Zobrazeno 1 - 10
of 23
pro vyhledávání: '"Wenyuan Zeng"'
Publikováno v:
IEEE transactions on neural networks and learning systems.
With the goal of learning to localize specific object semantics using the low-cost image-level annotation, weakly supervised object localization (WSOL) has been receiving increasing attention in recent years. Although existing literatures have studie
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::96e0ca105f99e8b5ec5d8bc64d32983c
https://pubmed.ncbi.nlm.nih.gov/36129872
https://pubmed.ncbi.nlm.nih.gov/36129872
Autor:
Chris Zhang, Runsheng Guo, Wenyuan Zeng, Yuwen Xiong, Binbin Dai, Rui Hu, Mengye Ren, Raquel Urtasun
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031198410
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2b059481519c631bd044ab662a224e5f
https://doi.org/10.1007/978-3-031-19842-7_16
https://doi.org/10.1007/978-3-031-19842-7_16
Publikováno v:
2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::59058454df813c704d3dab13761fcd25
https://doi.org/10.1109/iros51168.2021.9636691
https://doi.org/10.1109/iros51168.2021.9636691
Publikováno v:
ICRA
An intelligent agent operating in the real-world must balance achieving its goal with maintaining the safety and comfort of not only itself, but also other participants within the surrounding scene. This requires jointly reasoning about the behavior
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::468c8c2c8f626448212b7ffb8a7f8656
https://doi.org/10.1109/icra48506.2021.9561123
https://doi.org/10.1109/icra48506.2021.9561123
Publikováno v:
ICRA
In this paper, we propose an end-to-end self-driving network featuring a sparse attention module that learns to automatically attend to important regions of the input. The attention module specifically targets motion planning, whereas prior literatur
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3d136c608afac8c2197a4e8c7a79d00f
https://doi.org/10.1109/icra48506.2021.9561904
https://doi.org/10.1109/icra48506.2021.9561904
Forecasting the future behaviors of dynamic actors is an important task in many robotics applications such as self-driving. It is extremely challenging as actors have latent intentions and their trajectories are governed by complex interactions betwe
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1f4e95ef736368bc005fd70bb6ad3807
Publikováno v:
IEEE transactions on pattern analysis and machine intelligence. 44(6)
In recent years, weakly supervised object detection has attracted great attention in the computer vision community. Although numerous deep learning-based approaches have been proposed in the past few years, such an ill-posed problem is still challeng
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::fe92f520f881c301024b8072a87b4bd2
https://pubmed.ncbi.nlm.nih.gov/33351751
https://pubmed.ncbi.nlm.nih.gov/33351751
Autor:
Ioan Andrei Barsan, Raquel Urtasun, Jashan Shewakramani, Julieta Martinez, Ting Wei Liu, Wenyuan Zeng
Publikováno v:
CVPR
Compressing large neural networks is an important step for their deployment in resource-constrained computational platforms. In this context, vector quantization is an appealing framework that expresses multiple parameters using a single code, and ha
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::11f4e7bd7a83ab26cbf3038f2f81f8d8
http://arxiv.org/abs/2010.15703
http://arxiv.org/abs/2010.15703
Publikováno v:
Lecture Notes in Civil Engineering ISBN: 9789811546716
For warships with long superstructure and complex cabin structure, the obvious stress concentration at the superstructure end had generally led to serious fatigue problem.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1e9b69d2751fbbf348b1d3fb8d3478bb
https://doi.org/10.1007/978-981-15-4672-3_34
https://doi.org/10.1007/978-981-15-4672-3_34
Publikováno v:
IROS
In this paper, we tackle the problem of detecting objects in 3D and forecasting their future motion in the context of self-driving. Towards this goal, we design a novel approach that explicitly takes into account the interactions between actors. To c
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7f987fa518c8dcde04812b999fbb613c
http://arxiv.org/abs/2008.05927
http://arxiv.org/abs/2008.05927