Zobrazeno 1 - 10
of 49
pro vyhledávání: '"Zenilton Kleber Gonçalves do Patrocínio"'
Autor:
Neves, Daniel Eugênio, Batisteli, João Pedro Oliveira, Lopes, Eduardo Felipe, Ishitani, Lucila, Júnior, Zenilton Kleber Gonçalves do Patrocínio
In this work, we propose and evaluate a new reinforcement learning method, COMPact Experience Replay (COMPER), which uses temporal difference learning with predicted target values based on recurrence over sets of similar transitions, and a new approa
Externí odkaz:
http://arxiv.org/abs/2111.06907
Autor:
Guillaume Gravier, Gabriel Barbosa da Fonseca, Zenilton Kleber Gonçalves do Patrocínio, Silvio Jamil Ferzoli Guimarães, Gabriel Sargent, Ronan Sicre
Publikováno v:
Multimedia Tools and Applications
Multimedia Tools and Applications, Springer Verlag, In press, pp.1-27. ⟨10.1007/s11042-020-09692-x⟩
Multimedia Tools and Applications, In press, pp.1-27. ⟨10.1007/s11042-020-09692-x⟩
Multimedia Tools and Applications, Springer Verlag, In press, pp.1-27. ⟨10.1007/s11042-020-09692-x⟩
Multimedia Tools and Applications, In press, pp.1-27. ⟨10.1007/s11042-020-09692-x⟩
International audience; TV archives are growing in size so fast that manually indexing becomes unfeasible. Automatic indexing techniques can be applied to overcome this issue, and this work proposes an unsupervised technique for multimodal person dis
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::929c159bb1f113927f68c066c8e93b55
https://doi.org/10.1007/s11042-020-09692-x
https://doi.org/10.1007/s11042-020-09692-x
Publikováno v:
Pattern Recognition Letters. 133:287-294
A hierarchical image segmentation is a set of image segmentations at different detail levels. However, objects (or even parts of the same object) may appear at different scales due to their size differences or to their distinct distances from the cam
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e7e9d86a57782a6b031982ae8ec68a2b
https://doi.org/10.1016/j.patrec.2020.03.010
https://doi.org/10.1016/j.patrec.2020.03.010
Autor:
Felipe Belém, Alexandre X. Falcão, Silvio Jamil Ferzoli Guimarães, Zenilton Kleber Gonçalves do Patrocínio, Laurent Najman, Sarah Almeida Carneiro, Carolina Stephanie Jerônimo de Almeida
Publikováno v:
Discrete Geometry and Mathematical Morphology (DGMM)
Discrete Geometry and Mathematical Morphology (DGMM), May 2021, Uppsala, Sweden
Lecture Notes in Computer Science ISBN: 9783030766566
DGMM
Discrete Geometry and Mathematical Morphology (DGMM), May 2021, Uppsala, Sweden
Lecture Notes in Computer Science ISBN: 9783030766566
DGMM
Supervoxel segmentation leads to major improvements in video analysis since it generates simpler but meaningful primitives (i.e., supervoxels). Thanks to the flexibility of the Iterative Spanning Forest (ISF) framework and recent strategies introduce
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::edd45e134facf4b3ea29504c9541cf23
https://hal.archives-ouvertes.fr/hal-03171076
https://hal.archives-ouvertes.fr/hal-03171076
Autor:
Felipe Belém, Alexandre X. Falcão, Isabela Borlido Barcelos, Silvio Jamil Ferzoli Guimarães, Zenilton Kleber Gonçalves do Patrocínio, Paulo A. V. Miranda
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783030766566
DGMM
DGMM
Interactive image segmentation aims to partition the image into background and foreground objects by taking into account seeds inserted by users. Nowadays, many methods are capable of generating segmentations with few user interactions, especially re
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2a5cccf794bdb153aaaff0d46e76d074
https://doi.org/10.1007/978-3-030-76657-3_25
https://doi.org/10.1007/978-3-030-76657-3_25
Autor:
Silvio Jamil Ferzoli Guimarães, Victor Hugo Roldão Reis, Zenilton Kleber Gonçalves do Patrocínio
Publikováno v:
IWSSIP
In this paper, we proposed and evaluated the adoption of a capsule network-based (CapsNet-based) model rather than the convolutional neural network-based (CNN-based) models which are predominant in crowd counting tasks. The aim is to join the task of
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::cbe15f4293b1dbf163802d8be813e9fe
https://doi.org/10.1109/iwssip48289.2020.9145163
https://doi.org/10.1109/iwssip48289.2020.9145163
Autor:
Juan R. S. Carvalho, Magali Rezende Gouvêa Meireles, Zenilton Kleber Gonçalves do Patrocínio Júnior, Paulo Eduardo Maciel de Almeida
Publikováno v:
iSys - Brazilian Journal of Information Systems. 10:06-18
Patents are usually organized in classes generated by the offices responsible for patents protection, to create a useful format to the information retrieval process. The complexity of patent taxonomies is a challenge for the automation of patent clas
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4decf3bba3399d902329af7bed3a005f
https://doi.org/10.5753/isys.2017.325
https://doi.org/10.5753/isys.2017.325
Autor:
Zenilton Kleber Gonçalves do Patrocínio, Silvio Jamil Ferzoli Guimarães, Raquel Almeida, Roberto Miranda, Simon Malinowski, Renato Augusto de Souza
Publikováno v:
CIARP 2019-24th Iberoamerican Congress on Pattern Recognition
CIARP 2019-24th Iberoamerican Congress on Pattern Recognition, Oct 2019, La Havane, Cuba. pp.449-457, ⟨10.1007/978-3-030-33904-3_42⟩
Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications ISBN: 9783030339036
CIARP
CIARP 2019-24th Iberoamerican Congress on Pattern Recognition, Oct 2019, La Havane, Cuba. pp.449-457, ⟨10.1007/978-3-030-33904-3_42⟩
Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications ISBN: 9783030339036
CIARP
Time series classification has been widely explored over the last years. Amongst the best approaches for that task, many are based on the Bag-of-Words framework, in which time series are transformed into a histogram of word occurrences. These words r
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::47617d14b9e84224b82bff218de9c223
https://inria.hal.science/hal-02371260
https://inria.hal.science/hal-02371260
Publikováno v:
Anais Estendidos do XXXII Conference on Graphics, Patterns and Images (SIBRAPI Estendido 2019).
A hierarchical image segmentation is a set of image segmentations at different detail levels. However, objects can be located at different scales due to their size differences or to their distinct distances from the camera. In literature, many works
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8a6e14e4d2997d31b10b3d19068bbb3c
https://doi.org/10.5753/sibgrapi.est.2019.8311
https://doi.org/10.5753/sibgrapi.est.2019.8311
Autor:
Felipe A. L. Reis, Zenilton Kleber Gonçalves do Patrocínio, Ewa Kijak, Silvio Jamil Ferzoli Guimarães, Simon Malinowski, Raquel Almeida
Publikováno v:
IJCNN 2019-International Joint Conference on Neural Networks
IJCNN 2019-International Joint Conference on Neural Networks, Jul 2019, Budapest, Hungary. pp.1-8, ⟨10.1109/IJCNN.2019.8851843⟩
IJCNN
IJCNN 2019-International Joint Conference on Neural Networks, Jul 2019, Budapest, Hungary. pp.1-8, ⟨10.1109/IJCNN.2019.8851843⟩
IJCNN
Image segmentation consists in creating partitions within an image into meaningful areas and objects. It can be used in scene understanding and recognition, in fields like biology, medicine, robotics, satellite imaging, amongst others. In this work w
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::014269cc6477c7e3748f46a20e07a642
https://hal.inria.fr/hal-02370834/document
https://hal.inria.fr/hal-02370834/document