Research map / Video / Video segmentation and tracking
Spatio-Temporal Representation Factorization for Video-Based Person Re-Identification
Abhishek Aich, Meng Zheng, Srikrishna Karanam, Terrence Chen, Amit K. Roy-Chowdhury, Ziyan Wu
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 STRF module to P3DC baseline | P3DC · MARS | mAP: 83.10 -> 86.10 | Improved |
| add STRF module to P3DA baseline | P3DA · MARS | mAP: 83.20 -> 85.40 | Improved |
| add STRF module to P3DB baseline | P3DB · MARS | mAP: 83.00 -> 85.60 | Improved |
| add STRF module to I3D baseline | I3D · MARS | mAP: 82.70 -> 83.10 | Improved |
| add STRF module to I3D baseline | I3D · DukeMTMC-VideoReID | mAP: 95.20 -> 95.20 | No clear effect |
| add STRF module to P3DC baseline | P3DC · DukeMTMC-VideoReID | R@1: 95.30 -> 97.20 | Improved |
| replace STRF with non-local module (ablation) | P3DC · MARS | mAP: 86.1 -> 84.8 | Hurt |
| add all four factorization modules versus only spatial-fine module (ablation) | STRF-P3DC · MARS | mAP: 85.20 -> 86.10 | Improved |
| add temporal modules to spatial modules (ablation) | STRF-P3DC · MARS | mAP: 85.50 -> 86.10 | Improved |
| add STRF in Stages 2 and 3 versus Stage 1 only (ablation) | P3DC · MARS | mAP: 83.40 -> 86.10 | Improved |
| add STRF also in Stage 1 to Stages 2 and 3 (ablation) | P3DC · MARS | mAP: 86.10 -> 84.70 | Hurt |
| add STRF in Stage 4 too (Stages 2,3,4) (ablation) | P3DC · MARS | mAP: 86.10 -> 85.50 | Hurt |
Closest papers by meaning
- Spatial-Temporal Graph Convolutional Network for Video-Based Person Re-Identification (CVPR 2020 · similarity 0.91)
- Video-Based Person Re-Identification With Spatial and Temporal Memory Networks (ICCV 2021 · similarity 0.91)
- Spatial and Temporal Mutual Promotion for Video-Based Person Re-Identification (AAAI 2019 · similarity 0.91)
- Diversity Regularized Spatiotemporal Attention for Video-Based Person Re-Identification (CVPR 2018 · similarity 0.90)
- Learning Instance-Level Spatial-Temporal Patterns for Person Re-Identification (ICCV 2021 · similarity 0.90)
- Relation-Guided Spatial Attention and Temporal Refinement for Video-Based Person Re-Identification (AAAI 2020 · similarity 0.90)
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.
