{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,27]],"date-time":"2026-08-27T15:18:55Z","timestamp":1787843935797,"version":"build-2784847793"},"publisher-location":"Cham","reference-count":33,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030012519","type":"print"},{"value":"9783030012526","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\/978-3-030-01252-6_39","type":"book-chapter","created":{"date-parts":[[2018,10,5]],"date-time":"2018-10-05T09:48:05Z","timestamp":1538732885000},"page":"656-672","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":140,"title":["Dynamic Multimodal Instance Segmentation Guided by Natural Language Queries"],"prefix":"10.1007","author":[{"given":"Edgar","family":"Margffoy-Tuay","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Juan C.","family":"P\u00e9rez","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Emilio","family":"Botero","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pablo","family":"Arbel\u00e1ez","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2018,10,6]]},"reference":[{"key":"39_CR1","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":"39_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"297","DOI":"10.1007\/978-3-319-10584-0_20","volume-title":"Computer Vision \u2013 ECCV 2014","author":"B Hariharan","year":"2014","unstructured":"Hariharan, B., Arbel\u00e1ez, P., Girshick, R., Malik, J.: Simultaneous detection and segmentation. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8695, pp. 297\u2013312. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10584-0_20"},{"key":"39_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1007\/978-3-319-46448-0_7","volume-title":"Computer Vision \u2013 ECCV 2016","author":"R Hu","year":"2016","unstructured":"Hu, R., Rohrbach, M., Darrell, T.: Segmentation from natural language expressions. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 108\u2013124. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_7"},{"key":"39_CR4","doi-asserted-by":"crossref","unstructured":"Liu, C., Lin, Z.L., Shen, X., Yang, J., Lu, X., Yuille, A.L.: Recurrent multimodal interaction for referring image segmentation. In: International Conference on Computer Vision (ICCV), pp. 1280\u20131289 (2017)","DOI":"10.1109\/ICCV.2017.143"},{"key":"39_CR5","doi-asserted-by":"crossref","unstructured":"Li, Z., Tao, R., Gavves, E., Snoek, C.G.M., Smeulders, A.W.M.: Tracking by natural language specification. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.777"},{"key":"39_CR6","unstructured":"Lei, T., Zhang, Y., Artzi, Y.: Training RNNs as fast as CNNs. CoRR abs\/1709.02755 (2017)"},{"issue":"8","key":"39_CR7","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"39_CR8","unstructured":"Paszke, A., et al.: Automatic differentiation in pytorch. In: Conference on Neural Information Processing Systems (NIPS) (2017)"},{"key":"39_CR9","doi-asserted-by":"crossref","unstructured":"Hu, R., Xu, H., Rohrbach, M., Feng, J., Saenko, K., Darrell, T.: Natural language object retrieval. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2016), pp. 4555\u20134564","DOI":"10.1109\/CVPR.2016.493"},{"issue":"1\u20133","key":"39_CR10","doi-asserted-by":"publisher","first-page":"265","DOI":"10.1177\/0278364915602059","volume":"35","author":"S Guadarrama","year":"2016","unstructured":"Guadarrama, S., Rodner, E., Saenko, K., Darrell, T.: Understanding object descriptions in robotics by open-vocabulary object retrieval and detection. Int. J. Robot. Res. 35(1\u20133), 265\u2013280 (2016)","journal-title":"Int. J. Robot. Res."},{"key":"39_CR11","doi-asserted-by":"crossref","unstructured":"Hendricks, L.A., Venugopalan, S., Rohrbach, M., Mooney, R.J., Saenko, K., Darrell, T.: Deep compositional captioning: Describing novel object categories without paired training data. In: Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1\u201310 (2016)","DOI":"10.1109\/CVPR.2016.8"},{"key":"39_CR12","doi-asserted-by":"crossref","unstructured":"Gan, Z., et al.: Semantic compositional networks for visual captioning. In: Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1141\u20131150 (2017)","DOI":"10.1109\/CVPR.2017.127"},{"key":"39_CR13","doi-asserted-by":"crossref","unstructured":"Johnson, J., Karpathy, A., Fei-Fei, L., Li, C., Li, Y.W., fei Li, F.: Densecap: Fully convolutional localization networks for dense captioning. In: Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4565\u20134574 (2016)","DOI":"10.1109\/CVPR.2016.494"},{"key":"39_CR14","unstructured":"Yang, Z., Yuan, Y., Wu, Y., Cohen, W.W., Salakhutdinov, R.: Review networks for caption generation. In: Conference on Neural Information Processing Systems (NIPS) (2016)"},{"key":"39_CR15","doi-asserted-by":"crossref","unstructured":"Goyal, Y., Khot, T., Summers-Stay, D., Batra, D., Parikh, D.: Making the V in VQA matter: elevating the role of image understanding in visual question answering. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6325\u20136334 (2017)","DOI":"10.1109\/CVPR.2017.670"},{"key":"39_CR16","doi-asserted-by":"crossref","unstructured":"Li, C., Groth, O., Bernstein, M.S., Fei-Fei, L., Li, Y.W., Li, F.F.: Visual7w: grounded question answering in images. In: Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4995\u20135004 (2016)","DOI":"10.1109\/CVPR.2016.540"},{"key":"39_CR17","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1007\/s11263-016-0981-7","volume":"123","author":"R Krishna","year":"2016","unstructured":"Krishna, R., Li, C., Groth, O., Johnson, J., Hata, K., Kravitz, J., Chen, S., Kalantidis, Y., Shamma, D.A., Bernstein, M.S., Fei-Fei, L.: Visual genome: connecting language and vision using crowdsourced dense image annotations. Int. J. Comput. Vis. (IJCV) 123, 32\u201373 (2016)","journal-title":"Int. J. Comput. Vis. (IJCV)"},{"key":"39_CR18","doi-asserted-by":"crossref","unstructured":"Agrawal, A., et al.: VQA: visual question answering. In: International Conference on Computer Vision (ICCV), pp. 2425\u20132433 (2015)","DOI":"10.1109\/ICCV.2015.279"},{"key":"39_CR19","doi-asserted-by":"crossref","unstructured":"Teney, D., Liu, L., van den Hengel, A.: Graph-structured representations for visual question answering. In: Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3233\u20133241 (2017)","DOI":"10.1109\/CVPR.2017.344"},{"issue":"2","key":"39_CR20","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.I., Winn, J., Zisserman, A.: The pascal visual object classes (voc) challenge. Int. J. Comput. Vis. 88(2), 303\u2013338 (2010)","journal-title":"Int. J. Comput. Vis."},{"key":"39_CR21","unstructured":"Nair, V., Hinton, G.E.: Rectified linear units improve restricted boltzmann machines. In: Proceedings of the 27th International Conference on Machine Learning (ICML-10), pp. 807\u2013814 (2010)"},{"key":"39_CR22","doi-asserted-by":"crossref","unstructured":"Odena, A., Dumoulin, V., Olah, C.: Deconvolution and checkerboard artifacts. Distill (2016)","DOI":"10.23915\/distill.00003"},{"key":"39_CR23","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: International Conference on Learning Representations (ICLR) (2015)"},{"key":"39_CR24","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 \u2014 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":"39_CR25","doi-asserted-by":"crossref","unstructured":"Shelhamer, E., Long, J., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3431\u20133440 (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"issue":"4","key":"39_CR26","doi-asserted-by":"publisher","first-page":"627","DOI":"10.1109\/TPAMI.2016.2578328","volume":"39","author":"B Hariharan","year":"2017","unstructured":"Hariharan, B., Arbel\u00e1ez, P., Girshick, R., Malik, J.: Object instance segmentation and fine-grained localization using hypercolumns. IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI) 39(4), 627\u2013639 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI)"},{"key":"39_CR27","unstructured":"Chen, Y., Li, J., Xiao, H., Jin, X., Yan, S., Feng, J.: Dual path networks. In: Conference on Neural Information Processing Systems (NIPS) (2017)"},{"key":"39_CR28","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Weinberger, K.Q.: Densely connected convolutional networks. In: Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2261\u20132269 (2017)","DOI":"10.1109\/CVPR.2017.243"},{"key":"39_CR29","doi-asserted-by":"crossref","unstructured":"Kazemzadeh, S., Ordonez, V., Matten, M., Berg, T.L.: Referit game: referring to objects in photographs of natural scenes. In: EMNLP (2014)","DOI":"10.3115\/v1\/D14-1086"},{"key":"39_CR30","doi-asserted-by":"crossref","unstructured":"Mao, J., Huang, J., Toshev, A., Camburu, O., Yuille, A.L., Murphy, K.: Generation and comprehension of unambiguous object descriptions. In: Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11\u201320 (2016)","DOI":"10.1109\/CVPR.2016.9"},{"key":"39_CR31","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1007\/978-3-319-46475-6_5","volume-title":"Computer Vision \u2013 ECCV 2016","author":"L Yu","year":"2016","unstructured":"Yu, L., Poirson, P., Yang, S., Berg, A.C., Berg, T.L.: Modeling context in referring expressions. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 69\u201385. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46475-6_5"},{"key":"39_CR32","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: International Conference on Learning Representations (ICLR) (2015)"},{"key":"39_CR33","doi-asserted-by":"crossref","unstructured":"Hu, R., Rohrbach, M., Venugopalan, S., Darrell, T.: Utilizing large scale vision and text datasets for image segmentation from referring expressions. In: European Conference on Computer Vision (ECCV) (2016)","DOI":"10.1007\/978-3-319-46448-0_7"}],"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\/978-3-030-01252-6_39","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T15:48:13Z","timestamp":1773762493000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-01252-6_39"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030012519","9783030012526"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-01252-6_39","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"}]}}