Binary silhouettes and keypoint-based skeletons have dominated human gai...
Visible-Infrared person Re-IDentification (VI-ReID) is a challenging
cro...
Although the estimation of 3D human pose and shape (HPS) is rapidly
prog...
Human pose estimation aims to figure out the keypoints of all people in
...
We develop WOC, a webcam-based 3D virtual online chatroom for multi-pers...
Human Video Motion Transfer (HVMT) aims to, given an image of a source
p...
Recognizing human actions from point cloud videos has attracted tremendo...
Existing studies for gait recognition are dominated by in-the-lab scenar...
Human motion transfer refers to synthesizing photo-realistic and tempora...
In this paper, we investigate how to achieve better visual grounding wit...
Detection of object anomalies is crucial in industrial processes, but
un...
To date, visual question answering (VQA) (i.e., image QA and video QA) i...
Existing studies for gait recognition are dominated by 2D representation...
Action recognition from videos, i.e., classifying a video into one of th...
Given an image with multiple people, our goal is to directly regress the...
The RGB-infrared cross-modality person re-identification (ReID) task aim...
Visible-infrared cross-modality person re-identification is a challengin...
This technical report introduces our 2nd place solution to Kinetics-TPS ...
Existing person re-identification (re-id) methods are stuck when deploye...
Person re-identification (Re-ID) aims to match pedestrians under dis-joi...
The performance of human pose estimation depends on the spatial accuracy...
Estimation of the human pose from a monocular camera has been an emergin...
Unsupervised Domain Adaptive (UDA) person re-identification (ReID) aims ...
Person Re-identification (ReID) has achieved significant improvement due...
Gait, i.e., the movement pattern of human limbs during locomotion, is a
...
Recovering 3D human mesh from monocular images is a popular topic in com...
In this paper, we propose a method to recover multi-person 3D mesh from ...
Person re-identification (Re-ID) aims at retrieving an input person imag...
Deep neural networks have achieved remarkable success for video-based ac...
We present FastReID, as a widely used object re-identification (re-id)
s...
Quantization has been an effective technology in ANN (approximate neares...
Re-identifying a person across multiple disjoint camera views is importa...
This paper presents a review of the 2018 WIDER Challenge on Face and
Ped...
Discovering social relations in images can make machines better interpre...
This paper is focused on the task of searching for a specific vehicle th...
To reduce the large computation and storage cost of a deep convolutional...
Mobile visual search applications are emerging that enable users to sens...
Action recognition in surveillance video makes our life safer by detecti...
Recent progress has been made in using attention based encoder-decoder
f...