{"type":"ScholarlyArticle","title":"Motion Invariance in Visual Environments","authors":[{"name":"Alessandro Betti","slug":"alessandro-betti","given":"Alessandro","family":"Betti","affiliation":"University of Florence , Florence , Italy; DIISM , University of Siena , Siena , Italy"},{"name":"Marco Gori","slug":"marco-gori","given":"Marco","family":"Gori","affiliation":"DIISM , University of Siena , Siena , Italy"},{"name":"Stefano Melacci","slug":"stefano-melacci","given":"Stefano","family":"Melacci","affiliation":"DIISM , University of Siena , Siena , Italy"}],"abstract":"The puzzle of computer vision might find new challenging solutions when we realize that most successful methods are working at image level, which is remarkably more difficult than processing directly visual streams, just as it happens in nature. In this paper, we claim that the processing of a stream of frames naturally leads to formulate the motion invariance principle, which enables the construction of a new theory of visual learning based on convolutional features. The theory addresses a number of intriguing questions that arise in natural vision, and offers a well-posed computational scheme for the discovery of convolutional filters over the retina. They are driven by the Euler- Lagrange differential equations derived from the principle of least cognitive action, that parallels the laws of mechanics. Unlike traditional convolutional networks, which need massive supervision, the proposed theory offers a truly new scenario in which feature learning takes place by unsupervised processing of video signals. An experimental report of the theory is presented where we show that features extracted under motion invariance yield an improvement that can be assessed by measuring information-based indexes.","doi":"10.24963/ijcai.2019/278","url":"https://ijcai.org/proceedings/2019/278","pdf":"https://ijcai.org/proceedings/2019/0278.pdf","markdown":"https://ijcai.org/proceedings/2019/278.md","bibtex":"https://ijcai.org/proceedings/2019/bibtex/278","volume":{"slug":"2019","title":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2019","url":"https://ijcai.org/proceedings/2019/","year":2019,"location":"Macao","dates":"10-16 August 2019","editors":"Sarit Kraus","isbn":"978-0-9992411-4-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2019"},"section":"Machine Learning A-L","track":"Main track","number":278,"pages":{"first":2009,"last":2015},"keywords":["Machine Learning: Unsupervised Learning","Computer Vision: Computer Vision","Machine Learning: Learning Theory","Computer Vision: Motion and Tracking"],"videos":[],"references":[{"position":1,"raw":"[Anderson and Rosenfeld, 1988] J.A. Anderson and E. Rosenfeld, editors. Neurocomputing: Foundations of Research. MIT Press, Cambridge, 1988.","title":"Neurocomputing: Foundations of Research","authors":"Anderson, Rosenfeld","year":"1988","venue":null,"doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Baker et al., 2011] Simon Baker, Daniel Scharstein, J. P. Lewis, Stefan Roth, Michael J. Black, and Richard Szeliski. A database and evaluation methodology for opti- cal flow. Int. J. Comput. Vision, 92(1):1-31, March 2011.","title":"A database and evaluation methodology for optical flow","authors":"Simon Baker, J P Daniel Scharstein, Stefan Lewis, Michael J Roth, Richard Black, Szeliski","year":"2011","venue":"Int. J. Comput. Vision","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Betti and Gori, 2016] Alessandro Betti and Marco Gori. The principle of least cognitive action. Theor. Comput. Sci., 633:83-99, 2016.","title":"The principle of least cognitive action","authors":"Alessandro Betti, Marco Gori","year":"2016","venue":"Theor. Comput. Sci","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Deng et al., 2009] J. Deng, W. Dong, R. Socher, L.-J. Li, K. Li, and L. Fei-Fei. ImageNet: A Large-Scale Hierar- chical Image Database. In CVPR09, pages 248-255, 2009.","title":"ImageNet: A Large-Scale Hierarchical Image Database","authors":"J Deng, W Dong, R Socher, L.-J Li, K Li, L Fei-Fei","year":"2009","venue":"CVPR09","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Goodale and Milner, 1992] Melvyn A. Goodale and A. David. Milner. Separate visual pathways for perception and action. Trends in Neurosciences, 15(1):20-25, 1992.","title":"Separate visual pathways for perception and action","authors":"Melvyn A Goodale, A David, Milner","year":"1992","venue":"Trends in Neurosciences","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Gori et al., 2012] Marco Gori, Stefano Melacci, Marco Lippi, and Marco Maggini. Information theoretic learn- ing for pixel-based visual agents. In European Conference on Computer Vision, pages 864-875. Springer, 2012.","title":"Information theoretic learning for pixel-based visual agents","authors":"Marco Gori, Stefano Melacci, Marco Lippi, Marco Maggini","year":"2012","venue":"European Conference on Computer Vision","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Gori et al., 2016] Marco Gori, Marco Lippi, Marco Mag- gini, and Stefano Melacci. Semantic video labeling by developmental visual agents. Computer Vision and Image Understanding, 146:9-26, 2016.","title":"Semantic video labeling by developmental visual agents","authors":"Marco Gori, Marco Lippi, Marco Maggini, Stefano Melacci","year":"2016","venue":"Computer Vision and Image Understanding","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Horn and Schunck, 1981] B. K.P. Horn and B.G. Schunck. Determining optical flow. Artificial Intelligence, 17(1- 3):185-203, 1981.","title":"Determining optical flow","authors":"B K P Horn, B G Schunck","year":"1981","venue":"Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Huang et al., 2007] Fu Jie Huang, Y-Lan Boureau, Yann LeCun, et al. Unsupervised learning of invariant feature hi- erarchies with applications to object recognition. In Com- puter Vision and Pattern Recognition, 2007. CVPR'07. IEEE Conference on, pages 1-8. IEEE, 2007.","title":"Unsupervised learning of invariant feature hierarchies with applications to object recognition","authors":"Jie Fu, Y-Lan Huang, Yann Boureau, Lecun","year":"2007","venue":"Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Kavukcuoglu et al., 2010] Koray Kavukcuoglu, Pierre Ser- manet, Y lan Boureau, Karol Gregor, Michael Mathieu, and Yann L. Cun. Learning convolutional feature hierar- chies for visual recognition. In J. D. Lafferty, C. K. I. Williams, J. Shawe-Taylor, R. S. Zemel, and A. Culotta, editors, Advances in Neural Information Processing Sys- tems 23, pages 1090-1098.","title":"Learning convolutional feature hierarchies for visual recognition","authors":"Koray Kavukcuoglu, Pierre Sermanet, Y Lan Boureau, Karol Gregor, Michael Mathieu, Yann L Cun","year":null,"venue":"Advances in Neural Information Processing Systems 23","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"Curran Associates, Inc., 2010.","title":null,"authors":"Curran Associates, Inc","year":"2010","venue":null,"doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Li et al., 2016] Yin Li, Manohar Paluri, James M Rehg, and Piotr Dollár. Unsupervised learning of edges. In Proceed- ings of the IEEE Conference on Computer Vision and Pat- tern Recognition, pages 1619-1627, 2016.","title":"Unsupervised learning of edges","authors":"Yin Li, Manohar Paluri, James M Rehg, Piotr Dollár","year":"2016","venue":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Lowe, 2004] D. Lowe. Distinctive image features from scale-invariant keypoints. International Journal of Com- puter Vision, 60(2):91-110, 2004.","title":"Distinctive image features from scale-invariant keypoints","authors":"D Lowe","year":"2004","venue":"International Journal of Computer Vision","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Marr, 1982] D. Marr. Vision. Freeman, San Francisco, 1982. Partially reprinted in [Anderson and Rosenfeld, 1988].","title":"Vision. Freeman","authors":"D Marr","year":"1982","venue":null,"doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Marszałek et al., 2009] Marcin Marszałek, Ivan Laptev, and Cordelia Schmid. Actions in context. In IEEE Conference on Computer Vision & Pattern Recognition, pages 2929- 2936, 2009.","title":"Actions in context","authors":"Marcin Marszałek, Ivan Laptev, Cordelia Schmid","year":"2009","venue":"IEEE Conference on Computer Vision & Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Melacci and Gori, 2012] Stefano Melacci and Marco Gori. Unsupervised learning by minimal entropy encoding. IEEE Trans. Neural Netw. Learning Syst., 23(12):1849- 1861, 2012.","title":"Unsupervised learning by minimal entropy encoding","authors":"Gori Melacci, Stefano Melacci, Marco Gori","year":"2012","venue":"IEEE Trans. Neural Netw. Learning Syst","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Pathak et al., 2017] Deepak Pathak, Ross B Girshick, Piotr Dollár, Trevor Darrell, and Bharath Hariharan. Learning features by watching objects move. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recog- nition, pages 2701-2710, 2017.","title":"Learning features by watching objects move","authors":"Deepak Pathak, Ross B Girshick, Piotr Dollár, Trevor Darrell, Bharath Hariharan","year":"2017","venue":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Poggio and Anselmi, 2016] Tomaso A. Poggio and Fabio Anselmi. Visual Cortex and Deep Networks: Learning In- variant Representations. The MIT Press, 1st edition, 2016.","title":"Visual Cortex and Deep Networks: Learning Invariant Representations","authors":"A Tomaso, Fabio Poggio, Anselmi","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Sun et al., 2014] Lin Sun, Kui Jia, Tsung-Han Chan, Yuqiang Fang, Gang Wang, and Shuicheng Yan. Dl-sfa: deeply-learned slow feature analysis for action recogni- tion. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 2625-2632, 2014.","title":"Dl-sfa: deeply-learned slow feature analysis for action recognition","authors":"Lin Sun, Kui Jia, Tsung-Han Chan, Yuqiang Fang, Gang Wang, Shuicheng Yan","year":"2014","venue":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Wang and Gupta, 2015] Xiaolong Wang and Abhinav Gupta. Unsupervised learning of visual representations using videos. In Proceedings of the IEEE International Conference on Computer Vision, pages 2794-2802, 2015.","title":"Unsupervised learning of visual representations using videos","authors":"Wang, Gupta, Xiaolong Wang, Abhinav Gupta","year":"2015","venue":"Proceedings of the IEEE International Conference on Computer Vision","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Wiskott and Sejnowski, 2002] Laurenz Wiskott and Ter- rence J Sejnowski. Slow feature analysis: Unsupervised learning of invariances. Neural computation, 14(4):715- 770, 2002.","title":"Slow feature analysis: Unsupervised learning of invariances","authors":"Laurenz Wiskott, Terrence J Sejnowski","year":"2002","venue":"Neural computation","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}