Local spatiotemporal features or interest points provide compact but descriptive representations for efficient video analysis and motion recognition. Current local feature extract...
We consider the problem of learning a similarity function from a set of positive equivalence constraints, i.e. 'similar' point pairs. We define the similarity in informa...
We present a new approach to robust pose-variant face
recognition, which exhibits excellent generalization ability
even across completely different datasets due to its weak
depe...
John Wright (University of Illinois), Gang Hua (Mi...
Background: To exploit the flood of data from advances in high throughput imaging of optically sectioned nuclei, image analysis methods need to correctly detect thousands of nucle...
Anthony Santella, Zhuo Du, Sonja Nowotschin, Anna-...
The existence of large image datasets such as the set of photos on the World Wide Web make it possible to build powerful generic models for low-level image attributes like color u...