Research map / Video / Video segmentation and tracking
Jointly Attentive Spatial-Temporal Pooling Networks for Video-Based Person Re-Identification
Shuangjie Xu, Yu Cheng, Kang Gu, Yang Yang, Shiyu Chang, Pan 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 attentive temporal pooling and spatial pooling to RNN-CNN | RNN-CNN · iLIDS-VID | CMC rank-1: 58 -> 62 | Improved |
| add attentive temporal pooling and spatial pooling to RNN-CNN | RNN-CNN · PRID-2011 | CMC rank-1: 70 -> 77 | Improved |
| add attentive pooling to RNN-CNN | RNN-CNN · MARS | CMC rank-1: 40 -> 44 | Improved |
| add attentive temporal pooling (ATPN) instead of max/mean pooling (ablation) | RNN-CNN · PRID-2011 | CMC rank-2: almost 10% at rank 2 | Improved |
| add attentive temporal pooling (ATPN) instead of max/mean pooling (ablation) | RNN-CNN · iLIDS-VID | CMC rank-3: 5% at rank 3 | Improved |
| add attentive spatial pooling (ASPN) alone (ablation) | RNN-CNN · iLIDS-VID vs PRID-2011 | CMC | Mixed |
| add attentive spatial pooling to ATPN (ASTPN) (ablation) | ATPN · MARS | CMC rank-3: about 5% at rank 3 | Improved |
| use video sequences instead of single-shot images at test time | ASTPN · PRID-2011 (cross-dataset) | CMC rank-1: 15 -> 30 | Improved |
| use video sequences instead of single-shot images at test time | RNN-CNN · PRID-2011 (cross-dataset) | CMC rank-1: 14 -> 28 | Improved |
| replace RNN-CNN with ASTPN in cross-dataset transfer | RNN-CNN · PRID-2011 (cross-dataset) | CMC rank-1: 28 -> 30 | Improved |
| add identity classification loss to Siamese loss (ablation) | ASTPN · video re-id | accuracy | Improved |
Closest papers by meaning
- Relation-Guided Spatial Attention and Temporal Refinement for Video-Based Person Re-Identification (AAAI 2020 · similarity 0.90)
- Recurrent Convolutional Network for Video-Based Person Re-Identification (CVPR 2016 · similarity 0.90)
- Spatial-Temporal Graph Convolutional Network for Video-Based Person Re-Identification (CVPR 2020 · similarity 0.89)
- See the Forest for the Trees: Joint Spatial and Temporal Recurrent Neural Networks for Video-Based Person Re-Identification (CVPR 2017 · similarity 0.89)
- Diversity Regularized Spatiotemporal Attention for Video-Based Person Re-Identification (CVPR 2018 · similarity 0.89)
- Video-Based Person Re-Identification With Spatial and Temporal Memory Networks (ICCV 2021 · 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.
