{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T16:45:50Z","timestamp":1777567550687,"version":"3.51.4"},"publisher-location":"Cham","reference-count":44,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030585945","type":"print"},{"value":"9783030585952","type":"electronic"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-58595-2_19","type":"book-chapter","created":{"date-parts":[[2020,11,20]],"date-time":"2020-11-20T03:29:28Z","timestamp":1605842968000},"page":"305-321","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Attend and Segment: Attention Guided Active Semantic Segmentation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4791-5350","authenticated-orcid":false,"given":"Soroush","family":"Seifi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3307-9723","authenticated-orcid":false,"given":"Tinne","family":"Tuytelaars","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,11,20]]},"reference":[{"key":"19_CR1","doi-asserted-by":"crossref","unstructured":"Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3213\u20133223 (2016)","DOI":"10.1109\/CVPR.2016.350"},{"key":"19_CR2","doi-asserted-by":"crossref","unstructured":"Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? the KITTI vision benchmark suite. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 3354\u20133361. IEEE (2012)","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"19_CR3","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1016\/j.media.2016.05.004","volume":"35","author":"M Havaei","year":"2017","unstructured":"Havaei, M., et al.: Brain tumor segmentation with deep neural networks. Med. Image Anal. 35, 18\u201331 (2017)","journal-title":"Med. Image Anal."},{"key":"19_CR4","doi-asserted-by":"crossref","unstructured":"Yu, L., Yang, X., Chen, H., Qin, J., Heng, P.A.: Volumetric convnets with mixed residual connections for automated prostate segmentation from 3D MR images. In: Thirty-First AAAI Conference on Artificial Intelligence (2017)","DOI":"10.1609\/aaai.v31i1.10510"},{"key":"19_CR5","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431\u20133440 (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"19_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015","author":"O Ronneberger","year":"2015","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234\u2013241. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28"},{"key":"19_CR7","unstructured":"Li, H., Xiong, P., An, J., Wang, L.: Pyramid attention network for semantic segmentation. In: The British Machine Vision Conference (2018)"},{"issue":"4","key":"19_CR8","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"L-C Chen","year":"2017","unstructured":"Chen, L.-C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. IEEE Trans. Pattern Anal. Mach. Intell. 40(4), 834\u2013848 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"19_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"424","DOI":"10.1007\/978-3-030-01258-8_26","volume-title":"Computer Vision \u2013 ECCV 2018","author":"SK Ramakrishnan","year":"2018","unstructured":"Ramakrishnan, S.K., Grauman, K.: Sidekick policy learning for active visual exploration. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11216, pp. 424\u2013442. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01258-8_26"},{"key":"19_CR10","doi-asserted-by":"crossref","unstructured":"Jayaraman, D., Grauman, K.: Learning to look around: intelligently exploring unseen environments for unknown tasks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1238\u20131247 (2018)","DOI":"10.1109\/CVPR.2018.00135"},{"key":"19_CR11","unstructured":"Seifi, S., Tuytelaars, T.: Where to look next: unsupervised active visual exploration on 360$$^\\circ $$ input. arXiv preprint arXiv:1909.10304 (2019)"},{"key":"19_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1007\/978-3-540-88682-2_5","volume-title":"Computer Vision \u2013 ECCV 2008","author":"GJ Brostow","year":"2008","unstructured":"Brostow, G.J., Shotton, J., Fauqueur, J., Cipolla, R.: Segmentation and recognition using structure from motion point clouds. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008. LNCS, vol. 5302, pp. 44\u201357. Springer, Heidelberg (2008). https:\/\/doi.org\/10.1007\/978-3-540-88682-2_5"},{"key":"19_CR13","doi-asserted-by":"crossref","unstructured":"Garcia-Garcia, A., Orts-Escolano, S., Oprea, S., Villena-Martinez, V., Garcia-Rodriguez, J.: A review on deep learning techniques applied to semantic segmentation. arXiv preprint arXiv:1704.06857 (2017)","DOI":"10.1016\/j.asoc.2018.05.018"},{"key":"19_CR14","unstructured":"Chen, L.-C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: Semantic image segmentation with deep convolutional nets and fully connected CRFs. arXiv preprint arXiv:1412.7062 (2014)"},{"key":"19_CR15","doi-asserted-by":"crossref","unstructured":"Chai, Y.: Patchwork: a patch-wise attention network for efficient object detection and segmentation in video streams. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3415\u20133424 (2019)","DOI":"10.1109\/ICCV.2019.00351"},{"issue":"4","key":"19_CR16","doi-asserted-by":"publisher","first-page":"333","DOI":"10.1007\/BF00133571","volume":"1","author":"J Aloimonos","year":"1988","unstructured":"Aloimonos, J., Weiss, I., Bandyopadhyay, A.: Active vision. Int. J. Comput. Vis. 1(4), 333\u2013356 (1988). https:\/\/doi.org\/10.1007\/BF00133571","journal-title":"Int. J. Comput. Vis."},{"issue":"2","key":"19_CR17","doi-asserted-by":"publisher","first-page":"429","DOI":"10.1109\/TRO.2016.2533639","volume":"32","author":"D Navarro-Alarcon","year":"2016","unstructured":"Navarro-Alarcon, D., et al.: Automatic 3-D manipulation of soft objects by robotic arms with an adaptive deformation model. IEEE Trans. Robot. 32(2), 429\u2013441 (2016)","journal-title":"IEEE Trans. Robot."},{"key":"19_CR18","doi-asserted-by":"crossref","unstructured":"Caicedo, J.C., Lazebnik, S.: Active object localization with deep reinforcement learning. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2488\u20132496 (2015)","DOI":"10.1109\/ICCV.2015.286"},{"issue":"4","key":"19_CR19","doi-asserted-by":"publisher","first-page":"986","DOI":"10.1109\/TRO.2013.2256686","volume":"29","author":"A Aydemir","year":"2013","unstructured":"Aydemir, A., Pronobis, A., G\u00f6belbecker, M., Jensfelt, P.: Active visual object search in unknown environments using uncertain semantics. IEEE Trans. Rob. 29(4), 986\u20131002 (2013)","journal-title":"IEEE Trans. Rob."},{"key":"19_CR20","doi-asserted-by":"crossref","unstructured":"Gupta, S., Davidson, J., Levine, S., Sukthankar, R., Malik, J.: Cognitive mapping and planning for visual navigation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2616\u20132625 (2017)","DOI":"10.1109\/CVPR.2017.769"},{"key":"19_CR21","unstructured":"Xu, K., et al.: Show, attend and tell: neural image caption generation with visual attention. In: International conference on machine learning, pp. 2048\u20132057 (2015)"},{"key":"19_CR22","unstructured":"Mnih, V., Heess, N., Graves, A., et al.: Recurrent models of visual attention. In: Advances in Neural Information Processing Systems, pp. 2204\u20132212 (2014)"},{"key":"19_CR23","unstructured":"Hausknecht, M., Stone, P.: Deep recurrent Q-learning for partially observable MDPs. In: 2015 AAAI Fall Symposium Series (2015)"},{"key":"19_CR24","unstructured":"Mnih, V., et al.: Asynchronous methods for deep reinforcement learning. In: International Conference on Machine Learning, pp. 1928\u20131937 (2016)"},{"key":"19_CR25","unstructured":"Parisotto, E., Salakhutdinov, R.: Neural map: structured memory for deep reinforcement learning. arXiv preprint arXiv:1702.08360 (2017)"},{"key":"19_CR26","doi-asserted-by":"crossref","unstructured":"Henriques, J.F., Vedaldi, A.: MapNet: an allocentric spatial memory for mapping environments. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8476\u20138484 (2018)","DOI":"10.1109\/CVPR.2018.00884"},{"key":"19_CR27","unstructured":"Oh, J., Chockalingam, V., Singh, S., Lee, H.: Control of memory, active perception, and action in minecraft. arXiv preprint arXiv:1605.09128 (2016)"},{"key":"19_CR28","doi-asserted-by":"crossref","unstructured":"Cheng, J., Dong, L., Lapata, M.: Long short-term memory-networks for machine reading. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing (2016)","DOI":"10.18653\/v1\/D16-1053"},{"key":"19_CR29","unstructured":"Zhang, H., Goodfellow, I., Metaxas, D., Odena, A.: Self-attention generative adversarial networks. In: International Conference on Machine Learning, pp. 7354\u20137363 (2019)"},{"key":"19_CR30","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998\u20136008 (2017)"},{"key":"19_CR31","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473 (2014)"},{"key":"19_CR32","doi-asserted-by":"crossref","unstructured":"Luong, M.-T., Pham, H., Manning, C.D.: Effective approaches to attention-based neural machine translation. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing (2015)","DOI":"10.18653\/v1\/D15-1166"},{"key":"19_CR33","unstructured":"Kendall, A., Gal, Y.: What uncertainties do we need in Bayesian deep learning for computer vision? In: Advances in Neural Information Processing Systems, pp. 5574\u20135584 (2017)"},{"key":"19_CR34","doi-asserted-by":"crossref","unstructured":"Pathak, D., Krahenbuhl, P., Donahue, J., Darrell, T., Efros, A.A.: Context encoders: feature learning by inpainting. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2536\u20132544 (2016)","DOI":"10.1109\/CVPR.2016.278"},{"key":"19_CR35","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1007\/978-3-030-01252-6_6","volume-title":"Computer Vision \u2013 ECCV 2018","author":"G Liu","year":"2018","unstructured":"Liu, G., Reda, F.A., Shih, K.J., Wang, T.-C., Tao, A., Catanzaro, B.: Image inpainting for irregular holes using partial convolutions. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11215, pp. 89\u2013105. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01252-6_6"},{"key":"19_CR36","doi-asserted-by":"crossref","unstructured":"Yu, J., Lin, Z., Yang, J., Shen, X., Lu, X., Huang, T.S.: Generative image inpainting with contextual attention. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5505\u20135514 (2018)","DOI":"10.1109\/CVPR.2018.00577"},{"issue":"6","key":"19_CR37","first-page":"173","volume":"33","author":"M Wang","year":"2014","unstructured":"Wang, M., Lai, Y., Liang, Y., Martin, R.R., Hu, S.-M.: BiggerPicture: data-driven image extrapolation using graph matching. ACM Trans. Graph. 33(6), 173 (2014)","journal-title":"ACM Trans. Graph."},{"key":"19_CR38","doi-asserted-by":"crossref","unstructured":"Wang, Y., Tao, X., Shen, X., Jia, J.: Wide-context semantic image extrapolation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1399\u20131408 (2019)","DOI":"10.1109\/CVPR.2019.00149"},{"key":"19_CR39","unstructured":"Sabini, M., Rusak, G.: Painting outside the box: image outpainting with GANs. arXiv preprint arXiv:1808.08483 (2018)"},{"key":"19_CR40","doi-asserted-by":"crossref","unstructured":"Lin, C.H., Chang, C.-C., Chen, Y.-S., Juan, D.-C., Wei, W., Chen, H.-T.: COCO-GAN: generation by parts via conditional coordinating. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4512\u20134521 (2019)","DOI":"10.1109\/ICCV.2019.00461"},{"key":"19_CR41","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1007\/978-3-7091-6025-1_18","volume-title":"Sensors and Sensing in Biology and Engineering","author":"G Sandini","year":"2003","unstructured":"Sandini, G., Metta, G.: Retina-like sensors: motivations, technology and applications. In: Barth, F.G., Humphrey, J.A.C., Secomb, T.W. (eds.) Sensors and Sensing in Biology and Engineering, pp. 251\u2013262. Springer, Vienna (2003). https:\/\/doi.org\/10.1007\/978-3-7091-6025-1_18"},{"issue":"6","key":"19_CR42","doi-asserted-by":"publisher","first-page":"335","DOI":"10.1038\/nphoton.2017.87","volume":"11","author":"O Graydon","year":"2017","unstructured":"Graydon, O.: Retina-like single-pixel camera. Nat. Photonics 11(6), 335\u2013335 (2017)","journal-title":"Nat. Photonics"},{"key":"19_CR43","doi-asserted-by":"crossref","unstructured":"Ude, A.: Foveal vision for humanoid robots. In: Humanoid Robotics and Neuroscience: Science, Engineering and Society. CRC Press\/Taylor & Francis, Boca Raton (2015)","DOI":"10.1201\/b17949-8"},{"key":"19_CR44","doi-asserted-by":"crossref","unstructured":"Zhou, B., Zhao, H., Puig, X., Fidler, S., Barriuso, A., Torralba, A.: Scene parsing through ADE20K dataset. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 633\u2013641 (2017)","DOI":"10.1109\/CVPR.2017.544"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2020"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-58595-2_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,20]],"date-time":"2024-11-20T00:07:46Z","timestamp":1732061266000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58595-2_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030585945","9783030585952"],"references-count":44,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58595-2_19","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"20 November 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Glasgow","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 August 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2020.eu\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"OpenReview","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5025","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1360","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"27% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"7","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"The conference was held virtually due to the COVID-19 pandemic. From the ECCV Workshops 249 full papers, 18 short papers, and 21 further contributions were published out of a total of 467 submissions.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}