Video Understanding
Overview
Video understanding studies how systems interpret actions, objects, interactions, and events as they unfold, supporting tasks such as action recognition, temporal localization, video question answering, and summarization. Approaches range from spatiotemporal transformers and self-supervised motion learning to multimodal language models that use retrieval, memory, or visual tools to analyze long videos. Benchmarks test short clips, long-form and egocentric footage, procedural tasks, and audio-visual settings, but results can depend heavily on frame sampling, token budgets, and evaluation design. A central challenge is making models rely on temporal evidence and maintain coherent reasoning over long or multiple videos rather than exploiting static cues or struggling with context limits.
Latest papers
116 papers21 papers in the last four weeks, up 91% on the four weeks before. 0.1% of all new papers.