Abstract. We propose a theoretical framework for the optimal collaboration among researchers in a knowledge network in which researchers are not limited to a single discipline and ...
Scalability and reliability are inseparable in high-performance computing. Fault-isolation through hardware is a popular means of providing reliability. Unfortunately, such isolat...
Visual attributes expose human-defined semantics to object recognition models, but existing work largely restricts their influence to mid-level cues during classifier training....
We propose a novel system for associating multi-target tracks across multiple non-overlapping cameras by an on-line learned discriminative appearance affinity model. Collecting rel...
Domain adaptation solves a learning problem in a target domain by utilizing the training data in a different but related source domain. Intuitively, discovering a good feature rep...
Sinno Jialin Pan, Ivor W. Tsang, James T. Kwok, Qi...