Research map / Video / Video segmentation and tracking
Relation-Guided Spatial Attention and Temporal Refinement for Video-Based Person Re-Identification
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 RGSA module (replace spatial average pooling) (ablation) | ResNet50 baseline + Ltotal · MARS | mAP (%): 81.8 -> 83.2 | Helped |
| add RGTR module (replace temporal average pooling) (ablation) | ResNet50 baseline + Ltotal · MARS | mAP (%): 81.8 -> 83.3 | Helped |
| add both RGSA and RGTR (ablation) | ResNet50 baseline + Ltotal · MARS | mAP (%): 81.8 -> 84.0 | Helped |
| add triplet loss (ablation) | RGSA+RGTR · MARS | mAP (%): 83.5 -> 84.0 | Helped |
| replace inner-product relation with proposed relation module (ablation) | RGSA+RGTR · MARS | mAP (%): 82.5 -> 84.0 | Helped |
| vary relation reduction factors r1, r2 (ablation) | RGSA+RGTR · MARS / DukeMTMC-VideoReID | mAP (%): 84.0-84.1 on MARS | No clear effect |
| increase clip length from 2 to 8 frames (ablation) | RGSA+RGTR · MARS | mAP (%): 82.5 -> 84.0 | Helped |
| RGSA+RGTR vs best prior on PRID-2011 | RGSA+RGTR · PRID-2011 | rank-1 (%): 94.4 -> 93.7 | Hurt |
Closest papers by meaning
- Relation-Aware Global Attention for Person Re-Identification (CVPR 2020 · similarity 0.91)
- Spatial and Temporal Mutual Promotion for Video-Based Person Re-Identification (AAAI 2019 · similarity 0.91)
- Watching You: Global-Guided Reciprocal Learning for Video-Based Person Re-Identification (CVPR 2021 · similarity 0.91)
- Spatial-Temporal Graph Convolutional Network for Video-Based Person Re-Identification (CVPR 2020 · similarity 0.90)
- See the Forest for the Trees: Joint Spatial and Temporal Recurrent Neural Networks for Video-Based Person Re-Identification (CVPR 2017 · similarity 0.90)
- Temporal Correlation Vision Transformer for Video Person Re-Identification (AAAI 2024 · similarity 0.88)
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.