Výsledky vyhledávání - "Lee, Won-Hee"

Report

MAD: Multi-Alignment MEG-to-Text Decoding

Autor: Yang, Yiqian, Jo, Hyejeong, Duan, Yiqun, Zhang, Qiang, Zhou, Jinni, Lee, Won Hee, Xu, Renjing, Xiong, Hui

Deciphering language from brain activity is a crucial task in brain-computer interface (BCI) research. Non-invasive cerebral signaling techniques including electroencephalography (EEG) and magnetoencephalography (MEG) are becoming increasingly popula

Externí odkaz: http://arxiv.org/abs/2406.01512

Zobrazit plný text záznamu

Report

Are EEG-to-Text Models Working?

Autor: Jo, Hyejeong, Yang, Yiqian, Han, Juhyeok, Duan, Yiqun, Xiong, Hui, Lee, Won Hee

This work critically analyzes existing models for open-vocabulary EEG-to-Text translation. We identify a crucial limitation: previous studies often employed implicit teacher-forcing during evaluation, artificially inflating performance metrics. Addit

Externí odkaz: http://arxiv.org/abs/2405.06459

Zobrazit plný text záznamu

Report

NeuSpeech: Decode Neural signal as Speech

Autor: Yang, Yiqian, Duan, Yiqun, Zhang, Qiang, Jo, Hyejeong, Zhou, Jinni, Lee, Won Hee, Xu, Renjing, Xiong, Hui

Decoding language from brain dynamics is an important open direction in the realm of brain-computer interface (BCI), especially considering the rapid growth of large language models. Compared to invasive-based signals which require electrode implanta

Externí odkaz: http://arxiv.org/abs/2403.01748

Zobrazit plný text záznamu

Report

Neural Video Compression with Temporal Layer-Adaptive Hierarchical B-frame Coding

Autor: Kim, Yeongwoong, Bahk, Suyong, Kim, Seungeon, Lee, Won Hee, Oh, Dokwan, Kim, Hui Yong

Neural video compression (NVC) is a rapidly evolving video coding research area, with some models achieving superior coding efficiency compared to the latest video coding standard Versatile Video Coding (VVC). In conventional video coding standards,

Externí odkaz: http://arxiv.org/abs/2308.15791

Zobrazit plný text záznamu