Research map / Video / Video-language understanding
Learning Fine-Grained Representations through Textual Token Disentanglement in Composed Video Retrieval
Yue WU, Zhaobo Qi, Yiling Wu, Junshu Sun, Yaowei Wang, Shuhui Wang
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes a method for composed video retrieval that disentangles textual tokens to learn fine-grained query representations for combining video and text modifications.
Problem
Composed video retrieval, where users query with a video plus textual modification, suffers from heterogeneity between visual and textual modalities; textual data are highly abstract and semantically dense.
Approach
Disentangles textual tokens to learn fine-grained representations for composed video retrieval, addressing the abstraction and density of text relative to video content.
Closest papers by meaning
- Towards Efficient and Effective Text-to-Video Retrieval with Coarse-to-Fine Visual Representation Learning (AAAI 2024 · similarity 0.92)
- Mitigating Semantic Collapse in Partially Relevant Video Retrieval (NeurIPS 2025 · similarity 0.90)
- Bridging Information Asymmetry in Text-video Retrieval: A Data-centric Approach (ICLR 2025 · similarity 0.89)
- Bridging the Semantic Granularity Gap Between Text and Frame Representations for Partially Relevant Video Retrieval (AAAI 2025 · similarity 0.89)
- From Play to Replay: Composed Video Retrieval for Temporally Fine-Grained Videos (NeurIPS 2025 · similarity 0.88)
- Ambiguity-Restrained Text-Video Representation Learning for Partially Relevant Video Retrieval (AAAI 2025 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
