{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T18:12:04Z","timestamp":1742926324858,"version":"3.40.3"},"publisher-location":"Cham","reference-count":44,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030336752"},{"type":"electronic","value":"9783030336769"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019]]},"DOI":"10.1007\/978-3-030-33676-9_37","type":"book-chapter","created":{"date-parts":[[2019,10,25]],"date-time":"2019-10-25T17:20:30Z","timestamp":1572024030000},"page":"522-536","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Localized Interactive Instance Segmentation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0150-1208","authenticated-orcid":false,"given":"Soumajit","family":"Majumder","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7418-6141","authenticated-orcid":false,"given":"Angela","family":"Yao","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,10,25]]},"reference":[{"issue":"11","key":"37_CR1","doi-asserted-by":"publisher","first-page":"2274","DOI":"10.1109\/TPAMI.2012.120","volume":"34","author":"R Achanta","year":"2012","unstructured":"Achanta, R., Shaji, A., Smith, K., Lucchi, A., Fua, P., S\u00fcsstrunk, S., et al.: SLIC superpixels compared to state-of-the-art superpixel methods. TPAMI 34(11), 2274\u20132282 (2012)","journal-title":"TPAMI"},{"issue":"2","key":"37_CR2","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1007\/s11263-008-0191-z","volume":"82","author":"X Bai","year":"2009","unstructured":"Bai, X., Sapiro, G.: Geodesic matting: a framework for fast interactive image and video segmentation and matting. IJCV 82(2), 113\u2013132 (2009)","journal-title":"IJCV"},{"key":"37_CR3","unstructured":"Benard, A., Gygli, M.: Interactive video object segmentation in the wild. arXiv preprint arXiv:1801.00269 (2017)"},{"key":"37_CR4","doi-asserted-by":"crossref","unstructured":"Benenson, R., Popov, S., Ferrari, V.: Large-scale interactive object segmentation with human annotators. In: CVPR, pp. 11700\u201311709 (2019)","DOI":"10.1109\/CVPR.2019.01197"},{"key":"37_CR5","unstructured":"Boykov, Y.Y., Jolly, M.P.: Interactive graph cuts for optimal boundary and region segmentation of objects in N-D images. In: ICCV, pp. 105\u2013112 (2001)"},{"key":"37_CR6","doi-asserted-by":"crossref","unstructured":"Caelles, S., Maninis, K.K., Pont-Tuset, J., Leal-Taix\u00e9, L., Cremers, D., Van Gool, L.: One-shot video object segmentation. In: CVPR, pp. 221\u2013230 (2017)","DOI":"10.1109\/CVPR.2017.565"},{"key":"37_CR7","doi-asserted-by":"crossref","unstructured":"Chen, D.J., Chien, J.T., Chen, H.T., Chang, L.W.: Tap and shoot segmentation. In: AAAI (2018)","DOI":"10.1609\/aaai.v32i1.11906"},{"issue":"4","key":"37_CR8","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"LC Chen","year":"2018","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. TPAMI 40(4), 834\u2013848 (2018)","journal-title":"TPAMI"},{"key":"37_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"833","DOI":"10.1007\/978-3-030-01234-2_49","volume-title":"Computer Vision \u2013 ECCV 2018","author":"L-C Chen","year":"2018","unstructured":"Chen, L.-C., Zhu, Y., Papandreou, G., Schroff, F., Adam, H.: Encoder-decoder with atrous separable convolution for semantic image segmentation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 833\u2013851. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01234-2_49"},{"key":"37_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1007\/978-3-540-88682-2_9","volume-title":"Computer Vision \u2013 ECCV 2008","author":"A Criminisi","year":"2008","unstructured":"Criminisi, A., Sharp, T., Blake, A.: GeoS: geodesic image segmentation. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008. LNCS, vol. 5302, pp. 99\u2013112. Springer, Heidelberg (2008). https:\/\/doi.org\/10.1007\/978-3-540-88682-2_9"},{"key":"37_CR11","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: CVPR, pp. 248\u2013255 (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"37_CR12","doi-asserted-by":"crossref","unstructured":"Dutt Jain, S., Grauman, K.: Predicting sufficient annotation strength for interactive foreground segmentation. In: ICCV, pp. 1313\u20131320 (2013)","DOI":"10.1109\/ICCV.2013.166"},{"issue":"2","key":"37_CR13","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham, M., Van Gool, L., Williams, C.K., Winn, J., Zisserman, A.: The pascal visual object classes (voc) challenge. IJCV 88(2), 303\u2013338 (2010)","journal-title":"IJCV"},{"key":"37_CR14","doi-asserted-by":"crossref","unstructured":"Faktor, A., Irani, M.: Video segmentation by non-local consensus voting. In: BMVC (2014)","DOI":"10.5244\/C.28.21"},{"key":"37_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"773","DOI":"10.1007\/11566489_95","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2005","author":"L Grady","year":"2005","unstructured":"Grady, L., Schiwietz, T., Aharon, S., Westermann, R.: Random walks for interactive organ segmentation in two and three dimensions: implementation and validation. In: Duncan, J.S., Gerig, G. (eds.) MICCAI 2005. LNCS, vol. 3750, pp. 773\u2013780. Springer, Heidelberg (2005). https:\/\/doi.org\/10.1007\/11566489_95"},{"key":"37_CR16","doi-asserted-by":"crossref","unstructured":"Gulshan, V., Rother, C., Criminisi, A., Blake, A., Zisserman, A.: Geodesic star convexity for interactive image segmentation. In: CVPR, pp. 3129\u20133136 (2010)","DOI":"10.1109\/CVPR.2010.5540073"},{"key":"37_CR17","doi-asserted-by":"crossref","unstructured":"Hariharan, B., Arbelaez, P., Bourdev, L., Maji, S., Malik, J.: Semantic contours from inverse detectors. In: ICCV, pp. 991\u2013998 (2011)","DOI":"10.1109\/ICCV.2011.6126343"},{"key":"37_CR18","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"37_CR19","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"338","DOI":"10.1007\/11744023_27","volume-title":"Computer Vision \u2013 ECCV 2006","author":"X He","year":"2006","unstructured":"He, X., Zemel, R.S., Ray, D.: Learning and incorporating top-down cues in image segmentation. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3951, pp. 338\u2013351. Springer, Heidelberg (2006). https:\/\/doi.org\/10.1007\/11744023_27"},{"key":"37_CR20","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1016\/j.neunet.2018.10.009","volume":"109","author":"Y Hu","year":"2019","unstructured":"Hu, Y., Soltoggio, A., Lock, R., Carter, S.: A fully convolutional two-stream fusion network for interactive image segmentation. Neural Netw. 109, 31\u201342 (2019)","journal-title":"Neural Netw."},{"key":"37_CR21","doi-asserted-by":"crossref","unstructured":"Jang, W.D., Kim, C.S.: Interactive image segmentation via backpropagating refinement scheme. In: CVPR, pp. 5297\u20135306 (2019)","DOI":"10.1109\/CVPR.2019.00544"},{"issue":"4","key":"37_CR22","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1007\/BF00133570","volume":"1","author":"M Kass","year":"1988","unstructured":"Kass, M., Witkin, A., Terzopoulos, D.: Snakes: Active contour models. IJCV 1(4), 321\u2013331 (1988)","journal-title":"IJCV"},{"issue":"3","key":"37_CR23","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1145\/1015706.1015719","volume":"23","author":"Y Li","year":"2004","unstructured":"Li, Y., Sun, J., Tang, C.K., Shum, H.Y.: Lazy snapping. ACM Trans. Graph. (ToG) 23(3), 303\u2013308 (2004)","journal-title":"ACM Trans. Graph. (ToG)"},{"key":"37_CR24","doi-asserted-by":"crossref","unstructured":"Li, Z., Chen, Q., Koltun, V.: Interactive image segmentation with latent diversity. In: CVPR, pp. 577\u2013585 (2018)","DOI":"10.1109\/CVPR.2018.00067"},{"key":"37_CR25","doi-asserted-by":"crossref","unstructured":"Liew, J., Wei, Y., Xiong, W., Ong, S.H., Feng, J.: Regional interactive image segmentation networks. In: ICCV, pp. 2746\u20132754 (2017)","DOI":"10.1109\/ICCV.2017.297"},{"key":"37_CR26","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"37_CR27","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: CVPR, pp. 3431\u20133440 (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"37_CR28","unstructured":"Mahadevan, S., Voigtlaender, P., Leibe, B.: Iteratively trained interactive segmentation. In: BMVC (2018)"},{"key":"37_CR29","doi-asserted-by":"crossref","unstructured":"Majumder, S., Yao, A.: Content-aware multi-level guidance for interactive instance segmentation. In: CVPR, pp. 11602\u201311611 (2019)","DOI":"10.1109\/CVPR.2019.01187"},{"key":"37_CR30","doi-asserted-by":"crossref","unstructured":"Maninis, K.K., Caelles, S., Pont-Tuset, J., Van Gool, L.: Deep extreme cut: from extreme points to object segmentation. In: CVPR, pp. 616\u2013625 (2018)","DOI":"10.1109\/CVPR.2018.00071"},{"issue":"2","key":"37_CR31","doi-asserted-by":"publisher","first-page":"434","DOI":"10.1016\/j.patcog.2009.03.008","volume":"43","author":"K McGuinness","year":"2010","unstructured":"McGuinness, K., O\u2019connor, N.E.: A comparative evaluation of interactive segmentation algorithms. Pattern Recogn. 43(2), 434\u2013444 (2010)","journal-title":"Pattern Recogn."},{"key":"37_CR32","doi-asserted-by":"crossref","unstructured":"Mortensen, E.N., Barrett, W.A.: Intelligent scissors for image composition. In: SIGGRAPH, pp. 191\u2013198 (1995)","DOI":"10.1145\/218380.218442"},{"key":"37_CR33","doi-asserted-by":"crossref","unstructured":"Papazoglou, A., Ferrari, V.: Fast object segmentation in unconstrained video. In: ICCV, pp. 1777\u20131784 (2013)","DOI":"10.1109\/ICCV.2013.223"},{"key":"37_CR34","doi-asserted-by":"crossref","unstructured":"Perazzi, F., Pont-Tuset, J., McWilliams, B., Van Gool, L., Gross, M., Sorkine-Hornung, A.: A benchmark dataset and evaluation methodology for video object segmentation. In: CVPR, pp. 724\u2013732 (2016)","DOI":"10.1109\/CVPR.2016.85"},{"issue":"1","key":"37_CR35","doi-asserted-by":"publisher","first-page":"128","DOI":"10.1109\/TPAMI.2016.2537320","volume":"39","author":"J Pont-Tuset","year":"2017","unstructured":"Pont-Tuset, J., Arbelaez, P., Barron, J.T., Marques, F., Malik, J.: Multiscale combinatorial grouping for image segmentation and object proposal generation. TPAMI 39(1), 128\u2013140 (2017)","journal-title":"TPAMI"},{"key":"37_CR36","doi-asserted-by":"crossref","unstructured":"Price, B.L., Morse, B., Cohen, S.: Geodesic graph cut for interactive image segmentation. In: CVPR, pp. 3161\u20133168 (2010)","DOI":"10.1109\/CVPR.2010.5540079"},{"issue":"3","key":"37_CR37","doi-asserted-by":"publisher","first-page":"309","DOI":"10.1145\/1015706.1015720","volume":"23","author":"C Rother","year":"2004","unstructured":"Rother, C., Kolmogorov, V., Blake, A.: Grabcut: Interactive foreground extraction using iterated graph cuts. ACM Trans. Graph. (TOG) 23(3), 309\u2013314 (2004)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"37_CR38","first-page":"150","volume":"1","author":"V Vezhnevets","year":"2005","unstructured":"Vezhnevets, V., Konouchine, V.: Growcut: Interactive multi-label nd image segmentation by cellular automata. Graphicon. 1, 150\u2013156 (2005)","journal-title":"Graphicon."},{"key":"37_CR39","doi-asserted-by":"publisher","first-page":"1559","DOI":"10.1109\/TPAMI.2018.2840695","volume":"41","author":"G Wang","year":"2018","unstructured":"Wang, G., et al.: DeepIGeoS: a deep interactive geodesic framework for medical image segmentation. TPAMI 41, 1559\u20131572 (2018)","journal-title":"TPAMI"},{"key":"37_CR40","doi-asserted-by":"crossref","unstructured":"Xu, N., Price, B., Cohen, S., Yang, J., Huang, T.: Deep grabcut for object selection. In: BMVC (2017)","DOI":"10.5244\/C.31.182"},{"key":"37_CR41","doi-asserted-by":"crossref","unstructured":"Xu, N., Price, B., Cohen, S., Yang, J., Huang, T.S.: Deep interactive object selection. In: CVPR, pp. 373\u2013381 (2016)","DOI":"10.1109\/CVPR.2016.47"},{"key":"37_CR42","doi-asserted-by":"crossref","unstructured":"Yu, C., Wang, J., Peng, C., Gao, C., Yu, G., Sang, N.: Learning a discriminative feature network for semantic segmentation. In: CVPR, pp. 1857\u20131866 (2018)","DOI":"10.1109\/CVPR.2018.00199"},{"key":"37_CR43","doi-asserted-by":"crossref","unstructured":"Zhang, H., et al.: Context encoding for semantic segmentation. In: CVPR, pp. 7151\u20137160 (2018)","DOI":"10.1109\/CVPR.2018.00747"},{"key":"37_CR44","doi-asserted-by":"crossref","unstructured":"Zhao, H., Shi, J., Qi, X., Wang, X., Jia, J.: Pyramid scene parsing network. In: CVPR, pp. 2881\u20132890 (2017)","DOI":"10.1109\/CVPR.2017.660"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-33676-9_37","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,2]],"date-time":"2022-10-02T17:04:19Z","timestamp":1664730259000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-33676-9_37"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030336752","9783030336769"],"references-count":44,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-33676-9_37","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"25 October 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"DAGM GCPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"German Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Dortmund","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 September 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 September 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"41","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"dagm2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/gcpr2019.tu-dortmund.de\/","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":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"91","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":"43","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":"47% - 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":"5","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)"}}]}}