参考文献：
[1].Stevens K A. The vision of David Marr[J]. Perception, 2012, 41(9): 1061-1072.
[2].Dalal N, Triggs B. Histograms of oriented gradients for human detection[C] 2005 IEEE computer society conference on computer vision and pattern recognition (CVPR'05). Ieee, 2005, 1: 886-893.
[3].Ojala T, Pietik?inen M, Harwood D. A comparative study of texture measures with classification based on featured distributions[J]. Pattern recognition, 1996, 29(1): 51-59.
[4].Dosovitskiy A, Beyer L, Kolesnikov A, et al. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale[C] International Conference on Learning Representations. 2020.
[5].Liu Z, Lin Y, Cao Y, et al. Swin transformer: Hierarchical vision transformer using shifted windows[C] Proceedings of the IEEE International Conference on Computer Vision, 2021.
[6].Ganin Y, Lempitsky V. Unsupervised domain adaptation by backpropagation[C] International conference on machine learning. PMLR, 2015: 1180-1189.
[7].He K, Fan H, Wu Y, et al. Momentum contrast for unsupervised visual representation learning[C] Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2020: 9729-9738.
[8].Kenneth Marino, Ruslan Salakhutdinov, Abhinav Gupta; The More You Know: Using Knowledge Graphs for Image Classification [C] Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, pp. 2673-2681
[9].Wang G, Wang K, Wang G, et al. Solving Inefficiency of Self-supervised Representation Learning[C]. Proceedings of the IEEE International Conference on Computer Vision, 2021.
[10].Lin L, Gao Y, Gong K, et al. Graphonomy: Universal Image Parsing via Graph Reasoning and Transfer[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020.
[11].Qingxing Cao, Bailin Li, Xiaodan Liang, Keze Wang, and Liang Lin, “Knowledge-Routed Visual Question Reasoning: Challenges for Deep Representation Embedding”, IEEE Transactions on Neural Networks and Learning Systems (T-NNLS)
[12].Sekhon, Jasjeet S. "The Neyman-Rubin model of causal inference and estimation via matching methods." The Oxford handbook of political methodology 2 (2008): 1-32.
[13].Pearl, Judea, and Dana Mackenzie. The book of why: the new science of cause and effect. Basic books, 2018.
[14].H. Reichenbach. The Direction of Time. University of California Press, Berkeley, CA, 1956.
[15].Sch?lkopf B, Locatello F, Bauer S, et al. Toward causal representation learning[J]. Proceedings of the IEEE, 2021, 109(5): 612-634.
林倞教授简介

文章图片

林倞 ， 中山大学计算机学院教授 / 博导 ， 国家优秀青年基金获得者 ， 教育部超算工程软件工程研究中心副主任 ， IET Fellow ， 先后在美国加州大学洛杉矶分校、香港中文大学等机构工作或访问研究 。 长期致力于视觉计算与推理学习的基础研究 ， 提出认知模型引导的视觉表征学习理论和方法体系 ， 包括结构化视觉语法模型、长效自主学习等基础方法 ， 深入探索面向海量复杂视觉数据的模型泛化和推广能力 ， 迄今在国际知名学术期刊与会议上发表论文 200 余篇 ， 论文被引用接近 2 万次 。 获得 ICME 2017 最佳论文钻石奖 ， Pattern Recognition 期刊年度最佳论文奖 ， ICCV 2019 最佳论文提名；指导学生获得 ACM 中国区优秀博士论文奖(每年度 2 名)、中国计算机学会优秀博士论文奖；作为第一完成人获得 2018 年度吴文俊人工智能自然科学奖、2019 年度中国图像图形学会科学技术一等奖 。