A
Ashwin Thangali
Researcher at Boston University
Publications - 14
Citations - 530
Ashwin Thangali is an academic researcher from Boston University. The author has contributed to research in topics: Object detection & Video tracking. The author has an hindex of 10, co-authored 14 publications receiving 470 citations.
Papers
More filters
Proceedings ArticleDOI
The American Sign Language Lexicon Video Dataset
Vassilis Athitsos,Carol Neidle,Stan Sclaroff,Joan Nash,Alexandra Stefan,Quan Yuan,Ashwin Thangali +6 more
TL;DR: The ASL lexicon video dataset is introduced, a large and expanding public dataset containing video sequences of thousands of distinct ASL signs, as well as annotations of those sequences, including start/end frames and class label of every sign.
Proceedings ArticleDOI
Coupling detection and data association for multiple object tracking
TL;DR: A novel framework for multiple object tracking in which the problems of object detection and data association are expressed by a single objective function, which follows the Lagrange dual decomposition strategy.
Journal ArticleDOI
Learning a Family of Detectors via Multiplicative Kernels
TL;DR: This work shows that foreground-background classification (detection) and within-class classification of the foreground class (pose estimation) can be jointly learned in a multiplicative form of two kernel functions.
Challenges in development of the American Sign Language Lexicon Video Dataset (ASLLVD) corpus
TL;DR: An example computer vision application that leverages the ASLLVD is reported: the formulation employs a HandShapes Bayesian Network (HSBN), which models the transition probabilities between start and end handshapes in monomorphemic lexical signs.
Proceedings ArticleDOI
Exploiting phonological constraints for handshape inference in ASL video
TL;DR: In this work, linguistic constraints on the relationship between start and end handshapes are leveraged to improve handshape recognition accuracy, and a Bayesian network formulation is proposed for learning and exploiting these constraints, while taking into consideration inter-signer variations in the production of particular handsh shapes.