We describe efficient techniques for construction of large term co-occurrence graphs, and investigate an application to the discovery of numerous fine-grained (specific) topics. A...
Unsupervised clustering can be significantly improved using supervision in the form of pairwise constraints, i.e., pairs of instances labeled as belonging to same or different clu...
We introduce a new model for semantic annotation and retrieval from image databases. The new model is based on a probabilistic formulation that poses annotation and retrieval as c...
— Handling catastrophic forgetting is an interesting and challenging topic in modeling the memory mechanisms of the human brain using machine learning models. From a more general...
We present a novel method for the discovery and statistical representation of motion patterns in a scene observed by a static camera. Related methods involving learning of pattern...