Research map / Video / Video segmentation and tracking
Frame-Guided Region-Aligned Representation for Video Person Re-Identification
Zengqun Chen, Zhiheng Zhou, Junchu Huang, Pengyu Zhang, Bo Li
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 global branch to region-based baseline (ablation) | FGRA · MARS | mAP (%): 72.0 -> 74.7 | Improved |
| add region alignment mechanism (ablation) | FGRA · MARS | mAP (%): 74.7 -> 79.0 | Improved |
| add region alignment mechanism (ablation) | FGRA · iLIDS-VID | Top-1 (%): 80.3 -> 83.3 | Improved |
| use temporal attention instead of average pooling after alignment (ablation) | FGRA · MARS | mAP (%): 79.0 -> 80.2 | Improved |
| use temporal alignment score instead of temporal attention (ablation) | FGRA · MARS | mAP (%): 80.2 -> 79.9 | No clear effect |
| add consistency regularization (ablation) | FGRA · MARS | mAP (%): 79.9 -> 80.9 | Improved |
| add spatial attention (ablation) | FGRA · MARS | mAP (%): 80.9 -> 81.2 | Improved |
| increase spatial regions from 4 to 8 (ablation) | FGRA · iLIDS-VID, PRID2011 | Top-1 / mAP | Hurt |
| reduce input sequence length to 2 (ablation) | FGRA · iLIDS-VID, PRID2011 | Top-1 / mAP | Hurt |
Closest papers by meaning
- Relation-Guided Spatial Attention and Temporal Refinement for Video-Based Person Re-Identification (AAAI 2020 · similarity 0.89)
- Spatial and Temporal Mutual Promotion for Video-Based Person Re-Identification (AAAI 2019 · similarity 0.88)
- Spatio-Temporal Representation Factorization for Video-Based Person Re-Identification (ICCV 2021 · similarity 0.87)
- See the Forest for the Trees: Joint Spatial and Temporal Recurrent Neural Networks for Video-Based Person Re-Identification (CVPR 2017 · similarity 0.87)
- Spatial-Temporal Graph Convolutional Network for Video-Based Person Re-Identification (CVPR 2020 · similarity 0.87)
- Diversity Regularized Spatiotemporal Attention for Video-Based Person Re-Identification (CVPR 2018 · 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.
