MemoryCard: Topic-Aware Multi-Modal Clue Compression for Long-Video Question Answering 事件

MemoryCard: Topic-Aware Multi-Modal Clue Compression for Long-Video Question Answering arXiv:2606.05917v1 Announce Type: new Abstract: Long-video question answering remains challenging for Vision-Language Models (VLMs), as answer-relevant evidence is often sparse, transient, and temporally dispersed across lengthy video contexts. Existing frame-centric approaches improve efficiency through uniform sampling, query-aware frame selection, visual-token compression, and adaptive resolution strategie