Research map / Video / Video segmentation and tracking
Weakly Supervised Person Re-Identification
Jingke Meng, Sheng Wu, Wei-Shi Zheng
Check 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 |
|---|---|---|---|
| Use Deep CV-MIML instead of DeepMIML | weakly supervised person re-identification · WL-DukeMTMC-REID | rank-1 accuracy: +12.68% | Improved |
| Use Deep CV-MIML instead of DeepMIML | weakly supervised person re-identification · WL-PRID2011 | rank-1 accuracy: +5.00% | Improved |
| Use Deep CV-MIML instead of DeepMIML | weakly supervised person re-identification · WL-iLIDS-VID | rank-1 accuracy: +16.00% | Improved |
| Use Deep CV-MIML instead of DeepMIML | weakly supervised person re-identification · WL-MARS | rank-1 accuracy: +19.72% | Improved |
| Add intra-bag alignment (ablation) | CV-MIML · four weakly labeled datasets | rank-1 accuracy: 67.26 -> 74.69; 67.00 -> 69.00; 41.33 -> 55.33; 53.47 -> 62.15 | Improved |
| Add cross-view bag alignment (ablation) | CV-MIML · four weakly labeled datasets | rank-1 accuracy: 67.26 -> 72.92; 67.00 -> 68.00; 41.33 -> 52.67; 53.47 -> 63.09 | Improved |
| Add entropy regularization (ablation) | CV-MIML · WL-DukeMTMC-REID | rank-1 accuracy: 67.26 -> 70.56 | Improved |
| Add entropy regularization (ablation) | CV-MIML · WL-PRID2011 | rank-1 accuracy: 67.00 -> 70.00 | Improved |
| Add entropy regularization (ablation) | CV-MIML · WL-iLIDS-VID | rank-1 accuracy: 41.33 -> 44.67 | Improved |
| Add entropy regularization (ablation) | CV-MIML · WL-MARS | rank-1 accuracy: 53.47 -> 60.88 | Improved |
| Use time-dependent delta instead of a fixed delta (ablation) | Deep CV-MIML · WL-PRID2011 and WL-iLIDS-VID | performance | Improved |
| Set prototype smoothing alpha to zero, removing historical prototype information (ablation) | Deep CV-MIML · hyperparameter analysis | performance | Hurt |
Closest papers by meaning
- Deep Graph Metric Learning for Weakly Supervised Person Re-Identification (TPAMI 2021 · similarity 0.92)
- Intra-Camera Supervised Person Re-Identification (IJCV 2021 · similarity 0.91)
- Weakly Supervised Tracklet Association Learning With Video Labels for Person Re-Identification (TPAMI 2023 · similarity 0.90)
- Unsupervised Person Re-Identification by Soft Multilabel Learning (CVPR 2019 · similarity 0.90)
- Intra-Inter Camera Similarity for Unsupervised Person Re-Identification (CVPR 2021 · similarity 0.89)
- Intra-Inter Domain Similarity for Unsupervised Person Re-Identification (TPAMI 2022 · similarity 0.89)
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.
