Shuchang Ye
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Shuchang Ye has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Jinman Kim
The University of Sydney
5 shared publications - Mingyuan Meng
The University of Sydney
5 shared publications - Dagan Feng
Biomedical and Multimedia Information Technology Research Group, School of Computer Science, The University of Sydney, Sydney, NSW, Australia
3 shared publications - Mingjian Li
School of Computer Science, The University of Sydney
3 shared publications - Usman Naseem
Macquarie University, Australia
2 shared publications - Andre Z. Kyme
The University of Sydney
1 shared publication
Latest Publications
- 24 September 2026
- Published by Springer Nature
- p. 108-118
Case-Specific Priors-Guided Multimodal Fusion for Prognosis Prediction in Head and Neck Cancer
- 24 September 2026
- Published by Springer Nature
- p. 108-118
Case-Specific Priors-Guided Multimodal Fusion for Prognosis Prediction in Head and Neck Cancer
- Open Access
- 3 July 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 332
Language-guided medical image segmentation with target-informed multi-level contrastive alignments
- 3 July 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 332
Open AccessLanguage-guided medical image segmentation with target-informed multi-level contrastive alignments
- Open Access
- 28 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Artificial Intelligence
- Vol. PP (10) , 1-11
SMPL-GPTexture: Scalable, Training-Free SMPL Texture Synthesis with World Knowledge Transfer from GPT via Geometry-Aware Projection
Texturing 3D human avatars from natural-language prompts remains challenging because generated UV texture maps must be both high-quality and semantically consistent with the prompt. Prior work typically re-trains generative adversarial or diffusion models on curated datasets, which constrain generalization to clothing, stylistic, and cultural variations present in those datasets. To address these limitations, we present SMPL-GPTexture, a training-free pipeline that leverages the rich world knowledge of a pre-trained GPT model to synthesize SMPL human textures. Given a tailored natural-language prompt, GPT- 4o generates geometry-consistent front/back views; we fit SMPL to each view, and invert-rasterize colours into canonical UV space with a geometry-aware view-quality weight, and close remaining gaps with diffusion-based inpainting. On a 550-prompt benchmark, SMPL-GPTexture achieves +17.6% CLIP similarity and +22.4% BLIP improvement over state-of-the-art text-to-texture methods while reducing visible seam artifacts. It generalizes to diverse scenarios such as fantasy avatars, stylized body art, and specialized uniforms without domain-specific finetuning. This facilitates the generation of high-quality textures that surpass current text-to-texture pipelines for fashion prototyping, AR telepresence and digital asset generation. We open-source a UV texture map dataset that covers 23 artistic styles, 49 professions, 19 ethnicities, and 67 clothing descriptors, and a set of easily adaptable prompt templates that can be repurposed to generate any desired texture, fostering research on prompt-driven avatar appearance. The code, sample dataset and prompts will be available at https://github.com/DavidTu21/SMPL-GPTexture.
- 28 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Artificial Intelligence
- Vol. PP (10) , 1-11
Open AccessSMPL-GPTexture: Scalable, Training-Free SMPL Texture Synthesis with World Knowledge Transfer from GPT via Geometry-Aware Projection
Texturing 3D human avatars from natural-language prompts remains challenging because generated UV texture maps must be both high-quality and semantically consistent with the prompt. Prior work typically re-trains generative adversarial or diffusion models on curated datasets, which constrain generalization to clothing, stylistic, and cultural variations present in those datasets. To address these limitations, we present SMPL-GPTexture, a training-free pipeline that leverages the rich world knowledge of a pre-trained GPT model to synthesize SMPL human textures. Given a tailored natural-language prompt, GPT- 4o generates geometry-consistent front/back views; we fit SMPL to each view, and invert-rasterize colours into canonical UV space with a geometry-aware view-quality weight, and close remaining gaps with diffusion-based inpainting. On a 550-prompt benchmark, SMPL-GPTexture achieves +17.6% CLIP similarity and +22.4% BLIP improvement over state-of-the-art text-to-texture methods while reducing visible seam artifacts. It generalizes to diverse scenarios such as fantasy avatars, stylized body art, and specialized uniforms without domain-specific finetuning. This facilitates the generation of high-quality textures that surpass current text-to-texture pipelines for fashion prototyping, AR telepresence and digital asset generation. We open-source a UV texture map dataset that covers 23 artistic styles, 49 professions, 19 ethnicities, and 67 clothing descriptors, and a set of easily adaptable prompt templates that can be repurposed to generate any desired texture, fostering research on prompt-driven avatar appearance. The code, sample dataset and prompts will be available at https://github.com/DavidTu21/SMPL-GPTexture.
- 27 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. PP (15209210) , 1-11
Dynamic Traceback Learning for Medical Report Generation
Automated medical report generation has demonstrated the potential to significantly reduce the workload associated with time-consuming medical reporting. Recent generative representation learning methods have shown promise in integrating vision and language modalities for medical report generation. However, when trained end-to-end and applied directly to medical image-to-text generation, they face two significant challenges: i) difficulty in accurately capturing subtle yet crucial pathological details, and ii) reliance on both visual and textual inputs during inference, leading to performance degradation in zero-shot inference when only images are available. To address these challenges, this study proposes a novel multimodal dynamic traceback learning framework (DTrace)1. Specifically, we introduce a traceback mechanism to supervise the semantic validity of generated content and a dynamic learning strategy to adapt to various proportions of image and text input, enabling text generation without strong reliance on the input from both modalities during inference. The learning of cross-modal knowledge is enhanced by supervising the model to recover masked semantic information from a complementary counterpart. Extensive experiments conducted on two benchmark datasets, IU-Xray and MIMIC-CXR, demonstrate that the proposed DTrace framework outperforms state-of-the-art methods for medical report generation.
- 27 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. PP (15209210) , 1-11
Dynamic Traceback Learning for Medical Report Generation
Automated medical report generation has demonstrated the potential to significantly reduce the workload associated with time-consuming medical reporting. Recent generative representation learning methods have shown promise in integrating vision and language modalities for medical report generation. However, when trained end-to-end and applied directly to medical image-to-text generation, they face two significant challenges: i) difficulty in accurately capturing subtle yet crucial pathological details, and ii) reliance on both visual and textual inputs during inference, leading to performance degradation in zero-shot inference when only images are available. To address these challenges, this study proposes a novel multimodal dynamic traceback learning framework (DTrace)1. Specifically, we introduce a traceback mechanism to supervise the semantic validity of generated content and a dynamic learning strategy to adapt to various proportions of image and text input, enabling text generation without strong reliance on the input from both modalities during inference. The learning of cross-modal knowledge is enhanced by supervising the model to recover masked semantic information from a complementary counterpart. Extensive experiments conducted on two benchmark datasets, IU-Xray and MIMIC-CXR, demonstrate that the proposed DTrace framework outperforms state-of-the-art methods for medical report generation.
- Open Access
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 13-17
A Causal Approach to Mitigate Modality Preference Bias in Medical Visual Question Answering
Medical Visual Question Answering (MedVQA) is crucial for enhancing the efficiency of clinical diagnosis by providing accurate and timely responses to clinicians' inquiries regarding medical images. Existing MedVQA models suffered from modality preference bias, where predictions are heavily dominated by one modality while overlooking the other (in MedVQA, usually questions dominate the answer but images are overlooked), thereby failing to learn multimodal knowledge. To overcome the modality preference bias, we proposed a Medical CounterFactual VQA (MedCFVQA) model, which trains with bias and leverages causal graphs to eliminate the modality preference bias during inference. Existing MedVQA datasets exhibit substantial prior dependencies between questions and answers, which results in acceptable performance even if the model significantly suffers from the modality preference bias. To address this issue, we reconstructed new datasets by leveraging existing MedVQA datasets and Changed their P3rior dependencies (CP) between questions and their answers in the training and test set. Extensive experiments demonstrate that MedCFVQA significantly outperforms its non-causal counterpart on both SLAKE, RadVQA and SLAKE-CP, RadVQA-CP datasets.
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 13-17
Open AccessA Causal Approach to Mitigate Modality Preference Bias in Medical Visual Question Answering
Medical Visual Question Answering (MedVQA) is crucial for enhancing the efficiency of clinical diagnosis by providing accurate and timely responses to clinicians' inquiries regarding medical images. Existing MedVQA models suffered from modality preference bias, where predictions are heavily dominated by one modality while overlooking the other (in MedVQA, usually questions dominate the answer but images are overlooked), thereby failing to learn multimodal knowledge. To overcome the modality preference bias, we proposed a Medical CounterFactual VQA (MedCFVQA) model, which trains with bias and leverages causal graphs to eliminate the modality preference bias during inference. Existing MedVQA datasets exhibit substantial prior dependencies between questions and answers, which results in acceptable performance even if the model significantly suffers from the modality preference bias. To address this issue, we reconstructed new datasets by leveraging existing MedVQA datasets and Changed their P3rior dependencies (CP) between questions and their answers in the training and test set. Extensive experiments demonstrate that MedCFVQA significantly outperforms its non-causal counterpart on both SLAKE, RadVQA and SLAKE-CP, RadVQA-CP datasets.
- 6 October 2024
- Published by Springer Nature
- p. 242-252
Enabling Text-Free Inference in Language-Guided Segmentation of Chest X-Rays via Self-guidance
- 6 October 2024
- Published by Springer Nature
- p. 242-252
Enabling Text-Free Inference in Language-Guided Segmentation of Chest X-Rays via Self-guidance