謝曉華(中山大學數據科學與計算機學院副教授)

謝曉華,男,博士,中山大學數據科學與計算機學院副教授、博士生導師,廣東省“特支計畫”科技青年拔尖人才,深圳市“孔雀計畫”海外高層次引進人才(B類)。主持包括國家基金委項目、廣東省自然科學基金-重點項目在內的縱向課題10項;參與包括國家自然科學基金-重大項目、國家自然科學基金-重點項目、國家“863”項目在內的課題多項;主持橫向課題2項。在包括IEEE Trans. Image Processing、ICCV、CVPR、AAAI在內的國際著名刊物和會議發表論文近60篇。多次擔任國家自然科學基金委通訊評審專家,是廣東省科技項目評審專家,是IEEE TPAMI、IEEE TIP、CVPR、AAAI等著名雜誌和會議的審稿人。參與研發的人臉識別系統成功套用於2017年財富論壇安保、廣州市高考考生身份認證系統、中山大學門禁系統等。獲2018年度廣東省自然科學獎一等獎。

基本介紹

  • 中文名:謝曉華
  • 畢業院校:中山大學
  • 學位/學歷:博士
  • 專業方向:套用數學
  • 任職院校:中山大學
研究領域,人物經歷,教育背景,工作經歷,海外經歷,獲獎榮譽,科研項目,學術兼職,教授課程,代表論著,

研究領域

計算機視覺、圖像處理、模式識別。
目前專注於:行人識別、人臉識別、低層視覺處理與生成(光照變換、去模糊、去雨霧、運動遷移)、視覺分析智慧型終端

人物經歷

教育背景

2010年12月在中山大學獲得套用數學專業博士(國家公派加拿大Concordia大學聯合培養)

工作經歷

2018.07-至今, 中山大學,副教授、博士生導師
2015.07-2018.07, 中山大學,特聘研究員
2013.12-2015.07, 中國科學院深圳先進技術研究院,副研究員、碩士生導師
2011.02-2013.11, 中國科學院深圳先進技術研究院,助理研究員(2011年11月被遴選為碩士生導師)

海外經歷

2009.09-2010.09, 國家公派留學,加拿大Concordia大學計算機科學系

獲獎榮譽

  • 2018年度廣東省科學技術獎(自然科學獎)一等獎
  • 廣東省“特支計畫”科技青年拔尖人才
  • 深圳市“孔雀計畫”海外高層次引進人才(B類)

科研項目

  1. 基於場景本徵屬性感知的圖像重渲染研究,國家自然科學-面上基金(主持,在研)
  2. 基於上下文感知的部件組裝三維建模,國家自然科學-青年基金(主持,結題)
  3. 基於顏色與深度感知的場景本徵屬性重建研究,廣東省自然科學基金-重點項目(主持,結題)
  4. “廣東省特支計畫”科技青年拔尖人才,廣東省人才項目(主持,在研)
  5. 基於總變分模型的圖像光照歸一化研究,廣東省自然科學基金-博士啟動 (主持,結題)
  6. 基於深度表征學習的圖像重渲染,中央高校基本科研業務費專項(主持,結題)
  7. 人臉識別關鍵技術,企業技術委託開發(主持,在研)
  8. 人像背景摳圖及色彩最佳化項目,企業技術委託開發(主持,在研)
  9. 視頻大數據高效表達、深度分析與綜合利用,國家自然科學基金-聯合重大項目(課題排名第二,在研)
  10. 基於多感測信息的大尺度場景高維建模與表達,國家自然科學基金-重點項目(主要成員,結題)
  11. 城市多源密集型動態運行數據呈現技術與服務系統,863計畫—智慧城市(二期)(主要成員,結題)
  12. 面向城市街景感知套用示範,863計畫—真實場景感知及數位化方法與裝置(主要成員,結題)
  13. 數據獲取與動態感知技術研究,863計畫—智慧城市(一期)(主要成員,結題)
  14. 城市監控視頻大數據時空關聯分析技術研發與智慧型套用示範,廣東省重大科技專項(排名第二,在研)
  15. 面向多警種協同的綜合實戰套用系統,廣州市對外重大合作(中大方主持人,在研)
  16. 面向智慧城市的人臉識別身份認證網際網路+雲平台系統建設及示範套用,智慧廣州專項資金項目(中大方主持人,結題)
  17. 基於海量人臉圖像深度學習的身份核驗系列產品研發套用,廣州市科技計畫重點項目(中大方主持人,結題)

學術兼職

中國計算機學會計算機視覺專委會委員
中國人工智慧學會模式識別專委會委員
中國圖象圖形學會視覺大數據專委員會委員
廣東省圖像圖形學會理事
廣東省圖象圖形學學會-計算機視覺專委會副主任

教授課程

《數字圖像處理》(本科、研究生)

代表論著

  • [行人再識別]Zhanxiang Feng, Jianhuang Lai, andXiaohua Xie. Learning View-Specific Deep Networks for Person Re-Identification. IEEE Transactions on Image Processing(TIP), 27 (7): 3472-3483, July 2018. (ISI-JCR1區,CCF A類)
  • [行人再識別]Guangcong Wang, Jianhuang Lai,Xiaohua Xie. P2SNet: Can an Image Match a Video for Person Re-identification in an End-to-end Way? IEEE Trans. on Circuits and Systems for Video Technology (TCSVT), DOI:10.1109/TCSVT.2017.2748698, 2017 (ISI-JCR1區,CCF B類)
  • [行人再識別]Guangcong Wang, Jian-Huang Lai, Peigen Huang,Xiaohua Xie. Spatial-Temporal Person Re-identification.AAAI2019. (CCF A類)
  • [人臉光照處理]Xiaohua Xie, Wei-Shi Zheng, Jianhuang Lai, Pong C. Yuan, and Ching Y. Suen. Normalization of Face Illumination Based on Large- and Small- Scale Features. IEEE Transactions on Image Processing (TIP), 20 (7), July 2011, PP.1807-1821. (ISI-JCR1區,CCF A類)
  • [人臉光照處理]Xiaohua Xie, Wei-Shi Zheng, Jianhuang Lai, and Pong C. Yuan. Face Illumination Normalization on Large and Small Scale Features. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Alaska, 2008.(CCF A類)
  • [人臉光照處理]Xiaohua Xie, Jianhuang Lai, and Wei-Shi Zheng. Extraction of Illumination Invariant Facial Features from a Single Image using Nonsubsampled Contourlet Transform.Pattern Recognition, 43 (12), December 2010, pp. 4177-4189. (ISI-JCR1區,CCF B類)
  • [人臉光照處理]Xiaohua Xie, Jianhuang Lai, Ching Y. Suen, and Wei-Shi Zheng. Non-Ideal Class Non-Point Light Source Quotient Image for Face Relighting.Signal Processing, 91(4), April 2011, PP.1048-1053. (ISI-JCR1區)
  • [人臉光照處理]Xiaohua Xie.Illumination Preprocessing for Face Images based on Empirical Mode Decomposition.Signal Processing, vol.103, October 2014, PP. 250-257. (ISI-JCR1區)
  • [人臉光照處理]Xiaohua Xie, Wei-Shi Zheng, Jianhuang Lai, and Ching Y. Suen. Restoration of a Frontal Illuminated Face Image Based on KPCA. In: Proceedings of International Conference on Pattern Recognition (ICPR), Istanbul, Turkey, 2010. (Oral)
  • [人臉光照處理]Wei Ma,Xiaohua Xie, Chong Yiny, and Jianhuang Lai. Face Image Illumination Processing Based on Generative Adversarial Nets. In: Proceedings of International Conference on Pattern Recognition (ICPR), Beijing, 2018.
  • [光流估計]Jun Chen, Zemin Cai, Jianhuang Lai,Xiaohua Xie. A Filtering Based Framework For Optical Flow Estimation. IEEE Trans. on Circuits and Systems for Video Technology (TCSVT), 2019, 29 (5): 1350-1364. (ISI-JCR 1區,CCF B類)
  • [光流估計]Jun Chen, Jianhuang Lai, Zemin Cai,Xiaohua Xie. Fast Optical Flow Estimation Based on Split Bregman Method. IEEE Transactions on Circuits and Systems for Video Technology (TCSVT). 28(3): 664-678, March 2018. (ISI-JCR1區,CCF B類)
  • [光流估計]Jun Chen, Zemin Cai, Jianhuang Lai,Xiaohua Xie. Efficient Segmentation-Based PatchMatch for Large Displacement Optical Flow Estimation. IEEE Transactions on Circuits and Systems for Video Technology (TCSVT). 2018.(ISI-JCR1區,CCF B類)[光流估計]Ling Mei, Jianhuang Lai,Xiaohua Xie, Junyong Zhu, Jun Chen. Illumination-Invariance Optical Flow Estimation Using Weighted Regularization Transform. IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2019.(ISI-JCR1區,CCF B類)
  • [視覺識別深度學習]Guangcong Wang,Xiaohua Xie, Jianhuang Lai, Jiaxuan Zhuo. Deep Growing Learning. International Conference on Computer Vision (ICCV), 2017.(CCF A類)
  • [視覺識別深度學習]Lingxiao Yang andXiaohua Xie. Max-margin Analysis Based Patch Sampling for Discovery of Mid-Level Parts. In:Proceedings of International Conference on Image Processing (ICIP), Quebec, Canada, 2015, pp.2214-2218. (Oral)
  • [視覺識別深度學習]Lingxiao Yang,Xiaohua Xie, Jianhuang Lai. Learning Discriminative Visual Elements using Part-based Convolutional Neural Network.Neurocomputing, 316 (2018): 135-143. (ISI-JCR1區)
  • [視覺識別深度學習]Lingxiao Yang,Xiaohua Xie, Peihua Li, David Zhang, Lei Zhang. Part-based Convolutional Neural Network for Visual Recognition. IEEEInternational Conference on Image Processing(ICIP), 2017. (Oral)
  • [多種材料識別]Xiaohua Xie,Lingxiao Yang, Wei-Shi Zheng. Learning Object-Specific DAGs for Multi-Label Material Recognition. Computer Vision and Image Understanding(CVIU), 143 (2016): 183-190. (CCF B類)
  • [多種材料識別]Lingxiao Yang,Xiaohua Xie. Exploiting Object Semantic Cues for Multi-label Material Recognition.Neurocomputing, vol. 173, part 3, January 2016, P. 1646-1654 (ISI-JCR 1區).
  • [圖像本徵屬性分解]Guangyun Han,Xiaohua Xie, Jianhuang Lai, Wei-Shi Zheng. Learning an Intrinsic Image Decomposer Using Synthesized RGB-D Dataset.IEEE Signal Processing Letters, 25 (6): 753-757, June 2018.
  • [圖像本徵屬性分解]Xiaohua Xie, Wenyong Gong, Minglun Gong, Tieru Wu. Recovering Intrinsic Images From Image Sequences Using Total Variation Models. In:Proceedings of International Conference on Image Processing (ICIP), Quebec, Canada, 2015, pp. 3570 - 3574.
  • [圖像本徵屬性分解]Guangyun Han,Xiaohua Xie, Wei-Shi Zhengz and Jianhuang Lai. Learning Intrinsic Image Decomposition by Deep Neural Network with Perceptual Loss. In: Proceedings of International Conference on Pattern Recognition (ICPR), Beijing, 2018.
  • [超解析度]Zhanxiang Feng, Jianhuang Lai,Xiaohua Xie,Junyong Zhu. Image super-resolution via a densely connected recursive network.Neurocomputing, 316 (2018): 270-276.(ISI-JCR1區)
  • [超解析度]Yan Liang,Xiaohua Xie, and Jian-Huang Lai. Face hallucination based on morphological component analysis.Signal Processing, Volume 93, Issue 2, February 2013, Pages 445–458. (ISI-JCR1區)
  • [超解析度]Yan Liang, Jian-huang Lai,Xiaohua Xie, and Wanquan Liu. Face Hallucination under an Image Decomposition Perspective. In: Proceedings of International Conference on Pattern Recognition (ICPR), Istanbul, Turkey, 2010. (Oral)
  • [超解析度]Zhanxiang Feng, Jian-huang Lai,Xiaohua Xie, Dakun Yang, Ling Mei. Face Hallucination by Deep Traversal Network. In: Proceedings of International Conference on Pattern Recognition (ICPR), Cancun, Mexico, 2016. (Oral
  • [人臉三維重構]Jian-Fang Hu, Wei-Shi Zheng,Xiaohua Xie, and Jianhuang Lai. Sparse Transfer for Facial Shape-from-Shading.Pattern Recognition, vol. 68, August 2017: 272–285. (ISI-JCR1區,CCF B類)
  • [手繪三維建模]Xiaohua Xie, Kai Xu, Niloy J. Mitra, Daniel Cohen-Or, Wenyong Gong, Qi Su, Baoquan Chen. Sketch-to-Design: Context-based Part Assembly.Computer Graphics Forum, 32 (8), 2013, pp. 233–245. (ISI-JCR1區,CCF B類)
  • [圖形格線化]Wenyong Gong,Xiaohua Xie, Rui Ma, Tieru Wu. Angle-Preserving Quadrilateral Mesh Parameterization.IEEE Computer Graphics and Applications, 2015, 35(6), 51-59.
  • [視頻目標分割]Zixuan Chen, Chunchao Guo, Jianhuang Lai,Xiaohua Xie. Motion-Appearance Interactive Encoding for Object Segmentation in Unconstrained Videos. IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2019. (ISI-JCR 1區,CCF B類)
  • [人臉識別]Rui Huang,Xiaohua Xie, Zhanxiang Feng, Jianhuang Lai. Face Recognition by Landmark Pooling-based CNN with Concentrate Loss. IEEEInternational Conference on Image Processing(ICIP), 2017. (Oral)
  • [人臉美化]Xi Lu, Xiaobin Chang,Xiaohua Xie, Jian-Fang Hu and Wei-Shi Zheng. Facial Skin Beautification via Sparse Representation Over Learned Layer Dictionary. In proceedings of International Joint Conference on Neural Networks (IJCNN), Oct. 2016.
  • [猴臉檢測]Manning Zhang, Susu Guo,Xiaohua Xie. Towards Automatic Detection of Monkey Faces. In: Proceedings of International Conference on Pattern Recognition (ICPR), Beijing, 2018.
  • [醫學圖像分析]Hongwei Li, Hao Huang, Wei-Shi Zheng,Xiaohua Xie, Jianguo Zhang. HEp-2 Specimen Classification via Deep CNNs and Pattern Histogram. In: Proceedings of International Conference on Pattern Recognition (ICPR), Cancun, Mexico, 2016.

相關詞條

熱門詞條

聯絡我們