Junsong Yuan
University at Buffalo
481 Papers
1.8K Citations
Junsong Yuan is an academic researcher from University at Buffalo. The author has contributed to research in topics: Computer science & Object detection. The author has an hindex of 59, co-authored 401 publications. Previous affiliations of Junsong Yuan include Zhejiang University & Northwestern University.
Chat about Author
Papers
Robust Discriminative Tracking via Landmark-Based Label Propagation
TL;DR: Qualitative and quantitative evaluations on the benchmark data set containing 51 challenging image sequences demonstrate that the proposed algorithm outperforms the state-of-the-art methods.
50
Fusing disparate object signatures for salient object detection in video
Zhigang Tu,Zhigang Tu,Zuwei Guo,Wei Xie,Mengjia Yan,Remco C. Veltkamp,Baoxin Li,Junsong Yuan +7 more
TL;DR: A novel spatiotemporal saliency model for object detection in videos that aims to use object signatures which can be identified by any kinds of object segmentation methods and outperforms existing state-of-the-art approaches is presented.
50
Query Driven Localized Linear Discriminant Models for Head Pose Estimation
Zhu Li,Yun Fu,Junsong Yuan,Thomas S. Huang,Ying Wu +4 more
- 02 Jul 2007
TL;DR: This work develops a query point driven, localized linear subspace learning method that approximates the non-linearity of the head pose manifold structure with piece-wise linear discriminating subspaces/metrics.
Boosting Positive and Unlabeled Learning for Anomaly Detection With Multi-Features
TL;DR: This work introduces a novel PU learning method, which can tackle the situation where an unlabeled data set is mostly composed of positive instances, and starts by using a linear model to extract the most reliable negative instances followed by a self-learning process to add reliable negative and positive instances with different speeds based on the estimated positive class prior.
47
Dynamic Graph CNN for Event-Camera Based Gesture Recognition
Junming Chen,Jingjing Meng,Xinchao Wang,Junsong Yuan +3 more
- 12 Oct 2020
TL;DR: This work adapt DGCNN to perform action recognition by recognizing 3D geometry features in spatio-temporal space of the event data using Dynamic Graph CNN (DGCNN) which directly takes 3D points as input and is successfully used for 3D object recognition.
44