Zobrazeno 1 - 10
of 11
pro vyhledávání: '"Hemeng Tao"'
Publikováno v:
2022 International Joint Conference on Neural Networks (IJCNN).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b5d3bbbbee4b7fa6ec3e48a2e25428e8
https://doi.org/10.1109/ijcnn55064.2022.9892894
https://doi.org/10.1109/ijcnn55064.2022.9892894
Publikováno v:
IJCNN
A social media user's geographical location is vital to many applications like local search and event detection. The scarcity of publicly available location information motivates researchers to predict user geolocation based on information such as tw
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9657167407e8e888b80a4a31de4e86e1
https://doi.org/10.1109/ijcnn52387.2021.9533550
https://doi.org/10.1109/ijcnn52387.2021.9533550
Autor:
Latifur Khan, Xujiang Zhao, Yu Lin, Zhuoyi Wang, Yigong Wang, Hemeng Tao, Chen Zhao, Yuqiao Chen
Publikováno v:
WWW
Non-stationary data stream mining aims to classify large scale online instances that emerge continuously. The most apparent challenge compared with the offline learning manner is the issue of consecutive emergence of new categories, when tackling non
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8ecca903a00b45ba2e466fc8472aac61
https://doi.org/10.1145/3442381.3449820
https://doi.org/10.1145/3442381.3449820
Publikováno v:
IEEE BigData
Existing solutions to multi-task learning typically rely on manually enumerating multiple network architectures to find the optimal structure, which incurs a heavy design workload. In addition, extending these models to new tasks is difficult in many
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0fc41814baf2f66043d588503e95ddfe
https://doi.org/10.1109/bigdata50022.2020.9378210
https://doi.org/10.1109/bigdata50022.2020.9378210
Publikováno v:
ICIP
Automated diagnosis of significant abnormalities (or lesions) from radiology images has been well exploited in Deep Learning (DL) because of the ability to model sophisticated features. However, a deep neural network should be trained on a huge amoun
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c14ddcdc70c9cff89d5c67b8d87fbd7a
https://doi.org/10.1109/icip40778.2020.9191155
https://doi.org/10.1109/icip40778.2020.9191155
Publikováno v:
AAAI
Continuously mining complexity data stream has recently been attracting an increasing amount of attention, due to the rapid growth of real-world vision/signal applications such as self-driving cars and online social media messages. In this paper, we
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::08d9dc12001b66f8392df73eb1db598b
https://doi.org/10.1609/aaai.v34i10.7253
https://doi.org/10.1609/aaai.v34i10.7253
Publikováno v:
IJCNN
A primary challenge in label prediction over a stream of continuously occurring data instances is the emergence of instances belonging to unknown or novel classes. It is imperative to detect such novel-class instances quickly along the stream for a s
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::36fada9e66ceacab78a8c448e1089929
https://doi.org/10.1109/ijcnn.2019.8851934
https://doi.org/10.1109/ijcnn.2019.8851934
Publikováno v:
IJCNN
With the tremendous increase of the online data, training a single classifier may suffer because of the large variety of data domains. One solution could be to learn separate classifiers for each domain. However, this would arise a huge cost to gathe
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::68cd42ea74ab4f7091bfc661830a7d69
https://doi.org/10.1109/ijcnn.2019.8851931
https://doi.org/10.1109/ijcnn.2019.8851931
Publikováno v:
WWW
Under a newly introduced setting of multistream classification, two data streams are involved, which are referred to as source and target streams. The source stream continuously generates data instances from a certain domain with labels, while the ta
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::889546f00a4c7460be76fb6b929b9949
https://doi.org/10.1145/3308558.3313572
https://doi.org/10.1145/3308558.3313572
Publikováno v:
ICDE
A primary challenge in label prediction over a data stream is the emergence of instances belonging to unknown or novel class over time. Traditionally, studies addressing this problem aim to detect such instances using cluster-based mechanisms. They t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ded22052124024bdfa152b1309de51e0
https://doi.org/10.1109/icde.2019.00128
https://doi.org/10.1109/icde.2019.00128