ViSAGE: Constructing Self-Correcting Memories for Long-Form Video Understanding
英文标题：ViSAGE: Constructing Self-Correcting Memories for Long-Form Video Understanding
arXiv:2607.28678v1 Announce Type: new Abstract: Multimodal agents operating in long-horizon environments must build and continually update multimedia memories to support entity-consistent, temporally grounded reasoning. However, existing agentic memory approaches often discard fine-grained dentity
打开原文相关 8.8 · 机会 1
2.1 KB
640 B
612 B
380 B
9.1 KB
32.7 KB
22.8 KB
24.2 KB
34.7 KB
中文
arXiv:2607.28678v1 Announce Type: new Abstract: Multimodal agents operating in long-horizon environments must build and continually update multimedia memories to support entity-consistent, temporally grounded reasoning. However, existing agentic memory approaches often discard fine-grained dentity
中文全文翻译正在补齐，可先查看下方英文原文。
English / 原文
BibTeX formatted citation
×