Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- research-articleDecember 2015
Scale and Rotation Invariant Matching Using Linearly Augmented Trees
IEEE Transactions on Pattern Analysis and Machine Intelligence (ITPM), Volume 37, Issue 12Pages 2558–2572https://doi.org/10.1109/TPAMI.2015.2409880We propose a novel linearly augmented tree method for efficient scale and rotation invariant object matching. The proposed method enforces pairwise matching consistency defined on trees, and high-order constraints on all the sites of a template. The ...
- ArticleJune 2011
Exploiting phonological constraints for handshape inference in ASL video
CVPR '11: Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern RecognitionPages 521–528https://doi.org/10.1109/CVPR.2011.5995718Handshape is a key linguistic component of signs, and thus, handshape recognition is essential to algorithms for sign language recognition and retrieval. In this work, linguistic constraints on the relationship between start and end handshapes are ...
- ArticleJune 2011
Scale and rotation invariant matching using linearly augmented trees
CVPR '11: Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern RecognitionPages 2473–2480https://doi.org/10.1109/CVPR.2011.5995580We propose a novel linearly augmented tree method for efficient scale and rotation invariant object matching. The proposed method enforces pairwise matching consistency defined on trees, and high-order constraints on all the sites of a template. The ...
- ArticleAugust 2010
Object Recognition and Localization Via Spatial Instance Embedding
ICPR '10: Proceedings of the 2010 20th International Conference on Pattern RecognitionPages 452–455https://doi.org/10.1109/ICPR.2010.119We propose an approach for improving object recognition and localization using spatial kernels together with instance embedding. Our approach treats each image as a bag of instances (image features) within a multiple instance learning framework, where ...
- articleNovember 2009
Mining frequent arrangements of temporal intervals
The problem of discovering frequent arrangements of temporal intervals is studied. It is assumed that the database consists of sequences of events, where an event occurs during a time-interval. The goal is to mine temporal arrangements of event ...