Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Trung X. Pham"'
Contrastive learning (CL) is widely known to require many negative samples, 65536 in MoCo for instance, for which the performance of a dictionary-free framework is often inferior because the negative sample size (NSS) is limited by its mini-batch siz
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b6c0f553468d35a3e4e108cb7daaf0b6
Autor:
Bo-Yeon Lee, Keon Jae Lee, Dias Issa, Jae Hee Lee, Mingi Chung, Gwangsu Kim, Chang D. Yoo, Younghoon Jung, Trung X. Pham, Hee Seung Wang
Flexible piezoelectric acoustic sensors (f-PAS) have attracted significant attention as a promising component for voice user interfaces (VUI) in the era of artificial intelligence of things (AIoT). The signal distortion issue of highly sensitive biom
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::92cabaf89e2b7335c6d4ee1cce0c4984
https://doi.org/10.21203/rs.3.rs-799114/v1
https://doi.org/10.21203/rs.3.rs-799114/v1
Publikováno v:
ICASSP
Model agnostic meta-learning (MAML) is a popular state-of-the-art meta-learning algorithm that provides good weight initialization of a model given a variety of learning tasks. The model initialized by provided weight can be fine-tuned to an unseen t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a826089a6b15b673a96922229c80da6a
Publikováno v:
CVPR
This paper considers a network referred to as Modality Shifting Attention Network (MSAN) for Multimodal Video Question Answering (MVQA) task. MSAN decomposes the task into two sub-tasks: (1) localization of temporal moment relevant to the question, a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::547cf1f8a9c43713353e5a831199093d
https://doi.org/10.1109/cvpr42600.2020.01012
https://doi.org/10.1109/cvpr42600.2020.01012
Autor:
Yongwoo Kim, Munchurl Kim, Subeesh Vasu, Jae-Seok Choi, Tong Tong, Jiewen Ran, Rang Meng, Hu Fengshuo, Kehui Nie, Xingguang Zhou, Cao Van Nguyen, Luc Van Gool, Pablo Navarrete Michelini, Wushao Wen, Zhu Dan, Yan Zhao, Zheng Hui, Nikolay Kobyshev, Yukai Shi, Chao Dong, Chen Xing, Etienne de Stoutz, Thang Vu, Eirikur Agustsson, Qinquan Gao, Cheolkon Jung, Mingrui Geng, Xiumei Wang, Tung Minh Luu, Liu Hanwen, Jie Huang, Jinghui Qin, Nimisha Thekke Madam, A. N. Rajagopalan, Yu Qiao, Shuhang Gu, Trung X. Pham, Andrey Ignatov, Pengfei Zhu, Ruicheng Feng, Shixiang Wu, Lirui Deng, Gen Li, Yawei Li, Liang Lin, Praveen Kandula, Radu Timofte, Jie Liu
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783030110208
ECCV Workshops (5)
ECCV Workshops (5)
This paper reviews the first challenge on efficient perceptual image enhancement with the focus on deploying deep learning models on smartphones. The challenge consisted of two tracks. In the first one, participants were solving the classical image s
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::73c9a600b16f07532c7f76b9af32b80f
https://doi.org/10.1007/978-3-030-11021-5_20
https://doi.org/10.1007/978-3-030-11021-5_20
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783030110208
ECCV Workshops (5)
ECCV Workshops (5)
This paper considers a convolutional neural network for image quality enhancement referred to as the fast and efficient quality enhancement (FEQE) that can be trained for either image super-resolution or image enhancement to provide accurate yet visu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::96e96f4a471a871a84bde40cc1212c0f
https://doi.org/10.1007/978-3-030-11021-5_16
https://doi.org/10.1007/978-3-030-11021-5_16
Autor:
Sunghun Kang, Hee Seung Wang, Seong Kwang Hong, Jae Hyun Han, Younghoon Jung, Junyeong Kim, Trung X. Pham, Keon Jae Lee, Hyunsin Park, Chang D. Yoo
Publikováno v:
Advanced Materials. 32:2070259
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::903d7707ce179c87a63f5192b137aa3f
https://doi.org/10.1002/adma.202070259
https://doi.org/10.1002/adma.202070259
Autor:
Seong Kwang Hong, Hee Seung Wang, Trung X. Pham, Sunghun Kang, Jae Hyun Han, Younghoon Jung, Junyeong Kim, Chang D. Yoo, Keon Jae Lee, Hyunsin Park
Publikováno v:
Advanced Materials. 32:1904020
Flexible piezoelectric acoustic sensors have been developed to generate multiple sound signals with high sensitivity, shifting the paradigm of future voice technologies. Speech recognition based on advanced acoustic sensors and optimized machine lear
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::db4bfaa99691950d265bcdacee348135
https://doi.org/10.1002/adma.201904020
https://doi.org/10.1002/adma.201904020