In this paper, we propose a novel Co-Attentive Sharing (CAS) module which extracts discriminative channels and spatial regions for more effective feature sharing in multi-task learning.
To further verify the scalability of our method, we propose a new large-scale multi-human dataset with 12 to 28 camera views.
Ranked #4 on 3D Multi-Person Pose Estimation on Campus
The fundamental difficulty in person re-identification (ReID) lies in learning the correspondence among individual cameras.
Ranked #14 on Unsupervised Domain Adaptation on Duke to Market
It remains very challenging to build a pedestrian detection system for real world applications, which demand for both accuracy and speed.
One paradigm to deal with this problem is to use some complicated methods for mapping all images into an artificial image space, which however will disrupt the natural image distribution and requires heavy image preprocessing.
Online multi-object tracking is a fundamental problem in time-critical video analysis applications.
Ranked #3 on Online Multi-Object Tracking on MOT16