SVAgent improves long video question answering by constructing storylines via multi-agent collaboration and aligning cross-modal predictions for more robust, human-like reasoning.
Xr: Cross-modal agents for composed image retrieval
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 2polarities
background 2representative citing papers
ReCoVR introduces a reflexive dual-pathway architecture for interactive composed video retrieval that outperforms baselines by combining intent routing with trajectory-level reflection on retrieval history.
citing papers explorer
-
SVAgent: Storyline-Guided Long Video Understanding via Cross-Modal Multi-Agent Collaboration
SVAgent improves long video question answering by constructing storylines via multi-agent collaboration and aligning cross-modal predictions for more robust, human-like reasoning.
-
ReCoVR: Closing the Loop in Interactive Composed Video Retrieval
ReCoVR introduces a reflexive dual-pathway architecture for interactive composed video retrieval that outperforms baselines by combining intent routing with trajectory-level reflection on retrieval history.