DBCON: Dual Bias Control in Zero-Shot Video Moment Retrieval
Year: 2025
Type: article
Abstract: Zero-shot Video Moment Retrieval (ZVMR) is a task that localizes temporal moments within a video using only natural language queries, without requiring large-scale datasets or extensive training resources. While previous ZVMR studies have focused on aligning high-quality video and query representations, they have faced performance limitations by overlooking the ‘Dual Bias’ problem, which arises from the excessive specificity of queries and the generality of video captions. To address this challenge, we propose the DBCON (Dual Bias CONtrol) framework, which simultaneously controls caption specificity and query generalization. DBCON employs ‘Query-Aware Caption Refinement’ to induce captions that explicitly reflect the core information of the query, and ‘Query Debiasing’ to rephrase the user query into a more universal expression via an LLM. Our experiments show that DBCON effectively mitigates this dual bias, achieving up to 1.73% higher retrieval accuracy on mAP@avg compared to the state-of-the-art model on the QVHighlights test benchmark. This study is significant as it presents a new direction for developing scalable and efficient video-language retrieval systems.
Source: IEEE Access
Authors: Mingyu Jeon, Minuk Ma, Junyeong Kim
Institutions: Chung-Ang University, University of British Columbia
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
Estimated APC paid: $2,075
OpenAlex ID: W4414431971