Jhih-Ciang Wu

Jhih-Ciang Wu

Auto-generated profile, based on publicly available information

Jhih-Ciang Wu

National Taiwan Normal University, Taipei, Taiwan

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
3 November 2022
Verified
Book Chapter
Closed access
PDF file
JWJhih-Ciang Wu
Jhih-Ciang Wu
HHHe-Yen Hsieh
He-Yen Hsieh
DCDing-Jie Chen
Ding-Jie Chen
CFChiou-Shann Fuh
Chiou-Shann Fuh
TLTyng-Luh Liu
Tyng-Luh Liu

28 October 2024
Verified
Conference Paper
Open access
JJJian-Yu Jiang-Lin
Jian-Yu Jiang-Lin
KHKang-Yang Huang
Kang-Yang Huang
LLLing Lo
Ling Lo
YHYi-Ning Huang
Yi-Ning Huang
TLTerence Lin
Terence Lin
WCWen-Huang Cheng
Wen-Huang Cheng
Diffusion models revolutionize image generation by leveraging natural language to guide the creation of multimedia content. Despite significant advancements in such generative models, challenges persist in depicting detailed human-object interactions, especially regarding pose and object placement accuracy. We introduce a training-free method named Reasoning and Correcting Diffusion (ReCorD) to address these challenges. Our model couples Latent Diffusion Models with Visual Language Models to refine the generation process, ensuring precise depictions of HOIs. We propose an interaction-aware reasoning module to improve the interpretation of the interaction, along with an interaction correcting module to refine the output image for more precise HOI generation delicately. Through a meticulous process of pose selection and object positioning, ReCorD achieves superior fidelity in generated images while efficiently reducing computational requirements. We conduct comprehensive experiments on three benchmarks to demonstrate the significant progress in solving text-to-image generation tasks, showcasing ReCorD's ability to render complex interactions accurately by outperforming existing methods in HOI classification score, as well as FID and Verb CLIP-Score. Project website is available at https://alberthkyhky.github.io/ReCorD/.

27 October 2025
Verified
Conference Paper
Open access
KLKun-Hsiang Lin
Kun-Hsiang Lin
YTYu-Wen Tseng
Yu-Wen Tseng
KHKang-Yang Huang
Kang-Yang Huang
JWJhih-Ciang Wu
Jhih-Ciang Wu
WCWen-Huang Cheng
Wen-Huang Cheng

17 November 2024
Verified
Book Chapter
Closed access
PDF file
LTLi-Wu Tsao
Li-Wu Tsao
HTHao-Tang Tsui
Hao-Tang Tsui
YTYu-Rou Tuan
Yu-Rou Tuan
PCPei-Chi Chen
Pei-Chi Chen
KWKuan-Lin Wang
Kuan-Lin Wang
WCWen-Huang Cheng
Wen-Huang Cheng

27 October 2025
Verified
Conference Paper
Open access
FHFeng-Kai Huang
Feng-Kai Huang
BHBo-Lun Huang
Bo-Lun Huang
LTLi-Wu Tsao
Li-Wu Tsao
JWJhih-Ciang Wu
Jhih-Ciang Wu
HSHong-Han Shuai
Hong-Han Shuai
WCWen-Huang Cheng
Wen-Huang Cheng