364
click to vote
Publication
Regression-based techniques have shown promising results for people counting in crowded scenes. However, most existing techniques require expensive and laborious data annotation fo...
393
click to vote
Publication
Owing to visual ambiguities and disparities, person re-identification methods inevitably produce suboptimal rank-list, which still requires exhaustive human eyeballing to identify ...
430
Voted
Publication
Generating coherent synopsis for surveillance video stream remains a formidable challenge due to the ambiguity and uncertainty inherent to visual observations. In contrast to exist...
473
click to vote
Publication
While clustering is usually an unsupervised operation, there are circumstances in which we have prior belief that pairs of samples should (or should not) be assigned to the same cl...
343
click to vote
Publication
This paper introduces a simple, general framework for likelihood-free Bayesian reinforcement learning, through Approximate Bayesian Computation (ABC). The main advantage is th...