Wenrui Lu

Wenrui Lu

Auto-generated profile, based on publicly available information

Wenrui Lu

The Chinese University of Hong Kong, Hong Kong, New Territories, Hong Kong

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
18 June 2023
Verified
Conference Paper
Open access
ZXZhiyuan Xie
Zhiyuan Xie
XOXiaomin Ouyang
Xiaomin Ouyang
LPLi Pan
Li Pan
WLWenrui Lu
Wenrui Lu
GXGuoliang Xing
Guoliang Xing
XLXiaoming Liu
Xiaoming Liu

20 June 2026
Verified
Conference Paper
Open access
SJSiyang Jiang
Siyang Jiang
MYMu Yuan
Mu Yuan
XJXiang Ji
Xiang Ji
BYBufang Yang
Bufang Yang
ZLZeyu Liu
Zeyu Liu
GXGuoliang Xing
Guoliang Xing
Multimodal human action recognition (HAR) utilizes complementary data for activity classification. Built on traditional HAR tasks, recent advances in Large Language Models (LLMs) enable detailed descriptions and causal reasoning of human actions, advancing new tasks of human action understanding (HAU) and human action reasoning (HARn). However, most LLMs, especially multimodal Large Vision-Language Models (LVLMs), struggle with modalities other than RGB images, like depth, IMU, ormmWave, due to a lack of large-scale datasets in these task domains. Existing HAR datasets provide only coarse-grained annotations, in-sufficient for depicting the detailed action dynamics required in HAU and HARn tasks. Simply combining annotations and generating captions with LLMs often lacks necessary logical and spatiotemporal consistency. In this paper, we introduce CUHK-X, a large-scale multi-modal dataset and benchmarks for HAR, HAU, and HARn. It includes 64,267 samples of 40 actions performed by 30 participants across two indoor environments, covering diverse daily scenarios. To address the challenge of spatiotemporal inconsistencies in captions, we propose a prompt-based scene creation method that leverages LLMs to generate logically connected activity sequences. CUHK-X also includes three benchmarks with six tasks to evaluate state-of-the-art models. Experimental results show average accuracies of 76.52% for HAR, 40.76% for HAU, and 70.25% for HARn. This large-scale multimodal dataset aims to empower the research community to apply, develop, and adapt data-intensive learning techniques for a wide range of human activity-related tasks.


20 June 2026
Verified
Conference Paper
Open access
WLWenrui Lu
Wenrui Lu
MYMu Yuan
Mu Yuan
BYBufang Yang
Bufang Yang
KLKaiwei Liu
Kaiwei Liu
MJMuye Jia
Muye Jia
GXGuoliang Xing
Guoliang Xing

26 October 2026
Verified
Conference Paper
Open access
WLWenrui Lu
Wenrui Lu
MYMu Yuan
Mu Yuan
BYBufang Yang
Bufang Yang
SJSiyang Jiang
Siyang Jiang
Wei GaoWei Gao
Wei Gao
GXGuoliang Xing
Guoliang Xing