Pre-trained vision transformers have strong representation benefits to
v...
Current research on cross-modal retrieval is mostly English-oriented, as...
Unsupervised contrastive learning methods have recently seen significant...
Person Re-identification (ReID) plays a more and more crucial role in re...
Unsupervised domain adaptive person re-identification (Re-ID) methods
al...
Vision Transformers (ViTs) are normally regarded as a stack of transform...
One of the essential missions in the AI research community is to build a...
Parameter-Efficient Transfer Learning (PETL) aims at efficiently adaptin...
Decentralized policy optimization has been commonly used in cooperative
...
Deep supervised learning algorithms generally require large numbers of
l...
It has been witnessed that masked image modeling (MIM) has shown a huge
...
Current scene depth estimation approaches mainly rely on optical sensing...
Recent masked image modeling (MIM) has received much attention in
self-s...
We study the backward compatible problem for person re-identification
(R...
This paper is devoted to the error analysis of a time-spectral algorithm...
This paper introduces our solution for the Track2 in AI City Challenge 2...
Multi-Target Multi-Camera Tracking has a wide range of applications and ...
In this paper, we explore the Vision Transformer (ViT), a pure
transform...
This paper presents our proposed methods for domain adaptive pedestrian
...
A key challenge of oversampling in imbalanced classification is that the...
Lane marker extraction is a basic yet necessary task for autonomous driv...
This paper introduces our solution for the Track2 in AI City Challenge 2...
Due to its potential wide applications in video surveillance and other
c...
An effective approach for voice conversion (VC) is to disentangle lingui...
Vehicle re-identification (Re-ID) has been attracting increasing interes...
Recent cutting-edge feature aggregation paradigms for video object detec...
This study explores a simple but strong baseline for person re-identific...
Partial person re-identification (ReID) is a challenging task because on...
This paper explores a simple and efficient baseline for person
re-identi...
This paper explores a simple and efficient baseline for person
re-identi...
Statistical body shape models are widely used in 3D pose estimation due ...
State-of-the-art object detectors and trackers are developing fast. Trac...
Holistic person re-identification (ReID) has received extensive study in...
Many current successful Person Re-Identification(ReID) methods train a m...
In this paper, we propose a novel method called AlignedReID that extract...
Person re-identification (ReID) is an important task in computer vision....