陶大程

陶大程

主要研究方向： 机器学习、深度学习、计算机视觉、数据挖掘、图像与多媒体信息处理

陶大程博士目前是中国科学技术大学大师讲席教授、悉尼大学数字科学研究院首席科学家和顾问。他的主要研究方向是：机器学习、深度学习、计算机视觉、数据挖掘、图像与多媒体信息处理等。陶教授两度荣获澳大利亚尤里卡奖，是ACM/AAAS/IEEE/IAPR/OSA/SPIE Fellow、澳大利亚科学院院士，连续6年入选全球高被引科学家。

Dacheng Tao is a Grand Master Chair Professor (visiting track) in University of Science and Technology of China and an advisor and Chief Scientist of Digital Science Institute in the University of Sydney. He received his BEng from USTC, MPhil from the Chinese University of Hong Kong, and PhD from the University of London. He mainly applies statistics and mathematics to artificial intelligence and data science. His research is detailed in one monograph and over 200 publications in prestigious journals and proceedings at prominent conferences such as IEEE TPAMI, IJCV, NeurIPS (or NIPS), ICML, CVPR, ICCV, ECCV, AAAI, IJCAI, ICDM and ACM SIGKDD, with several best paper awards, such as the Best Theory/Algorithm Paper Runner Up Award at IEEE ICDM’07, the Distinguished Paper Award at 2018 IJCAI, the 2014 ICDM 10-year Highest-Impact Paper Award, and the 2017 IEEE Signal Processing Society Best Paper Award. He received the 2015 Australian Scopus-Eureka Prize, the 2020 Australian Eureka Prize for Excellence in Data Science, and the 2018 IEEE ICDM Research Contributions Award. He is a fellow of the Australian Academy of Science, AAAS, ACM and IEEE.

主要奖项：

1. November 2020, Australian Museum Eureka Prize for Excellence in Data Science

2. November 2020, Vice-Chancellor’s Award for Outstanding Research, The University of Sydney.

3. June 2020, IEEE TCSC (IEEE Computer Society Technical Committee on Scalable Computing) Most Influential Paper Award for “Tianyi Zhou, Dacheng Tao: GoDec: Randomized Lowrank & Sparse Matrix Decomposition in Noisy Case. ICML 2011: 33-40”.

4. June 2019, IEEE CVPR Best Paper Award Finalist for (Huan Fu, Mingming Gong, Chaohui Wang, Kayhan Batmanghelich, Kun Zhang, and Dacheng Tao, “Geometry-Consistent Generative Adversarial Networks for One-Sided Unsupervised Domain Mapping”)

5. November 2018, IEEE ICDM Research Contributions Award for outstanding research contributions to the data mining field, Singapore, November 17-20, 2018.

6. July 2018, the IJCAI 2018 Distinguished Paper Award for “R-SVM+: Robust Learning with Privileged Information” at the International Joint Conference on Artificial Intelligence (IJCAI), Stockholm, Sweden, July 13-19, 2018.

7. October 2017, Andrew P. Sage Best Transactions Paper Award to “Jun Yu, Dacheng Tao, Meng Wang, and Yong Rui, Learning to Ranking using User Clicks and Visual Features for Image Retrieval, IEEE Transactions on Cybernetics, vol. 45, no. 4, pp. 767-779, April 2015”.

8. October 2015, the UTS Vice-Chancellor’s Medal for Exceptional Research

9. July 2015, the Australian Scopus-Eureka Prize

主要论著：

[1] Changxing Ding, Kan Wang, Pengfei Wang, and Dacheng Tao, “Multi-task Learning with Coarse Priors for Robust Part-aware Person Re-identification”, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), Accepted on 15 September 2020.

[2] Chen Gong, Shi Hong, Tongliang Liu, Chuang Zhang, Jian Yang, and Dacheng Tao, “Loss Decomposition and Centroid Estimation for Positive and Unlabeled Learning”, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), Accepted on 11 September 2019.

[3] Jiayan Qiu, Xinchao Wang, Pascal Fua, and Dacheng Tao, “Matching Seqlets: An Unsupervised Approach for Locality Preserving Sequence Matching”, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), Accepted on 5 August 2019.

[4] Jun Yu, Min Tan, Hongyuan Zhang, Yong Rui, and Dacheng Tao, “Hierarchical Deep Click Feature Prediction for Fine-grained Image Recognition”, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), Accepted on 28 July 2019.

[5] Zhe Chen, Jing Zhang, and Dacheng Tao, “Recursive Context Routing for Object Detection”, International Journal of Computer Vision (IJCV), Accepted on 8 August 2020.

[6] Chao Zhang, Xianjie Gao, Min-Hsiu Hsieh, Han, and Dacheng Tao, “Matrix Infinitely Divisible Series: Tail Inequalities and Their Applications”, IEEE Transactions on Information Theory (TIT), vol. 66, no. 2, pp. 1099-1177, February 2020.

[7] Yibing Zhan, Jun Yu, Ting Yu, and Dacheng Tao, “Multi-task Compositional Network for Visual Relationship Detection”, International Journal of Computer Vision (IJCV), vol. 128, no. 8, pp. 2146-2165, 2020.

[8] Long Lan, Xinchao Wang, H. Gang, Thomas Huang, and Dacheng Tao, “Semi-online Multi-people Tracking by Re-identification”, International Journal of Computer Vision (IJCV), vol. 128, no. 7, pp. 1937-1955, July 2020.

[9] Fengxiang He, Tongliang Liu, and Dacheng Tao, “Why ResNet Works? Residuals Generalize”, IEEE Transactions on Neural Networks and Learning Systems (TNNLS), vol. 31, no. 12, pp. 5349-5362, December 2020.

[10] Xikun Zhang, Chang Xu, Xinmei Tian, and Dacheng Tao, “Graph Edge Convolutional Neural Networks for Skeleton-Based Action Recognition”, IEEE Transactions on Neural Networks and Learning Systems (TNNLS), vol. 31, no. 8, pp. 3047-3060, August 2020.

[11] Jing Zhang and Dacheng Tao, “FAMED-Net: A Fast and Accurate Multi-scale End-to-end Dehazing Network,” IEEE Transactions on Image Processing (TIP), vol. 29, pp. 72-84, 2020.

[12] Yunhe Wang, Chang Xu, Chao Xu, and Dacheng Tao, “Packing Convolutional Neural Networks in the Frequency Domain”, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), vol. 41, no. 10, pp. 2495-2510, October 2019.

[13] Yong Luo, Yonggang Wen, Tongliang Liu, and Dacheng Tao, “Transferring Knowledge Fragments for Learning Distance Metric from a Heterogeneous Domain”, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), vol. 41, no. 4, pp. 1013-1026, April 2019.

[14] Chaoyue Wang, Chang Xu, Xin Yao, and Dacheng Tao, “Evolutionary Generative Adversarial Networks”, IEEE Transactions on Evolutionary Compuation (TEC), vol. 23, no. 6, pp. 921-934, June 2019.

[15] Baosheng Yu and Dacheng Tao, “Anchor Cascade for Efficient Face Detection”, IEEE Transactions on Image Processing (TIP), vol. 28, no. 5, pp. 2490-2501, May 2019.

[16] Xinyuan Chen, Chang Xu, Xiaokang Yang, and Dacheng Tao, “Gated-GAN: Adversarial Gated Networks for Multi-Collection Style Transfer”, IEEE Transactions on Image Processing (TIP), vol. 28, no. 2, pp. 546-560, February 2019.

[17] Liu Liu, Ji Liu, and Dacheng Tao, “Duality-free Methods for Stochastic Composition Optimization”, IEEE Transactions on Neural Networks and Learning Systems (TNNLS), vol. 30, no. 4, pp. 1205-1217, April 2019.

[18] Guoliang Kang, Jun Li, and Dacheng Tao, “Shakeout: A New Approach to Regularized Deep Neural Network Training”, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), vol. 40, no. 5, pp. 1245-1258, May 2018.

[19] Zhe Xu, Shaoli Huang, Ya Zhang, and Dacheng Tao, “Webly-supervised Fine-grained Visual Categorization via Deep Domain Adaptation”, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), vol. 40, no. 5, pp. 1100-1113, May 2018.

[20] Changxing Ding and Dacheng Tao, “Trunk-Branch Ensemble Convolutional Neural Networks for Video-based Face Recognition”, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), vol. 40, no. 4, pp. 1002-1014, April 2018.

[21] Haoyu He, Jing Zhang, Bhavani Thuraisingham, and Dacheng Tao, “Progressive One-shot Human Parsing”, the Thirty-fourth AAAI Conference on Artificial Intelligence (AAAI), pp. ***, Vancouver, Canada, February 2 – 9, 2021.

[22] Jun Yu, Hao Zhou, Yibing Zhan, and Dacheng Tao, “Deep Graph-neighbor Coherence Preserving Network for Unsupervised Cross-modal Hashing”, the Thirty-fourth AAAI Conference on Artificial Intelligence (AAAI), pp. ***, Vancouver, Canada, February 2 – 9, 2021.

[23] Benteng Ma, Jing Zhang, Yong Xia, and Dacheng Tao, “Auto Learning Attention”, Advances in Neural Information Processing Systems (NeurIPS), pp. **, Vancouver, Canada, December 6-12, 2020.

[24] Shanshan Zhao, Mingming Gong, Tongliang Liu, Huan Fu, and Dacheng Tao, “Domain Generalization via Entropy Regularization”, Advances in Neural Information Processing Systems (NeurIPS), pp. **, Vancouver, Canada, December 6-12, 2020.

[25] Youjian Zhang, Chaoyue Wang, and Dacheng Tao, “Generalized Video Frame Interpolation”, Advances in Neural Information Processing Systems (NeurIPS), pp. **, Vancouver, Canada, December 6-12, 2020.

[26] Xiaobo Xia, Tongliang Liu, Bo Han, Nannan Wang, Mingming Gong, Haifeng Liu, Gang Niu, Dacheng Tao, and Masashi Sugiyama, “Parts-dependent Label Noise: Towards Instance-dependent Label Noise”, Advances in Neural Information Processing Systems (NeurIPS), pp. **, Cancouver, Canada, December 6-12, 2020.

[27] Zhen Wang, Liu Liu, and Dacheng Tao, “Deep Streaming Label Learning”, International Conference on Machine Learning (ICML), Vienna, Austria, July 12-18, 2020.

[28] Jiaxian Guo, Mingming Gong, Tongliang Liu, Kun Zhang, and Dacheng Tao, “LTF: A Label Transformation Framework for Correcting Label Shift”, International Conference on Machine Learning (ICML), Vienna, Austria, July 12-18, 2020.

[29] Jiacheng Cheng, Tongliang Liu, Kotagiri Ramamohanarao, and Dacheng Tao, “Learning with Bounded Instance- and Label-dependent Label Noise”, International Conference on Machine Learning (ICML), Vienna, Austria, July 12-18, 2020.

[30] Xiyu Yu, Tongliang Liu, Mingming Gong, Kun Zhang, Kayhan Batmanghelich, and Dacheng Tao, “Label-Noise Robust Domain Adaptation”, International Conference on Machine Learning (ICML), Vienna, Austria, July 12-18, 2020.

[31] Xin Lin, Changxing Ding, Jinquan Zhang, and Dacheng Tao, “GPS-Net: Graph Property Sensing Network for Scene Graph Generation”, IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3743-3752, Seattle, Washington, USA, June 14-19, 2020.

[32] Tong Zhou, Changxing Ding, Shaowen Lin, Xinchao Wang, and Dacheng Tao, “Learning Oracle Attention for High-fidelity Face Completion”, IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7677-7686, Seattle, Washington, USA, June 14-19, 2020.

[33] Jingyuan Li, Ning Wang, Lefei Zhang, Bo Du, and Dacheng Tao, “Recurrent Feature Reasoning for Image Inpainting”, IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7757-7765, Seattle, Washington, USA, June 14-19, 2020.

[34] Qi Zheng, Chaoyue Wang, and Dacheng Tao, “Syntax-Aware Action Targeting for Video Captioning”, IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), pp. 13093-13102, Seattle, Washington, USA, June 14-19, 2020.

[35] Zhuo Chen, Chaoyue Wang, Bo Yuan, and Dacheng Tao, “PuppeteerGAN: Arbitrary Portrait Animation with Semantic-aware Appearance Transformation”, IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), pp. 13515-13524, Seattle, Washington, USA, June 14-19, 2020.

[36] Shurui Gui, Chaoyue Wang, Qihua Chen, and Dacheng Tao, “SemanticFlow: Robust Video Interpolation via Structure-to-texture Generation”, IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), pp. 14001-14010, Seattle, Washington, USA, June 14-19, 2020.

[37] Xikun Zhang, Chang Xu, and Dacheng Tao, “Context Aware Graph Convolution for Skeleton-Based Action Recognition”, IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), pp. 14321-14330, Seattle, Washington, USA, June 14-19, 2020.

[38] Yu-Tong Cao, Jingya Wang, and Dacheng Tao, “Symbiotic Adversarial Learning for Attribute-Based Person Search”, 16th European Conference on Computer Vision (ECCV), vol. *, pp. ***, Glasgow, United Kingdom, August 23-27, 2020.

[39] Zhi Hou, Xiaojiang Peng, Yu Qiao, and Dacheng Tao, “Visual Compositional Learning for Human Object Interaction Detection”, 16th European Conference on Computer Vision (ECCV), vol. *, pp. ***, Glasgow, United Kingdom, August 23-27, 2020.

[40] Jiayan Qiu, Yiding Yang, Xinchao Wang, and Dacheng Tao, “Hallucinating Visual Instances in Total Absentia”, 16th European Conference on Computer Vision (ECCV), vol. *, pp. ***, Glasgow, United Kingdom, August 23-27, 2020.

[41] Xubin Zhong, Changxing Ding, Xian Qu, and Dacheng Tao, “Polysemy Deciphering Network for Human-Object Interaction Detection”, 16th European Conference on Computer Vision (ECCV), vol. *, pp. ***, Glasgow, United Kingdom, August 23-27, 2020.

[42] Xinqi Zhu, Chang Xu, and Dacheng Tao, “Learning Disentangled Representations with Latent Variation Predictability”, 16th European Conference on Computer Vision (ECCV), vol. *, pp. ***, Glasgow, United Kingdom, August 23-27, 2020.

[43] Xikun Zhang, Chang Xu, and Dacheng Tao, “On Dropping Clusters to Regularize Graph Convolutional Neural Networks”, 16th European Conference on Computer Vision (ECCV), vol. *, pp. ***, Glasgow, United Kingdom, August 23-27, 2020.

[44] Haimei Zhao, Wei Bian, Bo Yuan, and Dacheng Tao, “Collaborative Learning of Depth Estimation, Visual Odometry and Camera Relocalization from Monocular Videos”, The 29th International Joint Conference on Artificial Intelligence and the 17th Pacific Rim International Conference on Artificial Intelligence (IJCAI), pp. 488-494, Yokohama, Japan, July 11-17, 2020.

[45] Haoyu He, Jing Zhang, Qiming Zhang, and Dacheng Tao, “Grapy-ML: Graph Pyramid Mutual Learning for Cross-dataset Human Parsing”, the Thirty-fourth AAAI Conference on Artificial Intelligence (AAAI), pp. 10949-10956, New York, USA, February 7 – 12, 2020.

[46] Fengxiang He, Bohan Wang, and Dacheng Tao, “Nonlinearities in activations substantially shape the loss surfaces of neural networks”, International Conference on Learning Representations (ICLR), pp. 1-45, Addis Ababa, Ethiopia, April 26-30, 2020.

[47] Zhuozhuo Tu, Fengxiang He, and Dacheng Tao, “Understanding Generalization in Recurrent Neural Networks”, International Conference on Learning Representations (ICLR), pp. 1-16, Addis Ababa, Ethiopia, April 26-30, 2020.

[48] Liang Ding, Longyue Wang, and Dacheng Tao, “Self-Attention with Cross-Lingual Position Representation”, the 58th Annual Conference of the Association for Computational Linguistics (ACL), pp. 1679-1685, Seattle, Washington, USA, July 5-10, 2020.

[49] Yu Cao, Wei Bi, Meng Fang, and Dacheng Tao, “Pretrained Language Models for Dialogue Generation with Multiple Input Sources”, Conference on Empirical Methods in Natural Language Processing (EMNLP – Findings), pp. **, Punta Cana, Dominican Republic, 16 – 20 November 2020.

[50] Jing Zhang, Yang Cao, Zheng-Jun Zha, and Dacheng Tao, “Nighttime Dehazing with a Synthetic Benchmark”, Twenty-eighth ACM SIGMM International Conference on Multimedia (MM), pp. ***, Seattle, United States, 12 - 16 October 2020.