Research map / Video / Video-language understanding
PIDRo: Parallel Isomeric Attention with Dynamic Routing for Text-Video Retrieval
Peiyan Guan, Renjing Pei, Bin Shao, Jianzhuang Liu, Weimian Li, Jiaxi Gu, Hang Xu, Songcen Xu, Youliang Yan, Edmund Y. Lam
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 dynamic routing to the text encoder (ablation) | PIDRo base model · MSR-VTT-1kA | t2v R@1: 46.9 -> 47.5 | Improved |
| add T-S patch branch (ablation) | PIDRo base model · MSR-VTT-1kA | t2v R@1: 46.9 -> 47.9 | Improved |
| add both dynamic routing and T-S patch branch (ablation) | PIDRo base model · MSR-VTT-1kA | t2v R@1: 46.9 -> 48.2 | Improved |
| add DR and T-S modules (ablation) | PIDRo base model · MSR-VTT-1kA | FLOPs (G): 53 -> 67 | Hurt |
| select only K=8 patch tokens instead of all | PIDRo patch selector · MSR-VTT-1kA | t2v R@1 | Mixed |
| reduce temporal transformer layers in T-S branch | PIDRo · MSR-VTT-1kA | t2v R@1: worst-case drop 0.4% | Mixed |
| set branch balancing weight lambda to 0.2 versus larger values | PIDRo · MSR-VTT-1kA | t2v R@1 | Mixed |
| use ViT-B/16 encoder and DSL inference post-processing | PIDRo · MSR-VTT-1kA | t2v R@1: 50.2 -> 55.9 | Improved |
Later papers that compared with this method
1 later accepted paper reports PIDRo as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- Learning Dynamic Similarity by Bidirectional Hierarchical Sliding Semantic Probe for Efficient Text Video Retrieval (AAAI 2025 · better on 1 of 1 shared result)
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.
- TS2-Net — TS2-Net: Token Shift and Selection Transformer for Text-Video Retrieval (ECCV 2022) · 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
- TempMe: Video Temporal Token Merging for Efficient Text-Video Retrieval (ICLR 2025 · similarity 0.87)
- Mitigating Semantic Collapse in Partially Relevant Video Retrieval (NeurIPS 2025 · similarity 0.87)
- Towards Efficient and Effective Text-to-Video Retrieval with Coarse-to-Fine Visual Representation Learning (AAAI 2024 · similarity 0.87)
- Learning Dynamic Similarity by Bidirectional Hierarchical Sliding Semantic Probe for Efficient Text Video Retrieval (AAAI 2025 · similarity 0.87)
- Bridging the Semantic Granularity Gap Between Text and Frame Representations for Partially Relevant Video Retrieval (AAAI 2025 · similarity 0.86)
- Video-RAG: Visually-aligned Retrieval-Augmented Long Video Comprehension (NeurIPS 2025 · similarity 0.86)
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.
