Zobrazeno 1 - 10
of 187
pro vyhledávání: '"Guiguang, Ding"'
Publikováno v:
IET Computer Vision, Vol 13, Iss 2, Pp 117-124 (2019)
This study considers the zero‐shot learning problem under the multi‐label setting where each test sample is associated with multiple labels that are unseen in training data. The authors propose a novel learning framework based on label factorisat
Externí odkaz:
https://doaj.org/article/30582b65af284060bafa4c5b39eb2ebf
Publikováno v:
Neurocomputing. 509:290-309
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e6878f0115b4781430ed348bd78413ca
https://doi.org/10.1016/j.neucom.2022.08.031
https://doi.org/10.1016/j.neucom.2022.08.031
Autor:
Yuchen, Guo, Yuwei, He, Jinhao, Lyu, Zhanping, Zhou, Dong, Yang, Liangdi, Ma, Hao-Tian, Tan, Changjian, Chen, Wei, Zhang, Jianxing, Hu, Dongshan, Han, Guiguang, Ding, Shixia, Liu, Hui, Qiao, Feng, Xu, Xin, Lou, Qionghai, Dai
Publikováno v:
The Lancet Digital Health. 4:e584-e593
A large training dataset with high-quality annotations is necessary for building an accurate and generalisable deep learning system, which can be difficult and expensive to prepare in medical applications. We present a novel deep-learning-based syste
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::04ec00afc23c9f21941de7a855587c81
https://doi.org/10.1016/s2589-7500(22)00090-5
https://doi.org/10.1016/s2589-7500(22)00090-5
Autor:
Liuyu Xiang, Jundong Zhou, Jirui Liu, Zerun Wang, Haidong Huang, Jie Hu, Jungong Han, Yuchen Guo, Guiguang Ding
Publikováno v:
Proceedings of the AAAI Conference on Artificial Intelligence. 36:2786-2794
While deep neural network-based video denoising methods have achieved promising results, it is still hard to deploy them on mobile devices due to their high computational cost and memory demands. This paper aims to develop a lightweight deep video de
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0482dbb4c5a491d16a15d325908fd392
https://doi.org/10.1609/aaai.v36i3.20182
https://doi.org/10.1609/aaai.v36i3.20182
Publikováno v:
Artificial Intelligence Review. 56:457-531
As one of the fundamental problems in the field of video understanding, video object segmentation aims at segmenting objects of interest throughout the given video sequence. Recently, with the advancements of deep learning techniques, deep neural net
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bc5ccf4cd33d1c46c7de6b5e52f8c298
https://doi.org/10.1007/s10462-022-10176-7
https://doi.org/10.1007/s10462-022-10176-7
Publikováno v:
Neurocomputing. 477:14-24
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b1e7f132dc550a485825b386c3251190
https://doi.org/10.1016/j.neucom.2021.12.049
https://doi.org/10.1016/j.neucom.2021.12.049
Publikováno v:
ISPRS International Journal of Geo-Information, Vol 9, Iss 9, p 538 (2020)
The rapidly growing location-based social network (LBSN) has become a promising platform for studying users’ mobility patterns. Many online applications can be built based on such studies, among which, recommending locations is of particular intere
Externí odkaz:
https://doaj.org/article/815a07f1564e4a2eb04d8e0d28819215
Autor:
Yaoqi Sun, Liang Li, Tingting Yao, Tongyv Lu, Bolun Zheng, Chenggang Yan, Hua Zhang, Yongjun Bao, Guiguang Ding, Gregory Slabaugh
Publikováno v:
International Journal of Intelligent Systems. 37:2969-2987
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::cc4d1a5861fd6667df8c1a312ab668f8
https://doi.org/10.1002/int.22821
https://doi.org/10.1002/int.22821
Publikováno v:
Pattern Recognition. 141:109608
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8756017016f233da4aca6df27901825b
https://doi.org/10.1016/j.patcog.2023.109608
https://doi.org/10.1016/j.patcog.2023.109608
Publikováno v:
International Journal of Computer Vision. 129:2399-2424
Domain adaptation aims to learn a transferable model to bridge the domain shift between one labeled source domain and another sparsely labeled or unlabeled target domain. Since the labeled data may be collected from multiple sources, multi-source dom
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::462795650dc5405db6ea119d9e2c211d
https://doi.org/10.1007/s11263-021-01479-3
https://doi.org/10.1007/s11263-021-01479-3