ADEPT introduces an entropy-driven dual-strategy agent that selects between ASK and REFINE actions to improve interactive video retrieval and outperforms non-interactive, heuristic, and Video-LLM baselines on two datasets.
TraveLER: A modular multi- LMM agent framework for video question-answering,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
ADEPT: An Entropy-Driven Dual-Strategy Agent for Interactive Video Retrieval
ADEPT introduces an entropy-driven dual-strategy agent that selects between ASK and REFINE actions to improve interactive video retrieval and outperforms non-interactive, heuristic, and Video-LLM baselines on two datasets.