{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:16:11Z","timestamp":1778080571691,"version":"3.51.4"},"publisher-location":"Cham","reference-count":49,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319464657","type":"print"},{"value":"9783319464664","type":"electronic"}],"license":[{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"vor","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":[[2016]]},"DOI":"10.1007\/978-3-319-46466-4_19","type":"book-chapter","created":{"date-parts":[[2016,9,16]],"date-time":"2016-09-16T09:31:58Z","timestamp":1474018318000},"page":"312-329","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":138,"title":["Recurrent Instance Segmentation"],"prefix":"10.1007","author":[{"given":"Bernardino","family":"Romera-Paredes","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Philip Hilaire Sean","family":"Torr","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2016,9,17]]},"reference":[{"key":"19_CR1","unstructured":"VA-ST: Smart specs. \n                      http:\/\/www.va-st.com\/smart-specs"},{"key":"19_CR2","doi-asserted-by":"crossref","unstructured":"Arteta, C., Lempitsky, V., Noble, J.A., Zisserman, A.: Learning to detect partially overlapping instances. In: Computer Vision and Pattern Recognition (CVPR), pp. 3230\u20133237. IEEE (2013)","DOI":"10.1109\/CVPR.2013.415"},{"issue":"4254","key":"19_CR3","doi-asserted-by":"publisher","first-page":"673","DOI":"10.1126\/science.781840","volume":"193","author":"W Trager","year":"1976","unstructured":"Trager, W., Jensen, J.B.: Human malaria parasites in continuous culture. Science 193(4254), 673\u2013675 (1976)","journal-title":"Science"},{"key":"19_CR4","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, Heidelberg (2014). doi:\n                      10.1007\/978-3-319-10584-0_20"},{"key":"19_CR5","doi-asserted-by":"crossref","unstructured":"Chen, Y.T., Liu, X., Yang, M.H.: Multi-instance object segmentation with occlusion handling. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3470\u20133478 (2015)","DOI":"10.1109\/CVPR.2015.7298969"},{"key":"19_CR6","doi-asserted-by":"crossref","unstructured":"Vineet, V., Warrell, J., Ladicky, L., Torr, P.H.: Human instance segmentation from video using detector-based conditional random fields. In: British Machine Vision Conference (BMVC), pp. 1\u201311 (2011)","DOI":"10.5244\/C.25.80"},{"issue":"5","key":"19_CR7","doi-asserted-by":"publisher","first-page":"958","DOI":"10.1037\/0096-1523.20.5.958","volume":"20","author":"S Dehaene","year":"1994","unstructured":"Dehaene, S., Cohen, L.: Dissociable mechanisms of subitizing and counting: neuropsychological evidence from simultanagnosic patients. J. Exp. Psychol. Hum. Percept. Perform. 20(5), 958 (1994)","journal-title":"J. Exp. Psychol. Hum. Percept. Perform."},{"issue":"2","key":"19_CR8","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1080\/17470210600673818","volume":"60","author":"G Porter","year":"2007","unstructured":"Porter, G., Troscianko, T., Gilchrist, I.D.: Effort during visual search and counting: insights from pupillometry. Q. J. Exp. Psychol. 60(2), 211\u2013229 (2007)","journal-title":"Q. J. Exp. Psychol."},{"key":"19_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"424","DOI":"10.1007\/978-3-642-15561-1_31","volume-title":"Computer Vision \u2013 ECCV 2010","author":"\u013d Ladick\u00fd","year":"2010","unstructured":"Ladick\u00fd, \u013d., Sturgess, P., Alahari, K., Russell, C., Torr, P.H.S.: What, where and how many? Combining object detectors and CRFs. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6314, pp. 424\u2013437. Springer, Heidelberg (2010). doi:\n                      10.1007\/978-3-642-15561-1_31"},{"key":"19_CR10","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: Computer Vision and Pattern Recognition (CVPR), pp. 580\u2013587. IEEE (2014)","DOI":"10.1109\/CVPR.2014.81"},{"key":"19_CR11","doi-asserted-by":"crossref","unstructured":"Arbelaez, P., Pont-Tuset, J., Barron, J., Marques, F., Malik, J.: Multiscale combinatorial grouping. In: 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 328\u2013335. IEEE (2014)","DOI":"10.1109\/CVPR.2014.49"},{"key":"19_CR12","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 (CVPR), pp. 3431\u20133440 (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"19_CR13","unstructured":"Liang-Chieh, C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.: Semantic image segmentation with deep convolutional nets and fully connected CRFs. In: International Conference on Learning Representations (ICLR) (2015)"},{"key":"19_CR14","doi-asserted-by":"crossref","unstructured":"Zheng, S., Jayasumana, S., Romera-Paredes, B., Vineet, V., Su, Z., Du, D., Huang, C., Torr, P.H.: Conditional random fields as recurrent neural networks. In: IEEE International Conference on Computer Vision (ICCV) (2015)","DOI":"10.1109\/ICCV.2015.179"},{"key":"19_CR15","unstructured":"Liang, X., Wei, Y., Shen, X., Yang, J., Lin, L., Yan, S.: Proposal-free network for instance-level object segmentation. arXiv preprint \n                      arXiv:1509.02636\n                      \n                     (2015)"},{"key":"19_CR16","doi-asserted-by":"crossref","unstructured":"Tighe, J., Niethammer, M., Lazebnik, S.: Scene parsing with object instances and occlusion ordering. In: Computer Vision and Pattern Recognition (CVPR), pp. 3748\u20133755. IEEE (2014)","DOI":"10.1109\/CVPR.2014.479"},{"issue":"9","key":"19_CR17","doi-asserted-by":"publisher","first-page":"1731","DOI":"10.1109\/TPAMI.2011.208","volume":"34","author":"Y Yang","year":"2012","unstructured":"Yang, Y., Hallman, S., Ramanan, D., Fowlkes, C.C.: Layered object models for image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 34(9), 1731\u20131743 (2012)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"19_CR18","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Schwing, A.G., Fidler, S., Urtasun, R.: Monocular object instance segmentation and depth ordering with CNNs. In: IEEE International Conference on Computer Vision (ICCV), pp. 2614\u20132622 (2015)","DOI":"10.1109\/ICCV.2015.300"},{"key":"19_CR19","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. arXiv preprint \n                      arXiv:1409.0473\n                      \n                     (2014)"},{"key":"19_CR20","unstructured":"Graves, A., Schmidhuber, J.: Offline handwriting recognition with multidimensional recurrent neural networks. In: Advances in Neural Information Processing Systems (NIPS), pp. 545\u2013552 (2009)"},{"key":"19_CR21","unstructured":"Vinyals, O., Le, Q.: A neural conversational model. arXiv preprint \n                      arXiv:1506.05869\n                      \n                     (2015)"},{"key":"19_CR22","unstructured":"Gregor, K., Danihelka, I., Graves, A., Wierstra, D.: Draw: a recurrent neural network for image generation. In: Proceedings of the 32nd International Conference on Machine Learning (ICML) (2015)"},{"key":"19_CR23","doi-asserted-by":"crossref","unstructured":"Donahue, J., Anne Hendricks, L., Guadarrama, S., Rohrbach, M., Venugopalan, S., Saenko, K., Darrell, T.: Long-term recurrent convolutional networks for visual recognition and description. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2625\u20132634 (2015)","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"19_CR24","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Fei-Fei, L.: Deep visual-semantic alignments for generating image descriptions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3128\u20133137 (2015)","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"19_CR25","doi-asserted-by":"crossref","unstructured":"Vinyals, O., Toshev, A., Bengio, S., Erhan, D.: Show and tell: a neural image caption generator. In: Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3156\u20133164 (2015)","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"19_CR26","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"68","DOI":"10.1007\/978-3-319-21233-3_6","volume-title":"Algorithms for Computational Biology","author":"SK S\u00f8nderby","year":"2015","unstructured":"S\u00f8nderby, S.K., S\u00f8nderby, C.K., Nielsen, H., Winther, O.: Convolutional LSTM networks for subcellular localization of proteins. In: Dediu, A.-H., Hern\u00e1ndez-Quiroz, F., Mart\u00edn-Vide, C., Rosenblueth, D.A. (eds.) AlCoB 2015. LNCS, vol. 9199, pp. 68\u201380. Springer, Heidelberg (2015). doi:\n                      10.1007\/978-3-319-21233-3_6"},{"key":"19_CR27","doi-asserted-by":"crossref","unstructured":"Stewart, R., Andriluka, M.: End-to-end people detection in crowded scenes. arXiv preprint \n                      arXiv:1506.04878\n                      \n                     (2015)","DOI":"10.1109\/CVPR.2016.255"},{"key":"19_CR28","doi-asserted-by":"crossref","unstructured":"Pavel, M.S., Schulz, H., Behnke, S.: Recurrent convolutional neural networks for object-class segmentation of rgb-d video. In: International Joint Conference on Neural Networks (IJCNN), pp. 1\u20138. IEEE (2015)","DOI":"10.1109\/IJCNN.2015.7280820"},{"issue":"5","key":"19_CR29","doi-asserted-by":"publisher","first-page":"1039","DOI":"10.1162\/089976604773135096","volume":"16","author":"CK Williams","year":"2004","unstructured":"Williams, C.K., Titsias, M.K.: Greedy learning of multiple objects in images using robust statistics and factorial learning. Neural Comput. 16(5), 1039\u20131062 (2004)","journal-title":"Neural Comput."},{"key":"19_CR30","unstructured":"Ba, J., Mnih, V., Kavukcuoglu, K.: Multiple object recognition with visual attention. In: International Conference on Learning Representations (ICLR) (2015)"},{"key":"19_CR31","unstructured":"Xu, K., Ba, J., Kiros, R., Cho, K., Courville, A., Salakhudinov, R., Zemel, R., Bengio, Y.: Show, attend and tell: neural image caption generation with visual attention. In: Proceedings of the 32nd International Conference on Machine Learning (ICML), pp. 2048\u20132057 (2015)"},{"key":"19_CR32","unstructured":"Mnih, V., Heess, N., Graves, A., et al.: Recurrent models of visual attention. In: Advances in Neural Information Processing Systems (NIPS), pp. 2204\u20132212 (2014)"},{"key":"19_CR33","unstructured":"Hermann, K.M., Kocisky, T., Grefenstette, E., Espeholt, L., Kay, W., Suleyman, M., Blunsom, P.: Teaching machines to read and comprehend. In: Advances in Neural Information Processing Systems (NIPS), pp. 1693\u20131701 (2015)"},{"issue":"8","key":"19_CR34","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":"19_CR35","doi-asserted-by":"crossref","unstructured":"Dosovitskiy, A., Fischery, P., Ilg, E., Hazirbas, C., Golkov, V., van der Smagt, P., Cremers, D., Brox, T., et al.: Flownet: learning optical flow with convolutional networks. In: IEEE International Conference on Computer Vision (ICCV), pp. 2758\u20132766. IEEE (2015)","DOI":"10.1109\/ICCV.2015.316"},{"key":"19_CR36","unstructured":"Xingjian, S., Chen, Z., Wang, H., Yeung, D.Y., Wong, W.k., Woo, W.c.: Convolutional lstm network: a machine learning approach for precipitation nowcasting. In: Advances in Neural Information Processing Systems (NIPS), pp. 802\u2013810 (2015)"},{"key":"19_CR37","unstructured":"Kr\u00e4henb\u00fchl, P., Koltun, V.: Parameter learning and convergent inference for dense random fields. In: Proceedings of the 30th International Conference on Machine Learning (ICML), pp. 513\u2013521 (2013)"},{"key":"19_CR38","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"616","DOI":"10.1007\/978-3-319-10590-1_40","volume-title":"Computer Vision \u2013 ECCV 2014","author":"N Silberman","year":"2014","unstructured":"Silberman, N., Sontag, D., Fergus, R.: Instance segmentation of indoor scenes using a coverage loss. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8689, pp. 616\u2013631. Springer, Heidelberg (2014). doi:\n                      10.1007\/978-3-319-10590-1_40"},{"key":"19_CR39","unstructured":"Collobert, R., Kavukcuoglu, K., Farabet, C.: Torch7: a matlab-like environment for machine learning. In: BigLearn, NIPS Workshop. Number EPFL-CONF-192376 (2011)"},{"key":"19_CR40","unstructured":"Kingma, D., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint \n                      arXiv:1412.6980\n                      \n                     (2014)"},{"key":"19_CR41","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., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., Zitnick, C.L.: 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, Heidelberg (2014). doi:\n                      10.1007\/978-3-319-10602-1_48"},{"key":"19_CR42","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems (NIPS), pp. 91\u201399 (2015)"},{"key":"19_CR43","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1016\/j.ecoinf.2013.07.004","volume":"23","author":"M Minervini","year":"2014","unstructured":"Minervini, M., Abdelsamea, M.M., Tsaftaris, S.A.: Image-based plant phenotyping with incremental learning and active contours. Ecol. Inform. 23, 35\u201348 (2014)","journal-title":"Ecol. Inform."},{"key":"19_CR44","doi-asserted-by":"crossref","unstructured":"Minervini, M., Fischbach, A., Scharr, H., Tsaftaris, S.A.: Finely-grained annotated datasets for image-based plant phenotyping. Pattern Recognition Letters Special Issue on Fine-grained Categorization in Ecological Multimedia (2015)","DOI":"10.1016\/j.patrec.2015.10.013"},{"key":"19_CR45","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1007\/978-3-319-16220-1_5","volume-title":"Computer Vision - ECCV 2014 Workshops","author":"J-M Pape","year":"2015","unstructured":"Pape, J.-M., Klukas, C.: 3-D histogram-based segmentation and leaf detection for rosette plants. In: Agapito, L., Bronstein, M.M., Rother, C. (eds.) ECCV 2014. LNCS, vol. 8928, pp. 61\u201374. Springer, Heidelberg (2015). doi:\n                      10.1007\/978-3-319-16220-1_5"},{"key":"19_CR46","doi-asserted-by":"publisher","first-page":"585","DOI":"10.1007\/s00138-015-0737-3","volume":"27","author":"H Scharr","year":"2016","unstructured":"Scharr, H., Minervini, M., French, A.P., Klukas, C., Kramer, D.M., Liu, X., Luengo Muntion, I., Pape, J.M., Polder, G., Vukadinovic, D., Yin, X., Tsaftaris, S.A.: Leaf segmentation in plant phenotyping: a collation study. Mach. Vision Appl. 27, 585\u2013606 (2016)","journal-title":"Mach. Vision Appl."},{"key":"19_CR47","unstructured":"Barrow, H.G., Tenenbaum, J.M., Bolles, R.C., Wolf, H.C.: Parametric correspondence and chamfer matching: two new techniquesfor image matching. Technical report, DTIC Document (1977)"},{"key":"19_CR48","doi-asserted-by":"crossref","unstructured":"Yin, X., Liu, X., Chen, J., Kramer, D.M.: Multi-leaf tracking from fluorescence plant videos. In: 2014 IEEE International Conference on Image Processing (ICIP), pp. 408\u2013412. IEEE (2014)","DOI":"10.1109\/ICIP.2014.7025081"},{"key":"19_CR49","doi-asserted-by":"crossref","unstructured":"Giuffrida, M.V., Minervini, M., Tsaftaris, S.A.: Learning to count leaves in rosette plants. In: British Machine Vision Conference (CVPPP Workshop). BMVA Press (2015)","DOI":"10.5244\/C.29.CVPPP.1"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2016"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-46466-4_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,10,10]],"date-time":"2020-10-10T01:27:14Z","timestamp":1602293234000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-46466-4_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319464657","9783319464664"],"references-count":49,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-46466-4_19","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016]]},"assertion":[{"value":"17 September 2016","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":"Amsterdam","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"The Netherlands","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2016","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 October 2016","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 October 2016","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2016","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.eccv2016.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"}]}}