Research map / Video / Video segmentation and tracking
SSN3D: Self-Separated Network to Align Parts for 3D Convolution in Video Person Re-Identification
Xiaoke Jiang, Yu Qiao, Junjie Yan, Qichen Li, Wanrong Zheng, Dapeng Chen
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 |
|---|---|---|---|
| combine a small amount of labeled part guidance with unlabeled data (ablation) | SSN3D · iLIDS-VID | top-1: 73.4 -> 88.9 | Improved |
| combine a small amount of labeled part guidance with unlabeled data (ablation) | SSN3D · MARS | mAP: 61.1 -> 86.2 | Improved |
| combine a small amount of labeled part guidance with unlabeled data (ablation) | SSN3D · DukeMTMC | mAP: 79.6 -> 96.3 | Improved |
| add labeled part guidance to unsupervised training (ablation) | SSN3D · iLIDS-VID | top-1: 83.1 -> 88.9 | Improved |
| add labeled part guidance to unsupervised training (ablation) | SSN3D · MARS | mAP: 67.5 -> 86.2 | Improved |
| add labeled part guidance to unsupervised training (ablation) | SSN3D · DukeMTMC | mAP: 86.2 -> 96.3 | Improved |
| share weights between spatial and temporal attention classifiers (ablation) | SSN3D · iLIDS-VID | top-1: 69.4 -> 88.9 | Improved |
| share weights between spatial and temporal attention classifiers (ablation) | SSN3D · MARS | mAP: 70.9 -> 86.2 | Improved |
| share weights between spatial and temporal attention classifiers (ablation) | SSN3D · DukeMTMC | mAP: 71.2 -> 96.3 | Improved |
| use SSN3D instead of AP3D | video person ReID · iLIDS-VID | top-1: 86.7 -> 88.9 | Improved |
| use SSN3D instead of AP3D | video person ReID · MARS | top-1: 90.1 -> 90.1 | No clear effect |
| use SSN3D instead of AP3D | video person ReID · MARS | mAP: 85.1 -> 86.2 | Improved |
Closest papers by meaning
- Temporal-Enhanced Convolutional Network for Person Re-Identification (AAAI 2018 · similarity 0.87)
- Deeply-Learned Part-Aligned Representations for Person Re-Identification (ICCV 2017 · similarity 0.87)
- Recurrent Convolutional Network for Video-Based Person Re-Identification (CVPR 2016 · similarity 0.87)
- Keypoint Message Passing for Video-Based Person Re-identification (AAAI 2022 · similarity 0.87)
- Spatial-Temporal Graph Convolutional Network for Video-Based Person Re-Identification (CVPR 2020 · similarity 0.87)
- Part-Aligned Bilinear Representations for Person Re-Identification (ECCV 2018 · similarity 0.87)
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.
