报告题目：Deep High-Resolution Representation Learning for Visual Recognition
报告人： 王井东 资深研究员
Jingdong Wang is a Senior Researcher with the Visual Computing Group, Microsoft Research, Beijing, China. His areas of current interest include efficient CNN architecture design, person re-identification, human pose estimation, semantic segmentation, large-scale indexing, and salient object detection. He has authored one book and 100+ papers in top conferences and prestigious international journals in computer vision, multimedia, and machine learning. His paper was selected into the Best Paper Finalist at the ACM MM 2015. He has shipped a dozen of technologies to Microsoft products, including Bing search, Cognitive service, and XiaoIce Chatbot. He is an Associate Editor of IEEE TPAMI, IEEE TCSVT and IEEE TMM. He was an Area Chair or a Senior Program Committee Member of top conferences, such as CVPR, ICCV, ECCV, AAAI, IJCAI, and ACM Multimedia. He is an ACM Distinguished Member and a Fellow of the IAPR（https://jingdongwang2017.github.io）
High-resolution representation learning plays an essential role in many vision problems, e.g., semantic segmentation, and has been attracting more and more attention. Most existing techniques recover high-resolution representations mainly from low-resolution representations output by one network similar to a classification network. In this work, we propose a high-resolution network (HRNet). The HRNet maintains high-resolution representations by connecting high-to-low resolution convolutions in parallel and produces strong high-resolution representations by repeatedly performing multi-scale fusions across the parallel convolutions. We demonstrate the effectives on pixel-level classification (semantic segmentation, face alignment and human pose estimation), region-level classification (MSCOCO object detection), and image classification.