Limin Wang

CoMo: Learning Continuous Latent Motion from Internet Videos for Scalable Robot Learning CVPR 2026 DDT: Decoupled Diffusion Transformer CVPR 2026 Flowing Backwards: Improving Normalizing Flows via Reverse Representation Alignment AAAI 2026 InternVideo-Next: Towards World-Understanding Video Models CVPR 2026 TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning CVPR 2026 TimeLens: Rethinking Video Temporal Grounding with Multimodal LLMs CVPR 2026 UniAVGen: Unified Audio and Video Generation with Asymmetric Cross-Modal Interactions CVPR 2026 VideoChat-A1: Thinking with Long Videos by Chain-of-Shot Reasoning AAAI 2026 VideoRealBench: A Chain-of-Thought Realism Evaluation Benchmark for Generated Human-Centric Videos CVPR 2026 VMonarch: Efficient Video Diffusion Transformers with Structured Attention CVPR 2026 Bootstrapping Language-Guided Navigation Learning with Self-Refining Data Flywheel ICLR 2025 CG-Bench: Clue-grounded Question Answering Benchmark for Long Video Understanding ICLR 2025 Contextual AD Narration with Interleaved Multimodal Sequence CVPR 2025 Differentiable Solver Search for Fast Diffusion Sampling ICML 2025 LeviTor: 3D Trajectory Oriented Image-to-Video Synthesis CVPR 2025 Make Your Training Flexible: Towards Deployment-Efficient Video Models ICCV 2025 MobileViCLIP: An Efficient Video-Text Model for Mobile Devices ICCV 2025 Modeling Fine-Grained Hand-Object Dynamics for Egocentric Video Representation Learning ICLR 2025 Multiple Object Tracking as ID Prediction CVPR 2025 OmniCorpus: A Unified Multimodal Corpus of 10 Billion-Level Images Interleaved with Text ICLR 2025 Online Video Understanding: OVBench and VideoChat-Online CVPR 2025 p-MoD: Building Mixture-of-Depths MLLMs via Progressive Ratio Decay ICCV 2025 Scalable Image Tokenization with Index Backpropagation Quantization ICCV 2025 SPA: 3D Spatial-Awareness Enables Effective Embodied Representation ICLR 2025 Stochastic Layer-Wise Shuffle for Improving Vision Mamba Training ICML 2025 Task Preference Optimization: Improving Multimodal Large Language Models with Vision Task Alignment CVPR 2025 TimeSuite: Improving MLLMs for Long Video Understanding via Grounded Tuning ICLR 2025 Tra-MoE: Learning Trajectory Prediction Model from Multiple Domains for Adaptive Policy Conditioning CVPR 2025 Transferring Foundation Models for Generalizable Robotic Manipulation WACV 2025 VRBench: A Benchmark for Multi-Step Reasoning in Long Narrative Videos ICCV 2025 Accelerating Image Generation with Sub-path Linear Approximation Model ECCV 2024 Adapting Short-Term Transformers for Action Detection in Untrimmed Videos CVPR 2024 Asymmetric Masked Distillation for Pre-Training Small Foundation Models CVPR 2024 AWT: Transferring Vision-Language Models via Augmentation, Weighting, and Transportation NeurIPS 2024 BIVDiff: A Training-Free Framework for General-Purpose Video Synthesis via Bridging Image and Video Diffusion Models CVPR 2024 Does Video-Text Pretraining Help Open-Vocabulary Online Action Detection? NeurIPS 2024 Dual DETRs for Multi-Label Temporal Action Detection CVPR 2024 EgoExoLearn: A Dataset for Bridging Asynchronous Ego- and Exo-centric View of Procedural Activities in Real World CVPR 2024 Exploring DCN-like architecture for fast image generation with arbitrary resolution NeurIPS 2024 Fully Sparse 3D Occupancy Prediction ECCV 2024 InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation ICLR 2024 InternVideo2: Scaling Foundation Models for Multimodal Video Understanding ECCV 2024 MVBench: A Comprehensive Multi-modal Video Understanding Benchmark CVPR 2024 Scaffold-GS: Structured 3D Gaussians for View-Adaptive Rendering CVPR 2024 SparseFormer: Sparse Visual Recognition via Limited Latent Tokens ICLR 2024 Sparse Global Matching for Video Frame Interpolation with Large Motion CVPR 2024 SportsHHI: A Dataset for Human-Human Interaction Detection in Sports Videos CVPR 2024 StableDrag: Stable Dragging for Point-based Image Editing ECCV 2024 VBench: Comprehensive Benchmark Suite for Video Generative Models CVPR 2024 VFIMamba: Video Frame Interpolation with State Space Models NeurIPS 2024 VideoMamba: State Space Model for Efficient Video Understanding ECCV 2024 ZeroI2V: Zero-Cost Adaptation of Pre-Trained Transformers from Image to Video ECCV 2024 CoMAE: Single Model Hybrid Pre-training on Small-Scale RGB-D Datasets AAAI 2023 Deep Equilibrium Object Detection ICCV 2023 Efficient Video Action Detection with Token Dropout and Context Refinement ICCV 2023 Extracting Motion and Appearance via Inter-Frame Attention for Efficient Video Frame Interpolation CVPR 2023 Filter-Recovery Network for Multi-Speaker Audio-Visual Speech Separation ICLR 2023 JourneyDB: A Benchmark for Generative Image Understanding NeurIPS 2023 LinK: Linear Kernel for LiDAR-Based 3D Perception CVPR 2023 Memory-and-Anticipation Transformer for Online Action Understanding ICCV 2023 MeMOTR: Long-Term Memory-Augmented Transformer for Multi-Object Tracking ICCV 2023 MGMAE: Motion Guided Masking for Video Masked Autoencoding ICCV 2023 MixFormerV2: Efficient Fully Transformer Tracking NeurIPS 2023 PDPP:Projected Diffusion for Procedure Planning in Instructional Videos CVPR 2023 SparseBEV: High-Performance Sparse 3D Object Detection from Multi-Camera Videos ICCV 2023 SportsMOT: A Large Multi-Object Tracking Dataset in Multiple Sports Scenes ICCV 2023 StageInteractor: Query-based Object Detector with Cross-stage Interaction ICCV 2023 STMixer: A One-Stage Sparse Action Detector CVPR 2023 UniFormerV2: Unlocking the Potential of Image ViTs for Video Understanding ICCV 2023 Unmasked Teacher: Towards Training-Efficient Video Foundation Models ICCV 2023 VideoMAE V2: Scaling Video Masked Autoencoders With Dual Masking CVPR 2023 AdaMixer: A Fast-Converging Query-Based Object Detector CVPR 2022 Cross-Architecture Self-Supervised Video Representation Learning CVPR 2022 DCAN: Improving Temporal Action Detection via Dual Context Aggregation AAAI 2022 Joint-Modal Label Denoising for Weakly-Supervised Audio-Visual Video Parsing ECCV 2022 MixFormer: End-to-End Tracking With Iterative Mixed Attention CVPR 2022 Negative Sample Matters: A Renaissance of Metric Learning for Temporal Grounding AAAI 2022 OCSampler: Compressing Videos to One Clip With Single-Step Sampling CVPR 2022 PointTAD: Multi-Label Temporal Action Detection with Learnable Query Points NeurIPS 2022 Progressive Attention on Multi-Level Dense Difference Maps for Generic Event Boundary Detection CVPR 2022 Structured Sparse R-CNN for Direct Scene Graph Generation CVPR 2022 Task-Specific Inconsistency Alignment for Domain Adaptive Object Detection CVPR 2022 VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training NeurIPS 2022 CGA-Net: Category Guided Aggregation for Point Cloud Semantic Segmentation CVPR 2021 MGSampler: An Explainable Sampling Strategy for Video Action Recognition ICCV 2021 MultiSports: A Multi-Person Video Dataset of Spatio-Temporally Localized Sports Actions ICCV 2021 Mutual Supervision for Dense Object Detection ICCV 2021 PyMAF: 3D Human Pose and Shape Regression With Pyramidal Mesh Alignment Feedback Loop ICCV 2021 Relaxed Transformer Decoders for Direct Action Proposal Generation ICCV 2021 Self Supervision to Distillation for Long-Tailed Visual Recognition ICCV 2021 TAM: Temporal Adaptive Module for Video Recognition ICCV 2021 Target Adaptive Context Aggregation for Video Scene Graph Generation ICCV 2021 TDN: Temporal Difference Networks for Efficient Action Recognition CVPR 2021 Actions as Moving Points ECCV 2020 Boundary-Aware Cascade Networks for Temporal Action Segmentation ECCV 2020 Context-Aware RCNN: A Baseline for Action Detection in Videos ECCV 2020 Finding Action Tubes with a Sparse-to-Dense Framework AAAI 2020 Knowledge Integration Networks for Action Recognition AAAI 2020 SketchyCOCO: Image Generation From Freehand Scene Sketches CVPR 2020 TEA: Temporal Excitation and Aggregation for Action Recognition CVPR 2020 TEINet: Towards an Efficient Architecture for Video Recognition AAAI 2020 V4D: 4D Convolutional Neural Networks for Video-level Representation Learning ICLR 2020 Dynamically Visual Disambiguation of Keyword-based Image Search IJCAI 2019 Learning Actor Relation Graphs for Group Activity Recognition CVPR 2019 LIP: Local Importance-Based Pooling ICCV 2019 StNet: Local and Global Spatial-Temporal Modeling for Action Recognition AAAI 2019 Translate-to-Recognize Networks for RGB-D Scene Recognition CVPR 2019 Appearance-and-Relation Networks for Video Classification CVPR 2018 Single Image Highlight Removal with a Sparse and Low-Rank Reflection Model ECCV 2018 Temporal Action Detection With Structured Segment Networks ICCV 2017 Thin-Slicing Network: A Deep Structured Model for Pose Estimation in Videos CVPR 2017 UntrimmedNets for Weakly Supervised Action Recognition and Detection CVPR 2017 Actionness Estimation Using Hybrid Fully Convolutional Networks CVPR 2016 Real-Time Action Recognition With Enhanced Motion Vector CNNs CVPR 2016 Action Recognition With Trajectory-Pooled Deep-Convolutional Descriptors CVPR 2015 Multi-View Super Vector for Action Recognition CVPR 2014 Mining Motion Atoms and Phrases for Complex Action Recognition ICCV 2013 Motionlets: Mid-level 3D Parts for Human Motion Recognition CVPR 2013 PAL: A Chatterbot System for Answering Domain-specific Questions ACL 2013