Research map / Video / Video-language understanding
PRVR: Partially Relevant Video Retrieval
Xianke Chen, Daizong Liu, Xun Yang, Xirong Li, Jianfeng Dong, Meng Wang, Xun Wang
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 frame-scale similarity branch (ablation) | MS-SL++ · TVR | SumR: 167.9 -> 174.4 | Improved |
| add clip-scale similarity branch (ablation) | MS-SL++ · TVR | SumR: 133.0 -> 174.4 | Improved |
| add key clip guide in attention (ablation) | MS-SL++ · TVR | SumR: 166.5 -> 174.4 | Improved |
| add weighted aggregation instead of mean pooling (ablation) | MS-SL++ · TVR | SumR: 164.5 -> 174.4 | Improved |
| add infoNCE loss to triplet loss (ablation) | MS-SL++ · TVR | SumR: 162.6 -> 174.4 | Improved |
| add triplet ranking loss to infoNCE (ablation) | MS-SL++ · TVR | SumR: 163.9 -> 174.4 | Improved |
| increase cluster number from 8 to 32 (ablation) | MS-SL++ · TVR | SumR: 167.3 -> 174.5 | Improved |
| use 32 clusters instead of no clustering (ablation) | MS-SL++ · TVR | SumR: 172.4 -> 174.5 | No clear effect |
| increase cluster number from 32 to 256 (ablation) | MS-SL++ · TVR | SumR: 174.5 -> 173.7 | No clear effect |
| use length-aware clustering instead of vanilla clustering (ablation) | MS-SL++ · TVR | SumR | Improved |
| use finer clip granularity (larger n_u, smaller stride) (ablation) | MS-SL++ · TVR | SumR | Improved |
| use CLIP features instead of CNN features | MS-SL++ · Charades-STA | SumR: 69.7 -> 55.2 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- X-Pool — X-Pool: Cross-Modal Language-Video Attention for Text-Video Retrieval (CVPR 2022) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Bridging the Semantic Granularity Gap Between Text and Frame Representations for Partially Relevant Video Retrieval (AAAI 2025 · similarity 0.92)
- Mitigating Semantic Collapse in Partially Relevant Video Retrieval (NeurIPS 2025 · similarity 0.91)
- Ambiguity-Restrained Text-Video Representation Learning for Partially Relevant Video Retrieval (AAAI 2025 · similarity 0.89)
- GMMFormer: Gaussian-Mixture-Model Based Transformer for Efficient Partially Relevant Video Retrieval (AAAI 2024 · similarity 0.88)
- MUVR: A Multi-Modal Untrimmed Video Retrieval Benchmark with Multi-Level Visual Correspondence (NeurIPS 2025 · similarity 0.87)
- From Play to Replay: Composed Video Retrieval for Temporally Fine-Grained Videos (NeurIPS 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.
