Video Understanding

MDP3: A Training-free Approach for List-wise Frame Selection in Video-LLMs ICCV 2025 METok: Multi-Stage Event-based Token Compression for Efficient Long Video Understanding EMNLP 2025 MHBench: Demystifying Motion Hallucination in VideoLLMs AAAI 2025 MimicMotion: High-Quality Human Motion Video Generation with Confidence-aware Pose Guidance ICML 2025 MINERVA: Evaluating Complex Video Reasoning ICCV 2025 Minimizing Labeled, Maximizing Unlabeled: An Image-Driven Approach for Video Instance Segmentation CVPR 2025 Mitigating the Discrepancy Between Video and Text Temporal Sequences: A Time-Perception Enhanced Video Grounding method for LLM COLING 2025 MITracker: Multi-View Integration for Visual Object Tracking CVPR 2025 M-LLM Based Video Frame Selection for Efficient Video Understanding CVPR 2025 MLVU: Benchmarking Multi-task Long Video Understanding CVPR 2025 MMEgo: Towards Building Egocentric Multimodal LLMs for Video QA ICLR 2025 MMVU: Measuring Expert-Level Multi-Discipline Video Understanding CVPR 2025 MoMa: Modulating Mamba for Adapting Image Foundation Models to Video Recognition ICML 2025 Moment Quantization for Video Temporal Grounding ICCV 2025 More Than Meets the Eye: Enhancing Multi-Object Tracking Even with Prolonged Occlusions ICML 2025 MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning ICCV 2025 MotionAgent: Fine-grained Controllable Video Generation via Motion Field Agent ICCV 2025 Motion-aware Contrastive Learning for Temporal Panoptic Scene Graph Generation AAAI 2025 MotionBench: Benchmarking and Improving Fine-grained Video Motion Understanding for Vision Language Models CVPR 2025 Motion Blender Gaussian Splatting for Dynamic Reconstruction CoRL 2025 Motion-Grounded Video Reasoning: Understanding and Perceiving Motion at Pixel Level CVPR 2025 MOVE: Motion-Guided Few-Shot Video Object Segmentation ICCV 2025 Movie101v2: Improved Movie Narration Benchmark ACL 2025 MPG-SAM 2: Adapting SAM 2 with Mask Priors and Global Context for Referring Video Object Segmentation ICCV 2025 MSR2: A Benchmark for Multi-Source Retrieval and Reasoning in Visual Question Answering NAACL 2025