Research map / Video / Video-language understanding
Imagine Before Concentration: Diffusion-Guided Registers Enhance Partially Relevant Video Retrieval
Jun Li, Xuhang Lou, Jinpeng Wang, Yuting Wang, Yaowei Wang, Shu-Tao Xia, Bin Chen
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 diffusion-generated global registers (ablation) | DreamPRVR · ActivityNet Captions | SumR: 153.4 -> 156.1 | Improved |
| add diffusion-generated global registers (ablation) | DreamPRVR · TVR | SumR: 187.0 -> 193.1 | Improved |
| use diffusion registers instead of adaptive pooling (ablation) | DreamPRVR · Charades-STA | SumR: 78.1 -> 80.0 | Improved |
| add diffusion refinement (DRE) instead of one-step mapping (ablation) | DreamPRVR · ActivityNet Captions | SumR: 150.6 -> 156.1 | Improved |
| initialize registers from PVS video-centric distribution rather than random noise (ablation) | DreamPRVR · Charades-STA | SumR: 77.6 -> 80.0 | Improved |
| initialize registers from PVS (ablation) | DreamPRVR · ActivityNet Captions | SumR: 154.9 -> 156.1 | No clear effect |
| add Lpvs KL loss (ablation) | DreamPRVR · ActivityNet Captions | SumR: 155.1 -> 156.1 | Improved |
| add Ldre textual supervision (ablation) | DreamPRVR · Charades-STA | SumR: 78.5 -> 80.0 | Improved |
| add textual semantic structure learning (QSP + diversity) (ablation) | DreamPRVR · Charades-STA | SumR: 76.9 -> 80.0 | Improved |
| add all proposed losses over Lsim only (ablation) | DreamPRVR · TVR | SumR: 187.0 -> 193.1 | Improved |
| increase register count above 8 (ablation) | DreamPRVR · ActivityNet Captions | SumR | Hurt |
| increase diffusion timesteps beyond 10 (ablation) | DreamPRVR · ActivityNet Captions | SumR | 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.
- GMMFormerV2 — GMMFormer: Gaussian-Mixture-Model Based Transformer for Efficient Partially Relevant Video Retrieval (AAAI 2024) · better on 4 of 4 shared results
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
- Mitigating Semantic Collapse in Partially Relevant Video Retrieval (NeurIPS 2025 · similarity 0.89)
- Bridging the Semantic Granularity Gap Between Text and Frame Representations for Partially Relevant Video Retrieval (AAAI 2025 · similarity 0.89)
- Generative Video Diffusion for Unseen Novel Semantic Video Moment Retrieval (AAAI 2025 · similarity 0.89)
- From Play to Replay: Composed Video Retrieval for Temporally Fine-Grained Videos (NeurIPS 2025 · similarity 0.88)
- MUVR: A Multi-Modal Untrimmed Video Retrieval Benchmark with Multi-Level Visual Correspondence (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.
