Bridging Information Asymmetry In Text-video Retrieval: A Data-centric Approach

Abstract

As online video content rapidly grows, the task of text-video retrieval (TVR) becomes increasingly important. A key challenge in TVR is the information asymmetry between video and text: videos are inherently richer in information, while their textual descriptions often capture only fragments of this complexity. This paper introduces a novel, data-centric framework to bridge this gap by enriching textual representations to better match the richness of video content. During training, videos are segmented into event-level clips and captioned to ensure comprehensive coverage. During retrieval, a large language model (LLM) generates semantically diverse queries to capture a broader range of possible matches. To enhance retrieval efficiency, we propose a query selection mechanism that identifies the most relevant and diverse queries, reducing computational cost while improving accuracy. Our method achieves state-of-the-art results across multiple benchmarks, demonstrating the power of data-c

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keybai2024bridging

Related papers

• UATVR: Uncertainty-adaptive Text-video Retrieval (2023)15.46
• Dual Encoding For Video Retrieval By Text (2020)16.05
• Narrating The Video: Boosting Text-video Retrieval Via Comprehensive Utilization Of Frame-level Captions (2025)6.77
• Use What You Have: Video Retrieval Using Representations From Collaborative Experts (2019)0.00
• Tree-augmented Cross-modal Encoding For Complex-query Video Retrieval (2020)15.57
• An Overview Of Challenges In Egocentric Text-video Retrieval (2023)0.00
• Ambiguity-restrained Text-video Representation Learning For Partially Relevant Video Retrieval (2025)5.84
• A Feature-space Multimodal Data Augmentation Technique For Text-video Retrieval (2022)12.43