Research map / Video / Video segmentation and tracking
Ordered or Orderless: A Revisit for Video Based Person Re-Identification
Le Zhang, Zenglin Shi, Joey Tianyi Zhou, Ming‐Ming Cheng, Yun Liu, Jia-Wang Bian, Zeng Zeng, Chunhua Shen
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 |
|---|---|---|---|
| shuffle frame order at test time (no retraining) (ablation) | CNN-RNN video re-id · iLIDS-VID / PRID-2011 | CMC rank-1 | Improved |
| train CNN-RNN on shuffled instead of ordinal sequences (ablation) | CNN-RNN video re-id · iLIDS-VID / PRID-2011 | CMC rank-1 | No clear effect |
| add optical flow input (ablation) | CNN-RNN video re-id · iLIDS-VID / PRID-2011 | CMC rank-1 | Mixed |
| replace RNN with LSTM or GRU (ablation) | CNN-RNN video re-id · iLIDS-VID / PRID-2011 | CMC rank-1 | No clear effect |
| use more frames (smaller sampling interval K) (ablation) | Ensemble-RW and Ensemble-CRF · PRID-2011 and iLIDS-VID | CMC rank-1 | Improved |
| use stronger base ranker than Ensemble-Baseline (ablation) | Ensemble ranker · PRID-2011 and iLIDS-VID | CMC rank-1 | Improved |
| use Cross-Entropy Monte Carlo aggregation instead of Kemeny-Young (ablation) | Ensemble ranker · MARS | CMC rank and mAP | No clear effect |
| replace CNN-RNN with orderless ensemble ranking of per-frame re-id | video re-id · PRID-2011, iLIDS-VID, MARS | CMC rank and mAP | Improved |
Closest papers by meaning
- Recurrent Convolutional Network for Video-Based Person Re-Identification (CVPR 2016 · similarity 0.91)
- See the Forest for the Trees: Joint Spatial and Temporal Recurrent Neural Networks for Video-Based Person Re-Identification (CVPR 2017 · similarity 0.90)
- Keypoint Message Passing for Video-Based Person Re-identification (AAAI 2022 · similarity 0.89)
- A Systematic Evaluation and Benchmark for Person Re-Identification: Features, Metrics, and Datasets (TPAMI 2018 · similarity 0.88)
- Person Re-identification via Recurrent Feature Aggregation (ECCV 2016 · similarity 0.88)
- Deep Learning for Person Re-Identification: A Survey and Outlook (TPAMI 2021 · similarity 0.88)
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.
