Tag: Long Video Understanding
Browse our exclusive articles!
TTF: Boost Video-Language Models with Temporal Token Fusion
Discover TTF, a training-free method that cuts visual tokens by 67% in video-language models, boosting efficiency without losing accuracy.
Event-Causal RAG: Advanced Framework for Long Video Reasoning
Discover Event-Causal RAG, a cutting-edge framework for efficient long video reasoning with event segmentation and causal inference in complex scenarios.
Audio Hallucination Challenges in Egocentric Video AI
Discover how audio hallucinations affect egocentric video AI models and the need for better evaluation to improve accuracy in multimodal understanding.
StoryTR: Video Retrieval with Theory of Mind Reasoning
Discover StoryTR, a benchmark for narrative-centric video retrieval using Theory of Mind to enhance understanding of character intent and story context.
Pistachio: Advanced Synthetic Benchmark for Video Anomaly Detection
Discover Pistachio, a synthetic, balanced, and long-form video anomaly benchmark enhancing detection and understanding of complex video anomalies.