Prototype-based meta-learning has emerged as a powerful technique for
ad...
Facial expression editing has attracted increasing attention with the ad...
Generative Adversarial Networks (GANs) rely heavily on large-scale train...
In this paper, we propose energy-based sample adaptation at test time fo...
Most existing few-shot learning (FSL) methods require a large amount of
...
This paper presents a Refinement Pyramid Transformer (RePFormer) for rob...
Recently, large-scale synthetic datasets are shown to be very useful for...
Pedestrian detection is the cornerstone of many vision based application...
Person search aims to jointly localize and identify a query person from
...
Domain generalizable person re-identification aims to apply a trained mo...
Person search aims to simultaneously localize and identify a query perso...
While single-view 3D reconstruction has made significant progress benefi...
Transformers have demonstrated great potential in computer vision tasks....
Person search has recently emerged as a challenging task that jointly
ad...
Unsupervised domain adaptation for object detection is a challenging pro...
Transformers have recently gained increasing attention in computer visio...
In recent years, significant progress has been made in the research of f...
Generalizable person re-identification has recently got increasing atten...
Person search aims to simultaneously localize and identify a query perso...
Existing person re-identification methods often have low generalization
...
Person re-identification has seen significant advancement in recent year...
Unsupervised domain adaptation (UDA) for person re-identification is
cha...
Pedestrian detection is used in many vision based applications ranging f...
Recently, heatmap regression based models become popular because of thei...
For image matching tasks, like face recognition and person re-identifica...
Object detection generally requires sliding-window classifiers in tradit...
Spectral super-resolution (SSR) aims at generating a hyperspectral image...
In order to resist the adverse effect of viewpoint variations for improv...
Color names based image representation is successfully used in person
re...
Person re-identification task has been greatly boosted by deep convoluti...
Person re-identification is challenging due to the large variations of p...
Pushing by big data and deep convolutional neural network (CNN), the
per...
We propose a method to address challenges in unconstrained face detectio...
Person re-identification is becoming a hot research for developing both
...
Person re-identification is an important technique towards automatic sea...
After intensive research, heterogenous face recognition is still a
chall...