Video Understanding

SAVA-X: Ego-to-Exo Imitation Error Detection via Scene-Adaptive View Alignment and Bidirectional Cross View Fusion CVPR 2026 Scaling the Long Video Understanding of Multimodal Large Language Models via Visual Memory Mechanism CVPR 2026 Scene-VLM: Multimodal Video Scene Segmentation via Vision-Language Models CVPR 2026 SciEducator: Scientific Video Understanding and Educating via Deming-Cycle Multi-Agent System CVPR 2026 SEASON: Mitigating Temporal Hallucination in Video Large Language Models via Self-Diagnostic Contrastive Decoding CVPR 2026 Seeing the Scene Matters: Revealing Forgetting in Video Understanding Models with a Scene-Aware Long-Video Benchmark CVPR 2026 See the Forest for the Trees: Loosely Speculative Decoding via Visual-Semantic Guidance for Efficient Inference of Video LLMs ACL 2026 Segment, Embed, and Align: A Universal Recipe for Aligning Subtitles to Signing ACL 2026 Select Less, Reason More: Prioritizing Evidence Purity for Video Reasoning CVPR 2026 Self-Critical Distillation Network for Video-based Commonsense Captioning CVPR 2026 SMV-EAR: Bring Spatiotemporal Multi-View Representation Learning into Efficient Event-Based Action Recognition CVPR 2026 SPARROW: Learning Spatial Precision and Temporal Referential Consistency in Pixel-Grounded Video MLLMs CVPR 2026 Spatio-Temporal Distortion Aware Omnidirectional Video Super-Resolution AAAI 2026 Spectral Scalpel: Amplifying Adjacent Action Discrepancy via Frequency-Selective Filtering for Skeleton-Based Action Segmentation CVPR 2026 SPOC: Spatially-Progressing Object State Change Segmentation in Video WACV 2026 State-Space Hierarchical Compression with Gated Attention and Learnable Sampling for Hour-Long Video Understanding in Large Multimodal Models AAAI 2026 Streaming Generation of Co-Speech Gestures via Accelerated Rolling Diffusion AAAI 2026 StreamingTOM: Streaming Token Compression for Efficient Video Understanding CVPR 2026 Streaming Video Crime Anticipation with Spatio-Temporal Causal Reasoning CVPR 2026 Streaming Video Instruction Tuning CVPR 2026 StreamRAG: Enhancing Real-Time Video Understanding with Retrieval Augmentation CVPR 2026 StreamReady: Learning What to Answer and When in Long Streaming Videos CVPR 2026 Structured Context Learning for Generic Event Boundary Detection WACV 2026 ST-Think: How Multimodal Large Language Models Reason About 4D Worlds from Ego-Centric Videos WACV 2026 SVAgent: Storyline-guided Long Video Understanding via Cross-Modal Multi-Agent Collaboration CVPR 2026