Research map / Video / Video segmentation and tracking
Pyramid Spatial-Temporal Aggregation for Video-Based Person Re-Identification
Yingquan Wang, Pingping Zhang, Shang Gao, Xia Geng, Hu Lu, Dong Wang
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 pyramid aggregation structure (ablation) | baseline · MARS | Rank-1 (%): 88.8 -> 90.6 | Improved |
| add pyramid aggregation structure (ablation) | baseline · DukeMTMC-VID | Rank-1 (%): 95.9 -> 97.3 | Improved |
| add spatial reference attention (SRA) on pyramid (ablation) | pyramid structure · MARS | Rank-1 (%): 90.6 -> 90.9 | Improved |
| add temporal reference attention (TRA) on pyramid (ablation) | pyramid structure · MARS | Rank-1 (%): 90.6 -> 91.2 | Improved |
| use both SRA and TRA with pyramid (ablation) | pyramid structure · MARS | Rank-1 (%): 90.6 -> 91.5 | Improved |
| use pyramid instead of adjacent reference aggregation (ARAS) (ablation) | STAM · MARS | Rank-1 (%): 90.2 -> 91.5 | Improved |
| use pyramid instead of global reference aggregation (GRAS) (ablation) | STAM · MARS | Rank-1 (%): 90.1 -> 91.5 | Improved |
| use pyramid instead of adjacent reference aggregation (ARAS) (ablation) | STAM · DukeMTMC-VID | Rank-1 (%): 96.8 -> 98.3 | Improved |
| add residual block in STAM (ablation) | PSTA · MARS | Rank-1 (%): 91.3 -> 91.5 | No clear effect |
| increase number of STAM stages from 0 to 3 (ablation) | PSTA · MARS | Rank-1 (%): 88.8 -> 91.5 | Improved |
| increase number of STAM stages from 0 to 3 (ablation) | PSTA · DukeMTMC-VID | Rank-1 (%): 96.9 -> 98.3 | Improved |
| PSTA instead of AP3D | video ReID backbone · MARS | Rank-1 (%): 90.7 -> 91.5 | Improved |
Closest papers by meaning
- STA: Spatial-Temporal Attention for Large-Scale Video-Based Person Re-Identification (AAAI 2019 · similarity 0.91)
- Spatial and Temporal Mutual Promotion for Video-Based Person Re-Identification (AAAI 2019 · similarity 0.90)
- Relation-Guided Spatial Attention and Temporal Refinement for Video-Based Person Re-Identification (AAAI 2020 · similarity 0.89)
- Video-Based Person Re-Identification With Spatial and Temporal Memory Networks (ICCV 2021 · similarity 0.89)
- Spatio-Temporal Representation Factorization for Video-Based Person Re-Identification (ICCV 2021 · similarity 0.89)
- 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.
