Owing to visual ambiguities and disparities, person re-identification methods inevitably produce suboptimal rank-list, which still requires exhaustive human eyeballing to identify ...
Existing person re-identification methods conventionally rely on labelled pairwise data to learn a task-specific distance metric for ranking. The value of unlabelled gallery instan...
The QMUL underGround person Re-IDentification (GRID) dataset contains 250 pedestrian image pairs. Each pair contains two images of the same individual seen from different camera vi...
State-of-the-art person re-identication methods seek robust person matching through combining various feature types. Often, these features are implicitly assigned with a single ve...
We propose a novel approach to understanding
activities from their partial observations monitored through
multiple non-overlapping cameras separated by unknown time
gaps. In our...