1 code implementation • 27 Nov 2017 • Guangfeng Lin, Yajun Chen, Fan Zhao
It is difficult to capture the relationship among image classes due to unseen classes, so that the manifold structure of image classes often is ignored in ZSL.
no code implementations • 25 Jan 2018 • Guangfeng Lin, Caixia Fan, Wanjun Chen, Yajun Chen, Fan Zhao
CLA can not only build a uniform framework for adapting to multi-semantic embedding spaces, but also construct the encoder-decoder mechanism for constraining the bidirectional projection between the feature space and the class label space.
no code implementations • 6 Mar 2019 • Guangfeng Lin, Wanjun Chen, Kaiyang Liao, Xiaobing Kang, Caixia Fan
To alleviate the negative influence of this inconsistence for ZSL and GZSL, transfer feature generating networks with semantic classes structure (TFGNSCS) is proposed to construct networks model for improving the performance of ZSL and GZSL.
no code implementations • The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2019 2019 • Duohan Liang, Guoliang Fan, Guangfeng Lin, Wanjun Chen, Xiaorong Pan, Hong Zhu
In this paper, we propose a three-stream convolutional neural network (3SCNN) for action recognition from skeleton sequences, which aims to thoroughly and fully exploit the skeleton data by extracting, learning, fusing and inferring multiple motion-related features, including 3D joint positions and joint displacements across adjacent frames as well as oriented bone segments.
Ranked #54 on Skeleton Based Action Recognition on NTU RGB+D
no code implementations • 2 Jul 2019 • Guangfeng Lin, Jing Wang, Kaiyang Liao, Fan Zhao, Wanjun Chen
By solving this function, we can simultaneously obtain the fusion spectral embedding from the multi-view data and the fusion structure as adjacent matrix to input graph convolutional networks for semi-supervised classification.
Ranked #33 on Node Classification on Citeseer
no code implementations • 29 May 2020 • Guangfeng Lin, Xiaobing Kang, Kaiyang Liao, Fan Zhao, Yajun Chen
Existing methods mostly combine the computational layer and the related losses into GCN for exploring the global graph(measuring graph structure from all data samples) or local graph (measuring graph structure from local data samples).
1 code implementation • 29 May 2020 • Guangfeng Lin, Ying Yang, Yindi Fan, Xiaobing Kang, Kaiyang Liao, Fan Zhao
Most existing methods try to model the similarity relationship of the samples in the intra tasks, and generalize the model to identify the new categories.
no code implementations • 12 Mar 2024 • Sijin He, Guangfeng Lin
Image deraining have have gained a great deal of attention in order to address the challenges posed by the effects of harsh weather conditions on visual tasks.