Research map / Video / Video-language understanding
Enhancing Partially Relevant Video Retrieval with Hyperbolic Learning
Jun Li, Jinpeng Wang, Chaolei Tan, Niu Lian, Long Chen, Yaowei Wang, Min Zhang, 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 gaze frame-level branch (ablation) | HLFormer · ActivityNet Captions | SumR: 146.1 -> 154.9 | Improved |
| add gaze frame-level branch (ablation) | HLFormer · TVR | SumR: 178.3 -> 187.7 | Improved |
| add glance clip-level branch (ablation) | HLFormer · ActivityNet Captions | SumR: 137.2 -> 154.9 | Improved |
| add glance clip-level branch (ablation) | HLFormer · TVR | SumR: 166.1 -> 187.7 | Improved |
| add L_div and L_pop to similarity loss (ablation) | HLFormer · ActivityNet Captions | SumR: 149.1 -> 154.9 | Improved |
| add L_div and L_pop to similarity loss (ablation) | HLFormer · Charades-STA | SumR: 75.3 -> 78.7 | Improved |
| add query diverse loss L_div (ablation) | HLFormer · Charades-STA | SumR: 76.4 -> 78.7 | Improved |
| add partial order preservation loss L_pop (ablation) | HLFormer · ActivityNet Captions | SumR: 154.0 -> 154.9 | Improved |
| add partial order preservation loss L_pop (ablation) | HLFormer · TVR | SumR: 186.8 -> 187.7 | Improved |
| use MAIM instead of mean pooling for aggregation (ablation) | HLFormer · ActivityNet Captions | SumR: 150.2 -> 154.9 | Improved |
| use MAIM instead of concat+linear aggregation (ablation) | HLFormer · TVR | SumR: 186.6 -> 187.7 | Improved |
| use concat+linear instead of mean pooling aggregation (ablation) | HLFormer · ActivityNet Captions | SumR: 150.2 -> 153.6 | Improved |
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.
- GMMFormer — GMMFormer: Gaussian-Mixture-Model Based Transformer for Efficient Partially Relevant Video Retrieval (AAAI 2024) · better on 3 of 3 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 0.88)
- Bridging the Semantic Granularity Gap Between Text and Frame Representations for Partially Relevant Video Retrieval (AAAI 2025 · similarity 0.87)
- Ambiguity-Restrained Text-Video Representation Learning for Partially Relevant Video Retrieval (AAAI 2025 · similarity 0.86)
- GMMFormer: Gaussian-Mixture-Model Based Transformer for Efficient Partially Relevant Video Retrieval (AAAI 2024 · similarity 0.86)
- HiHPQ: Hierarchical Hyperbolic Product Quantization for Unsupervised Image Retrieval (AAAI 2024 · similarity 0.85)
- Generative Video Diffusion for Unseen Novel Semantic Video Moment Retrieval (AAAI 2025 · similarity 0.85)
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.
