Generalization to out-of-distribution (OOD) data is a capability natural to humans yet
challenging for machines to reproduce. This is because most learning algorithms strongly …

As the globally increasing population drives rapid urbanization in various parts of the world,
there is a great need to deliberate on the future of the cities worth living. In particular, as …

Unsupervised person re-identification (re-ID) aims at learning discriminative representations
for person retrieval from unlabeled data. Recent techniques accomplish this task by using …

The challenging task of multi-object tracking (MOT) requires simultaneous reasoning about
track initialization, identity, and spatio-temporal trajectories. We formulate this task as a …

Person re-identification aims to retrieve persons in highly varying settings across different
cameras and scenarios, in which robust and discriminative representation learning is …

Recent advances in deep neural networks (DNNs) have mainly focused on innovations in
network architecture and loss function. In this paper, we introduce a flexible high-order …

Person re-identification (Re-ID) aims at retrieving a person of interest across multiple non-
overlapping cameras. With the advancement of deep neural networks and increasing …

Existing alignment-based methods have to employ the pre-trained human parsing models to
achieve the pixel-level alignment, and cannot identify the personal belongings (eg …

Object detection and tracking is one of the most important and challenging branches in
computer vision, and have been widely applied in various fields, such as health-care …

Gait benchmarks empower the research community to train and evaluate high-performance
gait recognition systems. Even though growing efforts have been devoted to cross-view …