To bring digital avatars into people's lives, it is highly demanded to
e...
Head generation with diverse identities is an important task in computer...
Person search is a challenging task which aims to achieve joint pedestri...
Conversation is an essential component of virtual avatar activities in t...
Most video understanding methods are learned on high-quality videos. How...
While recent advances in deep neural networks have made it possible to r...
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...
Efficiently modeling spatial-temporal information in videos is crucial f...
Transformers have demonstrated great potential in computer vision tasks....
Person search has recently emerged as a challenging task that jointly
ad...
Video-based person re-identification (re-ID) is an important research to...
Learning to re-identify or retrieve a group of people across non-overlap...
Person search aims to simultaneously localize and identify a query perso...
Person re-identification has achieved great progress with deep convoluti...
This work make the first attempt to generate articulated human motion
se...
Most existing matching algorithms are one-off algorithms, i.e., they usu...
Key to automatically generate natural scene images is to properly arrang...
Predicting human interaction is challenging as the on-going activity has...
We address the person re-identification problem by effectively exploitin...