The huge amount of temporal data generated from many important applications call for a highly efficient and scalable version index. The TSB-tree has the potential of large scalab...
Within the field of action recognition, features and descriptors are often engineered to be sparse and invariant to transformation. While sparsity makes the problem tractable, it ...
We present an approach for learning models that obtain accurate classification of large scale data objects, collected in spatiotemporal domains. The model generation is structured ...
Igor Vainer, Sarit Kraus, Gal A. Kaminka, Hamutal ...
Unsupervised categorization of objects is a fundamental problem in computer vision. While appearance-based methods have become popular recently, other important cues like function...
—For energy conservation, a wireless sensor network is usually designed to work in a low-duty-cycle mode, in which a sensor node keeps active for a small percentage of time durin...
Shuguang Xiong, Jianzhong Li, Mo Li, Jiliang Wang,...