---

一、个人基本信息
梁小丹，副教授，硕士生导师，中山大学“****”人才引进，主要从事机器学习、计算机视觉、智慧医疗等方面的研究。
电子邮箱： xdliang328@gmail.com
个人主页：https://lemondan.github.io

---

二、个人基本简历
2016年毕业于中山大学获得博士学位
2014年到2016年期间于新加坡国立大学访问交流
2016年7月到2018年在美国卡内基梅隆大学任职研究员
2018年10月任职中山大学

---

三、学科方向
机器学习，计算机视觉，自然语言理解，智慧医疗，智能驾驶

---

四、科研项目
1.国家自然科学基金面上项目（主持, 2020.01~2023.12）
2.国家自然科学区域联合基金重点项目（合作单位负责人, 2020.01~2023.12）
3.广东省基础与应用基础研究基金-重点项目（主持, 2020.01~2022.12）

---

五、论著专利
1.Xiaodan Liang, Si Liu, Xiaohui Shen, Jianchao Yang, Luoqi Liu, Jian Dong, Liang Lin, Shuicheng Yan. Deep Human Parsing with Active Template Regression. IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 37(12): 2402-2414, 2015. (SCI, 中科院一分区, 影响因子: 9.455)
2.Xiaodan Liang, Liang Lin, Yunchao Wei, Xiaohui Shen, Jianchao Yang, Shuicheng Yan. Proposal-free Network for Instance-level Semantic Object Segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), DOI: 10.1109/TPAMI.2017.**, 2017. (SCI,中科院一分区, 影响因子: 9.455)
3.Xiaodan Liang, Yunchao Wei, YunPeng Chen, Jianchao Yang, Liang Lin, Shuicheng Yan. Learning to Segment Human by Watching YouTube. IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), 39(7): 1462-1468, 2017. (SCI, 中科院一分区, 影响因子: 9.455)
4.Xiaodan Liang, Chunyan Xu, Xiaohui Shen, Jianchao Yang, Jinhui Tang, Liang Lin, Shuicheng Yan. Human Parsing with Contextualized Convolutional Neural Network. IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), 39(1): 115-127, 2017. (SCI, 中科院一分区, 影响因子: 9.455)
5.Xiaodan Liang, Ke Gong, Xiaohui Shen, Liang Lin. Look into Person: Joint Human Parsing and Pose Estimation Network and a New Benchmark. IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), 2018. (SCI,中科院JCR一区, 影响因子: 9.455)
6.Xiaodan Liang, Liang Lin, Qingxing Cao, Rui Huang, and Yongtian Wang. Recognizing Focal Liver Lesions in CEUS with Dynamically Trained Latent Structured Models. IEEE Transactions on Medical Imaging (T-MI), 35(3): 713-727, 2016. (SCI,中科院JCR一区, 影响因子: 6.131)
7.Xiaodan Liang, Liang Lin, Wei Yang, Ping Luo, Junshi Huang, and Shuicheng Yan. Clothes Co-Parsing via Joint Image Segmentation and Labeling with Application to Clothing Retrieval. IEEE Transactions on Multimedia (T-MM), 18(6): 1175-1186, 2016. (SCI,中科院JCR二区, 影响因子: 3.977)
8.Xiaodan Liang, Zhiting Hu, Hao Zhang, Liang Lin, Eric P. Xing. Symbolic Graph Reasoning Meets Convolutions. Conference on Neural Information Processing Systems (NIPS), 2018. (机器学习领域旗舰会议)
9.Chenhan Jiang, Hang Xu, Xiaodan Liang*, Liang Lin. Hybrid Knowledge Routed Modules for Large-scale Object Detection. Conference on Neural Information Processing Systems (NIPS), 2018. (机器学习领域旗舰会议, 通讯作者)
10.Xiaodan Liang, Lisa Lee, Eric P. Xing. Deep Variation-structured Reinforcement Learning for Visual Relationship and Attribute Detection. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017. (计算机视觉领域旗舰会议)
11.Haoye Dong,Xiaodan Liang, Ke Gong, Hanjiang Lai, Jia Zhu, Jian Yin. Soft-Gated Warping-GAN for Pose-Guided Person Image Synthesis. NIPS 2018
12.Zhiting Hu, Zichao Yang, Ruslan Salakhutdinov,Xiaodan Liang, Lianhui Qin, Haoye Dong, Eric Xing. Deep Generative Models with Learnable Knowledge Constraints. NIPS 2018
13.Generative Semantic Manipulation with Mask-Contrasting GAN
14.Xiaodan Liang, Hao Zhang, Eric P. Xing. ECCV 2018.
15.CIRL: Controllable Imitative Reinforcement Learning for Vision-based Self-driving
16.Xiaodan Liang, Tairui Wang, Luona Yang, Eric P. Xing. ECCV 2018.
17.Instance-level Human Parsing via Part Grouping Network(Oral)
18.Ke Gong,Xiaodan Liang, Yicheng Li, Yimin Chen, Liang Lin. ECCV 2018.
19.Adversarial Geometry-Aware Human Motion Prediction(Oral)
20.Liangyan Gui,Xiaodan Liang, Yuxiong Wang, Jose M.F. Moura. ECCV 2018.
21.Real-to-Virtual Domain Unification for End-to-End Autonomous Driving
22.Luona Yang,Xiaodan Liang, Eric P. Xing. ECCV 2018.
23.Toward Characteristic-Preserving Image-based Virtual Try-On Network
24.Bochao Wang, Huabin Zheng,Xiaodan Liang,Yimin Chen, Liang Lin. ECCV 2018.
25.RCAA: Relational Context-Aware Agents for Person Search
26.Xiaojun Chang, Po-Yao Huang,Xiaodan Liang, Yi Yang, Alexander Hauptmann. ECCV 2018.
27.A Modulation Module for Multi-task Learning with Applications in Image Retrieval
28.Xiangyun Zhao, Haoxiang Li, Xiaohui Shen,Xiaodan Liang, Ying Wu. ECCV 2018.
29.Adaptive Temporal Encoding Network for Video Instance-level Human Parsing
30.Qixian Zhou,Xiaodan Liang, Ke Gong, Liang Lin. ACM MM 2018.
31.Teaching Robots to Predict Human Motion. Liangyan Gui, Kevin Zhang, Yuxiong Wang,Xiaodan Liang, Jose M.F. Moura, Manuela Veloso. IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2018. (Oral)
32.Unsupervised Domain Adaptation for Automatic Estimation of Cardiothoracic Ratio
33.Nanqing Dong, Michael C. Kampffmeyer,Xiaodan Liang, Zeya Wang, Wei Dai, Eric P. Xing. MICCAI 2018
34.StepDeep: A Novel Spatial-temporal Mobility Event Prediction Framework based on Deep Neural Network. Bilong Shen,Xiaodan Liang, Yufeng Ouyang, Miaofeng Liu, Weimin Zheng, Kathleen M. Carley. KDD 2018
35.Dynamic-structured Semantic Propagation Network
36.Xiaodan Liang, Hongfei Zhou, Eric P. Xing. CVPR 2018
37.Visual Question Reasoning on General Dependency Tree
38.Qingxing Cao,Xiaodan Liang, Bailing Li, Guanbin Li, Liang Lin. CVPR 2018. (Spotlight)
39.Reinforcement Cutting-Agent Learning for Video Object Segmentation
40.Junwei Han, Le Yang, Dingwen Zhang, Xiaojun Chang,Xiaodan Liang. CVPR 2018. (Spotlight)

---

六、荣誉获奖情况
1. 2019 阿里巴巴达摩院青橙奖
2. 2019 吴文俊人工智能优秀青年奖
3. 2018 国际计算机人工智能学会ACM China 优秀博士论文奖(中国地区每年共2名)
4.2018中国计算机学会优秀博士论文奖(每年10名)
5.国家级2011高性能计算协同创新中心优秀博士论文奖（每年10名）

---

七、主要兼职
1.国际知名期刊Pattern Recognition Letters 和journal of Multimedia Tools and Applications的客座编辑
2.Programm Committee member of CVPR 2017, IJCAI 2017-2018, AAAI 2017-2019. Reviewer for TPAMI, IJCV, TKDE, TMM, TIP, TNNLS, TCSVT, and so on。
3.Reviewer for CVPR, ECCV, ACM MM, AAAI, NIPS, IJCAI, and so on

---

八、社会服务
在人工智能顶级国际会议CVPR 2017，CVPR 2018上，作为主要组织者承办了复杂场景下的人物分析研讨会和标准竞赛。提出第一个规范的评测标准和平台，包含了现实场景中大部分主要的难点（例如半身，遮挡和不同角度），并且提供了一系列基准方法结果便于比较。该竞赛受到了来自国际顶尖高校和工业界的14只队伍的广泛关注和参与，例如英国牛津大学，台湾清华大学，阿里巴巴和三星研究院,具有较大的国际影响力。也受邀在顶级国际会议ACM MM 2018上组织和举办面向像素级别理解深度结构化模型的讲座研讨会，将为与会的近2000名计算机领域专业人士做大会特邀报告。 受邀在国际顶级学术会议(ECCV, CVPR, ICCV, ACM MM)给了十二次大会口头报告介绍她在图像复杂模式解析和结构化模型的主要研究贡献。

---