MCG-NJU

[NeurIPS 2022 Spotlight] VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training

SteadyDancer: Harmonized and Coherent Human Image Animation with First-Frame Preservation

[CVPR 2025] Multiple Object Tracking as ID Prediction

[CVPR 2022 Oral & TPAMI 2024] MixFormer: End-to-End Tracking with Iterative Mixed Attention

[CVPR 2023] Extracting Motion and Appearance via Inter-Frame Attention for Efficient Video Frame Interpolatio

[ICCV 2023 & TPAMI 2026] SparseBEV: High-Performance Sparse 3D Object Detection from Multi-Camera Videos

[ECCV 2024] Fully Sparse 3D Occupancy Prediction & RayIoU Evaluation Metric

[CVPR 2026] DDT: Decoupled Diffusion Transformer

[CVPR 2021] TDN: Temporal Difference Networks for Efficient Action Recognition

VideoChat3: a generalist video MLLM built for fine-grained motion, long-form reasoning, temporal grounding, and online proactive response.

VideoJev: System One Model for Video Understanding and Interaction

TavernGym and TavernBench: a faithful, full-content Hearthstone Battlegrounds simulator with an RL interface, and a 960-task decision benchmark. Code and data for "Build, Don't Play".

[ECCV 2020] Actions as Moving Points

[CVPR 2022 Oral & TPAMI 2023] Learning Optical Flow and Scene Flow with Bidirectional Camera-LiDAR Fusion

OneStreamer: Unifying Perception, Memory, and Proactive Response in Streaming Video Interaction

[CVPR 2022 Oral] AdaMixer: A Fast-Converging Query-Based Object Detector

[ICCV 2023] MeMOTR: Long-Term Memory-Augmented Transformer for Multi-Object Tracking

[ICCV 2023] SportsMOT: A Large Multi-Object Tracking Dataset in Multiple Sports Scenes

[NeurIPS 2023] MixFormerV2: Efficient Fully Transformer Tracking

[ICLR 2026] PixNerd: Pixel Neural Field Diffusion

[NeurIPS 2024] VFIMamba: Video Frame Interpolation with State Space Models

TimeLens2: Generalist Video Temporal Grounding with Multimodal LLMs

[ICCV 2021] MultiSports: A Multi-Person Video Dataset of Spatio-Temporally Localized Sports Actions

[NeurIPS 2025 Spotlight] StreamForest: Efficient Online Video Understanding with Persistent Event Memory

[TIP 2021] SADRNet: Self-Aligned Dual Face Regression Networks for Robust 3D Dense Face Alignment and Reconstruction

[ICML 2026] Video-o3: Native Interleaved Clue Seeking for Long Video Multi-Hop Reasoning

[NeurIPS 2024] AWT: Transferring Vision-Language Models via Augmentation, Weighting, and Transportation

[ICCV2023] MixSort: The Customized Tracker in SportsMOT

[CVPR 2025] Online Video Understanding: OVBench and VideoChat-Online

[CVPR 2023] LinK: Linear Kernel for LiDAR-based 3D Perception

[ICCV 2021] Relaxed Transformer Decoders for Direct Action Proposal Generation

[CVIU] Fully Convolutional Online Tracking

[AAAI 2022] Negative Sample Matters: A Renaissance of Metric Learning for Temporal Grounding

[ECCV 2020] Boundary-Aware Cascade Networks for Temporal Action Segmentation

[CVPR 2024] Sparse Global Matching for Video Frame Interpolation with Large Motion

[CVPR 2024] BIVDiff: A Training-free Framework for General-Purpose Video Synthesis via Bridging Image and Video Diffusion Models

SAM 2++: Tracking Anything at Any Granularity

[NeurIPS 2022 Spotlight] VideoMAE for Action Detection

[CVPR 2022] Structured Sparse R-CNN for Direct Scene Graph Generation

[CVPR 2023] STMixer: A One-Stage Sparse Action Detector

UniAVGen: Unified Audio and Video Generation with Asymmetric Cross-Modal Interactions

Learning Spatiotemporal Features via Video and Text Pair Discrimination

[ICCV 2021] Target Adaptive Context Aggregation for Video Scene Graph Generation

[CVPR 2022] Progressive Attention on Multi-Level Dense Difference Maps for Generic Event Boundary Detection

[CVPR 2025] Tra-MoE: Learning Trajectory Prediction Model from Multiple Domains for Adaptive Policy Conditioning

Motion-Aware Generative Frame Interpolation

[ICCV 2021] MGSampler: An Explainable Sampling Strategy for Video Action Recognition

Context-aware RCNN: a Baseline for Action Detection in Videos

BasicTAD: an Astounding RGB-Only Baselinefor Temporal Action Detection