J
Joseph Tighe
Researcher at Amazon.com
Publications - 60
Citations - 2163
Joseph Tighe is an academic researcher from Amazon.com. The author has contributed to research in topics: Computer science & Video tracking. The author has an hindex of 15, co-authored 47 publications receiving 1713 citations. Previous affiliations of Joseph Tighe include University of North Carolina at Chapel Hill & Adobe Systems.
Papers
More filters
Book ChapterDOI
Superparsing: scalable nonparametric image parsing with superpixels
Joseph Tighe,Svetlana Lazebnik +1 more
TL;DR: This paper presents a simple and effective nonparametric approach to the problem of image parsing, or labeling image regions (in this case, superpixels produced by bottom-up segmentation) with their categories, and establishes a new benchmark for the problem.
Journal ArticleDOI
Superparsing: Scalable Nonparametric Image Parsing with Superpixels
Joseph Tighe,Svetlana Lazebnik +1 more
TL;DR: In this paper, a Markov Random Field (MRF) is used to combine scene-level matching with global image descriptors, followed by superpixel level matching with local features and efficient MRF optimization for incorporating neighborhood context.
Proceedings ArticleDOI
Finding Things: Image Parsing with Regions and Per-Exemplar Detectors
Joseph Tighe,Svetlana Lazebnik +1 more
TL;DR: This paper presents a system for image parsing, or labeling each pixel in an image with its semantic category, aimed at achieving broad coverage across hundreds of object categories, many of them sparsely sampled.
Proceedings ArticleDOI
Scene Parsing with Object Instances and Occlusion Ordering
TL;DR: A method to interpret a scene by assigning a semantic label at every pixel and inferring the spatial extent of individual object instances together with their occlusion relationships is proposed.
Proceedings ArticleDOI
SiamMOT: Siamese Multi-Object Tracking
TL;DR: SiamMOT as discussed by the authors introduces a motion model that estimates the instance's movement between two frames such that detected instances are associated, and it runs at 17 FPS for 720P videos on a single modern GPU.