In this paper, we focus on a new and challenging decentralized machine
l...
In recent years, significant progress has been made on the research of c...
Online continual learning in the wild is a very difficult task in machin...
Anomaly detection plays a key role in industrial manufacturing for produ...
Traditional crowd counting approaches usually use Gaussian assumption to...
In this paper, we focus on the multi-object tracking (MOT) problem of
au...
The ability to incrementally learn new classes is crucial to the develop...
Person re-identification (re-ID) has made great progress and achieved hi...
In crowd counting datasets, each person is annotated by a point, which i...
The performance of person re-identification (Re-ID) seriously depends on...
Person re-identification (Re-ID) usually suffers from noisy samples with...
Multi-face tracking in unconstrained videos is a challenging problem as ...
Person re-identification (Re-ID) aims at matching images of the same per...
Learning the distance metric between pairs of examples is of great impor...
In the recent years impressive advances were made for single image
super...
Superpixel segmentation is becoming ubiquitous in computer vision. In
pr...
Single modality action recognition on RGB or depth sequences has been
ex...
Salient object detection has been attracting a lot of interest, and rece...