Zobrazeno 1 - 10
of 20
pro vyhledávání: '"Fangshi Wang"'
Autor:
Qian Zhang, Ruiyang Quan, Siqin Qimuge, Rui Wei, Xin Zan, Fangshi Wang, Changchuan Chen, Qi Wei, Xinjun Liu, Fei Qiao
Publikováno v:
2022 IEEE 18th International Conference on Automation Science and Engineering (CASE).
Publikováno v:
Journal of Real-Time Image Processing. 18:1369-1381
Monocular depth estimation is a popular research topic in the field of autonomous driving. Nowadays many models are leading in accuracy but performing poorly in a real-time scenario. To effectively increase the depth estimation efficiency, we propose
Publikováno v:
IEEE Transactions on Image Processing. 29:5584-5595
Convolutional neural networks are built upon simple but useful convolution modules. The traditional convolution has a limitation on feature extraction and object localization due to its fixed scale and geometric structure. Besides, the loss of spatia
Autor:
Qi Wei, Fei Qiao, Dongjiang Li, Fangshi Wang, Wei Yang, Shenghui Liu, Qiwei Long, Xuesong Shi
Publikováno v:
IROS
A robust and efficient Simultaneous Localization and Mapping (SLAM) system is essential for robot autonomy. For visual SLAM algorithms, though the theoretical framework has been well established for most aspects, feature extraction and association is
Autor:
Rosa H. M. Chan, Qiwei Long, Pengpeng Zhao, Qi She, Dongjiang Li, Xuesong Shi, Fangshi Wang, Zhigang Wang, Le Song, Qinbin Tian, Wei Yang, Fei Qiao, Yimin Zhang, Yuxin Tian, Jingwei Song, Baoxing Qin, Chunhao Zhu, Yangquan Guo
Publikováno v:
ICRA
Service robots should be able to operate autonomously in dynamic and daily changing environments over an extended period of time. While Simultaneous Localization And Mapping (SLAM) is one of the most fundamental problems for robotic autonomy, most ex
Publikováno v:
Proceedings of the 2019 2nd International Conference on Control and Robot Technology.
Imitation Learning (IL) has facilitated many effective and efficient controllers for autonomous agents. Nevertheless, current methods suffer from severe partial observability problems when given incomplete observations, leading to short-sighted behav
Publikováno v:
International Journal of Computer Vision. 118:151-171
The performance of action recognition in video sequences depends significantly on the representation of actions and the similarity measurement between the representations. In this paper, we combine two kinds of features extracted from the spatio-temp
With the development of video-sharing websites, P2P, micro-blog, mobile WAP websites, and so on, sensitive videos can be more easily accessed. Effective sensitive video recognition is necessary for web content security. Among web sensitive videos, th
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6211690e430e09eff78c31a495be3d04
https://eprints.bbk.ac.uk/id/eprint/14041/1/14041.pdf
https://eprints.bbk.ac.uk/id/eprint/14041/1/14041.pdf
Publikováno v:
CVPR
In this paper, a multi-feature max-margin hierarchical Bayesian model (M3HBM) is proposed for action recognition. Different from existing methods which separate representation and classification into two steps, M3HBM jointly learns a high-level repre
Publikováno v:
Computer Vision-ACCV 2014 Workshops ISBN: 9783319166278
ACCV Workshops (1)
ACCV Workshops (1)
Motion is the most informative cue for human action recognition. Regions with high motion saliency indicate where actions occur and contain visual information that is most relevant to actions. In this paper, we propose a novel approach for human acti
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b363cbeace7af4b0101e9ae8630c6a3c
https://doi.org/10.1007/978-3-319-16628-5_9
https://doi.org/10.1007/978-3-319-16628-5_9