Zobrazeno 1 - 10
of 125
pro vyhledávání: '"Bohyung Han"'
Autor:
Doosoo Chang, Bohyung Han
Publikováno v:
2023 IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1db3d1219b94b4837fc7310c1230535e
https://doi.org/10.1109/wacvw58289.2023.00012
https://doi.org/10.1109/wacvw58289.2023.00012
Publikováno v:
Machine Vision and Applications. 33
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b6327e3e01103632e8ec988c531a6535
https://doi.org/10.1007/s00138-022-01331-9
https://doi.org/10.1007/s00138-022-01331-9
Publikováno v:
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a934f4de17cc0fd7af8783a199a8d4bb
https://doi.org/10.1109/cvpr52688.2022.01776
https://doi.org/10.1109/cvpr52688.2022.01776
Publikováno v:
Journal of KIISE. 48:211-216
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b70467be0a86ade1ce8513fac8915d4d
https://doi.org/10.5626/jok.2021.48.2.211
https://doi.org/10.5626/jok.2021.48.2.211
We tackle catastrophic forgetting problem in the context of class-incremental learning for video recognition, which has not been explored actively despite the popularity of continual learning. Our framework addresses this challenging task by introduc
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::339bed58d5f342bbca08b77162a08232
http://arxiv.org/abs/2203.13611
http://arxiv.org/abs/2203.13611
Publikováno v:
AAAI
Human ratings are currently the most accurate way to assess the quality of an image captioning model, yet most often the only used outcome of an expensive human rating evaluation is a few overall statistics over the evaluation dataset. In this paper,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c44c7bc599ae87a5fa25abaf6a1c7c8c
https://doi.org/10.1609/aaai.v34i03.5655
https://doi.org/10.1609/aaai.v34i03.5655
Publikováno v:
AAAI
Prevailing video frame interpolation techniques rely heavily on optical flow estimation and require additional model complexity and computational cost; it is also susceptible to error propagation in challenging scenarios with large motion and heavy o
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4872767ac7c03047f0981a0b2b8c4159
https://doi.org/10.1609/aaai.v34i07.6693
https://doi.org/10.1609/aaai.v34i07.6693
We propose an information-theoretic bias measurement technique through a causal interpretation of spurious correlation, which is effective to identify the feature-level algorithmic bias by taking advantage of conditional mutual information. Although
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b524e68c776666fbcc57c4a870d18d10
http://arxiv.org/abs/2201.03121
http://arxiv.org/abs/2201.03121
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031200465
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1f28f4ed96dfd4a270f01e77b3ee0614
https://doi.org/10.1007/978-3-031-20047-2_31
https://doi.org/10.1007/978-3-031-20047-2_31
Autor:
Dongwan Kim, Yi-Hsuan Tsai, Yumin Suh, Masoud Faraki, Sparsh Garg, Manmohan Chandraker, Bohyung Han
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031198144
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::18176401f1cd7403cd4a044b15ab3a1f
https://doi.org/10.1007/978-3-031-19815-1_2
https://doi.org/10.1007/978-3-031-19815-1_2