{"type":"ScholarlyArticle","title":"Co-attention CNNs for Unsupervised Object Co-segmentation","authors":[{"name":"Kuang-Jui Hsu","slug":"kuang-jui-hsu","given":"Kuang-Jui","family":"Hsu","affiliation":"Academia Sinica , Taiwan; National Taiwan University , Taiwan"},{"name":"Yen-Yu Lin","slug":"yen-yu-lin","given":"Yen-Yu","family":"Lin","affiliation":"Academia Sinica , Taiwan"},{"name":"Yung-Yu Chuang","slug":"yung-yu-chuang","given":"Yung-Yu","family":"Chuang","affiliation":"Academia Sinica , Taiwan; National Taiwan University , Taiwan"}],"abstract":"Object co-segmentation aims to segment the common objects in images. This paper presents a CNN-based method that is unsupervised and end-to-end trainable to better solve this task. Our method is unsupervised in the sense that it does not require any training data in the form of object masks but merely a set of images jointly covering objects of a specific class. Our method comprises two collaborative CNN modules, a feature extractor and a co-attention map generator. The former module extracts the features of the estimated objects and backgrounds, and is derived based on the proposed co-attention loss which minimizes inter-image object discrepancy while maximizing intra-image figure-ground separation. The latter module is learned to generated co-attention maps by which the estimated figure-ground segmentation can better fit the former module. Besides, the co-attention loss, the mask loss is developed to retain the whole objects and remove noises. Experiments show that our method achieves superior results, even outperforming the state-of-the-art, supervised methods.","doi":"10.24963/ijcai.2018/104","url":"https://ijcai.org/proceedings/2018/104","pdf":"https://ijcai.org/proceedings/2018/0104.pdf","markdown":"https://ijcai.org/proceedings/2018/104.md","bibtex":"https://ijcai.org/proceedings/2018/bibtex/104","volume":{"slug":"2018","title":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2018","url":"https://ijcai.org/proceedings/2018/","year":2018,"location":"Stockholm","dates":"13-19 July 2018","editors":"Jérôme Lang","isbn":"978-0-9992411-2-7","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2018"},"section":"Computer Vision","track":"Main track","number":104,"pages":{"first":748,"last":756},"keywords":["Machine Learning: Deep Learning","Computer Vision: Computer Vision","Machine Learning: Unsupervised Learning"],"videos":[],"references":[{"position":1,"raw":"[Batra et al., 2010] D. Batra, A. Kowdle, D. Parikh, J. Luo, and T. Chen. iCoseg: Interactive co-segmentation with intelligent scribble guidance. In CVPR, 2010.","title":"iCoseg: Interactive co-segmentation with intelligent scribble guidance","authors":"D Batra, A Kowdle, D Parikh, J Luo, T Chen","year":"2010","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Chang and Wang, 2015] H.-S. Chang and Y.-C. Wang. Op- timizing the decomposition for multiple foreground coseg- mentation. CVIU, 2015.","title":"Optimizing the decomposition for multiple foreground cosegmentation","authors":"H.-S Chang, Y.-C Wang","year":"2015","venue":"CVIU","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Chang et al., 2011] K.-Y. Chang, T.-L. Liu, and S.-H. Lai. From co-saliency to co-segmentation: An efficient and fully unsupervised energy minimization model. In CVPR, 2011.","title":"From co-saliency to co-segmentation: An efficient and fully unsupervised energy minimization model","authors":"K.-Y Chang, T.-L Liu, S.-H Lai","year":"2011","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Chaudhry et al., 2017] A. Chaudhry, P. Dokania, and P. Torr. Discovering class-specific pixels for weakly- supervised semantic segmentation. In BMVC, 2017.","title":"Discovering class-specific pixels for weaklysupervised semantic segmentation","authors":"A Chaudhry, P Dokania, P Torr","year":"2017","venue":"BMVC","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Chen et al., 2014] X. Chen, A. Shrivastava, and A. Gupta. Enriching visual knowledge bases via object discovery and segmentation. In CVPR, 2014.","title":"Enriching visual knowledge bases via object discovery and segmentation","authors":"Chen","year":"2014","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Chen et al., 2015] H.-Y. Chen, Y.-Y. Lin, and B.-Y Chen. Co-segmentation guided hough transform for robust fea- ture matching. TPAMI, 2015.","title":"Co-segmentation guided hough transform for robust feature matching","authors":"H.-Y Chen, Y.-Y Lin, B.-Y Chen","year":"2015","venue":"TPAMI","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Dai et al., 2015] J. Dai, K. He, and J. Sun. BoxSup: Ex- ploiting bounding boxes to supervise convolutional net- works for semantic segmentati. In ICCV, 2015.","title":"BoxSup: Exploiting bounding boxes to supervise convolutional networks for semantic segmentati","authors":"Dai","year":"2015","venue":"ICCV","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Dalal and Triggs, 2005] N. Dalal and B. Triggs. Histograms of oriented gradients for human detection. In CVPR, 2005.","title":"Histograms of oriented gradients for human detection","authors":"N Dalal, B Triggs","year":"2005","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Deng et al., 2009] J. Deng, W. Dong, R. Socher, L.-J. Li, K. Li, and L. Fei-Fei. ImageNet: A preview of a large- scale hierarchical database. In CVPR, 2009.","title":"ImageNet: A preview of a largescale hierarchical database","authors":"J Deng, W Dong, R Socher, L.-J Li, K Li, L Fei-Fei","year":"2009","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Everingham et al., 2015] M. Everingham, S. EslamiEmail, L. Van Gool, C. Williams, J. Winn, and A. Zisserman. The pascal visual object classes challenge: A retrospec- tive. IJCV, 2015.","title":"The pascal visual object classes challenge: A retrospective","authors":"M Everingham, S Eslamiemail, L Van Gool, C Williams, J Winn, A Zisserman","year":"2015","venue":"IJCV","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Faktor and Irani, 2013] A. Faktor and M. Irani. Co- segmentation by composition. In ICCV, 2013.","title":"Cosegmentation by composition","authors":"Irani Faktor, A Faktor, M Irani","year":"2013","venue":"ICCV","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Godard et al., 2017] C. Godard, O Aodha, and G. Brostow. Unsupervised monocular depth estimation with left-right consistency. In CVPR, 2017.","title":"Unsupervised monocular depth estimation with left-right consistency","authors":"C Godard, G Aodha, Brostow","year":"2017","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Hati et al., 2016] A. Hati, S. Chaudhuri, and R. Velmuru- gan. Image co-segmentation using maximum common subgraph matching and region co-growing. In ECCV, 2016.","title":"Image co-segmentation using maximum common subgraph matching and region co-growing","authors":"A Hati, S Chaudhuri, R Velmurugan","year":"2016","venue":"ECCV","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[He et al., 2016] K. He, X. Zhang, S. Ren, and J. Sun. Deep residual learning for image recognition. In CVPR, 2016.","title":"Deep residual learning for image recognition","authors":"K He, X Zhang, S Ren, J Sun","year":"2016","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Hou et al., 2017] Q. Hou, P. Dokania, D. Massiceti, Y. Wei, M.-M. Cheng, and P. Torr. Bottom-up top-down cues for weakly-supervised semantic segmentation. In EMM- CVPR, 2017.","title":"Bottom-up top-down cues for weakly-supervised semantic segmentation","authors":"Q Hou, P Dokania, D Massiceti, Y Wei, M.-M Cheng, P Torr","year":"2017","venue":"EMM-CVPR","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Hsu et al., 2014] K.-J. Hsu, Y.-Y. Lin, and Y.-Y. Chuang. Augmented multiple instance regression for inferring ob- ject contours in bounding boxes. TIP, 2014.","title":"Augmented multiple instance regression for inferring object contours in bounding boxes","authors":"K.-J Hsu, Y.-Y Lin, Y.-Y Chuang","year":"2014","venue":"TIP","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Hsu et al., 2015] K.-J. Hsu, Y.-Y. Lin, and Y.-Y. Chuang. Robust image alignment with multiple feature descriptors and matching-guided neighborhoods. In CVPR, 2015.","title":"Robust image alignment with multiple feature descriptors and matching-guided neighborhoods","authors":"K.-J Hsu, Y.-Y Lin, Y.-Y Chuang","year":"2015","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Hsu et al., 2017] K.-J. Hsu, Y.-Y. Lin, and Y.-Y. Chuang. Weakly supervised saliency detection with a category- driven map generator. In BMVC, 2017.","title":"Weakly supervised saliency detection with a categorydriven map generator","authors":"K.-J Hsu, Y.-Y Lin, Y.-Y Chuang","year":"2017","venue":"BMVC","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Jerripothula et al., 2016] K. Jerripothula, J. Cai, and J. Yuan. Image co-segmentation via saliency co-fusion. TMM, 2016.","title":"Image co-segmentation via saliency co-fusion","authors":"K Jerripothula, J Cai, J Yuan","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Jerripothula et al., 2017] K. Jerripothula, J. Cai, J. Lu, and J. Yuan. Object co-skeletonization with co-segmentation. In CVPR, 2017.","title":"Object co-skeletonization with co-segmentation","authors":"K Jerripothula, J Cai, J Lu, J Yuan","year":"2017","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Jin et al., 2017] Bin Jin, M. Segovia, and S. Susstrunk. We- bly supervised semantic segmentation. In CVPR, 2017.","title":"Webly supervised semantic segmentation","authors":"M Bin Jin, S Segovia, Susstrunk","year":"2017","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Joulin et al., 2010] A. Joulin, F. Bach, and J. Ponce. Dis- criminative clustering for image co-segmentation. In CVPR, 2010.","title":"Discriminative clustering for image co-segmentation","authors":"A Joulin, F Bach, J Ponce","year":"2010","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Joulin et al., 2012] A. Joulin, F. Bach, and J. Ponce. Multi- class cosegmentation. In CVPR, 2012.","title":"Multiclass cosegmentation","authors":"A Joulin, F Bach, J Ponce","year":"2012","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Kim et al., 2011] G. Kim, E. Xing, F.-F. Li, and T. Kanade. Distributed cosegmentation via submodular optimization on anisotropic diffusion. In ICCV, 2011.","title":"Distributed cosegmentation via submodular optimization on anisotropic diffusion","authors":"G Kim, E Xing, F.-F Li, T Kanade","year":"2011","venue":"ICCV","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Kingma and Ba, 2014] D. Kingma and J. Ba. ADAM: A method for stochastic optimization. In ICLR, 2014.","title":"ADAM: A method for stochastic optimization","authors":"D Kingma, J Ba","year":"2014","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Kolesnikov and Lampert, 2016] A. Kolesnikov and C. Lam- pert. Seed, expand and constrain: Three principles for weakly-supervised image segmentation. In ECCV, 2016.","title":"Seed, expand and constrain: Three principles for weakly-supervised image segmentation","authors":"Lampert Kolesnikov, A Kolesnikov, C Lampert","year":"2016","venue":"ECCV","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Krähenbühl and Koltun, 2011] P. Krähenbühl and V. Koltun. Efficient inference in fully connected crfs with gaussian edge potentials. In NIPS, 2011.","title":"Efficient inference in fully connected crfs with gaussian edge potentials","authors":"P Krähenbühl, V Koltun","year":"2011","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Krähenbühl and Koltun, 2014] P. Krähenbühl and V. Koltun. Geodesic object proposals. In ECCV, 2014.","title":"Geodesic object proposals","authors":"P Krähenbühl, V Koltun","year":"2014","venue":"ECCV","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Krizhevsky et al., 2012] A. Krizhevsky, I. Sutskever, and G. Hinton. Imagenet classification with deep convolu- tional neural networks. In NIPS, 2012.","title":"Imagenet classification with deep convolutional neural networks","authors":"A Krizhevsky, I Sutskever, G Hinton","year":"2012","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Lee et al., 2015] C. Lee, W.-D. Jang, J.-Y. Sim, and C.-S. Kim. Multiple random walkers and their application to image cosegmentation. In CVPR, 2015.","title":"Multiple random walkers and their application to image cosegmentation","authors":"C Lee, W.-D Jang, J.-Y Sim, C.-S Kim","year":"2015","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Li et al., 2018] L. Li, Z. Liua, and J. Zhang. Unsupervised image co-segmentation via guidance of simple images. CVIU, 2018.","title":"Unsupervised image co-segmentation via guidance of simple images","authors":"L Li, Z Liua, J Zhang","year":"2018","venue":"CVIU","doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Long et al., 2015] J. Long, E. Shelhamer, and T. Darrell. Fully convolutional models for semantic segmentation. In CVPR, 2015.","title":"Fully convolutional models for semantic segmentation","authors":"J Long, E Shelhamer, T Darrell","year":"2015","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":33,"raw":"[Lowe, 2004] D. Lowe. Distinctive image features from scale-invariant keypoints. IJCV, 2004.","title":"Distinctive image features from scale-invariant keypoints","authors":"D Lowe","year":"2004","venue":"IJCV","doi":null,"url":null,"internal_url":null},{"position":34,"raw":"[Meister et al., 2018] S. Meister, J. Hur, and S. Roth. Un- Flow: Unsupervised learning of optical flow with a bidi- rectional census loss. In AAAI, 2018.","title":"Un-Flow: Unsupervised learning of optical flow with a bidirectional census loss","authors":"S Meister, J Hur, S Roth","year":"2018","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":35,"raw":"[Mustafa and Hilton, 2017] A. Mustafa and A. Hilton. Se- mantically coherent co-segmentation and reconstruction of dynamic scenes. In CVPR, 2017.","title":"Semantically coherent co-segmentation and reconstruction of dynamic scenes","authors":"A Mustafa, A Hilton","year":"2017","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":36,"raw":"[Quan et al., 2016] R. Quan, J. Han, D. Zhang, and F. Nie. Object co-segmentation via graph optimized-flexible man- ifold ranking. In CVPR, 2016.","title":"Object co-segmentation via graph optimized-flexible manifold ranking","authors":"R Quan, J Han, D Zhang, F Nie","year":"2016","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":37,"raw":"[Reed et al., 2015] S. Reed, H. Lee, D. Anguelov, C. Szegedy, D. Erhan, and A. Rabinovich. Training deep neural networks on noisy labels with bootstrapping. In ICLRW, 2015.","title":"Training deep neural networks on noisy labels with bootstrapping","authors":"S Reed, H Lee, D Anguelov, C Szegedy, D Erhan, A Rabinovich","year":"2015","venue":"ICLRW","doi":null,"url":null,"internal_url":null},{"position":38,"raw":"[Ren et al., 2017] Z Ren, J. Yan, B. Ni, B. Liu, X. Yang, and H. Zha. Unsupervised deep learning for optical flow esti- mation. In AAAI, 2017.","title":"Unsupervised deep learning for optical flow estimation","authors":"J Z Ren, B Yan, B Ni, X Liu, H Yang, Zha","year":"2017","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":39,"raw":"[Rother et al., 2004] C. Rother, V. Kolmogorov, and A. Blake. Grabcut: Interactive foreground extraction using iterated graph cuts. TOG, 2004.","title":"Grabcut: Interactive foreground extraction using iterated graph cuts","authors":"C Rother, V Kolmogorov, A Blake","year":"2004","venue":null,"doi":null,"url":null,"internal_url":null},{"position":40,"raw":"[Rother et al., 2006] C. Rother, T. Minka, A. Blake, and V. Kolmogorov. Cosegmentation of image pairs by his- togram matching -incorporating a global constraint into MRFs. In CVPR, 2006.","title":"Cosegmentation of image pairs by histogram matching -incorporating a global constraint into MRFs","authors":"C Rother, T Minka, A Blake, V Kolmogorov","year":"2006","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":41,"raw":"[Roy and Todorovic, 2017] A. Roy and S. Todorovic. Com- bining bottom-up, top-down, and smoothness cues for weakly supervised image segmentation. In CVPR, 2017.","title":"Combining bottom-up, top-down, and smoothness cues for weakly supervised image segmentation","authors":"Roy, Todorovic, A Roy, S Todorovic","year":"2017","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":42,"raw":"[Rubinstein et al., 2013] M. Rubinstein, A. Joulin, J. Kopf, and C. Liu. Unsupervised joint object discovery and seg- mentation in internet images. In CVPR, 2013.","title":"Unsupervised joint object discovery and segmentation in internet images","authors":"M Rubinstein, A Joulin, J Kopf, C Liu","year":"2013","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":43,"raw":"[Rubio et al., 2012] J. Rubio, J. Serrat, A. Lopez, and N. Paragios. Unsupervised co-segmentation through re- gion matching. In CVPR, 2012.","title":"Unsupervised co-segmentation through region matching","authors":"J Rubio, J Serrat, A Lopez, N Paragios","year":"2012","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":44,"raw":"[Shen et al., 2017] T. Shen, G. Lin, L. Liu, and I. Reid. Weakly supervised semantic segmentation based on co- segmentation. In BMVC, 2017.","title":"Weakly supervised semantic segmentation based on cosegmentation","authors":"T Shen, G Lin, L Liu, I Reid","year":"2017","venue":"BMVC","doi":null,"url":null,"internal_url":null},{"position":45,"raw":"[Shimoda and Yanai, 2016] W. Shimoda and K. Yanai. Dis- tinct class-specific saliency maps for weakly supervised semantic segmentation. In ECCV, 2016.","title":"Distinct class-specific saliency maps for weakly supervised semantic segmentation","authors":"W Shimoda, K Yanai","year":"2016","venue":"ECCV","doi":null,"url":null,"internal_url":null},{"position":46,"raw":"[Shotton et al., 2009] J. Shotton, J. Winn, C. Rother, and A. Criminisi. Textonboost for image understanding: Multi-class object recognition and segmentation by jointly modeling texture, layout, and context. IJCV, 2009.","title":"Textonboost for image understanding: Multi-class object recognition and segmentation by jointly modeling texture, layout, and context","authors":"J Shotton, J Winn, C Rother, A Criminisi","year":"2009","venue":"IJCV","doi":null,"url":null,"internal_url":null},{"position":47,"raw":"[Simonyan and Zisserman, 2015] K. Simonyan and A. Zis- serman. Very deep convolutional networks for large-scale image recognition. In ICLR, 2015.","title":"Very deep convolutional networks for large-scale image recognition","authors":"K Simonyan, A Zisserman","year":"2015","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":48,"raw":"[Sun and Ponce, 2016] J. Sun and J. Ponce. Learning dictio- nary of discriminative part detectors for image categoriza- tion and cosegmentation. IJCV, 2016.","title":"Learning dictionary of discriminative part detectors for image categorization and cosegmentation","authors":"J Sun, J Ponce","year":"2016","venue":"IJCV","doi":null,"url":null,"internal_url":null},{"position":49,"raw":"[Tao et al., 2017] Z. Tao, H. Liu, H. Fu, and Y. Fu. Image cosegmentation via saliency-guided constrained clustering with cosine similarity. In AAAI, 2017.","title":"Image cosegmentation via saliency-guided constrained clustering with cosine similarity","authors":"Z Tao, H Liu, H Fu, Y Fu","year":"2017","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":50,"raw":"[Vedaldi and Lenc, 2015] A. Vedaldi and K. Lenc. Mat- ConvNet -convolutional neural networks for matlab. In ACMMM, 2015.","title":"Mat-ConvNet -convolutional neural networks for matlab","authors":"A Vedaldi, K Lenc","year":"2015","venue":"ACMMM","doi":null,"url":null,"internal_url":null},{"position":51,"raw":"[Wang et al., 2017] C. Wang, H. Zhang, L. Yang, X. Cao, and H. Xiong. Multiple semantic matching on augmented n-partite graph for object co-segmentation. TIP, 2017.","title":"Multiple semantic matching on augmented n-partite graph for object co-segmentation","authors":"C Wang, H Zhang, L Yang, X Cao, H Xiong","year":"2017","venue":"TIP","doi":null,"url":null,"internal_url":null},{"position":52,"raw":"[Wei et al., 2017a] X.-S. Wei, C.-L. Zhang, Y Li, C.-W. Xie, J. Wu, C. Shen, and Z.-H. Zhou. Deep descriptor trans- forming for image co-localization. In IJCAI, 2017.","title":"Deep descriptor transforming for image co-localization","authors":"Wei","year":"2017","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2017/425"},{"position":53,"raw":"[Wei et al., 2017b] Y. Wei, J. Feng, X. Liang, M.-M. Cheng, Y. Zhao, and S Yan. Object region mining with adversarial erasing: A simple classification to semantic segmentation approach. In CVPR, 2017.","title":"Object region mining with adversarial erasing: A simple classification to semantic segmentation approach","authors":"Wei","year":"2017","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":54,"raw":"[Yu et al., 2016] J. Yu, A. Harley, and K. Derpanis. Back to basics: Unsupervised learning of optical flow via bright- ness constancy and motion smoothness. In ECCVW, 2016.","title":"Back to basics: Unsupervised learning of optical flow via brightness constancy and motion smoothness","authors":"J Yu, A Harley, K Derpanis","year":"2016","venue":"ECCVW","doi":null,"url":null,"internal_url":null},{"position":55,"raw":"[Yuan et al., 2017] Z. Yuan, T. Lu, and Y. Wu. Deep-dense conditional random fields for object co-segmentation. In IJCAI, 2017.","title":"Deep-dense conditional random fields for object co-segmentation","authors":"Z Yuan, T Lu, Y Wu","year":"2017","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2017/471"},{"position":56,"raw":"[Zhong et al., 2016] G. Zhong, Y.-H. Tsai, and M.-H. Yang. Weakly-supervised video scene co-parsing. In ACCV, 2016.","title":"Weakly-supervised video scene co-parsing","authors":"G Zhong, Y.-H Tsai, M.-H Yang","year":"2016","venue":"ACCV","doi":null,"url":null,"internal_url":null},{"position":57,"raw":"[Zhou et al., 2017] C. Zhou, H. Zhang, X. Shen, and J. Jia. Unsupervised learning of stereo matching. In ICCV, 2017.","title":"Unsupervised learning of stereo matching","authors":"C Zhou, H Zhang, X Shen, J Jia","year":"2017","venue":"ICCV","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}