Video Understanding

Procedure Learning via Regularized Gromov-Wasserstein Optimal Transport WACV 2026 Progressive Visual Refinement for Multi-modal Summarization EACL 2026 ProSkill: Segment-Level Skill Assessment in Procedural Videos WACV 2026 Putting Captions to the Test: Evaluating Video Caption Quality through Multiple-Choice Question Answering ACL 2026 PyraTok: Language-Aligned Pyramidal Tokenizer for Video Understanding and Generation CVPR 2026 QUANTIPHY: A Quantitative Benchmark Evaluating Physical Reasoning Abilities of Vision-Language Models CVPR 2026 Question-guided Visual Compression with Memory Feedback for Long-Term Video Understanding CVPR 2026 RAVU: Retrieval Augmented Video Understanding with Compositional Reasoning over Graph WACV 2026 RefineVAD: Semantic-Guided Feature Recalibration for Weakly Supervised Video Anomaly Detection AAAI 2026 ReFlow: Self-correction Motion Learning for Dynamic Scene Reconstruction CVPR 2026 Reinforce to Learn, Elect to Reason: A Dual Paradigm for Video Reasoning CVPR 2026 Reinforcing Structured Chain-of-Thought for Video Understanding CVPR 2026 Remembrall: Leaning into Memory for Accurate Video Analytics on System-on-Chip GPUs NSDI 2026 ReMoRa: Multimodal Large Language Model based on Refined Motion Representation for Long-Video Understanding CVPR 2026 ReScene4D: Temporally Consistent Semantic Instance Segmentation of Evolving Indoor 3D Scenes CVPR 2026 Response-G1: Explicit Scene Graph Modeling for Proactive Streaming Video Understanding ACL 2026 Rethinking Surgical Smoke: A Smoke-Type-Aware Laparoscopic Video Desmoking Method and Dataset AAAI 2026 ReTrack: Evidence-Driven Dual-Stream Directional Anchor Calibration Network for Composed Video Retrieval AAAI 2026 REVISOR: Beyond Textual Reflection, Towards Multimodal Introspective Reasoning in Long-Form Video Understanding CVPR 2026 RipAlert: A Future-Frame-Aware Framework for Rip Current Forecasting and Early Alerting AAAI 2026 SAGA: Source Attribution of Generative AI Videos CVPR 2026 SAGE: Synergistic Adaptive Gating of Experts for Hateful Video Detection ACL 2026 SAGE: Training Smart Any-Horizon Agents for Long Video Reasoning with Reinforcement Learning CVPR 2026 SalDiff-DTM: A Novel Dual-Temporal Modulated Diffusion Model for Omnidirectional Images Scanpath Prediction AAAI 2026 SARL-STG: A Spatially Aware Reinforcement Learning Framework for Refining MLLMs in Spatio-Temporal Video Grounding CVPR 2026