Lin Zhao

I am a first-year Ph.D. student in College of Engineering, Northeastern University, supervised by Prof. Yanzhi Wang and Prof. Xue Lin. My research interests include deep learning algorithm, multi-modal AI and generative model. I got my M.S. and B.S. degrees from Nankai University, supervised by Zhenglu Yang.

Publications

	FlashEval: Towards Fast and Accurate Evaluation of Text-to-image Diffusion Generative Models Lin Zhao, Tianchen Zhao, Zinan Lin, Xuefei Ning, Guohao Dai, Huazhong Yang, Yu Wang Computer Vision and Pattern Recognition (CVPR), 2024 We propose FlashEval, which can identify a representative subset to speed up the evaluation of text-to-image Diffusion models (10x). [project] [code] [paper]
	THInImg: Cross-modal Steganography for Presenting Talking Heads in Images Lin Zhao, Hongxuan Li, Xuefei Ning, Xinru Jiang Winter Conference on Applications of Computer Vision (WACV), 2024 We propose THInImg, which can present up to 80 seconds of high quality talking-head video (including audio) in an identity image with 160×160 resolution. [paper]
	Deep Symmetric Network for Underexposed Image Enhancement with Recurrent Attentional Learning Lin Zhao, Shaoping Lu, Tao Chen, Zhenglu Yang, Ariel Shamir International Conference on Computer Vision (ICCV), 2021 We propose an invertible framework to solve both underexposed image enhancement and low-light image enhancement problems in a unified structure. [project] [code] [paper]