{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T20:16:48Z","timestamp":1773692208388,"version":"3.50.1"},"publisher-location":"Cham","reference-count":38,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030012571","type":"print"},{"value":"9783030012588","type":"electronic"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-030-01258-8_33","type":"book-chapter","created":{"date-parts":[[2018,10,5]],"date-time":"2018-10-05T20:35:31Z","timestamp":1538771731000},"page":"542-557","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Concept Mask: Large-Scale Segmentation from Semantic Concepts"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0729-908X","authenticated-orcid":false,"given":"Yufei","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1154-9907","authenticated-orcid":false,"given":"Zhe","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaohui","family":"Shen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9954-6294","authenticated-orcid":false,"given":"Jianming","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Scott","family":"Cohen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,10,6]]},"reference":[{"issue":"12","key":"33_CR1","doi-asserted-by":"publisher","first-page":"2481","DOI":"10.1109\/TPAMI.2016.2644615","volume":"39","author":"V Badrinarayanan","year":"2017","unstructured":"Badrinarayanan, V., Kendall, A., Cipolla, R.: SegNet: a deep convolutional encoder-decoder architecture for image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 39(12), 2481\u20132495 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"4","key":"33_CR2","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"L Chen","year":"2018","unstructured":"Chen, L., 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 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"33_CR3","doi-asserted-by":"crossref","unstructured":"Chen, X., Shrivastava, A., Gupta, A.: Enriching visual knowledge bases via object discovery and segmentation. In: CVPR, pp. 2035\u20132042. IEEE Computer Society (2014)","DOI":"10.1109\/CVPR.2014.261"},{"key":"33_CR4","unstructured":"Chollet, F.: Information-theoretical label embeddings for large-scale image classification. CoRR abs\/1607.05691 (2016)"},{"issue":"1","key":"33_CR5","first-page":"22","volume":"16","author":"KW Church","year":"1990","unstructured":"Church, K.W., Hanks, P.: Word association norms, mutual information, and lexicography. Comput. Linguist. 16(1), 22\u201329 (1990). http:\/\/dl.acm.org\/citation.cfm?id=89086.89095","journal-title":"Comput. Linguist."},{"key":"33_CR6","doi-asserted-by":"crossref","unstructured":"Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding. In: CVPR, pp. 3213\u20133223. IEEE Computer Society (2016)","DOI":"10.1109\/CVPR.2016.350"},{"key":"33_CR7","doi-asserted-by":"crossref","unstructured":"Dai, J., He, K., Sun, J.: BoxSup: exploiting bounding boxes to supervise convolutional networks for semantic segmentation, pp. 1635\u20131643 (2015)","DOI":"10.1109\/ICCV.2015.191"},{"key":"33_CR8","doi-asserted-by":"crossref","unstructured":"Dai, J., He, K., Sun, J.: Instance-aware semantic segmentation via multi-task network cascades. In: CVPR, pp. 3150\u20133158. IEEE Computer Society (2016)","DOI":"10.1109\/CVPR.2016.343"},{"issue":"2","key":"33_CR9","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham, M., Gool, L., Williams, C.K., Winn, J., Zisserman, A.: The pascal visual object classes (VOC) challenge. Int. J. Comput. Vis. 88(2), 303\u2013338 (2010). https:\/\/doi.org\/10.1007\/s11263-009-0275-4","journal-title":"Int. J. Comput. Vis."},{"key":"33_CR10","unstructured":"Frome, A., et al.: DeViSE: a deep visual-semantic embedding model. In: Burges, C.J.C., Bottou, L., Ghahramani, Z., Weinberger, K.Q. (eds.) NIPS, pp. 2121\u20132129 (2013)"},{"key":"33_CR11","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.B.: Mask R-CNN. In: ICCV, pp. 2980\u20132988. IEEE Computer Society (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"33_CR12","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770\u2013778. IEEE Computer Society (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"33_CR13","unstructured":"Hong, S., Noh, H., Han, B.: Decoupled deep neural network for semi-supervised semantic segmentation. In: Cortes, C., Lawrence, N.D., Lee, D.D., Sugiyama, M., Garnett, R. (eds.) NIPS, pp. 1495\u20131503 (2015)"},{"key":"33_CR14","doi-asserted-by":"crossref","unstructured":"Hong, S., Yeo, D., Kwak, S., Lee, H., Han, B.: Weakly supervised semantic segmentation using web-crawled videos, pp. 2224\u20132232 (2017)","DOI":"10.1109\/CVPR.2017.239"},{"key":"33_CR15","doi-asserted-by":"crossref","unstructured":"Hu, R., Doll\u00e1r, P., He, K., Darrell, T., Girshick, R.: Learning to segment every thing. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00445"},{"key":"33_CR16","unstructured":"Jayaraman, D., Grauman, K.: Zero-shot recognition with unreliable attributes. In: Ghahramani, Z., Welling, M., Cortes, C., Lawrence, N.D., Weinberger, K.Q. (eds.) NIPS, pp. 3464\u20133472 (2014)"},{"key":"33_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"695","DOI":"10.1007\/978-3-319-46493-0_42","volume-title":"Computer Vision \u2013 ECCV 2016","author":"A Kolesnikov","year":"2016","unstructured":"Kolesnikov, A., Lampert, C.H.: Seed, expand and constrain: three principles for weakly-supervised image segmentation. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 695\u2013711. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_42"},{"key":"33_CR18","unstructured":"Krasin, I., et al.: OpenImages: a public dataset for large-scale multi-label and multi-class image classification (2017). Dataset available from https:\/\/github.com\/openimages"},{"issue":"1","key":"33_CR19","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1007\/s11263-016-0981-7","volume":"123","author":"R Krishna","year":"2017","unstructured":"Krishna, R., et al.: Visual genome: connecting language and vision using crowdsourced dense image annotations. Int. J. Comput. Vis. 123(1), 32\u201373 (2017)","journal-title":"Int. J. Comput. Vis."},{"key":"33_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"459","DOI":"10.1007\/978-3-642-33786-4_34","volume-title":"Computer Vision \u2013 ECCV 2012","author":"D Kuettel","year":"2012","unstructured":"Kuettel, D., Guillaumin, M., Ferrari, V.: Segmentation propagation in ImageNet. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7578, pp. 459\u2013473. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-33786-4_34"},{"issue":"3","key":"33_CR21","doi-asserted-by":"publisher","first-page":"453","DOI":"10.1109\/TPAMI.2013.140","volume":"36","author":"CH Lampert","year":"2014","unstructured":"Lampert, C.H., Nickisch, H., Harmeling, S.: Attribute-based classification forzero-shot visual object categorization. IEEE Trans. Pattern Anal. Mach. Intell. 36(3), 453\u2013465 (2014). https:\/\/doi.org\/10.1109\/TPAMI.2013.140","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"33_CR22","doi-asserted-by":"publisher","unstructured":"Li, Y., Qi, H., Dai, J., Ji, X., Wei, Y.: Fully convolutional instance-aware semantic segmentation. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, Honolulu, HI, USA, 21\u201326 July 2017, pp. 4438\u20134446. IEEE Computer Society (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.472","DOI":"10.1109\/CVPR.2017.472"},{"key":"33_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"614","DOI":"10.1007\/978-3-319-46493-0_37","volume-title":"Computer Vision \u2013 ECCV 2016","author":"Z Li","year":"2016","unstructured":"Li, Z., Hoiem, D.: Learning without forgetting. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 614\u2013629. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_37"},{"key":"33_CR24","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":"33_CR25","doi-asserted-by":"publisher","unstructured":"Noh, H., Hong, S., Han, B.: Learning deconvolution network for semantic segmentation. In: Proceedings of the 2015 IEEE International Conference on Computer Vision (ICCV), ICCV 2015, pp. 1520\u20131528. IEEE Computer Society, Washington, DC (2015). https:\/\/doi.org\/10.1109\/ICCV.2015.178","DOI":"10.1109\/ICCV.2015.178"},{"key":"33_CR26","unstructured":"Norouzi, M., et al.: Zero-shot learning by convex combination of semantic embeddings. In: International Conference on Learning Representations (ICLR) (2014)"},{"key":"33_CR27","doi-asserted-by":"crossref","unstructured":"Parikh, D., Grauman, K.: Relative attributes. In: Metaxas, D.N., Quan, L., Sanfeliu, A., Gool, L.J.V. (eds.) ICCV, pp. 503\u2013510. IEEE Computer Society (2011)","DOI":"10.1109\/ICCV.2011.6126281"},{"key":"33_CR28","doi-asserted-by":"publisher","unstructured":"Pathak, D., Kr\u00e4henb\u00fchl, P., Darrell, T.: Constrained convolutional neural networks for weakly supervised segmentation. In: 2015 IEEE International Conference on Computer Vision, ICCV 2015, Santiago, Chile, 7\u201313 December 2015, pp. 1796\u20131804. IEEE Computer Society (2015). https:\/\/doi.org\/10.1109\/ICCV.2015.209","DOI":"10.1109\/ICCV.2015.209"},{"key":"33_CR29","unstructured":"Ren, S., He, K., Girshick, R.B., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks, pp. 91\u201399 (2015)"},{"key":"33_CR30","doi-asserted-by":"crossref","unstructured":"Rubinstein, M., Joulin, A., Kopf, J., Liu, C.: Unsupervised joint object discovery and segmentation in internet images, pp. 1939\u20131946 (2013)","DOI":"10.1109\/CVPR.2013.253"},{"issue":"4","key":"33_CR31","doi-asserted-by":"publisher","first-page":"640","DOI":"10.1109\/TPAMI.2016.2572683","volume":"39","author":"E Shelhamer","year":"2017","unstructured":"Shelhamer, E., Long, J., Darrell, T.: Fully convolutional networks for semantic segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 39(4), 640\u2013651 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"33_CR32","unstructured":"Socher, R., Ganjoo, M., Manning, C.D., Ng, A.Y.: Zero-shot learning through cross-modal transfer. In: Burges, C.J.C., Bottou, L., Ghahramani, Z., Weinberger, K.Q. (eds.) NIPS, pp. 935\u2013943 (2013)"},{"key":"33_CR33","doi-asserted-by":"crossref","unstructured":"Xu, N., Price, B.L., Cohen, S., Yang, J., Huang, T.S.: Deep GrabCut for object selection. CoRR abs\/1707.00243 (2017). http:\/\/arxiv.org\/abs\/1707.00243","DOI":"10.5244\/C.31.182"},{"key":"33_CR34","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"543","DOI":"10.1007\/978-3-319-46493-0_33","volume-title":"Computer Vision \u2013 ECCV 2016","author":"J Zhang","year":"2016","unstructured":"Zhang, J., Lin, Z., Brandt, J., Shen, X., Sclaroff, S.: Top-down neural attention by excitation backprop. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 543\u2013559. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_33"},{"key":"33_CR35","doi-asserted-by":"crossref","unstructured":"Zhao, H., Puig, X., Zhou, B., Fidler, S., Torralba, A.: Open vocabulary scene parsing. In: ICCV, pp. 2021\u20132029. IEEE Computer Society (2017)","DOI":"10.1109\/ICCV.2017.221"},{"key":"33_CR36","doi-asserted-by":"crossref","unstructured":"Zhao, H., Shi, J., Qi, X., Wang, X., Jia, J.: Pyramid scene parsing network. In: CVPR, pp. 6230\u20136239. IEEE Computer Society (2017)","DOI":"10.1109\/CVPR.2017.660"},{"key":"33_CR37","doi-asserted-by":"crossref","unstructured":"Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., Torralba, A.: Learning deep features for discriminative localization. In: CVPR, pp. 2921\u20132929. IEEE Computer Society (2016)","DOI":"10.1109\/CVPR.2016.319"},{"key":"33_CR38","doi-asserted-by":"crossref","unstructured":"Zhou, B., Zhao, H., Puig, X., Fidler, S., Barriuso, A., Torralba, A.: Scene parsing through ADE20K dataset. In: CVPR, pp. 5122\u20135130. IEEE Computer Society (2017)","DOI":"10.1109\/CVPR.2017.544"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2018"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-01258-8_33","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,5]],"date-time":"2022-10-05T00:43:11Z","timestamp":1664930591000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-01258-8_33"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030012571","9783030012588"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-01258-8_33","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"6 October 2018","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":"Munich","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":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 September 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2018.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}