{"type":"ScholarlyArticle","title":"AVA: Adversarial Vignetting Attack against Visual Recognition","authors":[{"name":"Binyu Tian","slug":"binyu-tian","given":"Binyu","family":"Tian","affiliation":"College of Intelligence and Computing , Tianjin University , China"},{"name":"Felix Juefei-Xu","slug":"felix-juefei-xu","given":"Felix","family":"Juefei-Xu","affiliation":"Alibaba Group , USA"},{"name":"Qing Guo","slug":"qing-guo","given":"Qing","family":"Guo","affiliation":"Nanyang Technological University , Singapore"},{"name":"Xiaofei Xie","slug":"xiaofei-xie","given":"Xiaofei","family":"Xie","affiliation":"Nanyang Technological University , Singapore"},{"name":"Xiaohong Li","slug":"xiaohong-li","given":"Xiaohong","family":"Li","affiliation":"College of Intelligence and Computing , Tianjin University , China"},{"name":"Yang Liu","slug":"yang-liu","given":"Yang","family":"Liu","affiliation":"Nanyang Technological University , Singapore"}],"abstract":"Vignetting is an inherent imaging phenomenon within almost all optical systems, showing as a radial intensity darkening toward the corners of an image. Since it is a common effect for photography and usually appears as a slight intensity variation, people usually regard it as a part of a photo and would not even want to post-process it. Due to this natural advantage, in this work, we study the vignetting from a new viewpoint, i.e., adversarial vignetting attack (AVA), which aims to embed intentionally misleading information into the vignetting and produce a natural adversarial example without noise patterns. This example can fool the state-of-the-art deep convolutional neural networks (CNNs) but is imperceptible to human. To this end, we first propose the radial-isotropic adversarial vignetting attack (RI-AVA) based on the physical model of vignetting, where the physical parameters (e.g., illumination factor and focal length) are tuned through the guidance of target CNN models. To achieve higher transferability across different CNNs, we further propose radial-anisotropic adversarial vignetting attack (RA-AVA) by allowing the effective regions of vignetting to be radial-anisotropic and shape-free. Moreover, we propose the geometry-aware level-set optimization method to solve the adversarial vignetting regions and physical parameters jointly. We validate the proposed methods on three popular datasets, i.e., DEV, CIFAR10, and Tiny ImageNet, by attacking four CNNs, e.g., ResNet50, EfficientNet-B0, DenseNet121, and MobileNet-V2, demonstrating the advantages of our methods over baseline methods on both transferability and image quality.","doi":"10.24963/ijcai.2021/145","url":"https://ijcai.org/proceedings/2021/145","pdf":"https://ijcai.org/proceedings/2021/0145.pdf","markdown":"https://ijcai.org/proceedings/2021/145.md","bibtex":"https://ijcai.org/proceedings/2021/bibtex/145","volume":{"slug":"2021","title":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2021","url":"https://ijcai.org/proceedings/2021/","year":2021,"location":"Montreal","dates":"19-27 August 2021","editors":"Zhi-Hua Zhou","isbn":"978-0-9992411-9-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2021"},"section":"Computer Vision II","track":"Main Track","number":145,"pages":{"first":1046,"last":1053},"keywords":["Machine Learning: Adversarial Machine Learning","Computer Vision: Recognition: Detection, Categorization, Indexing, Matching, Retrieval, Semantic Interpretation","Machine Learning: Classification"],"videos":[],"references":[{"position":1,"raw":"[Asada et al., 1996] Naoki Asada, Akira Amano, and Masashi Baba. Photometric calibration of zoom lens systems. In ICPR, volume 1, pages 186-190. IEEE, 1996.","title":"Photometric calibration of zoom lens systems","authors":"Naoki Asada, Akira Amano, Masashi Baba","year":"1996","venue":"ICPR","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Bhattad et al., 2019] Anand Bhattad, Min Jin Chong, Kaizhao Liang, Bo Li, and David A Forsyth. Unrestricted adver- sarial examples via semantic manipulation. arXiv preprint arXiv:1904.06347, 2019.","title":"Unrestricted adver-sarial examples via semantic manipulation","authors":"Anand Bhattad, Min, Jin Chong, Kaizhao Liang, Bo Li, David A Forsyth","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Carlini and Wagner, 2017] Nicholas Carlini and David Wagner. Towards evaluating the robustness of neural networks. In 2017 ieee symposium on security and privacy (sp), pages 39-57. IEEE, 2017.","title":"Towards evaluating the robustness of neural networks","authors":"Wagner Carlini, Nicholas Carlini, David Wagner","year":"2017","venue":"ieee symposium on security and privacy (sp)","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Chan and Vese, 2001] Tony F Chan and Luminita A Vese. Active contours without edges. IEEE TIP, 10(2):266-277, 2001.","title":"Active contours without edges","authors":"F Tony, Luminita A Chan, Vese","year":"2001","venue":"IEEE TIP","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Cheng et al., 2020a] Yupeng Cheng, Qing Guo, Felix Juefei-Xu, Xiaofei Xie, Shang-Wei Lin, Weisi Lin, Wei Feng, and Yang Liu. Pasadena: Perceptually aware and stealthy adversarial denoise attack. arXiv preprint arXiv:2007.07097, 2020.","title":"Pasadena: Perceptually aware and stealthy adversarial denoise attack","authors":"Cheng","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Cheng et al., 2020b] Yupeng Cheng, Felix Juefei-Xu, Qing Guo, Huazhu Fu, Xiaofei Xie, Shang-Wei Lin, Weisi Lin, and Yang Liu. Adversarial exposure attack on diabetic retinopathy imagery. arXiv preprint arXiv:2009.09231, 2020.","title":"Adversarial exposure attack on diabetic retinopathy imagery","authors":"Cheng","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Cheng et al., 2021] Ziyi Cheng, Xuhong Ren, Felix Juefei-Xu, Wanli Xue, Qing Guo, Lei Ma, and Jianjun Zhao. Deepmix: Online auto data augmentation for robust visual object tracking. arXiv preprint arXiv:2104.11585, 2021.","title":"Deepmix: Online auto data augmentation for robust visual object tracking","authors":"Ziyi Cheng, Xuhong Ren, Felix Juefei-Xu, Wanli Xue, Qing Guo, Lei Ma, Jianjun Zhao","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Croce and Hein, 2019] Francesco Croce and Matthias Hein. Sparse and imperceivable adversarial attacks. In Proceedings of the IEEE International Conference on Computer Vision, pages 4724-4732, 2019.","title":"Sparse and imperceivable adversarial attacks","authors":"Francesco Croce, Matthias Hein","year":"2019","venue":"Proceedings of the IEEE International Conference on Computer Vision","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Dong et al., 2018] Yinpeng Dong, Fangzhou Liao, Tianyu Pang, Hang Su, Jun Zhu, Xiaolin Hu, and Jianguo Li. Boosting ad- versarial attacks with momentum. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 9185-9193, 2018.","title":"Boosting adversarial attacks with momentum","authors":"Dong","year":"2018","venue":"Proceedings of the IEEE conference on computer vision and pattern recognition","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Dong et al., 2019] Yinpeng Dong, Tianyu Pang, Hang Su, and Jun Zhu. Evading defenses to transferable adversarial examples by translation-invariant attacks. In Proceedings of the IEEE Confer- ence on Computer Vision and Pattern Recognition, pages 4312- 4321, 2019.","title":"Evading defenses to transferable adversarial examples by translation-invariant attacks","authors":"Dong","year":"2019","venue":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Gao et al., 2020] Ruijun Gao, Qing Guo, Felix Juefei-Xu, Hongkai Yu, Xuhong Ren, Wei Feng, and Song Wang. Mak- ing images undiscoverable from co-saliency detection. arXiv preprint arXiv:2009.09258, 2020.","title":"Making images undiscoverable from co-saliency detection","authors":"Gao","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Gao et al., 2021] Ruijun Gao, Qing Guo, Felix Juefei-Xu, Hongkai Yu, and Wei Feng. Advhaze: Adversarial haze attack. arXiv preprint arXiv:2104.13673, 2021.","title":"Advhaze: Adversarial haze attack","authors":"Gao","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Goldman, 2010] Daniel B Goldman. Vignette and exposure cal- ibration and compensation. IEEE TPAMI, 32(12):2276-2288, 2010.","title":"Vignette and exposure calibration and compensation","authors":"Daniel B Goldman","year":"2010","venue":"IEEE TPAMI","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Gonzalez et al., 2004] Rafael C Gonzalez, Richard Eugene Woods, and Steven L Eddins. Digital image processing using MATLAB. Pearson Education India, 2004.","title":"Digital image processing using MATLAB","authors":"Richard Eugene Rafael C Gonzalez, Steven L Woods, Eddins","year":"2004","venue":null,"doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Goodfellow et al., 2014] Ian J Goodfellow, Jonathon Shlens, and Christian Szegedy. Explaining and harnessing adversarial exam- ples. arXiv preprint arXiv:1412.6572, 2014. [Google, 2017] Google. NIPS 2017: Adversarial Learn- ing Development Set. https://www.kaggle.com/google-brain/ nips-2017-adversarial-learning-development-set, 2017. Ac- cessed: 2021-01-20.","title":"Explaining and harnessing adversarial examples","authors":"Ian J Goodfellow, Jonathon Shlens, Christian Szegedy","year":"2014","venue":"Google. NIPS 2017: Adversarial Learning Development Set","doi":null,"url":"2021-01-20","internal_url":null},{"position":16,"raw":"[Guo et al., 2018] Qing Guo, Shuifa Sun, Xuhong Ren, Fangmin Dong, Bruce Zhi Gao, and Wei Feng. Frequency-tuned active contour model. Neurocomputing, 275:2307-2316, 2018.","title":"Frequency-tuned active contour model","authors":"Qing Guo, Shuifa Sun, Xuhong Ren, Fangmin Dong, Bruce Zhi Gao, Wei Feng","year":"2018","venue":"Neurocomputing","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Guo et al., 2020a] Chunle Guo, Chongyi Li, Jichang Guo, Chen Change Loy, Junhui Hou, Sam Kwong, and Runmin Cong. Zero-reference deep curve estimation for low-light image en- hancement. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 1780-1789, 2020.","title":"Zero-reference deep curve estimation for low-light image enhancement","authors":"Guo","year":"2020","venue":"Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Guo et al., 2020b] Qing Guo, Felix Juefei-Xu, Xiaofei Xie, Lei Ma, Jian Wang, Bing Yu, Wei Feng, and Yang Liu. Watch out! Motion is Blurring the Vision of Your Deep Neural Networks. NeurPIS, 33, 2020.","title":"Watch out! Motion is Blurring the Vision of Your Deep Neural Networks","authors":"Guo","year":"2020","venue":"NeurPIS","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Guo et al., 2020c] Qing Guo, Xiaofei Xie, Felix Juefei-Xu, Lei Ma, Zhongguo Li, Wanli Xue, Wei Feng, and Yang Liu. Spark: Spatial-aware online incremental attack against visual tracking. In Proceedings of the European Conference on Computer Vision (ECCV), volume 2. Springer, 2020.","title":"Spark: Spatial-aware online incremental attack against visual tracking","authors":"Guo","year":"2020","venue":"Proceedings of the European Conference on Computer Vision (ECCV)","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[He et al., 2016] Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Deep residual learning for image recognition. In Pro- ceedings of the IEEE conference on computer vision and pattern recognition, pages 770-778, 2016.","title":"Deep residual learning for image recognition","authors":"Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun","year":"2016","venue":"Proceedings of the IEEE conference on computer vision and pattern recognition","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Huang et al., 2017] Gao Huang, Zhuang Liu, Laurens Van Der Maaten, and Kilian Q Weinberger. Densely connected con- volutional networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 4700-4708, 2017.","title":"Densely connected convolutional networks","authors":"Gao Huang, Zhuang Liu, Laurens Van Der Maaten, Kilian Q Weinberger","year":"2017","venue":"Proceedings of the IEEE conference on computer vision and pattern recognition","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Juefei-Xu et al., 2021] Felix Juefei-Xu, Run Wang, Yihao Huang, Qing Guo, Lei Ma, and Yang Liu. Countering Malicious Deep- Fakes: Survey, Battleground, and Horizon. arXiv preprint arXiv:2103.00218, 2021.","title":"Countering Malicious Deep-Fakes: Survey, Battleground, and Horizon","authors":"Felix Juefei-Xu, Run Wang, Yihao Huang, Qing Guo, Lei Ma, Yang Liu","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Kang and Weiss, 2000] Sing Bing Kang and Richard Weiss. Can we calibrate a camera using an image of a flat, textureless lam- bertian surface? In ECCV, pages 640-653. Springer, 2000.","title":"Can we calibrate a camera using an image of a flat, textureless lambertian surface?","authors":"Weiss ; Kang, Bing Sing, Richard Kang, Weiss","year":"2000","venue":"ECCV","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Kass et al., 1988] Michael Kass, Andrew Witkin, and Demetri Ter- zopoulos. Snakes: Active contour models. International journal of computer vision, 1(4):321-331, 1988.","title":"Snakes: Active contour models","authors":"Michael Kass, Andrew Witkin, Demetri Terzopoulos","year":"1988","venue":"International journal of computer vision","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Kimia et al., 1992] Benjamin B Kimia, Allen Tannenbaum, and Steven W Zucker. On the evolution of curves via a function of curvature. I. The classical case. Journal of Mathematical Analy- sis and Applications, 163(2):438-458, 1992.","title":"On the evolution of curves via a function of curvature. I. The classical case","authors":"Allen Benjamin B Kimia, Steven W Tannenbaum, Zucker","year":"1992","venue":"Journal of Mathematical Analysis and Applications","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Krizhevsky and Hinton, 2009] Alex Krizhevsky and Geoffrey Hinton. Learning multiple layers of features from tiny images. Handbook of Systemic Autoimmune Diseases, 1(4), 2009.","title":"Learning multiple layers of features from tiny images","authors":"Alex Krizhevsky, Geoffrey Hinton","year":"2009","venue":"Handbook of Systemic Autoimmune Diseases","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Kurakin et al., 2016] Alexey Kurakin, Ian Goodfellow, and Samy Bengio. Adversarial machine learning at scale. arXiv preprint arXiv:1611.01236, 2016.","title":"Adversarial machine learning at scale","authors":"Alexey Kurakin, Ian Goodfellow, Samy Bengio","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Kurakin et al., 2017] Alexey Kurakin, Ian Goodfellow, and Samy Bengio. Adversarial examples in the physical world. ICLR (Workshop), 2017.","title":"Adversarial examples in the physical world","authors":"Alexey Kurakin, Ian Goodfellow, Samy Bengio","year":"2017","venue":"ICLR (Workshop)","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Li et al., 2021] Yiming Li, Congcong Wen, Felix Juefei-Xu, and Chen Feng. Fooling lidar perception via adversarial trajectory perturbation. arXiv preprint arXiv:2103.15326, 2021.","title":"Fooling lidar perception via adversarial trajectory perturbation","authors":"Yiming Li, Congcong Wen, Felix Juefei-Xu, Chen Feng","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Mittal et al., 2012a] Anish Mittal, Anush Krishna Moorthy, and Alan Conrad Bovik. No-reference image quality assessment in the spatial domain. IEEE Transactions on image processing, 21(12):4695-4708, 2012.","title":"No-reference image quality assessment in the spatial domain","authors":"Mittal","year":"2012","venue":"IEEE Transactions on image processing","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Mittal et al., 2012b] Anish Mittal, Rajiv Soundararajan, and Alan C Bovik. Making a \"completely blind\" image quality ana- lyzer. IEEE Signal processing letters, 20(3):209-212, 2012.","title":"Making a \"completely blind\" image quality analyzer","authors":"Mittal","year":"2012","venue":"IEEE Signal processing letters","doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Qi et al., 2020] Hua Qi, Qing Guo, Felix Juefei-Xu, Xiaofei Xie, Lei Ma, Wei Feng, Yang Liu, and Jianjun Zhao. Deeprhythm: exposing deepfakes with attentional visual heartbeat rhythms. In Proceedings of the 28th ACM International Conference on Mul- timedia, pages 4318-4327, 2020.","title":"Deeprhythm: exposing deepfakes with attentional visual heartbeat rhythms","authors":"Hua Qi, Qing Guo, Felix Juefei-Xu, Xiaofei Xie, Lei Ma, Wei Feng, Yang Liu, Jianjun Zhao","year":"2020","venue":"Proceedings of the 28th ACM International Conference on Multimedia","doi":null,"url":null,"internal_url":null},{"position":33,"raw":"[Ray, 2002] Sidney Ray. Applied photographic optics. Routledge, 2002.","title":"Sidney Ray. Applied photographic optics","authors":"Ray","year":"2002","venue":null,"doi":null,"url":null,"internal_url":null},{"position":34,"raw":"[Sandler et al., 2018] Mark Sandler, Andrew Howard, Menglong Zhu, Andrey Zhmoginov, and Liang-Chieh Chen. Mobilenetv2: Inverted residuals and linear bottlenecks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 4510-4520, 2018.","title":"Mobilenetv2: Inverted residuals and linear bottlenecks","authors":"Mark Sandler, Andrew Howard, Menglong Zhu, Andrey Zhmoginov, Liang-Chieh Chen","year":"2018","venue":"Proceedings of the IEEE conference on computer vision and pattern recognition","doi":null,"url":null,"internal_url":null},{"position":35,"raw":"[Stanford, 2017] Stanford. Tiny ImageNet. https://www.kaggle. com/c/tiny-imagenet, 2017. Accessed: 2021-01-20.","title":"Stanford. Tiny ImageNet","authors":null,"year":"2017","venue":null,"doi":null,"url":"https://www.kaggle.com/c/tiny-imagenet,2017","internal_url":null},{"position":36,"raw":"[Tan and Le, 2019] Mingxing Tan and Quoc Le. Efficientnet: Re- thinking model scaling for convolutional neural networks. In In- ternational Conference on Machine Learning, pages 6105-6114, 2019.","title":"Efficientnet: Rethinking model scaling for convolutional neural networks","authors":"Le ; Tan, Mingxing Tan, Quoc Le","year":"2019","venue":"International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":37,"raw":"[Tian et al., 2020] Binyu Tian, Qing Guo, Felix Juefei-Xu, Wen Le Chan, Yupeng Cheng, Xiaohong Li, Xiaofei Xie, and Shengchao Qin. Bias field poses a threat to dnn-based x-ray recognition. arXiv preprint arXiv:2009.09247, 2020.","title":"Bias field poses a threat to dnn-based x-ray recognition","authors":"Qing Binyu Tian, Felix Guo, Wen Juefei-Xu, Yupeng Le Chan, Xiaohong Cheng, Xiaofei Li, Shengchao Xie, Qin","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":38,"raw":"[Tsai, 1987] Roger Tsai. A versatile camera calibration technique for high-accuracy 3d machine vision metrology using off-the- shelf tv cameras and lenses. IEEE Journal on Robotics and Au- tomation, 3(4):323-344, 1987.","title":"A versatile camera calibration technique for high-accuracy 3d machine vision metrology using off-theshelf tv cameras and lenses","authors":"Roger Tsai","year":"1987","venue":"IEEE Journal on Robotics and Automation","doi":null,"url":null,"internal_url":null},{"position":39,"raw":"[Wang et al., 2020] Run Wang, Felix Juefei-Xu, Qing Guo, Yihao Huang, Xiaofei Xie, Lei Ma, and Yang Liu. Amora: Black-box adversarial morphing attack. In Proceedings of the 28th ACM In- ternational Conference on Multimedia, pages 1376-1385, 2020.","title":"Amora: Black-box adversarial morphing attack","authors":"Wang","year":"2020","venue":"Proceedings of the 28th ACM International Conference on Multimedia","doi":null,"url":null,"internal_url":null},{"position":40,"raw":"[Wong et al., 2019] Eric Wong, Frank R Schmidt, and J Zico Kolter. Wasserstein adversarial examples via projected sinkhorn iterations. arXiv preprint arXiv:1902.07906, 2019.","title":"Wasserstein adversarial examples via projected sinkhorn iterations","authors":"Eric Wong, Frank R Schmidt, J Zico Kolter","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":41,"raw":"[Yu, 2004] Wonpil Yu. Practical anti-vignetting methods for digital cameras. IEEE TCE, 50(4):975-983, 2004.","title":"Practical anti-vignetting methods for digital cameras","authors":"Yu ;, Wonpil Yu","year":"2004","venue":"IEEE TCE","doi":null,"url":null,"internal_url":null},{"position":42,"raw":"[Zhai et al., 2020] Liming Zhai, Felix Juefei-Xu, Qing Guo, Xi- aofei Xie, Lei Ma, Wei Feng, Shengchao Qin, and Yang Liu. It's raining cats or dogs? adversarial rain attack on dnn perception. arXiv preprint arXiv:2009.09205, 2020.","title":"It's raining cats or dogs? adversarial rain attack on dnn perception","authors":"Liming Zhai, Felix Juefei-Xu, Qing Guo, Xiaofei Xie, Lei Ma, Wei Feng, Shengchao Qin, Yang Liu","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":43,"raw":"[Zheng et al., 2008] Yuanjie Zheng, Stephen Lin, Chandra Kamb- hamettu, Jingyi Yu, and Sing Bing Kang. Single-image vi- gnetting correction. IEEE transactions on pattern analysis and machine intelligence, 31(12):2243-2256, 2008.","title":"Single-image vignetting correction","authors":"Zheng","year":"2008","venue":"IEEE transactions on pattern analysis and machine intelligence","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}