본문 바로가기

Publication4

Real-Time Machine Learning Competition on Data Streams at the IEEE Big Data 2019, accepted in 2019 IEEE International Conference on Big Data (Big Data) link: https://drive.google.com/file/d/18A-mQX90Ta-SlFQBtTw-oEXPRpYjbaMm/view Real-Time_Machine_Learning_Competition_on_Data_Streams_at_the_IEEE_Big_Data_2019.pdf drive.google.com Author: Dihia Boulegane, Nedeljko Radulovic, Albert Bifet, Ghislain Fievet, Jimin Sohn, Yeonwoo Nam, Seojeong Yu, Dong-Wan Choi Venue: 2019 IEEE International Conference on Big Data (Big Data) Remark: This work is the r.. 2024. 3. 18.
CT-FNO: Exploring Class Token of Fourier Neural Operator for Lightweight Semantic Segmentation (ECCV 2024 under review) link: https://drive.google.com/file/d/1wu5BzZT-qO6tMnltGbuLZ6S-4xvWclxO/view CT_FNO_Exploring_Class_Token_of_Fourier_Neural_Operator_for_Lightweight_Semantic_Segmentation.pdf drive.google.com Author: Jimin Sohn, Jeany Son Venue: ECCV 2024 under review Abstract: Vision Transformer(ViT)s has shown great performance increase in representation learning. However, the self-attention in ViT requires qu.. 2024. 3. 18.
Fashion Image Retrieval with Occlusion (CVPR 2024 Workshop under review) Link: https://drive.google.com/drive/folders/1QpOopO7dlNe1edj5XjTeP6WwWwpMLrY1 CVPR 2024 Workshop(under review) - Google Drive 이 폴더에 파일이 없습니다.이 폴더에 파일을 추가하려면 로그인하세요. drive.google.com Author: Jimin Sohn*, Hae ji Jung*, Zhiwen Yan∗, Vibha Masti∗, Xiang Li, Bhiksha Raj (*: equal contribution) Venue: CVPR 2024 Workshop under review (CVPRW 2024 on Computer Vision for Fashion, Art, and Design) Abstrac.. 2024. 3. 18.
Mitigating the Linguistic Gap with Phonemic Representations for Robust Multilingual Language Understanding (ACL 2024 short under review) arXiv link: https://arxiv.org/abs/2402.14279 Mitigating the Linguistic Gap with Phonemic Representations for Robust Multilingual Language Understanding Approaches to improving multilingual language understanding often require multiple languages during the training phase, rely on complicated training techniques, and -- importantly -- struggle with significant performance gaps between high-resourc.. 2024. 3. 18.