Zobrazeno 1 - 10
of 23
pro vyhledávání: '"Jonatas Wehrmann"'
Publikováno v:
2022 International Joint Conference on Neural Networks (IJCNN).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::03dc5081460e8e15a6f6f18357e8b66b
https://doi.org/10.1109/ijcnn55064.2022.9892610
https://doi.org/10.1109/ijcnn55064.2022.9892610
In this paper, we propose MAGICSTYLEGAN and MAGICSTYLEGAN-ADA - both incarnations of the state-of-the-art models StyleGan2 and StyleGan2 ADA - to experiment with their capacity of transfer learning into a rather different domain: creating new illustr
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::840e2abd799bc244f02df12fde3278a6
http://arxiv.org/abs/2205.14442
http://arxiv.org/abs/2205.14442
Publikováno v:
AAAI
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::29fa82bbb79fb35277b0a306fae64c1c
https://doi.org/10.1609/aaai.v34i07.6915
https://doi.org/10.1609/aaai.v34i07.6915
Autor:
Jonatas Wehrmann, Rodrigo C. Barros
Publikováno v:
Anais do XXXIV Concurso de Teses e Dissertações da SBC (CTD-SBC 2021).
We propose a framework for training language-invariant cross-modal retrieval models. We introduce four novel text encoding approaches, as well as a character-based word-embedding approach, allowing the model to project similar words across languages
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::11dd33cde278f4f134a90db1f1ee7e5d
https://doi.org/10.5753/ctd.2021.15751
https://doi.org/10.5753/ctd.2021.15751
Publikováno v:
IJCNN
Recent research advances in Computer Vision and Natural Language Processing have introduced novel tasks that are paving the way for solving AI-complete problems. One of those tasks is called Visual Question Answering (VQA). A VQA system must take an
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9f5a208733de7a64be7743cc934849a8
https://doi.org/10.1109/ijcnn48605.2020.9206679
https://doi.org/10.1109/ijcnn48605.2020.9206679
Publikováno v:
IJCNN
Text-to-image synthesis is the task of generating images from text descriptions. Image generation, by itself, is a challenging task. When we combine image generation and text, we bring complexity to a new level: we need to combine data from two diffe
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4efc780d731f253b6bd80f0238d00370
http://arxiv.org/abs/2004.11437
http://arxiv.org/abs/2004.11437
Autor:
Jonatas Wehrmann, Rodrigo C. Barros
Publikováno v:
Applied Soft Computing. 61:973-982
The task of labeling movies according to their corresponding genre is a challenging classification problem, having in mind that genre is an immaterial feature that cannot be directly pinpointed in any of the movie frames. Hence, off-the-shelf image c
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ca86ff91461fbc30623000519df6acf5
https://doi.org/10.1016/j.asoc.2017.08.029
https://doi.org/10.1016/j.asoc.2017.08.029
Publikováno v:
ICCV
This paper proposes a framework for training language-invariant cross-modal retrieval models. We also introduce a novel character-based word-embedding approach, allowing the model to project similar words across languages into the same word-embedding
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a6208651397da9d8e00cda5f37428b4a
https://doi.org/10.1109/iccv.2019.00590
https://doi.org/10.1109/iccv.2019.00590
Publikováno v:
IJCNN
Current state-of-the-art approaches for Natural Language Processing tasks such as text classification are either based on Recurrent or Convolutional Neural Networks. Notwithstanding, those approaches often require a long time to train, or large amoun
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4c7a282c492ff401d02d989987675e21
https://doi.org/10.1109/ijcnn.2019.8851837
https://doi.org/10.1109/ijcnn.2019.8851837