Zobrazeno 1 - 10
of 942
pro vyhledávání: '"G. HAUPTMANN"'
Publikováno v:
Synthetic Data for Artificial Intelligence and Machine Learning: Tools, Techniques, and Applications.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::56e219f3a29dbfbcb020a8fec5c2ec25
https://doi.org/10.1117/12.2664030
https://doi.org/10.1117/12.2664030
Publikováno v:
Neurocomputing. 486:215-224
Deep hashing has been widely used for large-scale cross-modal retrieval benefited from the low storage cost and fast search speed. However, most existing deep supervised methods only preserve the instance-pairwise relationship supervised by the seman
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2fae631b4b22e1eb7a0f64221602eed0
https://doi.org/10.1016/j.neucom.2021.11.035
https://doi.org/10.1016/j.neucom.2021.11.035
Publikováno v:
IEEE Transactions on Multimedia. 22:775-785
Image–sentence matching is a challenging task for the heterogeneity-gap between different modalities. Ranking-based methods have achieved excellent performance in this task in past decades. Given an image query, these methods typically assume that
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::17f8c144b0242d650ceb2addafad70ca
https://doi.org/10.1109/tmm.2019.2931352
https://doi.org/10.1109/tmm.2019.2931352
Autor:
Wenhe Liu, Dinh Phung, Xiaoqin Zhang, Alexander G. Hauptmann, Ling Chen, Yi Yang, Xiaojun Chang
Publikováno v:
ACM Transactions on Intelligent Systems and Technology. 11:1-15
The effective training of supervised Person Re-identification (Re-ID) models requires sufficient pairwise labeled data. However, when there is limited annotation resource, it is difficult to collect pairwise labeled data. We consider a challenging an
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::95f7adc7a267b0ef9cb9c36bbad7bc9c
https://doi.org/10.1145/3372121
https://doi.org/10.1145/3372121
Publikováno v:
IEEE Transactions on Industrial Informatics. 16:87-96
Fault diagnosis and remaining useful life (RUL) prediction are always two major issues in modern industrial systems, which are usually regarded as two separated tasks to make the problem easier but ignore the fact that there are certain information o
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::762800ecab4c1ac93647c058aa34b971
https://doi.org/10.1109/tii.2019.2915536
https://doi.org/10.1109/tii.2019.2915536
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031197710
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b17f5ce19c14d6ed6c734e0e79e5dc39
https://doi.org/10.1007/978-3-031-19772-7_7
https://doi.org/10.1007/978-3-031-19772-7_7
Publikováno v:
2022 IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::de409623c148079eb0dee43f8b89af67
https://doi.org/10.1109/wacvw54805.2022.00021
https://doi.org/10.1109/wacvw54805.2022.00021
Unsupervised domain adaptation (UDA) makes predictions for the target domain data while manual annotations are only available in the source domain. Previous methods minimize the domain discrepancy neglecting the class information, which may lead to m
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0a7e866bd3b1d08b14656fae082dc14d
https://hdl.handle.net/10453/167896
https://hdl.handle.net/10453/167896
Autor:
João Paulo Costeira, Alexander G. Hauptmann, Ricardo Sousa, Rafael Ferreira, João Magalhães, Pedro Azevedo, Pedro Moreira Costa, Carlos Santiago, Pedro M. Ferreira, David Semedo, Alexander I. Rudnicky
Publikováno v:
MuCAI @ ACM Multimedia
Most of the interaction between large organizations and their users will be mediated by AI agents in the near future. This perception is becoming undisputed as online shopping dominates entire market segments, and the new "digitally-native" generatio
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::15d73514d567ae3a2247762e5eb5091f
https://doi.org/10.1145/3475959.3485395
https://doi.org/10.1145/3475959.3485395
Publikováno v:
ACM Multimedia
The second edition of the International Workshop on Multimodal Conversational AI puts forward a diverse set of contributions that aim to brainstorm this new field. Conversational agents are now becoming a commodity as this technology is being applied
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2dafead395c20b2fce8119a34839cbac
https://doi.org/10.1145/3474085.3478580
https://doi.org/10.1145/3474085.3478580