Výsledky vyhledávání - "Mai, Weijian"

Report

Neuro-3D: Towards 3D Visual Decoding from EEG Signals

Autor: Guo, Zhanqiang, Wu, Jiamin, Song, Yonghao, Bu, Jiahui, Mai, Weijian, Zheng, Qihao, Ouyang, Wanli, Song, Chunfeng

Human's perception of the visual world is shaped by the stereo processing of 3D information. Understanding how the brain perceives and processes 3D visual stimuli in the real world has been a longstanding endeavor in neuroscience. Towards this goal,

Externí odkaz: http://arxiv.org/abs/2411.12248

Zobrazit plný text záznamu

Report

EMOdiffhead: Continuously Emotional Control in Talking Head Generation via Diffusion

Autor: Zhang, Jian, Mai, Weijian, Zhang, Zhijun

The task of audio-driven portrait animation involves generating a talking head video using an identity image and an audio track of speech. While many existing approaches focus on lip synchronization and video quality, few tackle the challenge of gene

Externí odkaz: http://arxiv.org/abs/2409.07255

Zobrazit plný text záznamu

Report

Brain-Conditional Multimodal Synthesis: A Survey and Taxonomy

Autor: Mai, Weijian, Zhang, Jian, Fang, Pengfei, Zhang, Zhijun

In the era of Artificial Intelligence Generated Content (AIGC), conditional multimodal synthesis technologies (e.g., text-to-image, text-to-video, text-to-audio, etc) are gradually reshaping the natural content in the real world. The key to multimoda

Externí odkaz: http://arxiv.org/abs/2401.00430

Zobrazit plný text záznamu

Report

UniBrain: Unify Image Reconstruction and Captioning All in One Diffusion Model from Human Brain Activity

Autor: Mai, Weijian, Zhang, Zhijun

Image reconstruction and captioning from brain activity evoked by visual stimuli allow researchers to further understand the connection between the human brain and the visual perception system. While deep generative models have recently been employed

Externí odkaz: http://arxiv.org/abs/2308.07428

Zobrazit plný text záznamu