Referring image segmentation, the task of segmenting any arbitrary entit...
Image restoration (IR) has been an indispensable and challenging task in...
Recent vision transformers, large-kernel CNNs and MLPs have attained
rem...
Recognizing elementary underlying concepts from observations
(disentangl...
In recent years, we have witnessed the great advancement of Deep neural
...
Representing a signal as a continuous function parameterized by neural
n...
Vision transformer has demonstrated great potential in abundant vision t...
Referring image segmentation is an advanced semantic segmentation task w...
Improving the generalization capability of Deep Neural Networks (DNNs) i...
This paper presents ActiveMLP, a general MLP-like backbone for computer
...
For deep reinforcement learning (RL) from pixels, learning effective sta...
Unsupervised domain adaptive person re-identification (ReID) has been
ex...
Confounders in deep learning are in general detrimental to model's
gener...
Skeleton data is of low dimension. However, there is a trend of using ve...
Skeleton data carries valuable motion information and is widely explored...
Domain generalization for semantic segmentation is highly demanded in re...
Occluded person re-identification (ReID) aims to match person images wit...
Unsupervised domain adaptive classification intends to improve
theclassi...
Learning good feature representations is important for deep reinforcemen...
Unsupervised domain adaptive (UDA) person re-identification (ReID) aims ...
For unsupervised domain adaptation (UDA), to alleviate the effect of dom...
Many unsupervised domain adaptation (UDA) methods exploit domain adversa...
Domain generalization (DG), i.e., out-of-distribution generalization, ha...
Vehicle Re-Identification (V-ReID) is a critical task that associates th...
For many practical computer vision applications, the learned models usua...
Many unsupervised domain adaptive (UDA) person re-identification (ReID)
...
Few-shot image classification aims to learn to recognize new categories ...
For domain generalization (DG) and unsupervised domain adaptation (UDA),...
Person Re-identification (ReID) aims at matching a person of interest ac...
Supervised person re-identification (ReID) often has poor scalability an...
Existing fully-supervised person re-identification (ReID) methods usuall...
Video-based person re-identification (reID) aims at matching the same pe...
In this paper, we propose a spatio-temporal contextual network, STC-Flow...
Optical flow estimation is an important yet challenging problem in the f...
Object re-identification (re-id) aims to identify a specific object acro...
Recurrent neural networks (RNNs) are capable of modeling temporal
depend...
Person re-identification (reID) aims to match person images to retrieve ...
Objects in an image exhibit diverse scales. Adaptive receptive fields ar...
Attention mechanism aims to increase the representation power by focusin...
Scene graph construction / visual relationship detection from an image a...
Skeleton-based human action recognition has attracted a lot of interests...
The recent success of deep networks has significantly advanced 3D human ...
We propose a densely semantically aligned person re-identification (re-I...
Deep learning models have enjoyed great success for image related comput...
Recurrent neural networks (RNNs) are capable of modeling the temporal
dy...
Skeleton-based human action recognition has recently attracted increasin...
In this paper, we address the problem of estimating the positions of hum...
Skeleton-based human action recognition has recently attracted increasin...
Human action recognition is an important task in computer vision. Extrac...
Human action recognition from well-segmented 3D skeleton data has been
i...