Zobrazeno 1 - 10
of 10
pro vyhledávání: '"Ruihai Wu"'
Publikováno v:
AAAI
Visual relation detection (VRD) aims to describe all interacting objects in an image using subject-predicate-object triplets. Critically, valid relations combinatorially grow in O(C2 R) for C object categories and R relationships. The frequencies of
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::85976d816873bbbeec6942d34d81544d
https://doi.org/10.1609/aaai.v34i07.6913
https://doi.org/10.1609/aaai.v34i07.6913
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031198175
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f98e653a3cddc0db39f04fec63fbbeb9
https://doi.org/10.1007/978-3-031-19818-2_6
https://doi.org/10.1007/978-3-031-19818-2_6
Learning an accurate model of the environment is essential for model-based control tasks. Existing methods in robotic visuomotor control usually learn from data with heavily labelled actions, object entities or locations, which can be demanding in ma
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8851dfcc9d9ed1d7cec4d0cb5ed8188d
Publikováno v:
Computer Vision – ECCV 2020 ISBN: 9783030585440
ECCV (9)
ECCV (9)
Unpaired image-to-image translation is a class of vision problems whose goal is to find the mapping between different image domains using unpaired training data. Cycle-consistency loss is a widely used constraint for such problems. However, due to th
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8c8a21089eb032d06e9d89c9ae19e3f9
https://doi.org/10.1007/978-3-030-58545-7_46
https://doi.org/10.1007/978-3-030-58545-7_46
Publikováno v:
Computer Vision – ECCV 2020 ISBN: 9783030585440
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::bfa8dd064a43e7b3d1f6ddb7619f5e36
https://doi.org/10.1007/978-3-030-58545-7_47
https://doi.org/10.1007/978-3-030-58545-7_47
Publikováno v:
Computer Vision – ECCV 2020 Workshops ISBN: 9783030660956
ECCV Workshops (2)
ECCV Workshops (2)
Despite deep convolutional neural networks’ great success in object classification, recent work has shown that they suffer from a severe generalization performance drop under occlusion conditions that do not appear in the training data. Due to the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0d41f84f4147263ebbedb0c61b1a5e2f
https://doi.org/10.1007/978-3-030-66096-3_31
https://doi.org/10.1007/978-3-030-66096-3_31
Publikováno v:
2010 2nd International Conference on Future Computer and Communication.
In dealing with the problem of premature, the swarm was divided into different types and different update strategy was carried on each swarm. In order to improve the algorithm's convergence precise we also introduced the chaos mutation operations to
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::70cdb7c528ac972eb3654f09e75c7644
https://doi.org/10.1109/icfcc.2010.5497842
https://doi.org/10.1109/icfcc.2010.5497842
Autor:
Jiwen Dong, Ruihai Wu
Publikováno v:
2009 9th International Conference on Electronic Measurement & Instruments.
In dealing with the problem of the quantum-behaved particle swarm optimization algorithm (QPSO) easy falling into the local optima, we proposed the diversity guided immune clonal QPSO. In this algorithm the swarm was defined two states: attraction an
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f622f9c15d5fe53dd0cef4253b3a2c13
https://doi.org/10.1109/icemi.2009.5274249
https://doi.org/10.1109/icemi.2009.5274249
Publikováno v:
2010 2nd International Asia Conference on Informatics in Control, Automation & Robotics (CAR); 2010, p109-112, 4p
Publikováno v:
2010 2nd International Conference on Future Computer & Communication (ICFCC); 2010, pV1-V35, 67p