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
Grid-based local feature bundling for efficient object search and localization
TL;DR: A new grid-based image representation for discriminative visual object search, with the goal to efficiently locate the query object in a large image collection, that enables faster object localization by searching visual object in the grid-level image.
Proceedings ArticleDOI
Group saliency propagation for large scale and quick image co-segmentation
TL;DR: Group Saliency Propagation model is proposed where a single group saliency map is developed, which can be propagated to segment the entire group, with the added advantage of speed up.
Proceedings ArticleDOI
Positive and Unlabeled Learning for Anomaly Detection with Multi-features
TL;DR: This work introduces a new framework based on Positive and Unlabeled (PU) Learning using multi- features to detect anomalies and extends previous PU learning methods to better address unbalanced class problem which is typical for anomaly detection.
Proceedings ArticleDOI
Real-time human action search using random forest based hough voting
Gang Yu,Junsong Yuan,Zicheng Liu +2 more
TL;DR: This paper proposes a novel framework for action retrieval which performs pattern matching at subvolume level and is very efficient in handling large corpus of videos and presents action search experiments on challenging datasets to validate the efficiency and effectiveness of the system.
Proceedings ArticleDOI
KPB-SIFT: a compact local feature descriptor
TL;DR: The produced KPB-SIFT descriptor is more compact as compared to the state-of-the-art, does not require pre-training step needed by PCA based descriptors, and shows superior advantages in terms of distinctiveness, invariance to scale, and tolerance of geometric distortions.