activity
20192022
most citedHuman Action Recognition from Various Data Modalities: A Review

599 citations · 842 across the 10 of their papers we have counts for

collaborators

11 papers

cs.CV2022★ 11 cited

Bridging the Source-to-target Gap for Cross-domain Person Re-Identification with Intermediate Domains

Yongxing Dai, Yifan Sun, Jun Liu +3

Cross-domain person re-identification (re-ID), such as unsupervised domain adaptive (UDA) re-ID, aims to transfer the identity-discriminative knowledge from the source to the targe…

cs.CV2021

Dual-Tuning: Joint Prototype Transfer and Structure Regularization for Compatible Feature Learning

Yan Bai, Jile Jiao, Shengsen Wu +4

Visual retrieval system faces frequent model update and deployment. It is a heavy workload to re-extract features of the whole database every time.Feature compatibility enables the…

cs.CV2021★ 7 cited

IDM: An Intermediate Domain Module for Domain Adaptive Person Re-ID

Yongxing Dai, Jun Liu, Yifan Sun +3

Unsupervised domain adaptive person re-identification (UDA re-ID) aims at transferring the labeled source domain's knowledge to improve the model's discriminability on the unlabele…

cs.CV2021★ 12 cited

Dual-Refinement: Joint Label and Feature Refinement for Unsupervised Domain Adaptive Person Re-Identification

Yongxing Dai, Jun Liu, Yan Bai +2

Unsupervised domain adaptive (UDA) person re-identification (re-ID) is a challenging task due to the missing of labels for the target domain data. To handle this problem, some rece…

cs.CV2020★ 599 cited

Human Action Recognition from Various Data Modalities: A Review

Zehua Sun, Qiuhong Ke, Hossein Rahmani +3

Human Action Recognition (HAR) aims to understand human behavior and assign a label to each action. It has a wide range of applications, and therefore has been attracting increasin…

cs.CV2020★ 48 cited

Skeleton-based Relational Reasoning for Group Activity Analysis

Mauricio Perez, Jun Liu, Alex C. Kot

Research on group activity recognition mostly leans on the standard two-stream approach (RGB and Optical Flow) as their input features. Few have explored explicit pose information,…