Zobrazeno 1 - 10
of 615
pro vyhledávání: '"Miao, Duoqian"'
Autor:
Gong, Zixuan, Bao, Guangyin, Zhang, Qi, Wan, Zhongwei, Miao, Duoqian, Wang, Shoujin, Zhu, Lei, Wang, Changwei, Xu, Rongtao, Hu, Liang, Liu, Ke, Zhang, Yu
Reconstruction of static visual stimuli from non-invasion brain activity fMRI achieves great success, owning to advanced deep learning models such as CLIP and Stable Diffusion. However, the research on fMRI-to-video reconstruction remains limited sin
Externí odkaz:
http://arxiv.org/abs/2410.19452
Autor:
Bao, Guangyin, Miao, Duoqian
Exploring the mysteries of the human brain is a long-term research topic in neuroscience. With the help of deep learning, decoding visual information from human brain activity fMRI has achieved promising performance. However, these decoding models re
Externí odkaz:
http://arxiv.org/abs/2409.02044
The twin support vector machine (TWSVM) classifier has attracted increasing attention because of its low computational complexity. However, its performance tends to degrade when samples are affected by noise. The granular-ball fuzzy support vector ma
Externí odkaz:
http://arxiv.org/abs/2408.00699
Autor:
Zhang, Yu, Zhang, Qi, Gong, Zixuan, Shi, Yiwei, Liu, Yepeng, Miao, Duoqian, Liu, Yang, Liu, Ke, Yi, Kun, Fan, Wei, Hu, Liang, Wang, Changwei
Contrastive Language-Image Pretraining (CLIP) has achieved remarkable success, leading to rapid advancements in multimodal studies. However, CLIP faces a notable challenge in terms of inefficient data utilization. It relies on a single contrastive su
Externí odkaz:
http://arxiv.org/abs/2406.01460
Autor:
Bao, Guangyin, Gong, Zixuan, Zhang, Qi, Zhou, Jialei, Fan, Wei, Yi, Kun, Naseem, Usman, Hu, Liang, Miao, Duoqian
Decoding visual information from human brain activity has seen remarkable advancements in recent research. However, due to the significant variability in cortical parcellation and cognition patterns across subjects, current approaches personalized de
Externí odkaz:
http://arxiv.org/abs/2404.13282
Decoding natural visual scenes from brain activity has flourished, with extensive research in single-subject tasks and, however, less in cross-subject tasks. Reconstructing high-quality images in cross-subject tasks is a challenging problem due to pr
Externí odkaz:
http://arxiv.org/abs/2404.12630
Multimodal Sentiment Analysis (MSA) aims to identify speakers' sentiment tendencies in multimodal video content, raising serious concerns about privacy risks associated with multimodal data, such as voiceprints and facial images. Recent distributed c
Externí odkaz:
http://arxiv.org/abs/2404.11938
Early exiting has demonstrated its effectiveness in accelerating the inference of pre-trained language models like BERT by dynamically adjusting the number of layers executed. However, most existing early exiting methods only consider local informati
Externí odkaz:
http://arxiv.org/abs/2402.05948
Autor:
Bao, Guangyin, Zhang, Qi, Miao, Duoqian, Gong, Zixuan, Hu, Liang, Liu, Ke, Liu, Yang, Shi, Chongyang
In real-world scenarios, multimodal federated learning often faces the practical challenge of intricate modality missing, which poses constraints on building federated frameworks and significantly degrades model inference accuracy. Existing solutions
Externí odkaz:
http://arxiv.org/abs/2312.13508
Multimodal content, such as mixing text with images, presents significant challenges to rumor detection in social media. Existing multimodal rumor detection has focused on mixing tokens among spatial and sequential locations for unimodal representati
Externí odkaz:
http://arxiv.org/abs/2312.11023