ADEPT: An Entropy-Driven Dual-Strategy Agent for Interactive Video Retrieval
Authors: Ke Chen, Shengyuan Han, Yongfeng Huang, Yujin Zhu, Jingwei Xiong, Liang Xu, Jundong Liu
Organizations: Institute of Science Tokyo, Japan · Nanjing University of Posts and Telecommunications, Jiangsu, China · The Chinese University of Hong Kong, Hong Kong SAR · City University of Hong Kong, Hong Kong, China · University of California, Davis, CA, USA · Artificial Intelligence Innovation Center, Yangtze Delta Region Institute of Tsinghua University, China
This research aims to solve the challenge of video retrieval from massive datasets, caused by ambiguous user queries. Prevailing single-round retrieval paradigms face a performance bottleneck, as they lack effective feedback mechanisms to handle complex search intentions. The root cause is the "Intent-Query Gap", where users' intent cannot be captured by a simple text query. To solve this, we propose the ADEPT framework: a training-free agent that pioneers an entropy-driven decision engine to efficiently guide dialogue by dynamically selecting between ASK and REFINE strategies. Experiments on two challenging datasets demonstrate that ADEPT significantly outperforms all non-interactive, heuristic, and Video-LLM baselines. The core contribution of this work is an efficient and interpretable entropy-driven interactive strategy that sets a new performance benchmark for the field of interactive video retrieval.