Haowen Wang

Haowen Wang

Auto-generated profile, based on publicly available information

Haowen Wang

The Chinese University of Hong Kong

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

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

Representative Publications

View All Publications
12 April 2024 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
HWHaowen Wang
Haowen Wang
ZCZhengping Che
Zhengping Che
YYYufan Yang
Yufan Yang
MWMingyuan Wang
Mingyuan Wang
ZXZhiyuan Xu
Zhiyuan Xu
JTJian Tang
Jian Tang
Raw depth images captured in indoor scenarios frequently exhibit extensive missing values due to the inherent limitations of the sensors and environments. For example, transparent materials frequently elude detection by depth sensors; surfaces may introduce measurement inaccuracies due to their polished textures, extended distances, and oblique incidence angles from the sensor. The presence of incomplete depth maps imposes significant challenges for subsequent vision applications, prompting the development of numerous depth completion techniques to mitigate this problem. Numerous methods excel at reconstructing dense depth maps from sparse samples, but they often falter when faced with extensive contiguous regions of missing depth values, a prevalent and critical challenge in indoor environments. To overcome these challenges, we design a novel two-branch end-to-end fusion network named RDFC-GAN, which takes a pair of RGB and incomplete depth images as input to predict a dense and completed depth map. The first branch employs an encoder-decoder structure, by adhering to the Manhattan world assumption and utilizing normal maps from RGB-D information as guidance, to regress the local dense depth values from the raw depth map. The other branch applies an RGB-depth fusion CycleGAN, adept at translating RGB imagery into detailed, textured depth maps while ensuring high fidelity through cycle consistency. We fuse the two branches via adaptive fusion modules named W-AdaIN and train the model with the help of pseudo depth maps. Comprehensive evaluations on NYU-Depth V2 and SUN RGB-D datasets show that our method significantly enhances depth completion performance particularly in realistic indoor settings.

9 August 2024 in Frontiers in Pharmacology
Verified
Journal Article
Open access
PDF file
QMQing-Yue Ma
Qing-Yue Ma
YLYi-Chong Liu
Yi-Chong Liu
QZQian Zhang
Qian Zhang
WYWen-Dan Yi
Wen-Dan Yi
YSYing Sun
Ying Sun
WLWen-Juan Luo
Wen-Juan Luo
Background: Artesunate (ART), a natural compound derived from Artemisia annua, has shown promising clinical potentials in the treatment of various tumors, but the exact mechanism is unclear. Choroidal melanoma (CM) is a major malignant ocular tumor in adults, known for its significant malignancy and poor prognosis, with limited efficacy in current treatments. This study explored the anti-CM effects and mechanisms of ART using a combination of network pharmacology, molecular docking and experimental validation.Methods: Potential targets of ART were screened in PubChem, Swiss Target Prediction and Traditional Chinese Medicine Systems Pharmacology (TCMSP) Database Analysis Platform databases, while target genes related to CM prognosis were selected from Online Mendelian Inheritance in Man (OMIM), GeneCards and DisGeNET databases. The intersection of these two groups of datasets yielded the target genes of ART involved in CM. Protein-protein interaction (PPI) network analysis of the intersecting targets, as well as Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) analyses, were conducted to identify core targets and critical pathways. Molecular docking methods were performed to predict the binding interactions between ART and core targets. The effects of ART on CM were evaluated through CCK8, colony formation, transwell, as well as flow cytometry assays to detect apoptosis, cell cycle, reactive oxygen species (ROS). Western blot (WB) assays were conducted to investigate the impact of ART on key proteins and pathways associated with CM. Finally, in vivo assays were conducted to further validate the effects of ART on subcutaneous tumors in nude mice.Results: Research has shown that key pathways and core targets for ART in treating CM were identified through a network pharmacology approach. Molecular docking results verified the strong binding affinity between ART and these core targets. The analysis and predicted results indicated that ART primarily exerted its effects on CM through various tumor-related pathways like apoptosis. The assays in vitro confirmed that ART significantly inhibited the proliferation and migration of CM cells. This was achieved by promoting apoptosis through activation of the p53 signaling pathway, causing cell cycle arrest at the G0/G1 phase by inhibiting the PI3K/AKT/mTOR signaling pathway and increasing the intracellular level of ROS by activating the NRF2/HO-1 signaling pathway. Additionally, the assays in vivo further validated the significant proliferation-inhibitory effect of ART on CM.Conclusion: This study, making the initial exploration, illustrated through network pharmacology combined with molecular docking and in vitro/in vivo assays, confirmed that ART exerted potential anti-cancer effects on CM by promoting apoptosis, inducing cell cycle arrest and increasing intracellular levels of ROS. These findings suggested that ART held significant therapeutic potential for CM.

26 October 2023
Verified
Conference Paper
Open access
HWHaowen Wang
Haowen Wang
ZFZhipeng Fan
Zhipeng Fan
ZZZhen Zhao
Zhen Zhao
ZCZhengping Che
Zhengping Che
ZXZhiyuan Xu
Zhiyuan Xu
JTJian Tang
Jian Tang

24 October 2016
Verified
Conference Paper
Closed access
ZCZhaoming Chen
Zhaoming Chen
YHYANJUN HU
YANJUN HU
Xue WangXue Wang
Xue Wang
HWHaowen Wang
Haowen Wang
DCDelin Cai
Delin Cai
The traditional LTE-A algorithm validation is limited to pure computer software simulation, which can't simulate the actual link scenes, missing scene parameters, the simulation results is invaluable in practice. Therefore, this paper designs LTE-A hardware-in-the-loop simulation system based on software-defined radio device USRP, and the physical layer real-time test level downlink is designed on the system. The downlink scheduled by the scheduling algorithm of the PC simulation platform, with scene parameters feedback to MAC layer in real time. The downlink designed with power interference between cells and users simulate the actual scene. Compare to current design of LTE hardware-in-the-loop simulation, this design presents data interaction between MAC layer and physical layer, implement of specific requirements for physical layer link, instead of generation of vector signal only. The results show that the system is running normally with easy scalability.

17 November 2023
Verified
Conference Paper
Closed access
HWHaowen Wang
Haowen Wang
QZQijie Zhao
Qijie Zhao
XWXianggang Wang
Xianggang Wang
WZWeichi Zhao
Weichi Zhao
Gaze detection is the basis for driver state monitoring and intent recognition as well as vision-based human-vehicle interaction. This paper proposed an appearance-based gaze direction vector detection model, taking the eye image, head posture and pupil center position as sample data and the gaze direction vector as sample labels, and using the improved VGG deep learning network for training to obtain the driver's gaze direction vector, and completing the gaze direction detection of the driver's gazing at different target regions. In the real car environment, we carried out experiments to recognize 6 different regions of the windshield, and the results show that the gaze direction detection method proposed in this paper is basically unaffected by changes in head posture and driving environment illumination, and the average detection accuracy for 10 drivers is 96.53%.

1 January 2026 in IEEE Transactions on Multimedia
Verified
Journal Article
Closed access
QCQiang Chen
Qiang Chen
XWXiao Wang
Xiao Wang
HWHaowen Wang
Haowen Wang
BJBo Jiang
Bo Jiang
LZLin Zhu
Lin Zhu
JTJin Tang
Jin Tang