no code implementations • 5 May 2024 • Seojin Kim, Jaehyun Nam, Sihyun Yu, Younghoon Shin, Jinwoo Shin
Compared to the conventional textual inversion method in the image domain using a single-level token embedding, our multi-level token embeddings allow the model to effectively learn the underlying low-shot molecule distribution.
no code implementations • 15 Dec 2023 • Sunghwa Lee, Younghoon Shin, Myungjong Kim, Jiwon Seo
This study demonstrated IR-UWB radar-based contactless SSR using four types of speech stimuli (vowels, consonants, words, and phrases).
no code implementations • ICCV 2023 • Geon Lee, SangHoon Lee, Dohyung Kim, Younghoon Shin, Yongsang Yoon, Bumsub Ham
To address the camera bias problem, we also introduce a camera-diversity (CD) loss encouraging person images of the same pseudo label, but captured across various cameras, to involve more for discriminative feature learning, providing person representations robust to inter-camera variations.
Domain Adaptation Domain Adaptive Person Re-Identification +4
no code implementations • 5 Sep 2022 • Sunghwa Lee, Younghoon Shin
Because an impulse radio ultra-wideband (IR-UWB) radar can detect targets with high accuracy, work through occluding materials, and operate without contact, it is an attractive hardware solution for building silent speech interfaces, which are non-audio-based speech communication devices.