Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Zhinan Qiao"'
Publikováno v:
Neurocomputing. 492:612-623
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f53af4a7e4e0c1cae80beb755e3351d5
https://doi.org/10.1016/j.neucom.2021.12.053
https://doi.org/10.1016/j.neucom.2021.12.053
Autor:
Xiaohui Yuan, Zhinan Qiao
Publikováno v:
International Journal of Geographical Information Science. 35:2129-2148
Urban regions are complicated functional systems that are closely associated with and reshaped by human activities. The propagation of online geographic information-sharing platforms and mobile devices equipped with Global Positioning System (GPS) gr
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::02f23f8afa2b8d52390fdc9326ea2162
https://doi.org/10.1080/13658816.2021.1919682
https://doi.org/10.1080/13658816.2021.1919682
Contrastive learning (CL) is widely known to require many negative samples, 65536 in MoCo for instance, for which the performance of a dictionary-free framework is often inferior because the negative sample size (NSS) is limited by its mini-batch siz
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b6c0f553468d35a3e4e108cb7daaf0b6
Autor:
Xu Ma, Zhinan Qiao, Jingda Guo, Nannan Wang, Paparao Palacharla, Sihai Tang, Qing Yang, Xi Wang, Qi Chen, Song Fu
Publikováno v:
2021 IEEE International Conference on Multimedia and Expo (ICME).
While self-attention mechanism has shown promising results for many vision tasks, it only considers the current features at a time. We show that such a manner cannot take full advantage of the attention mechanism. In this paper, we present Deep Conne
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::29d55af5768f3d2de8b3d08cb4ba557d
https://doi.org/10.1109/icme51207.2021.9428397
https://doi.org/10.1109/icme51207.2021.9428397
Publikováno v:
ICPR
The unrestricted open vocabulary and diverse substances of scenery images bring significant challenges to scene recognition. However, most deep learning architectures and attention methods are developed on general-purpose datasets and omit the charac
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3d7031a5257cb800bf11cd458c16995f
https://doi.org/10.1109/icpr48806.2021.9412235
https://doi.org/10.1109/icpr48806.2021.9412235
Publikováno v:
ICIP
In this paper, we present a cascaded context dependency module, which is a highly lightweight module that can improve the performance of deep convolutional neural networks for various visual tasks. Inspired by the feature pyramid work in object detec
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d59fbbc0545e052b8e9ed81c0addc838
https://doi.org/10.1109/icip40778.2020.9191033
https://doi.org/10.1109/icip40778.2020.9191033
Publikováno v:
2020 International Conference on Connected and Autonomous Driving (MetroCAD).
Recently, more and more attention has been paid to the connected object detection for better performance. One of the most interesting fields is learning from multiple resources in a connected fashion. In this paper, we present a connected object dete
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::063064a62bb5613efebde2d992b223df
https://doi.org/10.1109/metrocad48866.2020.00011
https://doi.org/10.1109/metrocad48866.2020.00011
Publikováno v:
Communications in Computer and Information Science ISBN: 9789813346000
Scene understanding remains a challenging task due to the complex and ambiguous nature of scene images in defiance of several networks pre-trained on large-scale benchmark datasets are available. In this paper, we proposed a multi-scale, discriminati
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3c9d0c0f78eb7ef06ae6583a57e4667f
https://doi.org/10.1007/978-981-33-4601-7_14
https://doi.org/10.1007/978-981-33-4601-7_14