RC-DETR: Improving DETRs in crowded pedestrian detection via rank-based contrastive learning
- 25 November 2024
- journal article
- research article
- Published by Elsevier in Neural Networks
- Vol. 182, 106911
Abstract
No abstract availableKeywords
Funding Information
- Innovative Research Group Project of the National Natural Science Foundation of China
This publication has 34 references indexed in Scilit:
- Dynamic-group-aware networks for multi-agent trajectory prediction with relational reasoningNeural Networks, 2023
- Enhancement, integration, expansion: Activating representation of detailed features for occluded person re-identificationNeural Networks, 2023
- IASA: An IoU-aware tracker with adaptive sample assignmentNeural Networks, 2023
- Momentum Contrast for Unsupervised Visual Representation Learning2020
- DR Loss: Improving Object Detection by Distributional Ranking2020
- NMS by Representative Region: Towards Crowded Pedestrian Detection by Proposal Pairing2020
- Towards Accurate One-Stage Object Detection With AP-Loss2019
- Unsupervised Feature Learning via Non-parametric Instance Discrimination2018
- Feature Pyramid Networks for Object Detection2017
- CityPersons: A Diverse Dataset for Pedestrian Detection2017