VLM - The Vision-Learning-Mining Research Lab
The VLM lab is a research lab at the Computer Science and Engineering
Department of the University of
Texas at Arlington. The lab is directed by Professor Vassilis Athitsos. At the
VLM lab we are conducting research in the areas of computer vision,
machine learning, and data mining. Areas of focus include sign language recognition, detection and tracking of complex shapes, large-scale multiclass recognition, and similarity-based retrieval and classification using large databases.
The goal of this project is to develop a system that lets users search dictionaries of American Sign Language (ASL), so as to look up the meaning of unknown signs.
The goal of this project is to develop methods for efficient identification of subsequence matches in large databases of time series. Demo applications are being developed for sign language video, query by humming, and handwritten text search.
Developing efficient indexing methods for similarity-based search in large image, video, and multimedia databases.
Detection and registration of complicated shapes, such as branches and articulated objects, that cannot be characterized as a configuration of a fixed number of parts.
Estimating 3D hand pose from a single, cluttered image, under arbitrary 3D orientations of the hand.
- Carolyn Stem, Research Associate/ASL Instructor.
- Srujana Gattupalli, M.S., 2013.
- Danny Hanson, M.S., 2013.
- Sanjay Vasudeva Iyer, M.S., 2013.
- Ameya Kulkarni, M.S., 2011.
- Rajesh Radhakrishnan, M.S., 2011.
- Himanshu Pahwa, M.S., 2010.
VLM Research in the News
Some Representative Recent Publications -
H. Zhu, G. Kollios, and V. Athitsos.
A Generic Framework for Efficient and Effective Subsequence Retrieval,
PVLDB, accepted May 2012, to appear.
A. Stefan, V. Athitsos, and G. Das.
The Move-Split-Merge Metric for Time Series,
TKDE, accepted April 2012, to appear.
P. Papapetrou, V. Athitsos, M. Potamias, G. Kollios, and D. Gunopulos.
Embedding-based Subsequence Matching in Time Series,
TODS, August 2011.
H. Wang, A. Stefan, S. Moradi, V. Athitsos, C. Neidle, and F. Kamangar.
A System for Large Vocabulary Sign Search,
Workshop on Sign, Gesture and Activity, 2010.
J. Alon, V. Athitsos, Q. Yuan, and S. Sclaroff.
A Unified Framework for Gesture Recognition and Spatiotemporal Gesture Segmentation,
PAMI, September 2009.
P. Papapetrou, V. Athitsos, G. Kollios, and D. Gunopulos.
Reference-Based Alignment in Large Sequence Databases,