Research map / Video / Video segmentation and tracking
Temporal Coherence or Temporal Motion: Which is More Critical for Video-based Person Re-identification?
Guangyi Chen, Yongming Rao, Jiwen Lu, Jie Zhou
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 AFA (adversarial feature augmentation) (ablation) | ResNet-50 · MARS | Rank-1: 88.1 -> 90.2 | Improved |
| add AFA (ablation) | ResNet-50 · MARS | mAP: 80.1 -> 82.9 | Improved |
| add AFA (ablation) | ResNet-50 · DukeMTMC-VideoReID | Rank-1: 95.2 -> 97.2 | Improved |
| add AFA (ablation) | QAN* · MARS | mAP: 80.9 -> 82.2 | Improved |
| add AFA (ablation) | QAN* · DukeMTMC-VideoReID | Rank-1: 95.5 -> 97.2 | Improved |
| add classification loss to triplet loss (ablation) | AFA · MARS | Rank-1: 85.3 -> 89.8 | Improved |
| add coherence constraint loss (ablation) | AFA · MARS | mAP: 82.6 -> 82.9 | Improved |
| add coherence constraint loss (ablation) | AFA · MARS | Rank-1: 89.8 -> 90.2 | Improved |
| add coherence constraint loss (ablation) | AFA · DukeMTMC-VideoReID | mAP: 95.0 -> 95.4 | Improved |
| add AFA (ablation) | ResNet-50 · MARS to DukeV (cross-dataset) | Rank-1: 37.6 -> 41.5 | Improved |
| add AFA (ablation) | ResNet-50 · DukeV to MARS (cross-dataset) | Rank-1: 43.3 -> 44.2 | Improved |
| add AFA (ablation) | QAN* · MARS to DukeV (cross-dataset) | Rank-1: 38.9 -> 41.5 | Improved |
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.
- VRSTC — VRSTC: Occlusion-Free Video Person Re-Identification (CVPR 2019) · 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
- Multi-Rate Gated Recurrent Convolutional Networks for Video-Based Pedestrian Re-Identification (AAAI 2018 · similarity 0.88)
- Spatial and Temporal Mutual Promotion for Video-Based Person Re-Identification (AAAI 2019 · similarity 0.87)
- Temporal-Enhanced Convolutional Network for Person Re-Identification (AAAI 2018 · similarity 0.86)
- Exploiting Temporal Coherence for Self-Supervised One-shot Video Re-identification (ECCV 2020 · similarity 0.86)
- Slow and Steady Feature Analysis: Higher Order Temporal Coherence in Video (CVPR 2016 · similarity 0.86)
- Temporal Correlation Vision Transformer for Video Person Re-Identification (AAAI 2024 · similarity 0.85)
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.
