Weakly-supervised object detection (WSOD) aims to train an object detect...
Contrastive Language Image Pretraining (CLIP) received widespread attent...
After DETR was proposed, this novel transformer-based detection paradigm...
Most existing human pose estimation (HPE) methods exploit multi-scale
in...
Graph Neural Network (GNN) has been demonstrated its effectiveness in de...
Occlusion is very challenging in pedestrian detection. In this paper, we...
In recent years, knowledge distillation has been proved to be an effecti...
Heatmap regression has become the most prevalent choice for nowadays hum...
In this paper, we propose an efficient human pose estimation network (DA...
We extend this idea further to explicitly model the distribution-level
r...
In this paper, we propose a novel method called Residual Steps Network (...
In this paper, we propose a method, called GridFace, to reduce facial
ge...
Face recognition performance improves rapidly with the recent deep learn...