Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Fanfan Ye"'
Autor:
Zekun Tang, Fanfan Ye, Huihui Wan, Yuming Song, Weiwei Fan, Zhanyou Chi, Qinqin Du, Rui Cai, Qiang Xu, Hua Zhang
Publikováno v:
Chromatographia. 85:395-403
Exemplar-free incremental learning is extremely challenging due to inaccessibility of data from old tasks. In this paper, we attempt to exploit the knowledge encoded in a previously trained classification model to handle the catastrophic forgetting p
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::58574fa440220713a627a41e8bff14ba
Publikováno v:
Analytical Letters. 54:453-467
The quantitative determination of drugs in urine by high performance liquid chromatography electrospray-ionization mass spectrometry (HPLC-ESI-MS) is challenging due to complex matrix interferences and the relatively low concentrations of analytes in
In the context of skeleton-based action recognition, graph convolutional networks (GCNs) have been rapidly developed, whereas convolutional neural networks (CNNs) have received less attention. One reason is that CNNs are considered poor in modeling t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::886de21936079ece2ad1579085fe8566
Publikováno v:
ACM Multimedia
Graph Convolutional Networks (GCNs) have attracted increasing interests for the task of skeleton-based action recognition. The key lies in the design of the graph structure, which encodes skeleton topology information. In this paper, we propose Dynam
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::dc4ba92fceb0b38d35ffe94c33702735
http://arxiv.org/abs/2007.14690
http://arxiv.org/abs/2007.14690
Autor:
Huiming Tang, Fanfan Ye
Publikováno v:
Electronics Letters. 55:933-935
A novel joints relation-reasoning, graph convolutional network (JRR-GCN) is proposed to solve the problem of skeleton-based action recognition (SAR). Different from the conventional spatial convolutional network-based methods, the adjacency matrices
Publikováno v:
ICIP
Recently, the graph convolutional networks based methods have achieved remarkable performance in skeleton-based action recognition. However, current methods do not make full use of the topology of the skeleton graph, because they set and fixed the re
Autor:
Fanfan Ye1, Huiming Tang1 thm@zju.edu.cn
Publikováno v:
Electronics Letters (Wiley-Blackwell). 8/22/2019, Vol. 55 Issue 17, p933-935. 3p.