most citedRelationNet++: Bridging Visual Representations for Object Detection via Transformer Decoder

36 citations · 70 across the 3 of their papers we have counts for

collaborators

7 papers

cs.CV202036 cited

RelationNet++: Bridging Visual Representations for Object Detection via Transformer Decoder

Cheng Chi, Fangyun Wei, Han Hu

Existing object detection frameworks are usually built on a single format of object/part representation, i.e., anchor/proposal rectangle boxes in RetinaNet and Faster R-CNN, center…

cs.CV202029 cited

Loss Function Search for Face Recognition

Xiaobo Wang, Shuo Wang, Cheng Chi +2

In face recognition, designing margin-based (e.g., angular, additive, additive angular margins) softmax loss functions plays an important role in learning discriminative features.…

cs.CV2019

Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection

Shifeng Zhang, Cheng Chi, Yongqiang Yao +2

Object detection has been dominated by anchor-based detectors for several years. Recently, anchor-free detectors have become popular due to the proposal of FPN and Focal Loss. In t…

cs.CV20195 cited

Relational Learning for Joint Head and Human Detection

Cheng Chi, Shifeng Zhang, Junliang Xing +3

Head and human detection have been rapidly improved with the development of deep convolutional neural networks. However, these two tasks are often studied separately without consid…

cs.CV2019

PedHunter: Occlusion Robust Pedestrian Detector in Crowded Scenes

Cheng Chi, Shifeng Zhang, Junliang Xing +3

Pedestrian detection in crowded scenes is a challenging problem, because occlusion happens frequently among different pedestrians. In this paper, we propose an effective and effici…

cs.CV2019

RefineFace: Refinement Neural Network for High Performance Face Detection

Shifeng Zhang, Cheng Chi, Zhen Lei +1

Face detection has achieved significant progress in recent years. However, high performance face detection still remains a very challenging problem, especially when there exists ma…