Zobrazeno 1 - 10
of 134
pro vyhledávání: '"Wee-Sun Lee"'
Publikováno v:
AAAI
We address the problem of Visual Relationship Detection (VRD) which aims to describe the relationships between pairs of objects in the form of triplets of (subject, predicate, object). We observe that given a pair of bounding box proposals, objects o
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::83418555f3dde0296ff2227f4def9180
https://doi.org/10.1609/aaai.v34i07.6702
https://doi.org/10.1609/aaai.v34i07.6702
Publikováno v:
CIKM
A Graph Convolutional Network (GCN) stacks several layers and in each layer performs a PROPagation operation~(PROP) and a TRANsformation operation~(TRAN) for learning node representations over graph-structured data. Though powerful, GCNs tend to suff
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b3a1e2f168a1b2d2d8d96a0cdf68b589
https://doi.org/10.1145/3459637.3482488
https://doi.org/10.1145/3459637.3482488
Publikováno v:
ACM Multimedia
We propose AI-Lyricist: a system to generate novel yet meaningful lyrics given a required vocabulary and a MIDI file as inputs. This task involves multiple challenges, including automatically identifying the melody and extracting a syllable template
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::abed4c76148616f03d320104b4dd39f6
https://doi.org/10.1145/3474085.3475502
https://doi.org/10.1145/3474085.3475502
Autor:
Wee Sun Lee, Muhammad Rizki Maulana
Publikováno v:
Machine Learning and Knowledge Discovery in Databases. Research Track ISBN: 9783030864859
ECML/PKDD (1)
ECML/PKDD (1)
Ensemble and auxiliary tasks are both well known to improve the performance of machine learning models when data is limited. However, the interaction between these two methods is not well studied, particularly in the context of deep reinforcement lea
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::dd46789a6734842350ab3cb087fda723
https://doi.org/10.1007/978-3-030-86486-6_8
https://doi.org/10.1007/978-3-030-86486-6_8
Publikováno v:
arXiv
This paper introduces the Differentiable Algorithm Network (DAN), a composable architecture for robot learning systems. A DAN is composed of neural network modules, each encoding a differentiable robot algorithm and an associated model; and it is tra
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::216ad766c3f6950aa720b7d00fe48c47
https://hdl.handle.net/1721.1/132313
https://hdl.handle.net/1721.1/132313
Publikováno v:
Springer Proceedings in Advanced Robotics ISBN: 9783030440503
WAFR
WAFR
Robot understanding of human intentions is essential for fluid human-robot interaction. Intentions, however, cannot be directly observed and must be inferred from behaviors. We learn a model of adaptive human behavior conditioned on the intention as
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::afbb640933aab31ac0aadd380428dfc4
https://doi.org/10.1007/978-3-030-44051-0_53
https://doi.org/10.1007/978-3-030-44051-0_53
Publikováno v:
Springer Proceedings in Advanced Robotics ISBN: 9783030430887
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::af7dd8ae2bb2027eb0953626124f73ce
https://doi.org/10.1007/978-3-030-43089-4_16
https://doi.org/10.1007/978-3-030-43089-4_16
Publikováno v:
IEEE Robotics and Automation Letters. 3:3418-3425
This letter presents a planning system for autonomous driving among many pedestrians. A key ingredient of our approach is Pedestrian Optimal Reciprocal Collision Avoidance, a pedestrian motion prediction model that accounts for both a pedestrian's gl
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6271cfa6713a7daf3205451186cde49a
https://doi.org/10.1109/lra.2018.2852793
https://doi.org/10.1109/lra.2018.2852793
Publikováno v:
The International Journal of Robotics Research. 38:162-181
The partially observable Markov decision process (POMDP) provides a principled general framework for robot planning under uncertainty. Leveraging the idea of Monte Carlo sampling, recent POMDP planning algorithms have scaled up to various challenging
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a50ab47c8147476bac2965315f6d9190
https://doi.org/10.1177/0278364918780322
https://doi.org/10.1177/0278364918780322
Publikováno v:
Journal of Artificial Intelligence Research. 58:231-266
The partially observable Markov decision process (POMDP) provides a principled general framework for planning under uncertainty, but solving POMDPs optimally is computationally intractable, due to the "curse of dimensionality" and the "curse of histo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0374dfccf3521ebd3e3572fca6b10fcf
https://doi.org/10.1613/jair.5328
https://doi.org/10.1613/jair.5328