no code implementations • 1 Apr 2024 • Bo Zou, Shaofeng Wang, Hao liu, Gaoyue Sun, Yajie Wang, FeiFei Zuo, Chengbin Quan, Youjian Zhao
Teeth localization, segmentation, and labeling in 2D images have great potential in modern dentistry to enhance dental diagnostics, treatment planning, and population-based studies on oral health.
no code implementations • 1 Apr 2024 • Bo Zou, Chao Yang, Yu Qiao, Chengbin Quan, Youjian Zhao
LLaMA-Excitor ensures a self-adaptive allocation of additional attention to input instructions, thus effectively preserving LLMs' pre-trained knowledge when fine-tuning LLMs on low-quality instruction-following datasets.
no code implementations • 1 Apr 2024 • Bo Zou, Chao Yang, Yu Qiao, Chengbin Quan, Youjian Zhao
In this paper, we are inspired by the human recognition and learning pattern and propose VideoDistill, a framework with language-aware (i. e., goal-driven) behavior in both vision perception and answer generation process.
no code implementations • 22 May 2023 • Jiazhi Guan, Tianshu Hu, Hang Zhou, Zhizhi Guo, Lirui Deng, Chengbin Quan, Errui Ding, Youjian Zhao
Unlike authentic images, where the hidden messages can be extracted with precision, manipulating the facial attributes through deepfake techniques can disrupt the decoding process.
no code implementations • 6 Jul 2022 • Jiazhi Guan, Hang Zhou, Zhibin Hong, Errui Ding, Jingdong Wang, Chengbin Quan, Youjian Zhao
Recent advances in face forgery techniques produce nearly visually untraceable deepfake videos, which could be leveraged with malicious intentions.
1 code implementation • 6 Jun 2022 • Yunsheng Ni, Depu Meng, Changqian Yu, Chengbin Quan, Dongchun Ren, Youjian Zhao
Specifically, we first capture the different representations with different augmentations, then regularize the cosine distance of the representations to enhance the consistency.