Jiayan Yang — accepted AI-conference papers

2026

ENDOCAVER: HANDLING FOG, BLUR AND GLARE IN ENDOSCOPIC IMAGES VIA JOINT DEBLURRING-SEGMENTATION

Zhuoyu Wu, Wenhui Ou, Pei-Sze Tan, Jiayan Yang, Raphaël C.-W Phan

ICASSP 2026poster

Endoscopic image analysis is vital for colorectal cancer screening, yet real-world conditions often suffer from lens fogging, motion blur, and specular highlights, which severely compromise automated polyp detection. We propose EndoCaver, a lightweight transformer with a unidirectional-guided dual-d…

Cited by 0 Source ↗PDF ↗Scholar ↗

2025

Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models

Hao Cheng, Erjia Xiao, Jiayan Yang, Jiahang Cao, Qiang Zhang, Jize Zhang +3

CVPR 2025poster

Current image generation models can effortlessly produce high-quality, highly realistic images, but this also increases the risk of misuse. In various Text-to-Image or Image-to-Image tasks, attackers can generate a series of images containing inappropriate content by simply editing the language moda…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗