Action segmentation with joint self-supervised temporal domain adaptation

MH Chen, B Li, Y Bao, G AlRegib… - Proceedings of the …, 2020 - openaccess.thecvf.com
Despite the recent progress of fully-supervised action segmentation techniques, the
performance is still not fully satisfactory. One main challenge is the problem of …

Unsupervised object detection with scene-adaptive concept learning

S Pu, W Zhao, W Chen, S Yang, D Xie… - Frontiers of Information …, 2021 - Springer
Object detection is one of the hottest research directions in computer vision, has already
made impressive progress in academia, and has many valuable applications in the industry …

Exploring Spatial-Temporal Instance Relationships in an Intermediate Domain for Image-to-Video Object Detection

Z Wen, J Chen, X Wu - Proceedings of the Asian …, 2022 - openaccess.thecvf.com
Image-to-video object detection leverages annotated images to help detect objects in
unannotated videos, so as to break the heavy dependency on the expensive annotation of …

基于场景自适应概念学习的无监督目标检测

S Pu, W Zhao, W Chen, S Yang, D Xie, Y Pan, AS Pu… - Frontiers, 2021 - jzus.zju.edu.cn
目标检测是机器视觉领域最热门的研究方向之一, 在学术界已取得令人瞩目的成果,
在工业界也存在许多有价值的应用. 然而, 主流的检测方法仍有两个缺陷:(1) …