学术论文

研究小组近年来发表的相关学术论文(部分)如下:

  • 全部论文
  • 异构特征融合及识别
  • 跨模态匹配
  • 图像处理和机器学习
  • 运动捕捉数据分析
  • W.T. Fan, N. Bouguila, J.X. Du, X. Liu

    Axially Symmetric Data Clustering Through Dirichlet Process Mixture Models of Watson Distributions[pdf] [bibtex]

    IEEE Transactions on Neural Networks and Learning Systems
    @article{FanTNNLS,
      title={Axially Symmetric Data Clustering Through Dirichlet Process Mixture Models of Watson Distributions},
      author={Wentao Fan and  Nizar Bouguila  and Ji-Xiang Du and Xin Liu},
      journal={IEEE Transactions on Neural Networks and Learning Systems},
     year={2018}
    }
  • 柳欣, 李鹤洋, 钟必能, 杜吉祥

    结合有监督联自编码器的跨音视频说话人标注[pdf] [bibtex]

    电子与信息学报,40 (7), pp. 1635-1642, 2018
    LIU Xin, LI Heyang, ZHONG Bineng, DU Jixiang. Efficient Audio-visual Cross-modal Speaker Tagging via Supervised Joint Correspondence Auto-encoder. JEIT, 2018, 40(7): 1635-1642. 
  • 胡 东, 彭淑娟*, 柳欣, 杜吉祥

    结合深度自编码和时空特征约束的运动风格转移方法[pdf] [bibtex]

    计算机辅助设计与图形学学报, 30 (5), pp. 946-956, 2018.
    胡东,彭淑娟*,柳欣,杜吉祥,结合深度自编码和时空特征约束的运动风格转移方法,计算机辅助设计与图形学学报, 30 (5), pp. 946-956, 2018. (EI, 核心)
  • X. Liu, Y.M. Cheung

    On incremental collaborative appearance model and regional particle filtering for lip region tracking[pdf] [bibtex]

    Integrated Computer-Aided Engineering , vol. 25, no. 1, pp. 63-80, 2018
    @article{liu2017incremental,
      title={On incremental collaborative appearance model and regional particle filtering for lip region tracking},
      author={Liu, Xin and Cheung, Yiu-Ming},
      journal={Integrated Computer-Aided Engineering},
      number={25:1},
      pages={63--80},
      year={2018}
      }
  • Z.K. Hu, X, Liu*, A. Li, B.N. Zhong, W.T. Fan, J.X. Du

    Efficient Cross-modal Retrieval via Discriminative Deep Correspondence[pdf] [bibtex]

    CCF Chinese Conference on Computer Vision (CCCV), 2017, pp. 662-673.
    @inproceedings{hu2017efficient,
      title={Efficient Cross-modal Retrieval via Discriminative Deep Correspondence Model},
      author={Hu, Zhikai and Liu, Xin and Li, An and Zhong, Bineng and Fan, Wentao and Du, Jixiang},
      booktitle={CCF Chinese Conference on Computer Vision},
      pages={662--673},
      year={2017},
      organization={Springer}
    }
  • B. Zou, X, Liu, S.J. Peng, B.N. Zhong, J.X. Du

    Efficient Human Motion Transition via Hybrid Deep Neural Network and Reliable Motion Graph Mining[pdf] [bibtex]

    CCF Chinese Conference on Computer Vision (CCCV), 2017, pp. 717-728.
    @inproceedings{zhou2017efficient,
      title={Efficient Human Motion Transition via Hybrid Deep Neural Network and Reliable Motion Graph Mining},
      author={Zhou, Bing and Liu, Xin and Peng, Shujuan and Zhong, Bineng and Du, Jixiang},
      booktitle={CCF Chinese Conference on Computer Vision},
      pages={717--728},
      year={2017},
      organization={Springer}
    }
  • D. Hu, X. Liu*, S.J. Peng, B.N. Zhong, J.X. Du

    Automatic Character Motion Style Transfer via Autoencoder Generative Model and Correlation Mining[pdf] [bibtex]

    Chinese Conference on Computer Vision (CCCV), 2017, pp. 705-716
    @inproceedings{hu2017automatic,
      title={Automatic Character Motion Style Transfer via Autoencoder Generative Model and Spatio-Temporal Correlation Mining},
      author={Hu, Dong and Liu, Xin and Peng, Shujuan and Zhong, Bineng and Du, Jixiang},
      booktitle={CCF Chinese Conference on Computer Vision},
      pages={705--716},
      year={2017},
      organization={Springer}
    }
  • 周兵,彭淑娟,柳欣

    融合生成模型和判别模型的双层 RBM 运动捕获数据语义识别算法[pdf] [bibtex]

    计算机辅助设计与图形学学报, 29(4), pp 689-698,2017. (EI, 核心)
    @article{zou2017,
      title={融合生成模型和判别模型的双层 RBM 运动捕获数据语义识别算法},
      author={周兵 and 彭淑娟 and 柳欣},
      journal={计算机辅助设计与图形学学报},
      volume={29},
      number={4},
      pages={689--698},
      year={2017}
    }
  • X. Liu*, H. Zhang, Y.M. Cheung, X.G. You, Y.Y. Tang

    Efficient Single Image Dehazing and Denosing: An Efficient Multi-scale Correlated Wavelet Approach[pdf] [bibtex] [code]

    Computer Vision and Image Understanding, vol. 162, pp, 22-33, 2017
    @article{liu2017efficient,
      title={Efficient single image dehazing and denoising: An efficient multi-scale correlated wavelet approach},
      author={Liu, Xin and Zhang, He and Cheung, Yiu-ming and You, Xinge and Tang, Yuan Yan},
      journal={Computer Vision and Image Understanding},
      volume={162},
      pages={23--33},
      year={2017},
      publisher={Elsevier}
    }
  • Yu-Hang Liu, Xin Liu*, Wentao Fan, Bineng Zhong, Ji-Xiang Du

    Efficient Audio-Visual Speaker Recognition via Deep Heterogeneous Feature Fusion[pdf] [bibtex]

    12th Chinese Conference on Biometric Recognition (CCBR), 2017: 575-583
    @inproceedings{liu2017efficient,
      title={Efficient Audio-Visual Speaker Recognition via Deep Heterogeneous Feature Fusion},
      author={Liu, Yu-Hang and Liu, Xin and Fan, Wentao and Zhong, Bineng and Du, Ji-Xiang},
      booktitle={Chinese Conference on Biometric Recognition},
      pages={575--583},
      year={2017},
      organization={Springer}
    }
  • J. Geng, X. Liu*, Y.M. Cheung

    Audio-visual Speaker Recognition via Multi-modal Correlated Neural Networks[pdf] [bibtex]

    IEEE/WIC/ACM International Conference on Web Intelligence Workshops, pp. 123-128, 2016
    @INPROCEEDINGS{Geng2016, 
    author={J. Geng and X. Liu and Y. m. Cheung}, 
    booktitle={IEEE/WIC/ACM International Conference on Web Intelligence Workshops (WIW)}, 
    title={Audio-Visual Speaker Recognition via Multi-modal Correlated Neural Networks}, 
    year={2016}, 
    pages={123-128}, 
    }
  • X. Liu, Y.M. Cheung, Y.Y. Tang,

    Lip Event Detection Using Oriented Histograms of Regional Optical Flow and Low Rank Affinity Pursuit[pdf] [bibtex]

    Computer Vision and Image Understanding, vol. 148, no. 7, pp, 153-163, 2016.
    @article{LIU2016153,
    title = {Lip event detection using oriented histograms of regional optical flow and low rank affinity pursuit},
    author = {Xin Liu and Yiu-ming Cheung and Yuan Yan Tang},
    journal = {Computer Vision and Image Understanding},
    volume = {148},
    pages = {153 - 163},
    year = {2016},
    }
  • X. Liu, Y.M. Cheung

    Learning Multi-Boosted HMMs for Lip-password Based Speaker Verification[pdf] [bibtex]

    IEEE Transactions on Information Forensics and Security, vol. 9, no. 2, pp. 233-246, 2014
    @ARTICLE{xliu2014, 
    author={X. Liu and Y. m. Cheung}, 
    journal={IEEE Transactions on Information Forensics and Security}, 
    title={Learning Multi-Boosted HMMs for Lip-Password Based Speaker Verification}, 
    year={2014}, 
    volume={9}, 
    number={2}, 
    pages={233-246}, 
    }
  • W.T. Fan, N. Bouguila, X. Liu

    A Hierarchical DPM of GID Distributions with Feature Selection for Video Modeling and Segmentation[pdf] [bibtex]

    42th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1173-1176, 2017.
    @INPROCEEDINGS{7952661, 
    author={W. Fan and N. Bouguila and X. Liu}, 
    booktitle={2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, 
    title={A hierarchical Dirichlet process mixture of GID Distributions with feature selection for spatio-temporal video modeling and segmentation}, 
    year={2017}, 
    pages={2771-2775}
    }
  • 赫高峰、彭淑娟、柳欣、钟必能

    结合模糊聚类和投影近似点算法的缺失人体运动捕捉数据重构[pdf] [bibtex]

    计算机辅助设计与图形学学报, 2015 , 27 ( 8 ): 1407-1415.
    赫高峰、彭淑娟、柳欣、钟必能,结合模糊聚类和投影近似点算法的缺失人体运动捕捉数据重构,计算机辅助设计与图形学学报,2015 , 27 ( 8 ): 1407-1415.  (EI检索, 中文核心期刊)
  • 彭淑娟,赫高峰,柳 欣,王华珍,钟必能

    基于运动分割和稀疏低秩分解的失真人体运动捕捉数据恢复[pdf] [bibtex]

    计算机辅助设计与图形学学报,2015,27(4):721-730
    彭淑娟,赫高峰,柳 欣,王华珍,钟必能 ,基于运动分割和稀疏低秩分解的失真人体运动捕捉数据恢复,计算机辅助设计与图形学学报,2015,27(4):721-730.  (EI检索, 中文核心期刊)
  • S.J. Peng, G..F. He, X. Liu*, H.Z. Wang

    Hierarchical block-based incomplete human mocap data recovery using adaptive nonnegative matrix factorization[pdf] [bibtex]

    Computers &Graphics, 49, pp:10–23, 2015.
    @article{peng2015hierarchical,
      title={Hierarchical block-based incomplete human mocap data recovery using adaptive nonnegative matrix factorization},
      author={Peng, Shu-Juan and He, Gao-Feng and Liu, Xin and Wang, Hua-Zhen},
      journal={Computers \& Graphics},
      volume={49},
      pages={10--23},
      year={2015}
    }
  • X. Liu, G.F. He, S.J. Peng, Y.M. Cheung, Y.Y. Tang

    Efficient Human Motion Retrieval via TA-BoW and Discriminative Neighborhood Preserving Dictionary Learning[pdf] [bibtex]

    IEEE Transactions on Human-Machine Systems, 2017, 47(6), pp, 763-776
    @article{liu2017efficient,
      title={Efficient human motion retrieval via temporal adjacent bag of words and discriminative neighborhood preserving dictionary learning},
      author={Liu, Xin and He, Gao-Feng and Peng, Shu-Juan and Cheung, Yiu-ming and Tang, Yuan Yan},
      journal={IEEE Transactions on Human-Machine Systems},
      volume={47},
      number={6},
      pages={763--776},
      year={2017}
    }
  • G.F. He, S.J. Peng, X. Liu*

    Motion Capture Behavior Recognition via Neighborhood Preserving Dictionary Learning[pdf] [bibtex]

    International Conference on Systems, Man, and Cybernetics (SMC), 2015, pp: 2725 - 2729
    @inproceedings{he2015motion,
      title={Motion Capture Behavior Recognition via Neighborhood Preserving Dictionary Learning},
      author={He, Gao-Feng and Peng, Shu-Juan and Liu, Xin},
      booktitle={Systems, Man, and Cybernetics (SMC), 2015 IEEE International Conference on},
      pages={2725--2729},
      year={2015},
      organization={IEEE}
    }
  • 周兵,彭淑娟,柳欣

    融合生成模型和判别模型的双层 RBM 运动捕获数据语义识别算法[pdf] [bibtex]

    计算机辅助设计与图形学学报, 29(4), pp 689-698,2017
    周兵,彭淑娟,柳欣,融合生成模型和判别模型的双层 RBM 运动捕获数据语义识别算法,计算机辅助设计与图形学学报, 29(4), pp 689-698,2017. (EI, 核心)
  • H. Zhang, X. Liu*, Y.M. Cheung

    Efficient Single Image Dehazing via Scene-adaptive Segmentation and Improved Dark Channel Model[pdf] [bibtex]

    IEEE International Joint Conference on Neural Networks (IJCNN), pp. 3440-3445, 2016.
    @inproceedings{zhang2016efficient,
      title={Efficient single image dehazing via scene-adaptive segmentation and improved dark channel model},
      author={Zhang, He and Liu, Xin and Cheung, Yiu-ming},
      booktitle={2016 International Joint Conference on Neural Networks (IJCNN)},
      pages={3440--3445},
      year={2016},
      organization={IEEE}
    }
  • X. Liu*, H. Zhang, Y.Y. Tang, J.X. Du

    Scene-adaptive Single Image Dehazing via Opening Dark Channel Model[pdf] [bibtex]

    IET image processing, vol. 10, no. 11, pp, 877-884, 2016.
    @ARTICLE{xliu7747329, 
    author={X. Liu and H. Zhang and Y. Y. Tang and J. X. Du}, 
    journal={IET Image Processing}, 
    title={Scene-adaptive single image dehazing via opening dark channel model}, 
    year={2016}, 
    volume={10}, 
    number={11}, 
    pages={877-884} 
    }
    
  • Yu-Hang Liu, Xin Liu*, Wentao Fan, Bineng Zhong, Ji-Xiang Du

    Efficient Audio-Visual Speaker Recognition via Deep Heterogeneous Feature Fusion [pdf] [bibtex]

    12th Chinese Conference on Biometric Recognition (CCBR), 2017: 575-583
    @inproceedings{liu2017efficient,
      title={Efficient Audio-Visual Speaker Recognition via Deep Heterogeneous Feature Fusion},
      author={Liu, Yu-Hang and Liu, Xin and Fan, Wentao and Zhong, Bineng and Du, Ji-Xiang},
      booktitle={Chinese Conference on Biometric Recognition},
      pages={575--583},
      year={2017},
      organization={Springer}
    }
  • J. Geng, X. Liu*, Y.M. Cheung

    Audio-visual Speaker Recognition via Multi-modal Correlated Neural Networks [pdf] [bibtex]

    IEEE/WIC/ACM International Conference on Web Intelligence Workshops, pp. 123-128, 2016
    @INPROCEEDINGS{Geng2016, 
    author={J. Geng and X. Liu and Y. m. Cheung}, 
    booktitle={IEEE/WIC/ACM International Conference on Web Intelligence Workshops (WIW)}, 
    title={Audio-Visual Speaker Recognition via Multi-modal Correlated Neural Networks}, 
    year={2016}, 
    pages={123-128}, 
    }
  • X. Liu, Y.M. Cheung, Y.Y. Tang,

    Lip Event Detection Using Oriented Histograms of Regional Optical Flow and Low Rank Affinity Pursuit [pdf] [bibtex]

    Computer Vision and Image Understanding, vol. 148, no. 7, pp, 153-163, 2016.
    @article{LIU2016153,
    title = {Lip event detection using oriented histograms of regional optical flow and low rank affinity pursuit},
    author = {Xin Liu and Yiu-ming Cheung and Yuan Yan Tang},
    journal = {Computer Vision and Image Understanding},
    volume = {148},
    pages = {153 - 163},
    year = {2016},
    }
  • X. Liu, Y.M. Cheung

    Learning Multi-Boosted HMMs for Lip-password Based Speaker Verification [pdf] [bibtex]

    IEEE Transactions on Information Forensics and Security, vol. 9, no. 2, pp. 233-246, 2014
    @ARTICLE{xliu2014, 
    author={X. Liu and Y. m. Cheung}, 
    journal={IEEE Transactions on Information Forensics and Security}, 
    title={Learning Multi-Boosted HMMs for Lip-Password Based Speaker Verification}, 
    year={2014}, 
    volume={9}, 
    number={2}, 
    pages={233-246}, 
    }
  • 柳欣, 李鹤洋, 钟必能, 杜吉祥

    结合有监督联自编码器的跨音视频说话人标注 [pdf] [bibtex]

    电子与信息学报,40 (7), pp. 1635-1642, 2018
    LIU Xin, LI Heyang, ZHONG Bineng, DU Jixiang. Efficient Audio-visual Cross-modal Speaker Tagging via Supervised Joint Correspondence Auto-encoder. JEIT, 2018, 40(7): 1635-1642. 
  • Z.K. Hu, X, Liu*, A. Li, B.N. Zhong, W.T. Fan, J.X. Du

    Efficient Cross-modal Retrieval via Discriminative Deep Correspondence [pdf] [bibtex]

    CCF Chinese Conference on Computer Vision (CCCV), 2017, pp. 662-673.
    @inproceedings{hu2017efficient,
      title={Efficient Cross-modal Retrieval via Discriminative Deep Correspondence Model},
      author={Hu, Zhikai and Liu, Xin and Li, An and Zhong, Bineng and Fan, Wentao and Du, Jixiang},
      booktitle={CCF Chinese Conference on Computer Vision},
      pages={662--673},
      year={2017},
      organization={Springer}
    }
  • W.T. Fan, N. Bouguila, J.X. Du, X. Liu

    Axially Symmetric Data Clustering Through Dirichlet Process Mixture Models of Watson Distributions [pdf] [bibtex]

    IEEE Transactions on Neural Networks and Learning Systems
    @article{FanTNNLS,
      title={Axially Symmetric Data Clustering Through Dirichlet Process Mixture Models of Watson Distributions},
      author={Wentao Fan and  Nizar Bouguila  and Ji-Xiang Du and Xin Liu},
      journal={IEEE Transactions on Neural Networks and Learning Systems},
     year={2018}
    }
  • X. Liu, Y.M. Cheung

    On incremental collaborative appearance model and regional particle filtering for lip region tracking [pdf] [bibtex]

    Integrated Computer-Aided Engineering , vol. 25, no. 1, pp. 63-80, 2018
    @article{liu2017incremental,
      title={On incremental collaborative appearance model and regional particle filtering for lip region tracking},
      author={Liu, Xin and Cheung, Yiu-Ming},
      journal={Integrated Computer-Aided Engineering},
      number={25:1},
      pages={63--80},
      year={2018}
      }
  • X. Liu*, H. Zhang, Y.M. Cheung, X.G. You, Y.Y. Tang

    Efficient Single Image Dehazing and Denosing: An Efficient Multi-scale Correlated Wavelet Approach [pdf] [code] [bibtex]

    Computer Vision and Image Understanding, vol. 162, pp, 22-33, 2017
    @article{liu2017efficient,
      title={Efficient single image dehazing and denoising: An efficient multi-scale correlated wavelet approach},
      author={Liu, Xin and Zhang, He and Cheung, Yiu-ming and You, Xinge and Tang, Yuan Yan},
      journal={Computer Vision and Image Understanding},
      volume={162},
      pages={23--33},
      year={2017},
      publisher={Elsevier}
    }
  • W.T. Fan, N. Bouguila, X. Liu

    A Hierarchical DPM of GID Distributions with Feature Selection for Video Modeling and Segmentation [pdf] [bibtex]

    42th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1173-1176, 2017.
    @INPROCEEDINGS{7952661, 
    author={W. Fan and N. Bouguila and X. Liu}, 
    booktitle={2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, 
    title={A hierarchical Dirichlet process mixture of GID Distributions with feature selection for spatio-temporal video modeling and segmentation}, 
    year={2017}, 
    pages={2771-2775}
    }
  • H. Zhang, X. Liu*, Y.M. Cheung

    Efficient Single Image Dehazing via Scene-adaptive Segmentation and Improved Dark Channel Model [pdf] [bibtex]

    IEEE International Joint Conference on Neural Networks (IJCNN), pp. 3440-3445, 2016.
    @inproceedings{zhang2016efficient,
      title={Efficient single image dehazing via scene-adaptive segmentation and improved dark channel model},
      author={Zhang, He and Liu, Xin and Cheung, Yiu-ming},
      booktitle={2016 International Joint Conference on Neural Networks (IJCNN)},
      pages={3440--3445},
      year={2016},
      organization={IEEE}
    }
  • X. Liu*, H. Zhang, Y.Y. Tang, J.X. Du

    Scene-adaptive Single Image Dehazing via Opening Dark Channel Model [pdf] [bibtex]

    IET image processing, vol. 10, no. 11, pp, 877-884, 2016.
    @ARTICLE{xliu7747329, 
    author={X. Liu and H. Zhang and Y. Y. Tang and J. X. Du}, 
    journal={IET Image Processing}, 
    title={Scene-adaptive single image dehazing via opening dark channel model}, 
    year={2016}, 
    volume={10}, 
    number={11}, 
    pages={877-884} 
    }
    
  • 胡 东, 彭淑娟*, 柳欣, 杜吉祥

    结合深度自编码和时空特征约束的运动风格转移方法 [pdf] [bibtex]

    计算机辅助设计与图形学学报, 30 (5), pp. 946-956, 2018.
    胡东,彭淑娟*,柳欣,杜吉祥,结合深度自编码和时空特征约束的运动风格转移方法,计算机辅助设计与图形学学报, 30 (5), pp. 946-956, 2018. (EI, 核心)
  • B. Zou, X, Liu, S.J. Peng, B.N. Zhong, J.X. Du

    Efficient Human Motion Transition via Hybrid Deep Neural Network and Reliable Motion Graph Mining [pdf] [bibtex]

    CCF Chinese Conference on Computer Vision (CCCV), 2017, pp. 717-728.
    @inproceedings{zhou2017efficient,
      title={Efficient Human Motion Transition via Hybrid Deep Neural Network and Reliable Motion Graph Mining},
      author={Zhou, Bing and Liu, Xin and Peng, Shujuan and Zhong, Bineng and Du, Jixiang},
      booktitle={CCF Chinese Conference on Computer Vision},
      pages={717--728},
      year={2017},
      organization={Springer}
    }
  • D. Hu, X. Liu*, S.J. Peng, B.N. Zhong, J.X. Du

    Automatic Character Motion Style Transfer via Autoencoder Generative Model and Correlation Mining [pdf] [bibtex]

    Chinese Conference on Computer Vision (CCCV), 2017, pp. 705-716
    @inproceedings{hu2017automatic,
      title={Automatic Character Motion Style Transfer via Autoencoder Generative Model and Spatio-Temporal Correlation Mining},
      author={Hu, Dong and Liu, Xin and Peng, Shujuan and Zhong, Bineng and Du, Jixiang},
      booktitle={CCF Chinese Conference on Computer Vision},
      pages={705--716},
      year={2017},
      organization={Springer}
    }
  • 周兵,彭淑娟,柳欣

    融合生成模型和判别模型的双层 RBM 运动捕获数据语义识别算法 [pdf] [bibtex]

    计算机辅助设计与图形学学报, 29(4), pp 689-698,2017. (EI, 核心)
    @article{zou2017,
      title={融合生成模型和判别模型的双层 RBM 运动捕获数据语义识别算法},
      author={周兵 and 彭淑娟 and 柳欣},
      journal={计算机辅助设计与图形学学报},
      volume={29},
      number={4},
      pages={689--698},
      year={2017}
    }
  • 赫高峰、彭淑娟、柳欣、钟必能

    结合模糊聚类和投影近似点算法的缺失人体运动捕捉数据重构 [pdf] [bibtex]

    计算机辅助设计与图形学学报, 2015 , 27 ( 8 ): 1407-1415.
    赫高峰、彭淑娟、柳欣、钟必能,结合模糊聚类和投影近似点算法的缺失人体运动捕捉数据重构,计算机辅助设计与图形学学报,2015 , 27 ( 8 ): 1407-1415.  (EI检索, 中文核心期刊)
  • 彭淑娟,赫高峰,柳 欣,王华珍,钟必能

    基于运动分割和稀疏低秩分解的失真人体运动捕捉数据恢复 [pdf] [bibtex]

    计算机辅助设计与图形学学报,2015,27(4):721-730
    彭淑娟,赫高峰,柳 欣,王华珍,钟必能 ,基于运动分割和稀疏低秩分解的失真人体运动捕捉数据恢复,计算机辅助设计与图形学学报,2015,27(4):721-730.  (EI检索, 中文核心期刊)
  • S.J. Peng, G..F. He, X. Liu*, H.Z. Wang

    Hierarchical block-based incomplete human mocap data recovery using adaptive nonnegative matrix factorization [pdf] [bibtex]

    Computers &Graphics, 49, pp:10–23, 2015.
    @article{peng2015hierarchical,
      title={Hierarchical block-based incomplete human mocap data recovery using adaptive nonnegative matrix factorization},
      author={Peng, Shu-Juan and He, Gao-Feng and Liu, Xin and Wang, Hua-Zhen},
      journal={Computers \& Graphics},
      volume={49},
      pages={10--23},
      year={2015}
    }
  • X. Liu, G.F. He, S.J. Peng, Y.M. Cheung, Y.Y. Tang

    Efficient Human Motion Retrieval via TA-BoW and Discriminative Neighborhood Preserving Dictionary Learning [pdf] [bibtex]

    IEEE Transactions on Human-Machine Systems, 2017, 47(6), pp, 763-776
    @article{liu2017efficient,
      title={Efficient human motion retrieval via temporal adjacent bag of words and discriminative neighborhood preserving dictionary learning},
      author={Liu, Xin and He, Gao-Feng and Peng, Shu-Juan and Cheung, Yiu-ming and Tang, Yuan Yan},
      journal={IEEE Transactions on Human-Machine Systems},
      volume={47},
      number={6},
      pages={763--776},
      year={2017}
    }
  • G.F. He, S.J. Peng, X. Liu*

    Motion Capture Behavior Recognition via Neighborhood Preserving Dictionary Learning [pdf] [bibtex]

    International Conference on Systems, Man, and Cybernetics (SMC), 2015, pp: 2725 - 2729
    @inproceedings{he2015motion,
      title={Motion Capture Behavior Recognition via Neighborhood Preserving Dictionary Learning},
      author={He, Gao-Feng and Peng, Shu-Juan and Liu, Xin},
      booktitle={Systems, Man, and Cybernetics (SMC), 2015 IEEE International Conference on},
      pages={2725--2729},
      year={2015},
      organization={IEEE}
    }
  • 周兵,彭淑娟,柳欣

    融合生成模型和判别模型的双层 RBM 运动捕获数据语义识别算法 [pdf] [bibtex]

    计算机辅助设计与图形学学报, 29(4), pp 689-698,2017
    周兵,彭淑娟,柳欣,融合生成模型和判别模型的双层 RBM 运动捕获数据语义识别算法,计算机辅助设计与图形学学报, 29(4), pp 689-698,2017. (EI, 核心)