Research map / Video / Video segmentation and tracking
Multi-Rate Gated Recurrent Convolutional Networks for Video-Based Pedestrian Re-Identification
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| use ResNet-50 instead of CaffeNet backbone | Multi-rate gated recurrent conv net · iLIDS-VID | Rank-1 CMC (%): 58.8 -> 60.8 | Helped |
| use ResNet-50 instead of CaffeNet backbone | Multi-rate gated recurrent conv net · PRID-2011 | Rank-1 CMC (%): 77.2 -> 78.4 | Helped |
| add context-reconstruction initialization (vs random init) (ablation) | Multi-rate gated recurrent conv net · iLIDS-VID | CMC | Helped |
| add context-reconstruction initialization (vs random init) (ablation) | Multi-rate gated recurrent conv net · PRID-2011 | CMC | Helped |
| add context reconstruction (two decoders) in initialization (ablation) | Multi-rate gated recurrent conv net · iLIDS-VID and PRID-2011 | CMC | Helped |
| add attention in reconstruction decoder (ablation) | Multi-rate gated recurrent conv net · iLIDS-VID and PRID-2011 | CMC | Helped |
| use multi-rate GRU instead of standard GRU (ablation) | Multi-rate gated recurrent conv net · iLIDS-VID and PRID-2011 | CMC | Helped |
| use proposed model instead of RCN in cross-dataset test | Multi-rate gated recurrent conv net · Train iLIDS-VID, test PRID-2011 | Rank-1 CMC (%): 28.4 -> 32.8 | Helped |
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)
- Multi-Shot Pedestrian Re-Identification via Sequential Decision Making (CVPR 2018 · similarity 0.90)
- Temporal-Enhanced Convolutional Network for Person Re-Identification (AAAI 2018 · similarity 0.89)
- Spatial-Temporal Graph Convolutional Network for Video-Based Person Re-Identification (CVPR 2020 · similarity 0.89)
- Event-Guided Person Re-Identification via Sparse-Dense Complementary Learning (CVPR 2023 · 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.