Research map / Video / Video-language understanding
Learning Linguistic Association towards Efficient Text-Video Retrieval
Sheng Fang, Shuhui Wang, Junbao Zhuo, Xinzhe Han, Qingming Huang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add LINAS distillation | Dual Encoding · MSR-VTT | SumR: 199.0 -> 213.1 | Improved |
| add LINAS distillation | Hybrid Space · MSR-VTT | SumR: 211.7 -> 217.2 | Improved |
| add LINAS distillation | CE+ · MSR-VTT | SumR: 243.6 -> 254.0 | Improved |
| add LINAS distillation | VSE++ · VATEX | Text2Video R@5: 65.8 -> 70.1 | Improved |
| add LINAS distillation | CE+ · MSVD | Text2Video R@5: 56.5 -> 57.6 | Improved |
| add LINAS distillation | MMT (pretrained) · MSR-VTT 1k-A | SumR: 304.8 -> 319.2 | Improved |
| add LINAS distillation | CLIP4Clip · MSVD | Text2Video R@1: 46.2 -> 46.7 | Improved |
| use adaptive diagonal mask LDrel instead of all-similarity L'Drel (ablation) | LINAS on Dual Encoding · MSR-VTT | SumR: 208.3 -> 213.1 | Improved |
| use attentional aggregation instead of mean pooling (ablation) | LINAS teacher · MSR-VTT | SumR: 207.1 -> 213.1 | Improved |
| increase support set size beyond 8 captions (ablation) | LINAS · MSR-VTT | SumR | Hurt |
| use a stronger Dual Encoding teacher for the Base student (ablation) | Base student · MSR-VTT | SumR: 193.4 -> 199.8 | Improved |
| add generalized LINAS (support from similar videos) when only one caption per video | Dual Encoding · MSR-VTT demo | SumR: 91.2 -> 97.5 | Improved |
Closest papers by meaning
- Bridging Information Asymmetry in Text-video Retrieval: A Data-centric Approach (ICLR 2025 · similarity 0.87)
- DiscoVLA: Discrepancy Reduction in Vision, Language, and Alignment for Parameter-Efficient Video-Text Retrieval (CVPR 2025 · similarity 0.87)
- Text Proxy: Decomposing Retrieval from a 1-to-N Relationship into N 1-to-1 Relationships for Text-Video Retrieval (AAAI 2025 · similarity 0.87)
- TOPA: Extending Large Language Models for Video Understanding via Text-Only Pre-Alignment (NeurIPS 2024 · similarity 0.87)
- Mitigating Semantic Collapse in Partially Relevant Video Retrieval (NeurIPS 2025 · similarity 0.87)
- Ambiguity-Restrained Text-Video Representation Learning for Partially Relevant Video Retrieval (AAAI 2025 · similarity 0.87)
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.
