Research map / Video / Video segmentation and tracking
Spatial and Temporal Mutual Promotion 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 video-level ranking constraint (ablation) | Inception-v3 baseline · iLIDS-VID | rank-1: 57.7 -> 72.2 | Helped |
| Replace LSTM temporal integration with STIM (ablation) | Inception-v3 baseline with L_v · iLIDS-VID | rank-1: 71.5 -> 77.3 | Helped |
| Add RRU with spatial and channel attention (ablation) | Inception-v3 baseline with L_v · iLIDS-VID | rank-1: 72.2 -> 75.0 | Helped |
| Use spatial attention only instead of combined spatial and channel attention (ablation) | RRU · iLIDS-VID | rank-1: 75.0 -> 73.5 | Hurt |
| Use channel attention only instead of combined spatial and channel attention (ablation) | RRU · iLIDS-VID | rank-1: 75.0 -> 73.4 | Hurt |
| Remove motion-difference input from the RRU gate (ablation) | RRU · iLIDS-VID | rank-1: 75.0 -> 74.0 | Hurt |
| Replace explicit appearance and motion differences with raw current and previous refined features as gate input (ablation) | RRU · iLIDS-VID | rank-1: 75.0 -> 73.3 | Hurt |
| Add RRU before STIM (ablation) | STIM with video-level ranking constraint · iLIDS-VID | rank-1: 77.3 -> 80.5 | Helped |
| Add part-level ranking constraint (ablation) | RRU + STIM with video-level ranking constraint · iLIDS-VID | rank-1: 80.5 -> 84.3 | Helped |
| Add RRU (ablation) | STIM with video-level ranking constraint · MARS | mAP: 71.1 -> 72.2 | Helped |
| Add part-level ranking constraint (ablation) | RRU + STIM with video-level ranking constraint · MARS | mAP: 72.2 -> 72.7 | Helped |
| Add RRU before LSTM (ablation) | LSTM with video-level ranking constraint · PRID-2011 | rank-1: 86.7 -> 89.6 | Helped |
Closest papers by meaning
- Relation-Guided Spatial Attention and Temporal Refinement for Video-Based Person Re-Identification (AAAI 2020 · similarity 0.91)
- See the Forest for the Trees: Joint Spatial and Temporal Recurrent Neural Networks for Video-Based Person Re-Identification (CVPR 2017 · similarity 0.91)
- Spatial-Temporal Graph Convolutional Network for Video-Based Person Re-Identification (CVPR 2020 · similarity 0.90)
- Spatial-Temporal Correlation and Topology Learning for Person Re-Identification in Videos (CVPR 2021 · similarity 0.89)
- BiCnet-TKS: Learning Efficient Spatial-Temporal Representation for Video Person Re-Identification (CVPR 2021 · similarity 0.89)
- Rethinking Temporal Fusion for Video-Based Person Re-Identification on Semantic and Time Aspect (AAAI 2020 · 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.