J
Junsong Yuan
Researcher at University at Buffalo
Publications - 471
Citations - 20391
Junsong Yuan is an academic researcher from University at Buffalo. The author has contributed to research in topics: Computer science & Feature extraction. The author has an hindex of 59, co-authored 401 publications receiving 15651 citations. Previous affiliations of Junsong Yuan include Zhejiang University & Northwestern University.
Papers
More filters
Proceedings ArticleDOI
Collaborative multi-view metric learning for visual classification
TL;DR: The proposed method jointly learns multiple distance metrics under which multiple feature representations are consistent across different views, i.e., the difference of the distance metrics learned in different views is enforced to be as small as possible.
Proceedings ArticleDOI
Handling Difficult Labels for Multi-label Image Classification via Uncertainty Distillation
TL;DR: In this article, the authors propose to calibrate the model, which not only predicts the labels but also estimates the uncertainty of the prediction, and leverage the calibrated model as the teacher network and teach the student network about handling difficult labels via uncertainty distillation.
Posted Content
Temporal Distinct Representation Learning for Action Recognition
Junwu Weng,Donghao Luo,Yabiao Wang,Ying Tai,Chengjie Wang,Jilin Li,Feiyue Huang,Xudong Jiang,Junsong Yuan +8 more
TL;DR: Wang et al. as mentioned in this paper design a sequential channel filtering mechanism, i.e., Progressive Enhancement Module (PEM), to excite the discriminative channels of features from different frames step by step and thus avoid repeated information extraction.
Book ChapterDOI
Body Movement Analysis and Recognition
TL;DR: In this chapter, a nonverbal way of communication for human–robot interaction by understanding human upper body gestures will be addressed and an effective and real-time human gesture recognition method is proposed.
Posted Content
SPAGAN: Shortest Path Graph Attention Network.
TL;DR: In this paper, the authors proposed a shortest path graph attention network (SPAGAN), which explicitly accounts for the influence of a sequence of nodes yielding the minimum cost, or shortest path, between the center node and its higher-order neighbors.