Video Understanding

TubeRMC: Tube-conditioned Reconstruction with Mutual Constraints for Weakly-supervised Spatio-Temporal Video Grounding AAAI 2026 TVHighlights: LLM-Guided Human-Free Collaborative Training for Video Highlight Detection in Movies and TV Dramas CVPR 2026 TWiST: Temporal Weakly-Supervised Triplets Recognition in Surgical Videos (Student Abstract) AAAI 2026 UFVideo: Towards Unified Fine-Grained Video Cooperative Understanding with Large Language Models CVPR 2026 Understanding Dynamic Scenes in Ego Centric 4D Point Clouds AAAI 2026 Understanding Temporal Logic Consistency in Video-Language Models through Cross-Modal Attention Discriminability CVPR 2026 Unified Spatiotemporal Token Compression for Video-LLMs at Ultra-Low Retention CVPR 2026 Unleashing Vision-Language Semantics for Deepfake Video Detection CVPR 2026 Unstitching the Chimera: Frame-Level Risk and Train-Free Mitigation for Video Hallucination CVPR 2026 VAGU & GtS: LLM-Based Benchmark and Framework for Joint Video Anomaly Grounding and Understanding AAAI 2026 VALU: A Benchmark for Video Anomaly Temporal Localization and Understanding at Multiple Semantic Levels ACL 2026 VAST: Video Ability-Stratified Taxonomy for Data-Efficient Video Reasoning CVPR 2026 VecAttention: Vector-wise Sparse Attention for Accelerating Long Context Inference CVPR 2026 VFace: A Training-Free Approach for Diffusion-Based Video Face Swapping WACV 2026 v-HUB: A Benchmark for Video Humor Understanding from Vision and Sound ACL 2026 VideoARM: Agentic Reasoning over Hierarchical Memory for Long-Form Video Understanding CVPR 2026 VideoAuto-R1: Video Auto Reasoning via Thinking Once, Answering Twice CVPR 2026 VideoChat-A1: Thinking with Long Videos by Chain-of-Shot Reasoning AAAI 2026 VideoChat-M1: Collaborative Policy Planning for Video Understanding via Multi-Agent Reinforcement Learning CVPR 2026 Video-CoE: Reinforcing Video Event Prediction via Chain of Events CVPR 2026 VideoCuRL: Video Curriculum Reinforcement Learning with Orthogonal Difficulty Decomposition ACL 2026 VideoITG: Multimodal Video Understanding with Instructed Temporal Grounding CVPR 2026 Video Mirror Detection with the Motion-in-Depth Cue AAAI 2026 Video Panels for Long Video Understanding CVPR 2026 VideoPro: Adaptive Program Reasoning for Long Video Understanding ACL 2026