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...
Learning the knowledge of scene structure and tracking a large number of targets are both active topics of computer vision in recent years, which plays a crucial role in surveilla...
Xuan Song, Xiaowei Shao, Huijing Zhao, Jinshi Cui,...
We propose a new technique for fusing multiple cues to robustly segment an object from its background in video sequences that suffer from abrupt changes of both illumination and po...
Francesc Moreno-Noguer, Alberto Sanfeliu, Dimitris...
This paper addresses the problem of learning object models from egocentric video of household activities, using extremely weak supervision. For each activity sequence, we know onl...
The design of robust classifiers, which can contend with the noisy and outlier ridden datasets typical of computer vision, is studied. It is argued that such robustness requires l...