Research map / Label-efficient and robust learning / Recognition and long-tail
Gated Siamese Convolutional Neural Network Architecture for Human Re-identification
Rahul Rama Varior, Mrinal Haloi, Gang Wang
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 Matching Gate between conv layers | Baseline S-CNN · Market-1501 (single query) | Rank-1 accuracy: 62.32 -> 65.88 | Improved |
| add Matching Gate between conv layers | Baseline S-CNN · Market-1501 (single query) | mAP: 36.23 -> 39.55 | Improved |
| add Matching Gate between conv layers | Baseline S-CNN · Market-1501 (multi query) | Rank-1 accuracy: 72.92 -> 76.04 | Improved |
| add Matching Gate between conv layers | Baseline S-CNN · Market-1501 (multi query) | mAP: 45.39 -> 48.45 | Improved |
| add Matching Gate between conv layers | Baseline S-CNN · CUHK03 (detected) (SQ) | Rank-1 accuracy: 58.1 -> 61.8 | Improved |
| add Matching Gate between conv layers | Baseline S-CNN · CUHK03 (detected) (MQ) | Rank-1 accuracy: 63.9 -> 68.1 | Improved |
| add Matching Gate between conv layers | Baseline S-CNN · CUHK03 (detected) (SQ) | mAP: 48.90 -> 51.25 | Improved |
| add Matching Gate between conv layers | Baseline S-CNN · CUHK03 (detected) (MQ) | mAP: 55.57 -> 58.84 | Improved |
| add Matching Gate between conv layers (fine-tuned from Market-1501 and CUHK03) | Baseline S-CNN · VIPeR | Rank-1 accuracy: 36.2 -> 37.8 | Improved |
Closest papers by meaning
- A Siamese Long Short-Term Memory Architecture for Human Re-identification (ECCV 2016 · similarity 0.91)
- Multi-Rate Gated Recurrent Convolutional Networks for Video-Based Pedestrian Re-Identification (AAAI 2018 · similarity 0.91)
- Re-Identification With Consistent Attentive Siamese Networks (CVPR 2019 · similarity 0.91)
- A Two Stream Siamese Convolutional Neural Network for Person Re-Identification (ICCV 2017 · similarity 0.90)
- Deep Neural Networks with Inexact Matching for Person Re-Identification (NeurIPS 2016 · similarity 0.89)
- Efficient and Deep Person Re-Identification Using Multi-Level Similarity (CVPR 2018 · 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.
