Zobrazeno 1 - 10
of 101
pro vyhledávání: '"Li (Erran) Li"'
Publikováno v:
ICASSP
Spoken language understanding (SLU) is the task of inferring the semantics of spoken utterances. Traditionally, this has been achieved with a cascading combination of Automatic Speech Recognition (ASR) and Natural Language Understanding (NLU) modules
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::18fbec36318820f020b03ffc55c48c5c
https://doi.org/10.1109/icassp39728.2021.9414313
https://doi.org/10.1109/icassp39728.2021.9414313
Publikováno v:
CVPR
Vehicle detection with visual sensors like lidar and camera is one of the critical functions enabling autonomous driving. While they generate fine-grained point clouds or high-resolution images with rich information in good weather conditions, they f
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ccfa81e6441d331b0d671dce2545883d
https://doi.org/10.1109/cvpr46437.2021.00051
https://doi.org/10.1109/cvpr46437.2021.00051
Publikováno v:
CVPR
Monocular 3D prediction is one of the fundamental problems in 3D vision. Recent deep learning-based approaches have brought us exciting progress on this problem. However, existing approaches have predominantly focused on end-to-end depth and normal p
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::677a99e7e8d41d087763a20f49a71d1a
https://doi.org/10.1109/cvpr46437.2021.00733
https://doi.org/10.1109/cvpr46437.2021.00733
Publikováno v:
Proceedings of the Third Workshop on Multimodal Artificial Intelligence.
Recent vision-language understanding approaches adopt a multi-modal transformer pre-training and finetuning paradigm. Prior work learns representations of text tokens and visual features with cross-attention mechanisms and captures the alignment sole
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::bf72442609662611eecd478848f85b86
https://doi.org/10.18653/v1/2021.maiworkshop-1.11
https://doi.org/10.18653/v1/2021.maiworkshop-1.11
Publikováno v:
Findings of the Association for Computational Linguistics: EMNLP 2021.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::50e356fd0b8fce8e512cbd0f85363cd7
https://doi.org/10.18653/v1/2021.findings-emnlp.171
https://doi.org/10.18653/v1/2021.findings-emnlp.171
Publikováno v:
2020 IEEE Intelligent Vehicles Symposium (IV).
High automated vehicles rely on the computing system in the car to understand the environment and make driving decisions. Therefore, computing system design is essential for ensuring the driving safety. However, to our knowledge, no clear guideline e
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d51664fd0bb382b83aa08617730c7e5b
https://doi.org/10.1109/iv47402.2020.9304602
https://doi.org/10.1109/iv47402.2020.9304602
Publikováno v:
ICCD
Recently, autonomous driving ignited competitions among car makers and technical corporations. Low-level autonomous vehicles are already commercially available. However, high autonomous vehicles where the vehicle drives by itself without human monito
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9a98d23f808a64f77cc15a50673ad2f6
https://doi.org/10.1109/iccd50377.2020.00031
https://doi.org/10.1109/iccd50377.2020.00031
Autor:
Mark Campbell, Bharath Hariharan, Wei-Lun Chao, Yan Wang, Kilian Q. Weinberger, Yurong You, Li Erran Li, Xiangyu Chen
Publikováno v:
CVPR
In the domain of autonomous driving, deep learning has substantially improved the 3D object detection accuracy for LiDAR and stereo camera data alike. While deep networks are great at generalization, they are also notorious to over-fit to all kinds o
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::40a3c1539e9acacf52b8a9eb91851f0b
http://arxiv.org/abs/2005.08139
http://arxiv.org/abs/2005.08139
Publikováno v:
CVPR
Feature learning for 3D object detection from point clouds is very challenging due to the irregularity of 3D point cloud data. In this paper, we propose Pointformer, a Transformer backbone designed for 3D point clouds to learn features effectively. S
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5be1a9feffca5f064313f674aeb822e6
Publikováno v:
IEEE/ACM Transactions on Networking. 25:2347-2360
Software-defined networking (SDN) promises unprecedentedly flexible network management but it is susceptible to forwarding faults. Such faults originate from data-plane rules with missing faults and priority faults. Yet existing fault detection ignor
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::afb6498234e8a9a6ab0e10e43ab81bb7
https://doi.org/10.1109/tnet.2017.2686443
https://doi.org/10.1109/tnet.2017.2686443