmentation

Hanxiang Ren, Yanchao Yang, He Wang, Bokui Shen, Qingnan Fan, Youyi Zheng, C. Karen Liu, Leonidas J. Guibas

利用注意力进行稠密伪标注，以适应视角变化带来的语义分割差异。

DCL: Differential Contrastive Learning for Geometry-Aware Depth Synthesis

Yuefan Shen, Yanchao Yang, Youyi Zheng, C. Karen Liu, Leonidas J. Guibas

用微分对比学习进行几何感知的深度图合成。

AS-MLP: An Axial Shifted MLP Architecture for Vision

Dongze Lian, Zehao Yu, Xing Sun, Shenghua Gao

以轴向移位的多层感知机建模视觉特征。

Liquid Warping GAN With Attention: A Unified Framework for Human Image Synthesis

Wen Liu, Zhixin Piao, Zhi Tu, Wenhan Luo, Lin Ma, Shenghua Gao

融合注意力与形变生成对抗网络，合成人体图像。

Domain Adversarial Reinforcement Learning for Partial Domain Adaptation

Jin Chen, Xinxiao Wu, Lixin Duan, Shenghua Gao

用域对抗强化学习解决目标域只覆盖部分源域类别的问题。

Chest X-Ray Diagnostic Quality Assessment: How Much Is Pixel-Wise Supervision Needed?

Junhao Hu, Chenyang Zhang, Kang Zhou, Shenghua Gao

评估胸部 X 光图像的诊断质量，并研究所需的逐像素监督量。

Computational Benefits of Intermediate Rewards for Goal-Reaching Policy Learning

Yuexiang Zhai, Christina Baek, Zhengyuan Zhou, Jiantao Jiao, Yi Ma

分析中间奖励如何影响到达指定目标的策略学习效率。

DeepPROTACs is a deep learning-based targeted degradation predictor for PROTACs

Fenglei Li, Qiaoyu Hu, Xianglei Zhang, Renhong Sun, Zhuanghua Liu, Sanan Wu, Siyuan Tian, Xinyue Ma, Zhizhuo Dai, Xiaobao Yang, Shenghua Gao, Fang Bai

用深度学习预测 PROTAC 分子诱导目标蛋白降解的能力。

Efficient Maximal Coding Rate Reduction by Variational Forms

Christina Baek, Ziyang Wu, Kwan Ho Ryan Chan, Tianjiao Ding, Yi Ma, Benjamin D. Haeffele

通过变分形式提高最大编码率约减的计算效率。

Fully convolutional line parsing

Xili Dai, Haigang Gong, Shuai Wu, Xiaojun Yuan, Yi Ma

使用全卷积网络解析图像中的线段结构。

Future Frame Prediction Network for Video Anomaly Detection

Weixin Luo, Wen Liu, Dongze Lian, Shenghua Gao

预测未来视频帧，并据此发现异常事件。

HaViT: Hybrid-Attention Based Vision Transformer for Video Classification

Li Li, Liansheng Zhuang, Shenghua Gao, Shafei Wang

用混合注意力视觉 Transformer 做视频分类。

In-Hand Object Rotation via Rapid Motor Adaptation

Haozhi Qi, Ashish Kumar, Roberto Calandra, Yi Ma, Jitendra Malik

通过快速运动适应学习机器人手内物体旋转。

Learning and Meshing From Deep Implicit Surface Networks Using an Efficient Implementation of Analytic Marching

Jiabao Lei, Kui Jia, Yi Ma

用解析推进算法从深度隐式曲面网络学习并提取网格。

Learning to Reconstruct 3D Non-Cuboid Room Layout from a Single RGB Image

Cheng Yang, Jia Zheng, Xili Dai, Rui Tang, Yi Ma, Xiaojun Yuan

从单张彩色图像重建非长方体房间的三维布局。

Locating and Counting Heads in Crowds With a Depth Prior

Dongze Lian, Xianing Chen, Jing Li, Weixin Luo, Shenghua Gao

结合深度先验，在人群中定位人头并计数。

Memorizing Structure-Texture Correspondence for Image Anomaly Detection

Kang Zhou, Jing Li, Yuting Xiao, Jianlong Yang, Jun Cheng, Wen Liu, Weixin Luo, Jiang Liu, Shenghua Gao

记忆结构与纹理的正常对应关系，检测图像异常。

On the Convergence of Stochastic Extragradient for Bilinear Games using Restarted Iteration Averaging

Chris Junchi Li, Yaodong Yu, Nicolas Loizou, Gauthier Gidel, Yi Ma, Nicolas Le Roux, Michael I. Jordan

分析重启迭代平均如何影响双线性博弈中随机额外梯度法的收敛。

On the principles of Parsimony and Self-consistency for the emergence of intelligence

Yi Ma, Doris Tsao, Heung-Yeung Shum

探讨简约性与自洽性在智能涌现中的作用。

Predicting Out-of-Distribution Error with the Projection Norm

Yaodong Yu, Zitong Yang, Alexander Wei, Yi Ma, Jacob Steinhardt

使用投影范数预测模型在分布外数据上的误差。

Revisiting Sparse Convolutional Model for Visual Recognition

Xili Dai, Mingyang Li, Pengyuan Zhai, Shengbang Tong, Xingjian Gao, Shao-Lun Huang, Zhihui Zhu, Chong You, Yi Ma

重新考察稀疏卷积模型在视觉识别中的作用。

Robust Calibration with Multi-domain Temperature Scaling

Yaodong Yu, Stephen Bates, Yi Ma, Michael I. Jordan

通过多域温度缩放提高模型置信度校准的鲁棒性。

Spherical DNNs and Their Applications in 360° Images and Videos

Yanyu Xu, Ziheng Zhang, Shenghua Gao

研究球面深度网络对全景图像与视频的建模。

TCT: Convexifying Federated Learning using Bootstrapped Neural Tangent Kernels

Yaodong Yu, Alexander Wei, Sai Praneeth Karimireddy, Yi Ma, Michael I. Jordan

利用自举神经切线核，将联邦学习问题转化为凸优化。

CTRL: Closed-Loop Transcription to an LDR via Minimaxing Rate Reduction

CTRL: Closed-Loop Transcription to an LDR via Minimaxing Rate Reduction

Xili Dai, Shengbang Tong, Mingyang Li, Ziyang Wu, Michael Psenka, Kwan Ho Ryan Chan, Pengyuan Zhai, Yaodong Yu, Xiaojun Yuan, Heung-Yeung Shum, Yi Ma

An encoder and a decoder form a loop. The model compares features before and after reconstruction to learn a separate linear subspace for each class.

通过编码率约减的极小极大优化，将数据闭环转录为线性判别表征。

ReduNet: A White-box Deep Network from the Principle of Maximizing Rate Reduction

ReduNet: A White-box Deep Network from the Principle of Maximizing Rate Reduction

Kwan Ho Ryan Chan, Yaodong Yu, Chong You, Haozhi Qi, John Wright, Yi Ma

ReduNet builds each network layer from an optimization step for coding rate reduction, giving the layer’s operation an explicit mathematical interpretation.

从最大编码率约减原理推导可解释的白盒深度网络 ReduNet。

Raw Bayer Pattern Image Synthesis for Computer Vision-oriented Image Signal Processing Pipeline Design

Wei Zhou, Xiangyu Zhang, Hongyu Wang, Shenghua Gao, Xin Lou

为面向计算机视觉任务的图像信号处理流程合成原始拜耳格式图像。

MOS: A Low Latency and Lightweight Framework for Face Detection, Landmark Localization, and Head Pose Estimation

Yepeng Liu, Zaiwang Gu, Shenghua Gao, Dong Wang, Yusheng Zeng, Jun Cheng

用轻量框架同时做人脸检测、面部关键点定位和头部姿态估计。

OH-Former: Omni-Relational High-Order Transformer for Person Re-Identification

Xianing Chen, Chunlin Xu, Qiong Cao, Jialang Xu, Yujie Zhong, Jiale Xu, Zhengxin Li, Jingya Wang, Shenghua Gao

用高阶关系 Transformer 进行行人重识别。

Speech Drives Templates: Co-Speech Gesture Synthesis with Learned Templates

Shenhan Qian, Zhi Tu, Yihao Zhi, Wen Liu, Shenghua Gao

从语音驱动学习到的手势模板，生成与说话同步的动作。

Protein contact map prediction using multiple sequence alignment dropout and consistency learning for sequences with fewer homologs

Xuyang Liu, Lei Jin, Shenghua Gao, Suwen Zhao

结合多序列比对随机丢弃与一致性学习，预测同源序列较少的蛋白质接触图。

Learning Semantic-Aware Dynamics for Video Prediction

Xinzhu Bei, Yanchao Yang, Stefano Soatto

通过建模语义区域的运动及遮挡解除，预测后续视频帧。

Look Before You Leap: Learning Landmark Features for One-Stage Visual Grounding

Binbin Huang, Dongze Lian, Weixin Luo, Shenghua Gao

学习地标特征，用单阶段模型定位语言描述的视觉对象。

Layout-Guided Novel View Synthesis From a Single Indoor Panorama

Jiale Xu, Jia Zheng, Yanyu Xu, Rui Tang, Shenghua Gao

根据室内布局，从单幅全景图合成新视角。

Learning To Recommend Frame for Interactive Video Object Segmentation in the Wild

Zhaoyuan Yin, Jia Zheng, Weixin Luo, Shenhan Qian, Hanling Zhang, Shenghua Gao

为交互式视频目标分割推荐值得标注的帧。

Amodal Segmentation Based on Visible Region Segmentation and Shape Prior

Yuting Xiao, Yanyu Xu, Ziming Zhong, Weixin Luo, Jiawei Li, Shenghua Gao

利用可见区域和形状先验，分割对象被遮挡的完整轮廓。

Accurate depth estimation from a hybrid event-RGB stereo setup

Yi-Fan Zuo, Li Cui, Xin Peng, Yanyu Xu, Shenghua Gao, Xia Wang, Laurent Kneip

融合事件相机与 RGB 相机的双目观测估计深度。

Adversarial Robustness of Stabilized Neural ODE Might be from Obfuscated Gradients

Yifei Huang, Yaodong Yu, Hongyang Zhang, Yi Ma, Yuan Yao

检验稳定化神经常微分方程的对抗鲁棒性是否源于梯度遮蔽。

Appearance-Motion Memory Consistency Network for Video Anomaly Detection

Ruichu Cai, Hao Zhang, Wen Liu, Shenghua Gao, Zhifeng Hao

利用外观与运动记忆的一致性发现视频异常。

Crowd Counting With Partial Annotations in an Image

Yanyu Xu, Ziming Zhong, Dongze Lian, Jing Li, Zhengxin Li, Xinxing Xu, Shenghua Gao

仅用图像中部分人群标注训练人群计数模型。

Incremental Learning via Rate Reduction

Ziyang Wu, Christina Baek, Chong You, Yi Ma

依据编码率约减原理增量学习新数据的表征。

KGDet: Keypoint-Guided Fashion Detection

Shenhan Qian, Dongze Lian, Binqiang Zhao, Tong Liu, Bohui Zhu, Hai Li, Shenghua Gao

通过服饰关键点引导时尚单品检测。

Learning Long-term Visual Dynamics with Region Proposal Interaction Networks

Haozhi Qi, Xiaolong Wang, Deepak Pathak, Yi Ma, Jitendra Malik

利用候选区域之间的交互学习长期视觉动态。

Marangoni Flow Manipulated Concentric Assembly of Cellulose Nanocrystals

Rongrong Shao, Xiao Meng, Zhaojie Shi, Jiajia Zhong, Zheren Cai, Junhao Hu, Xiao Wang, Gang Chen, Shenghua Gao, Yanlin Song, Chunhong Ye

利用马兰戈尼流控制纤维素纳米晶的同心组装。

Memory-Assisted Dual-End Adaptation Network For Choroid Segmentation In Multi-Domain Optical Coherence Tomography

Zhenjie Chai, Jianlong Yang, Kang Zhou, Zhi Chen, Yitian Zhao, Shenghua Gao, Jiang Liu

用记忆辅助的域适应模型，在不同来源的 OCT 图像中分割脉络膜。

NeRD: Neural 3D Reflection Symmetry Detector

Yichao Zhou, Shichen Liu, Yi Ma

使用神经网络检测三维物体的反射对称性。

Normal graph: Spatial temporal graph convolutional networks based prediction network for skeleton based video anomaly detection

Weixin Luo, Wen Liu, Shenghua Gao

用时空图卷积预测正常人体骨架运动，检测视频异常。

Partially-Supervised Learning for Vessel Segmentation in Ocular Images

Yanyu Xu, Xinxing Xu, Lei Jin, Shenghua Gao, Rick Siow Mong Goh, Daniel Shu Wei Ting, Yong Liu

在部分监督条件下进行眼部图像血管分割。

Prior Based Human Completion

Zibo Zhao, Wen Liu, Yanyu Xu, Xianing Chen, Weixin Luo, Lei Jin, Bohui Zhu, Tong Liu, Binqiang Zhao, Shenghua Gao

利用人体先验补全图像中缺失的人体部分。

RGB-D-based gaze point estimation via multi-column CNNs and facial landmarks global optimization

Ziheng Zhang, Dongze Lian, Shenghua Gao

结合 RGB-D、多列卷积网络和面部关键点优化，估计人的注视点。

Robust Low-Rank Tensor Recovery with Rectification and Alignment

Xiaoqin Zhang, Di Wang, Zhengyuan Zhou, Yi Ma

结合几何校正与对齐，稳健地恢复低秩张量。

SUNNet: A novel framework for simultaneous human parsing and pose estimation

Yanyu Xu, Zhixin Piao, Ziheng Zhang, Wen Liu, Shenghua Gao

联合估计人体部位分割与人体姿态。

Understanding Generalization in Adversarial Training via the Bias-Variance Decomposition

Yaodong Yu, Zitong Yang, Edgar Dobriban, Jacob Steinhardt, Yi Ma

通过偏差与方差分解，分析对抗训练模型的泛化能力。

Unified Acceleration of High-Order Algorithms under General Hölder Continuity

Chaobing Song, Yong Jiang, Yi Ma

研究一般 Hölder 连续性条件下高阶优化算法的统一加速方法。

Video Anomaly Detection with Sparse Coding Inspired Deep Neural Networks

Weixin Luo, Wen Liu, Dongze Lian, Jinhui Tang, Lixin Duan, Xi Peng, Shenghua Gao

研究受稀疏编码启发的深度网络，用于视频异常检测。

DyStaB: Unsupervised Object Segmentation via Dynamic-Static Bootstrapping

DyStaB: Unsupervised Object Segmentation via Dynamic-Static Bootstrapping

Yanchao Yang, Brian Lai, Stefano Soatto

结合视频运动分割与静态图像模型，以无监督方式学习目标分割。

SIRI: Spatial Relation Induced Network For Spatial Description Resolution

Peiyao Wang, Weixin Luo, Yanyu Xu, Haojie Li, Shugong Xu, Jianyu Yang, Shenghua Gao

根据物体的空间关系解析自然语言中的位置描述。

Encoding Structure-Texture Relation with P-Net for Anomaly Detection in Retinal Images

Kang Zhou, Yuting Xiao, Jianlong Yang, Jun Cheng, Wen Liu, Weixin Luo, Zaiwang Gu, Jiang Liu, Shenghua Gao

通过学习结构与纹理的关系发现视网膜图像中的异常。

P2Net: Patch-Match and Plane-Regularization for Unsupervised Indoor Depth Estimation

Zehao Yu, Lei Jin, Shenghua Gao

结合图块匹配与平面正则化进行无监督室内深度估计。

Learning to Manipulate Individual Objects in an Image

Yanchao Yang, Yutong Chen, Stefano Soatto

学习可独立调节图像局部对象的生成表示，无需对象级标注。

Phase Consistent Ecological Domain Adaptation

Yanchao Yang, Dong Lao, Ganesh Sundaramoorthi, Stefano Soatto

利用相位一致性等约束将语义分割知识从有标签源域迁移到目标域。

Fast-MVSNet: Sparse-to-Dense Multi-View Stereo With Learned Propagation and Gauss-Newton Refinement

Zehao Yu, Shenghua Gao

利用传播学习和高斯–牛顿细化，提高多视图立体重建效率。

Sparse-Gan: Sparsity-Constrained Generative Adversarial Network for Anomaly Detection in Retinal OCT Image

Kang Zhou, Shenghua Gao, Jun Cheng, Zaiwang Gu, Huazhu Fu, Zhi Tu, Jianlong Yang, Yitian Zhao, Jiang Liu

在生成对抗网络中引入稀疏约束，检测视网膜 OCT 异常。

Perceptual-Assisted Adversarial Adaptation for Choroid Segmentation in Optical Coherence Tomography

Zhenjie Chai, Kang Zhou, Jianlong Yang, Yuhui Ma, Zhi Chen, Shenghua Gao, Jiang Liu

利用感知信息辅助对抗域适应，在 OCT 图像中分割脉络膜。

Assessment of Generative Adversarial Networks Model for Synthetic Optical Coherence Tomography Images of Retinal Disorders

Ce Zheng, Xiaolin Xie, Kang Zhou, Bang Chen, Jili Chen, Haiyun Ye, Wen Li, Tong Qiao, Shenghua Gao, Jianlong Yang, Jiang Liu

评估生成对抗网络合成视网膜疾病 OCT 图像的能力。

High signal-to-noise ratio reconstruction of low bit-depth optical coherence tomography using deep learning

Qiangjiang Hao, Kang Zhou, Jianlong Yang, Yan Hu, Zhengjie Chai, Yuhui Ma, Gangjun Liu, Yitian Zhao, Shenghua Gao, Jiang Liu

从低位深 OCT 数据重建高信噪比图像。

Digital resolution enhancement in low transverse sampling optical coherence tomography angiography using deep learning

Ting Zhou, Jianlong Yang, Kang Zhou, Liyang Fang, Yan Hu, Jun Cheng, Yitian Zhao, Xiangping Chen, Shenghua Gao, Jiang Liu

用深度学习提升低横向采样 OCT 血管成像的数字分辨率。

Structured3D: A Large Photo-Realistic Dataset for Structured 3D Modeling

Jia Zheng, Junfei Zhang, Jing Li, Rui Tang, Shenghua Gao, Zihan Zhou

建立大规模照片级真实感合成数据集，用于结构化三维建模。

Visual Tracking With Multiview Trajectory Prediction

Minye Wu, Haibin Ling, Ning Bi, Shenghua Gao, Qiang Hu, Hao Sheng, Jingyi Yu

通过多视角轨迹预测进行视觉目标跟踪。

Breaking the O(1/epsilon) Optimal Rate for a Class of Minimax Problems

Chaobing Song, Yong Jiang, Yi Ma

研究一类极小极大问题中超越 O(1/ε) 收敛速率的方法。

Comments on Efficient Singular Value Thresholding Computation

Zhengyuan Zhou, Yi Ma

讨论高效计算奇异值阈值算子的方式。

Complete Dictionary Learning via L4-Norm Maximization over the Orthogonal Group

Yuexiang Zhai, Zitong Yang, Zhenyu Liao, John Wright, Yi Ma

在正交群上最大化 ℓ4 范数以学习完备字典。

Deep Isometric Learning for Visual Recognition

Haozhi Qi, Chong You, Xiaolong Wang, Yi Ma, Jitendra Malik

研究面向视觉识别的深度等距表征学习。

Disentangled Representation Learning for Controllable Image Synthesis: An Information-Theoretic Perspective

Shichang Tang, Xu Zhou, Xuming He, Yi Ma

从信息论角度研究可控图像合成中的解耦表征学习。

Geometric Structure Based and Regularized Depth Estimation From 360 Indoor Imagery

Lei Jin, Yanyu Xu, Jia Zheng, Junfei Zhang, Rui Tang, Shugong Xu, Jingyi Yu, Shenghua Gao

利用室内几何结构与正则化估计全景图像深度。

HoliCity: A City-Scale Data Platform for Learning Holistic 3D Structures

Yichao Zhou, Jingwei Huang, Xili Dai, Linjie Luo, Zhili Chen, Yi Ma

构建城市尺度的数据平台，用于学习整体三维结构。

Image saliency detection via multi-scale iterative CNN

Kun Huang, Shenghua Gao

用多尺度迭代卷积网络检测图像视觉显著区域。

Learning to Detect 3D Reflection Symmetry for Single-View Reconstruction

Yichao Zhou, Shichen Liu, Yi Ma

学习检测三维反射对称性，以辅助单视图三维重建。

Multi-level feature fusion based Locality-Constrained Spatial Transformer network for video crowd counting

Yanyan Fang, Shenghua Gao, Jing Li, Weixin Luo, Linfang He, Bo Hu

融合多层特征与局部约束空间变换网络，统计视频人群数量。

Noise Adaptation Generative Adversarial Network for Medical Image Analysis

Tianyang Zhang, Jun Cheng, Huazhu Fu, Zaiwang Gu, Yuting Xiao, Kang Zhou, Shenghua Gao, Rui Zheng, Jiang Liu

研究适应噪声的生成对抗网络及其在医学图像分析中的应用。

Open-Set OCT Image Recognition with Synthetic Learning

Yuting Xiao, Shenghua Gao, Zhenjie Chai, Kang Zhou, Tianyang Zhang, Yitian Zhao, Jun Cheng, Jiang Liu

利用合成样本训练模型，识别开放类别的 OCT 图像。

Optimistic Dual Extrapolation for Coherent Non-monotone Variational Inequalities

Chaobing Song, Zhengyuan Zhou, Yichao Zhou, Yong Jiang, Yi Ma

用乐观对偶外推算法求解满足相干性条件的非单调变分不等式。

Parameter-Free Gaussian PSF Model for Extended Depth of Field in Brightfield Microscopy

Xu Zhou, Rafael Molina, Yi Ma, Tianfu Wang, Dong Ni

使用无参高斯点扩散函数模型扩展明场显微成像景深。

Rethinking Bias-Variance Trade-off for Generalization of Neural Networks

Zitong Yang, Yaodong Yu, Chong You, Jacob Steinhardt, Yi Ma

重新分析神经网络泛化中的偏差与方差权衡。

Robust Recovery via Implicit Bias of Discrepant Learning Rates for Double Over-parameterization

Chong You, Zhihui Zhu, Qing Qu, Yi Ma

研究双重过参数化中不同学习率的隐式偏置如何帮助稳健恢复。

SUNet: A Lesion Regularized Model for Simultaneous Diabetic Retinopathy and Diabetic Macular Edema Grading

Zhi Tu, Shenghua Gao, Kang Zhou, Xianing Chen, Huazhu Fu, Zaiwang Gu, Jun Cheng, Zehao Yu, Jiang Liu

利用病灶约束联合评估糖尿病视网膜病变和黄斑水肿等级。

Towards Fast Adaptation of Neural Architectures with Meta Learning

Dongze Lian, Yin Zheng, Yintao Xu, Yanxiong Lu, Leyu Lin, Peilin Zhao, Junzhou Huang, Shenghua Gao

用元学习让神经网络架构快速适应新任务。

Understanding l4-based Dictionary Learning: Interpretation, Stability, and Robustness

Yuexiang Zhai, Hermish Mehta, Zhengyuan Zhou, Yi Ma

分析基于 ℓ4 范数的字典学习的含义、稳定性和鲁棒性。

Variance Reduction via Accelerated Dual Averaging for Finite-Sum Optimization

Chaobing Song, Yong Jiang, Yi Ma

利用加速对偶平均降低有限和优化中的方差。

FDA: Fourier Domain Adaptation for Semantic Segmentation

FDA: Fourier Domain Adaptation for Semantic Segmentation

Yanchao Yang, Stefano Soatto

通过交换源域与目标域的低频幅度信息，改善语义分割模型跨域迁移。

Learning Diverse and Discriminative Representations via the Principle of Maximal Coding Rate Reduction

Learning Diverse and Discriminative Representations via the Principle of Maximal Coding Rate Reduction

Yaodong Yu, Kwan Ho Ryan Chan, Chong You, Chaobing Song, Yi Ma

The objective measures how much more compact the data become when each class is encoded separately, encouraging features that distinguish classes and retain variation within them.

通过最大编码率约减学习兼具多样性与判别性的表征。

BioNet: Infusing Biomarker Prior into Global-to-Local Network for Choroid Segmentation in Optical Coherence Tomography Images

Huihong Zhang, Jianlong Yang, Kang Zhou, Zhenjie Chai, Jun Cheng, Shenghua Gao, Jiang Liu

在全局与局部网络中引入生物标志物先验，分割 OCT 中的脉络膜。

Liquid Warping GAN: A Unified Framework for Human Motion Imitation, Appearance Transfer and Novel View Synthesis

Wen Liu, Zhixin Piao, Jie Min, Wenhan Luo, Lin Ma, Shenghua Gao

以形变生成对抗网络实现人体动作模仿、外观迁移与新视角合成。

SkrGAN: Sketching-Rendering Unconditional Generative Adversarial Networks for Medical Image Synthesis

Tianyang Zhang, Huazhu Fu, Yitian Zhao, Jun Cheng, Mengjie Guo, Zaiwang Gu, Bing Yang, Yuting Xiao, Shenghua Gao, Jiang Liu

把草图构建与渲染结合，用生成对抗网络合成医学图像。

Locality-Constrained Spatial Transformer Network for Video Crowd Counting

Yanyan Fang, Biyun Zhan, Wandi Cai, Shenghua Gao, Bo Hu

用局部约束空间变换网络统计视频中的人群。

Eliminating Shadow Artifacts via Generative Inpainting Networks to Quantify Vascular Changes of the Choroid

Huihong Zhang, Jianlong Yang, Kang Zhou, Fei Li, Yan Hu, Shenghua Gao, Xiulan Zhang, Jiang Liu

用生成式图像修补消除阴影伪影，辅助量化脉络膜血管变化。

Learning Semantics-aware Distance Map with Semantics Layering Network for Amodal Instance Segmentation

Ziheng Zhang, Anpei Chen, Ling Xie, Jingyi Yu, Shenghua Gao

用语义分层和距离图分割包含遮挡区域的完整对象实例。

PPGNet: Learning Point-Pair Graph for Line Segment Detection

Ziheng Zhang, Zhengxin Li, Ning Bi, Jia Zheng, Jinlei Wang, Kun Huang, Weixin Luo, Yanyu Xu, Shenghua Gao

学习由点对构成的图，从图像中检测线段。

CE-Net: Context Encoder Network for 2D Medical Image Segmentation

Zaiwang Gu, Jun Cheng, Huazhu Fu, Kang Zhou, Huaying Hao, Yitian Zhao, Tianyang Zhang, Shenghua Gao, Jiang Liu

用上下文编码网络分割二维医学图像。

Single-Image Piece-Wise Planar 3D Reconstruction via Associative Embedding

Zehao Yu, Jia Zheng, Dongze Lian, Zihan Zhou, Shenghua Gao

利用关联嵌入从单张图像重建由多个平面组成的三维场景。

Dense Depth Posterior (DDP) From Single Image and Sparse Range

Yanchao Yang, Alex Wong, Stefano Soatto

结合单张图像与稀疏测距，估计各像素深度的后验分布。

Personalized Saliency and Its Prediction

Yanyu Xu, Shenghua Gao, Junru Wu, Nianyi Li, Jingyi Yu

分析观看者之间视觉注意力的差异，预测个人显著图。

A Fast Holistic Algorithm for Complete Dictionary Learning via L4 Norm Maximization

Yuexiang Zhai, Zitong Yang, Zhenyu Liao, John Wright, Yi Ma

利用 ℓ4 范数最大化设计快速求解完备字典的算法。

Density Map Regression Guided Detection Network for RGB-D Crowd Counting and Localization

Dongze Lian, Jing Li, Jia Zheng, Weixin Luo, Shenghua Gao

用密度图回归引导 RGB-D 图像中的人群检测、计数与定位。

End-to-End Wireframe Parsing

Yichao Zhou, Haozhi Qi, Yi Ma

以端到端方式解析图像中的线框结构。

FPN++: A Simple Baseline for Pedestrian Detection

Junhao Hu, Lei Jin, Shenghua Gao

用改进的特征金字塔网络检测行人。

Hybrid Neural Network for Photoacoustic Imaging Reconstruction

Hengrong Lan, Kang Zhou, Changchun Yang, Jiang Liu, Shenghua Gao, Fei Gao

用混合神经网络重建光声图像。

Ki-GAN: Knowledge Infusion Generative Adversarial Network for Photoacoustic Image Reconstruction In Vivo

Hengrong Lan, Kang Zhou, Changchun Yang, Jun Cheng, Jiang Liu, Shenghua Gao, Fei Gao

把领域知识融入生成对抗网络，用于活体光声图像重建。

Learning to Reconstruct 3D Manhattan Wireframes From a Single Image

Yichao Zhou, Haozhi Qi, Yuexiang Zhai, Qi Sun, Zhili Chen, Li-Yi Wei, Yi Ma

从单张图像重建遵循相互正交主方向的三维线框。

Local to Global Learning: Gradually Adding Classes for Training Deep Neural Networks

Hao Cheng, Dongze Lian, Bowen Deng, Shenghua Gao, Tao Tan, Yanlin Geng

逐步增加训练类别，研究深度网络的由局部到整体学习。

Margin Learning Embedded Prediction for Video Anomaly Detection with A Few Anomalies

Wen Liu, Weixin Luo, Zhengxin Li, Peilin Zhao, Shenghua Gao

以少量异常样本和间隔学习训练视频异常预测模型。

Multiview Multitask Gaze Estimation With Deep Convolutional Neural Networks

Dongze Lian, Lina Hu, Weixin Luo, Yanyu Xu, Lixin Duan, Jingyi Yu, Shenghua Gao

用多视角、多任务卷积网络估计人的注视方向。

NeurVPS: Neural Vanishing Point Scanning via Conic Convolution

Yichao Zhou, Haozhi Qi, Jingwei Huang, Yi Ma

用锥形卷积扫描图像，检测透视几何中的消失点。

RGBD Based Gaze Estimation via Multi-Task CNN

Dongze Lian, Ziheng Zhang, Weixin Luo, Lina Hu, Minye Wu, Zechao Li, Jingyi Yu, Shenghua Gao

用多任务卷积网络从彩色与深度图像中估计注视方向。

TARM: A Turbo-Type Algorithm for Affine Rank Minimization

Zhipeng Xue, Xiaojun Yuan, Junjie Ma, Yi Ma

采用 Turbo 型迭代算法求解仿射秩最小化问题。

Utilizing Information Bottleneck to Evaluate the Capability of Deep Neural Networks for Image Classification

Hao Cheng, Dongze Lian, Shenghua Gao, Yanlin Geng

利用信息瓶颈分析深度神经网络的图像分类能力。

Wireframe Parsing With Guidance of Distance Map

Kun Huang, Shenghua Gao

用距离图引导图像中的线框结构解析。

Unsupervised Moving Object Detection via Contextual Information Separation

Unsupervised Moving Object Detection via Contextual Information Separation

Yanchao Yang, Antonio Loquercio, Davide Scaramuzza, Stefano Soatto

通过分离目标运动与周围上下文的信息，在无标注视频中检测运动对象。

Learning to Parse Wireframes in Images of Man-Made Environments

Kun Huang, Yifan Wang, Zihan Zhou, Tianjiao Ding, Shenghua Gao, Yi Ma

学习解析建筑等人造环境图像中的线框结构。

Believe It or Not, We Know What You Are Looking At!

Dongze Lian, Zehao Yu, Shenghua Gao

从场景图像推断观察者正在注视的目标。

Deep Surface Light Fields

Anpei Chen, Minye Wu, Yingliang Zhang, Nianyi Li, Jie Lu, Shenghua Gao, Jingyi Yu

用深度模型表示表面光场。

Multi-Cell Multi-Task Convolutional Neural Networks for Diabetic Retinopathy Grading

Kang Zhou, Zaiwang Gu, Wen Liu, Weixin Luo, Jun Cheng, Shenghua Gao, Jiang Liu

用多单元多任务卷积网络对糖尿病视网膜病变分级。

Conditional Prior Networks for Optical Flow

Yanchao Yang, Stefano Soatto

学习给定图像条件下的光流先验，以估计像素的运动。

Future Frame Prediction for Anomaly Detection - A New Baseline

Wen Liu, Weixin Luo, Dongze Lian, Shenghua Gao

用未来帧预测建立视频异常检测基线。

Body Structure Aware Deep Crowd Counting

Siyu Huang, Xi Li, Zhongfei Zhang, Fei Wu, Shenghua Gao, Rongrong Ji, Junwei Han

引入人体结构信息改进密集人群计数。

Encoding Crowd Interaction With Deep Neural Network for Pedestrian Trajectory Prediction

Yanyu Xu, Zhixin Piao, Shenghua Gao

对人群交互建模，预测行人的未来运动轨迹。

Evaluating Capability of Deep Neural Networks for Image Classification via Information Plane

Hao Cheng, Dongze Lian, Shenghua Gao, Yanlin Geng

利用信息平面评价深度网络的图像分类能力。

Face Aging With Identity-Preserved Conditional Generative Adversarial Networks

Zongwei Wang, Xu Tang, Weixin Luo, Shenghua Gao

用保留人物身份的条件生成对抗网络合成人脸老化效果。

Fine-Grained Video Categorization with Redundancy Reduction Attention

Chen Zhu, Xiao Tan, Feng Zhou, Xiao Liu, Kaiyu Yue, Errui Ding, Yi Ma

利用抑制冗余信息的注意力机制进行细粒度视频分类。

Fundus Image Quality-Guided Diabetic Retinopathy Grading

Kang Zhou, Zaiwang Gu, Annan Li, Jun Cheng, Shenghua Gao, Jiang Liu

在糖尿病视网膜病变分级中考虑眼底图像质量。

Gaze Prediction in Dynamic 360° Immersive Videos

Yanyu Xu, Yanbing Dong, Junru Wu, Zhengzhong Sun, Zhiru Shi, Jingyi Yu, Shenghua Gao

预测观看动态全景视频时的视线分布。

Intraocular robotic interventional surgical system (IRISS): Semi‐automated OCT‐guided cataract removal

Cheng‐Wei Chen, Yu‐Hsiu Lee, Matthew J. Gerber, Harrison Cheng, Yan‐Chao Yang, Andrea Govetto, Anibal Andrés Francone, Stefano Soatto, Warren S. Grundfest, Jean‐Pierre Hubschman, Tsu‐Chin Tsao

将光学相干断层成像与眼内手术机器人结合，研究半自动白内障去除。

Robust Tensor Approximation With Laplacian Scale Mixture Modeling for Multiframe Image and Video Denoising

Weisheng Dong, Tao Huang, Guangming Shi, Yi Ma, Xin Li

用拉普拉斯尺度混合模型和稳健张量逼近为多帧图像及视频去噪。

Saliency Detection in 360° Videos

Ziheng Zhang, Yanyu Xu, Jingyi Yu, Shenghua Gao

预测全景视频中的视觉显著区域。

A new calibration technique for multi-camera systems of limited overlapping field-of-views

Ziran Xing, Jingyi Yu, Yi Ma

研究视野重叠有限的多相机系统的标定方法。

Beyond Universal Saliency: Personalized Saliency Prediction with Multi-task CNN

Yanyu Xu, Nianyi Li, Junru Wu, Jingyi Yu, Shenghua Gao

用多任务卷积网络预测个人视觉注意力分布。

Improving Training of Deep Neural Networks via Singular Value Bounding

Kui Jia, Dacheng Tao, Shenghua Gao, Xiangmin Xu

通过约束奇异值改进深度网络训练。

Label Information Guided Graph Construction for Semi-Supervised Learning

Liansheng Zhuang, Zihan Zhou, Shenghua Gao, Jingwen Yin, Zhouchen Lin, Yi Ma

利用样本标签信息指导构图，用于半监督学习。

Locality Constrained Deep Supervised Hashing for Image Retrieval

Hao Zhu, Shenghua Gao

用局部性约束的深度监督哈希进行图像检索。

Remembering history with convolutional LSTM for anomaly detection

Weixin Luo, Wen Liu, Shenghua Gao

用卷积 LSTM 记忆历史信息，检测时序异常。

S2F: Slow-to-Fast Interpolator Flow

Yanchao Yang, Stefano Soatto

按速度由慢到快匹配图像区域，以估计不同运动尺度的光流，特别关注快速移动的小物体。

Structured Attentions for Visual Question Answering

Chen Zhu, Yanpeng Zhao, Shuaiyi Huang, Kewei Tu, Yi Ma

在视觉问答中使用结构化注意力选择图像信息。

A Revisit of Sparse Coding Based Anomaly Detection in Stacked RNN Framework

A Revisit of Sparse Coding Based Anomaly Detection in Stacked RNN Framework

Weixin Luo, Wen Liu, Shenghua Gao

在堆叠循环神经网络中重新研究基于稀疏编码的异常检测。

ROML: A Robust Feature Correspondence Approach for Matching Objects in A Set of Images

Kui Jia, Tsung-Han Chan, Zinan Zeng, Shenghua Gao, Gang Wang, Tianzhu Zhang, Yi Ma

在一组图像之间建立稳健的特征对应关系以匹配物体。

Bi-Level Multi-column Convolutional Neural Networks for Facial Landmark Point Detection

Yanyu Xu, Shenghua Gao

用双层多列卷积网络定位人脸关键点。

Cold-Start Heterogeneous-Device Wireless Localization

Vincent W. Zheng, Hong Cao, Shenghua Gao, Aditi Adhikari, Miao Lin, Kevin Chen-Chuan Chang

研究缺少新设备训练数据时的异构无线设备定位。

DEFEATnet - A Deep Conventional Image Representation for Image Classification

Shenghua Gao, Lixin Duan, Ivor W. Tsang

研究用于图像分类的深层传统图像表示。

Image compression via multiple learned geometric dictionaries

Danlan Huang, Xiaoming Tao, Mai Xu, Shenghua Gao, Jianhua Lu

用多个学习到的几何字典压缩图像。

Locality-preserving low-rank representation for graph construction from nonlinear manifolds

Liansheng Zhuang, Jingjing Wang, Zhouchen Lin, Allen Y. Yang, Yi Ma, Nenghai Yu

采用保留局部结构的低秩表示，从非线性流形数据构图。

Patch-Set-Based Representation for Alignment-Free Image Set Classification

Shenghua Gao, Zinan Zeng, Kui Jia, Tsung-Han Chan, Jinhui Tang

用局部图块集合表示图像，在未对齐条件下分类图像集。

Progressively Parsing Interactional Objects for Fine Grained Action Detection

Bingbing Ni, Xiaokang Yang, Shenghua Gao

逐步解析交互对象，以检测细粒度动作。

Robust Plane-Based Calibration of Multiple Non-Overlapping Cameras

Chen Zhu, Zihan Zhou, Ziran Xing, Yanbing Dong, Yi Ma, Jingyi Yu

基于平面几何稳健地标定多个视野不重叠的相机。

Texture Repairing by Unified Low Rank Optimization

Xiao Liang, Xiang Ren, Zhengdong Zhang, Yi Ma

通过统一的低秩优化修复受损纹理。

Single-Image Crowd Counting via Multi-Column Convolutional Neural Network

Single-Image Crowd Counting via Multi-Column Convolutional Neural Network

Yingying Zhang, Desen Zhou, Siqin Chen, Shenghua Gao, Yi Ma

使用多列卷积神经网络估计单张图像中的人数。

Constructing a Nonnegative Low-Rank and Sparse Graph With Data-Adaptive Features

Liansheng Zhuang, Shenghua Gao, Jinhui Tang, Jingjing Wang, Zhouchen Lin, Yi Ma, Nenghai Yu

用数据自适应特征构建兼具非负、低秩与稀疏性的图。

PCANet: A Simple Deep Learning Baseline for Image Classification?

Tsung-Han Chan, Kui Jia, Shenghua Gao, Jiwen Lu, Zinan Zeng, Yi Ma

构建基于主成分分析的简易深度网络作为图像分类基线。

Shape Tracking with Occlusions via Coarse-to-Fine Region-Based Sobolev Descent

Yanchao Yang, Ganesh Sundaramoorthi

以从粗到细的优化追踪视频中的物体轮廓，同时处理遮挡。

Automatic Layer Separation using Light Field Imaging

Qiaosong Wang, Haiting Lin, Yi Ma, Sing Bing Kang, Jingyi Yu

利用光场成像分离图像中叠加的不同层。

Coarse-to-fine region selection and matching

Yanchao Yang, Zhaojin Lu, Ganesh Sundaramoorthi

由粗到细地选择和匹配图像区域，以估计两幅图像之间的对应关系。

Generalized Multiple Kernel Learning With Data-Dependent Priors

Qi Mao, Ivor W. Tsang, Shenghua Gao, Li Wang

在多核学习中引入由数据决定的先验。

Generalized Tensor Total Variation minimization for visual data recovery?

Xiaojie Guo, Yi Ma

研究广义张量总变差最小化在视觉数据恢复中的应用。

Image Restoration via Simultaneous Sparse Coding: Where Structured Sparsity Meets Gaussian Scale Mixture

Weisheng Dong, Guangming Shi, Yi Ma, Xin Li

结合结构化稀疏性和高斯尺度混合模型，同时编码图像块以复原图像。

Laplacian Auto-Encoders: An explicit learning of nonlinear data manifold

Kui Jia, Lin Sun, Shenghua Gao, Zhan Song, Bertram E. Shi

使用拉普拉斯自编码器显式学习非线性数据流形。

Low-Rank Tensor Approximation with Laplacian Scale Mixture Modeling for Multiframe Image Denoising

Weisheng Dong, Guangyu Li, Guangming Shi, Xin Li, Yi Ma

结合低秩张量逼近与拉普拉斯尺度混合建模为多帧图像去噪。

Neither Global Nor Local: Regularized Patch-Based Representation for Single Sample Per Person Face Recognition

Shenghua Gao, Kui Jia, Liansheng Zhuang, Yi Ma

用正则化的图像块表示，在每人仅有一个样本时进行人脸识别。

Non-blind deblurring of structured images with geometric deformation

Xin Zhang, Fuchun Sun, Guangcan Liu, Yi Ma

研究具有几何变形的结构化图像的非盲去模糊。

Partially Common-Semantic Pursuit for RGB-D Object Recognition

Lu Jin, Zechao Li, Xiangbo Shu, Shenghua Gao, Jinhui Tang

学习 RGB 和深度信息之间的部分共享语义以识别物体。

RGB-D Object Recognition via Incorporating Latent Data Structure and Prior Knowledge

Jinhui Tang, Lu Jin, Zechao Li, Shenghua Gao

利用数据隐含结构及先验知识识别 RGB-D 图像中的物体。

Robust Face Recognition by Constrained Part-based Alignment

Yuting Zhang, Kui Jia, Yueming Wang, Gang Pan, Tsung-Han Chan, Yi Ma

通过约束人脸各局部区域的对齐，实现稳健的人脸识别。

Self-Occlusions and Disocclusions in Causal Video Object Segmentation

Yanchao Yang, Ganesh Sundaramoorthi, Stefano Soatto

在逐帧视频分割中显式建模自遮挡以及重新显露的区域。

Single Sample Face Recognition via Learning Deep Supervised Autoencoders

Shenghua Gao, Yuting Zhang, Kui Jia, Jiwen Lu, Yingying Zhang

用深度监督自编码器开展单样本人脸识别。

Sparse Illumination Learning and Transfer for Single-Sample Face Recognition with Image Corruption and Misalignment

Liansheng Zhuang, Tsung-Han Chan, Allen Y. Yang, S. Shankar Sastry, Yi Ma

学习并迁移稀疏光照信息，识别受损或未对齐的单样本人脸。

Blind Image Deblurring Using Spectral Properties of Convolution Operators

Guangcan Liu, Shiyu Chang, Yi Ma

利用卷积算子的谱性质，在模糊核未知时恢复清晰图像。

Compressive Sensing via Nonlocal Low-Rank Regularization

Weisheng Dong, Guangming Shi, Xin Li, Yi Ma, Feng Huang

将非局部低秩正则化用于压缩感知信号恢复。

Concurrent Single-Label Image Classification and Annotation via Efficient Multi-Layer Group Sparse Coding

Shenghua Gao, Liang-Tien Chia, Ivor Wai-Hung Tsang, Zhixiang Ren

用高效多层组稀疏编码联合完成单标签图像分类与标注。

Discovering joint audio-visual codewords for video event detection

I-Hong Jhuo, Guangnan Ye, Shenghua Gao, Dong Liu, Yu-Gang Jiang, D. T. Lee, Shih-Fu Chang

学习音视频联合码字以检测视频事件。

Efficient Sparsity Estimation via Marginal-Lasso Coding

Tzu-Yi Hung, Jiwen Lu, Yap-Peng Tan, Shenghua Gao

通过边缘 Lasso 编码高效估计稀疏性。

Fast Low-Rank Subspace Segmentation

Xin Zhang, Fuchun Sun, Guangcan Liu, Yi Ma

利用低秩结构快速完成子空间分割。

Hand-Crafted Features or Machine Learnt Features? Together They Improve RGB-D Object Recognition

Lu Jin, Shenghua Gao, Zechao Li, Jinhui Tang

结合人工设计特征与机器学习特征识别 RGB-D 物体。

Hybrid Singular Value Thresholding for Tensor Completion

Xiaoqin Zhang, Zhengyuan Zhou, Di Wang, Yi Ma

使用混合奇异值阈值方法补全缺失的张量数据。

Image restoration via Bayesian structured sparse coding

Weisheng Dong, Xin Li, Yi Ma, Guangming Shi

通过贝叶斯结构化稀疏编码复原图像。

Learning Category-Specific Dictionary and Shared Dictionary for Fine-Grained Image Categorization

Shenghua Gao, Ivor Wai-Hung Tsang, Yi Ma

联合学习类别专属字典与共享字典，用于细粒度图像分类。

MMSE Design of Time and Color Multiplexing Codes

Tsung-Han Chan, Kui Jia, Eliot Wycoff, Yi Ma

按最小均方误差准则设计时间与颜色复用编码。

Nonlocal Sparse and Low-Rank Regularization for Optical Flow Estimation

Weisheng Dong, Guangming Shi, Xiaocheng Hu, Yi Ma

结合非局部稀疏与低秩正则化估计图像光流。

Partial Occlusion Handling for Visual Tracking via Robust Part Matching

Tianzhu Zhang, Kui Jia, Changsheng Xu, Yi Ma, Narendra Ahuja

通过稳健的局部匹配处理视觉跟踪中的部分遮挡。

Region-Based Saliency Detection and Its Application in Object Recognition

Zhixiang Ren, Shenghua Gao, Liang-Tien Chia, Ivor Wai-Hung Tsang

检测显著图像区域，并用于物体识别。

Robust Foreground Detection Using Smoothness and Arbitrariness Constraints

Xiaojie Guo, Xinggang Wang, Liang Yang, Xiaochun Cao, Yi Ma

利用平滑性与任意性约束稳健地检测前景。

Robust Separation of Reflection from Multiple Images

Xiaojie Guo, Xiaochun Cao, Yi Ma

从多张图像中稳健地分离反射成分。

Robust Subspace Discovery via Relaxed Rank Minimization

Xinggang Wang, Zhengdong Zhang, Yi Ma, Xiang Bai, Wenyu Liu, Zhuowen Tu

通过松弛的秩最小化方法稳健地发现数据子空间。

Transform invariant text extraction

Xin Zhang, Zhouchen Lin, Fuchun Sun, Yi Ma

研究对几何变换保持不变的图像文本提取方法。

Unsupervised Feature Learning for RGB-D Image Classification

I-Hong Jhuo, Shenghua Gao, Liansheng Zhuang, D. T. Lee, Yi Ma

以无监督方式学习用于彩色与深度图像分类的特征。

A New View-Invariant Feature for Cross-View Gait Recognition

Worapan Kusakunniran, Qiang Wu, Jian Zhang, Yi Ma, Hongdong Li

构建与观察视角无关的特征，用于跨视角步态识别。

A non-negative sparse promoting algorithm for high resolution hyperspectral imaging

Eliot Wycoff, Tsung-Han Chan, Kui Jia, Wing-Kin Ma, Yi Ma

采用促进非负稀疏解的算法，实现高分辨率高光谱成像。

Background subtraction via coherent trajectory decomposition

Zhixiang Ren, Liang-Tien Chia, Deepu Rajan, Shenghua Gao

通过分解一致运动轨迹，从视频中分离背景。

Fast ℓ1-Minimization Algorithms for Robust Face Recognition

Allen Y. Yang, Zihan Zhou, A. G. Balasubramanian, S. Shankar Sastry, Yi Ma

研究适用于稳健人脸识别的快速 ℓ1 最小化算法。

Joint topic-document modeling via low-dimensional sparse models

Kerui Min, Yi Ma

利用低维稀疏模型对文本主题与文档进行联合建模。

Laplacian Sparse Coding, Hypergraph Laplacian Sparse Coding, and Applications

Shenghua Gao, Ivor Wai-Hung Tsang, Liang-Tien Chia

研究拉普拉斯与超图拉普拉斯稀疏编码。

Learning by Associating Ambiguously Labeled Images

Zinan Zeng, Shijie Xiao, Kui Jia, Tsung-Han Chan, Shenghua Gao, Dong Xu, Yi Ma

通过关联标签含义模糊的图像进行学习。

Modeling Self-Occlusions in Dynamic Shape and Appearance Tracking

Yanchao Yang, Ganesh Sundaramoorthi

在动态形状与外观跟踪中显式建模物体的自遮挡。

Objective-Guided Image Annotation

Qi Mao, Ivor Wai-Hung Tsang, Shenghua Gao

研究以指定目标驱动的图像自动标注。

Plane-Based Content Preserving Warps for Video Stabilization

Zihan Zhou, Hailin Jin, Yi Ma

使用基于平面的保内容变形实现视频稳定。

Rectification of Optical Characters as Transform Invariant Low-Rank Textures

Xin Zhang, Zhouchen Lin, Fuchun Sun, Yi Ma

将光学字符视为变换不变的低秩纹理并进行几何校正。

Regularized Feature Reconstruction for Spatio-Temporal Saliency Detection

Zhixiang Ren, Shenghua Gao, Liang-Tien Chia, Deepu Rajan

通过正则化特征重建检测时空显著区域。

Robust Recovery of Subspace Structures by Low-Rank Representation

Guangcan Liu, Zhouchen Lin, Shuicheng Yan, Ju Sun, Yong Yu, Yi Ma

通过低秩表示稳健地恢复数据中的子空间结构。

Rotation-Invariant Features for Multi-Oriented Text Detection in Natural Images

Cong Yao, Xin Zhang, Xiang Bai, Wenyu Liu, Yi Ma, Zhuowen Tu

用旋转不变特征检测自然图像中不同朝向的文字。

Simultaneous Rectification and Alignment via Robust Recovery of Low-rank Tensors

Xiaoqin Zhang, Di Wang, Zhengyuan Zhou, Yi Ma

通过稳健的低秩张量恢复同时完成几何校正和对齐。

Single-Sample Face Recognition with Image Corruption and Misalignment via Sparse Illumination Transfer

Liansheng Zhuang, Allen Y. Yang, Zihan Zhou, S. Shankar Sastry, Yi Ma

在图像受损或错位时，通过稀疏光照迁移进行单样本人脸识别。

Sparse Representation With Kernels

Shenghua Gao, Ivor Wai-Hung Tsang, Liang-Tien Chia

研究在核空间中构建稀疏表示。

Video Editing with Temporal, Spatial and Appearance Consistency

Xiaojie Guo, Xiaochun Cao, Xiaowu Chen, Yi Ma

在视频编辑中维持时间、空间与外观的一致性。

Matching Through Features and Features Through Matching

Ganesh Sundaramoorthi, Yanchao Yang

联合估计图像特征和对应关系，研究匹配中的不变性与区分能力。

Collaborative Representation based Classification for Face Recognition

Lei Zhang, Meng Yang, Xiangchu Feng, Yi Ma, David Zhang

用协同表示对人脸图像分类，并研究其对识别的作用。

Compressive principal component pursuit

John Wright, Arvind Ganesh, Kerui Min, Yi Ma

研究利用压缩观测进行主成分追踪的方法。

Detecting texts of arbitrary orientations in natural images

Cong Yao, Xiang Bai, Wenyu Liu, Yi Ma, Zhuowen Tu

检测自然图像中任意朝向的文字。

Learning Class-to-Image Distance via Large Margin and L1-Norm Regularization

Zhengxiang Wang, Shenghua Gao, Liang-Tien Chia

用大间隔与 L1 正则化学习类别到图像的距离。

Non-negative low rank and sparse graph for semi-supervised learning

Liansheng Zhuang, Haoyuan Gao, Zhouchen Lin, Yi Ma, Xin Zhang, Nenghai Yu

构建非负、低秩且稀疏的图用于半监督学习。

One-Class Multiple Instance Learning via Robust PCA for Common Object Discovery

Xinggang Wang, Zhengdong Zhang, Yi Ma, Xiang Bai, Wenyu Liu, Zhuowen Tu

将稳健主成分分析用于单类多实例学习，以发现图像中的共同物体。

Principal Component Pursuit with reduced linear measurements

Arvind Ganesh, Kerui Min, John Wright, Yi Ma

分析主成分追踪如何在较少的线性观测下恢复信号。

RASL: Robust Alignment by Sparse and Low-Rank Decomposition for Linearly Correlated Images

YiGang Peng, Arvind Ganesh, John Wright, Wenli Xu, Yi Ma

对线性相关图像进行稀疏与低秩分解，实现稳健对齐。

Repairing Sparse Low-Rank Texture

Xiao Liang, Xiang Ren, Zhengdong Zhang, Yi Ma

修复同时具有稀疏和低秩结构的纹理。

Robust and Practical Face Recognition via Structured Sparsity

Kui Jia, Tsung-Han Chan, Yi Ma

以结构化稀疏表示实现稳健的人脸识别。

Robust plane-based structure from motion

Zihan Zhou, Hailin Jin, Yi Ma

利用平面几何约束稳健地从运动影像恢复三维结构。

Seeing through the blur

Hossein Mobahi, C. Lawrence Zitnick, Yi Ma

为仿射及单应变换下的图像配准推导平滑目标函数的模糊核。

Spatiotemporal Saliency Detection via Sparse Representation

Zhixiang Ren, Shenghua Gao, Deepu Rajan, Liang-Tien Chia, Yun Huang

利用稀疏表示检测时空显著区域。

TILT: Transform Invariant Low-Rank Textures

Zhengdong Zhang, Arvind Ganesh, Xiao Liang, Yi Ma

从几何变换后的图像中恢复低秩纹理。

Toward a Practical Face Recognition System: Robust Alignment and Illumination by Sparse Representation

Andrew Wagner, John Wright, Arvind Ganesh, Zihan Zhou, Hossein Mobahi, Yi Ma

利用稀疏表示处理人脸识别中的图像对齐和光照差异。

Towards Optimal Design of Time and Color Multiplexing Codes

Tsung-Han Chan, Kui Jia, Eliot Wycoff, Chong-Yung Chi, Yi Ma

研究时间与颜色复用编码的最优设计。

Camera calibration with lens distortion from low-rank textures

Zhengdong Zhang, Yasuyuki Matsushita, Yi Ma

利用低秩纹理，在存在镜头畸变时进行相机标定。

Face recovery in conference video streaming using robust principal component analysis

Wai-tian Tan, Gene Cheung, Yi Ma

使用稳健主成分分析恢复视频会议画面中的人脸。

Fast ℓ1-minimization and parallelization for face recognition

Victor Shia, Allen Y. Yang, S. Shankar Sastry, Andrew Wagner, Yi Ma

研究面向人脸识别的快速 ℓ1 最小化及并行计算。

Holistic 3D reconstruction of urban structures from low-rank textures

Hossein Mobahi, Zihan Zhou, Allen Y. Yang, Yi Ma

从低秩纹理出发，整体重建城市结构的三维几何。

Multi-layer group sparse coding - For concurrent image classification and annotation

Shenghua Gao, Liang-Tien Chia, Ivor Wai-Hung Tsang

用多层组稀疏编码同时进行图像分类和标注。

Segmentation of Natural Images by Texture and Boundary Compression

Hossein Mobahi, Shankar R. Rao, Allen Y. Yang, Shankar S. Sastry, Yi Ma

依据纹理与边界的压缩编码对自然图像进行分割。

Sparsity and Robustness in Face Recognition

John Wright, Arvind Ganesh, Allen Y. Yang, Zihan Zhou, Yi Ma

分析稀疏性在人脸识别鲁棒性中的作用。

Unwrapping low-rank textures on generalized cylindrical surfaces

Zhengdong Zhang, Xiao Liang, Yi Ma

展开广义柱面上的低秩纹理。

Robust principal component analysis?

Robust principal component analysis?

Emmanuel J. Candès, Xiaodong Li, Yi Ma, John Wright

研究如何从受异常值污染的数据中稳健地恢复主成分。

Adaptive control using quantized measurements with application to vision-only landing control

Yoav Sharon, Daniel Liberzon, Yi Ma

利用量化测量进行自适应控制，并用于仅依赖视觉的着陆控制。

Automatic image tagging via category label and web data

Shenghua Gao, Zhengxiang Wang, Liang-Tien Chia, Ivor Wai-Hung Tsang

利用类别标签和网络数据自动为图像加标签。

Compact projection: Simple and efficient near neighbor search with practical memory requirements

Kerui Min, Linjun Yang, John Wright, Lei Wu, Xian-Sheng Hua, Yi Ma

通过紧凑投影降低近邻搜索的内存需求。

Decomposing background topics from keywords by principal component pursuit

Kerui Min, Zhengdong Zhang, John Wright, Yi Ma

利用主成分追踪从关键词中分离背景主题。

Dense error correction for low-rank matrices via Principal Component Pursuit

Arvind Ganesh, John Wright, Xiaodong Li, Emmanuel J. Candès, Yi Ma

利用主成分追踪纠正低秩矩阵中的密集误差。

Dense error correction via l1-minimization

John Wright, Yi Ma

通过 ℓ1 最小化纠正密集误差。

Discovering Class-Specific Informative Patches and Its Application in Landmark Charaterization

Shenghua Gao, Xiangang Cheng, Liang-Tien Chia

发现能区分类别的局部图块，用于描述地标。

Fast l1-minimization algorithms and an application in robust face recognition: A review

Allen Y. Yang, S. Shankar Sastry, Arvind Ganesh, Yi Ma

综述快速 ℓ1 最小化算法及其在稳健人脸识别中的应用。

Image Super-Resolution Via Sparse Representation

Jianchao Yang, John Wright, Thomas S. Huang, Yi Ma

以稀疏表示从低分辨率图像重建高分辨率图像。

Image tag refinement towards low-rank, content-tag prior and error sparsity

Guangyu Zhu, Shuicheng Yan, Yi Ma

结合低秩结构、内容与标签先验及误差稀疏性修正图像标签。

Kernel Sparse Representation for Image Classification and Face Recognition

Shenghua Gao, Ivor Wai-Hung Tsang, Liang-Tien Chia

用核稀疏表示进行图像分类及人脸识别。

Local features are not lonely - Laplacian sparse coding for image classification

Shenghua Gao, Ivor Wai-Hung Tsang, Liang-Tien Chia, Peilin Zhao

在稀疏编码中关联局部特征以进行图像分类。

Motion Segmentation in the Presence of Outlying, Incomplete, or Corrupted Trajectories

Shankar R. Rao, Roberto Tron, René Vidal, Yi Ma

在轨迹含离群点、缺失或损坏的条件下分割不同运动。

On the Role of Sparse and Redundant Representations in Image Processing

Michael Elad, Mário A. T. Figueiredo, Yi Ma

分析稀疏表示与冗余表示在图像处理中的作用。

RASL: Robust alignment by sparse and low-rank decomposition for linearly correlated images

YiGang Peng, Arvind Ganesh, John Wright, Wenli Xu, Yi Ma

通过稀疏和低秩分解，对线性相关的一组图像进行稳健配准。

Robust Algebraic Segmentation of Mixed Rigid-Body and Planar Motions from Two Views

Shankar R. Rao, Allen Y. Yang, Shankar Sastry, Yi Ma

从两个视角稳健地分割混合的刚体运动和平面运动。

Robust Photometric Stereo via Low-Rank Matrix Completion and Recovery

Lun Wu, Arvind Ganesh, Boxin Shi, Yasuyuki Matsushita, Yongtian Wang, Yi Ma

利用低秩矩阵补全与恢复实现稳健的光度立体重建。

Sparse Representation for Computer Vision and Pattern Recognition

John Wright, Yi Ma, Julien Mairal, Guillermo Sapiro, Thomas S. Huang, Shuicheng Yan

介绍稀疏表示在计算机视觉和模式识别中的应用。

Stable Principal Component Pursuit

Zihan Zhou, Xiaodong Li, John Wright, Emmanuel J. Candès, Yi Ma

分析主成分追踪方法在存在扰动时的稳定性。

The Augmented Lagrange Multiplier Method for Exact Recovery of Corrupted Low-Rank Matrices

Zhouchen Lin, Minming Chen, Yi Ma

用增广拉格朗日乘子法精确恢复受到破坏的低秩矩阵。

TILT: Transform Invariant Low-Rank Textures

Zhengdong Zhang, Xiao Liang, Arvind Ganesh, Yi Ma

研究纹理低秩结构在几何变换下的恢复方法。

Towards a robust face recognition system using compressive sensing

Allen Y. Yang, Zihan Zhou, Yi Ma, Shankar Sastry

以压缩感知构建稳健的人脸识别系统。

Web image concept annotation with better understanding of tags and visual features

Shenghua Gao, Liang-Tien Chia, Xiangang Cheng

结合网页标签与视觉特征进行网络图像概念标注。

Wikipedia-assisted concept thesaurus for better web media understanding

Huan Wang, Liang-Tien Chia, Shenghua Gao

借助维基百科构建概念词表，辅助理解网络媒体。

Classification via Minimum Incremental Coding Length

John Wright, Yi Ma, Yangyu Tao, Zhouchen Lin, Heung-Yeung Shum

用编码长度的最小增量作为分类准则。

Concept model-based unsupervised web image re-ranking

Shenghua Gao, Xiangang Cheng, Huan Wang, Liang-Tien Chia

利用概念模型对网络图像的检索结果进行无监督重排序。