I am a recent graduate from the University of British Columbia, where I completed a combined major in Computer Science and Statistics with Distinction.
How can we design models that emulate human learning processes? This question has always lingered in my mind, drives my research interests across Generative AI, Multimodal Machine Learning, Spatial Intelligence, and Computer Vision. I am currently seeking opportunities for a PhD program or research assistant position to further my exploration in these fields.
Please feel free to reach out to discuss potential opportunities or research collaborations.
Cross-modal Steganography is the practice of concealing secret signals in publicly available cover signals (distinct from the modality of the secret signals) unobtrusively. While previous approaches primarily concentrated on concealing a relatively small amount of information, we propose THInImg, which manages to hide lengthy audio data (and subsequently decode talking head video) inside an identity image by leveraging the properties of human face, which can be effectively utilized for covert communication, transmission and copyright protection. THInImg consists of two parts: the encoder and decoder. Inside the encoder-decoder pipeline, we introduce a novel architecture that substantially increase the capacity of hiding audio in images. Moreover, our framework can be extended to iteratively hide multiple audio clips into an identity image, offering multiple levels of control over permissions. We conduct extensive experiments to prove the effectiveness of our method, demonstrating that THInImg can present up to 80 seconds of high quality talking-head video (including audio) in an identity image with 160x160 resolution.
@inproceedings{Zhao_2024_WACV,author={Zhao, Lin and Li, Hongxuan and Ning, Xuefei and Jiang, Xinru},title={THInImg: Cross-Modal Steganography for Presenting Talking Heads in Images},booktitle={Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)},month=jan,year={2024},pages={5553-5562},}
