Graph convolution networks (GCNs) have achieved remarkable performance i...
Human motion prediction has achieved a brilliant performance with the he...
Audio-visual question answering (AVQA) is a challenging task that requir...
The task of Group Activity Recognition (GAR) aims to predict the activit...
In the perception task of autonomous driving, multi-modal methods have b...
In this paper, we concern on the bottom-up paradigm in multi-person pose...
This technical report describes our first-place solution to the pose
est...
This work introduces a new task of instance-incremental scene graph
gene...
In this paper, we develop an efficient multi-scale network to predict ac...
Audio-visual event localization has attracted much attention in recent y...
Estimating human poses from videos is critical in human-computer interac...
Accurate and unbiased examinations of skin lesions are critical for earl...
In recent years, audio-visual event localization has attracted much
atte...
Human motion prediction is a challenge task due to the dynamic spatiotem...
Early action prediction aims to recognize human actions from only a part...
Reducing the scope of grasping detection according to the semantic
infor...
Amodal segmentation is a new direction of instance segmentation while
co...
Video-based human pose estimation (HPE) is a vital yet challenging task....
Human motion prediction is essential for tasks such as human motion anal...
Joint relation modeling is a curial component in human motion prediction...
Fusion is critical for a two-stream network. In this paper, we propose a...
The reliability of grasp detection for target objects in complex scenes ...
Human motion prediction is an essential part for human-robot collaborati...
Predicting future human motion is critical for intelligent robots to int...
Human motion prediction plays a vital role in human-robot interaction wi...
Action repetition counting is to estimate the occurrence times of the
re...
Pose prediction is an increasingly interesting topic in computer vision ...
Pose prediction is to predict future poses given a window of previous po...
We propose in this paper a deep-wide network (DWnet) which combines the ...