{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,8]],"date-time":"2026-08-08T17:42:02Z","timestamp":1786210922670,"version":"3.56.0"},"publisher-location":"Cham","reference-count":51,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030208691","type":"print"},{"value":"9783030208707","type":"electronic"}],"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\/978-3-030-20870-7_8","type":"book-chapter","created":{"date-parts":[[2019,5,24]],"date-time":"2019-05-24T16:14:21Z","timestamp":1558714461000},"page":"123-141","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":121,"title":["Video Object Segmentation with Language Referring Expressions"],"prefix":"10.1007","author":[{"given":"Anna","family":"Khoreva","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anna","family":"Rohrbach","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bernt","family":"Schiele","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2019,5,25]]},"reference":[{"key":"8_CR1","doi-asserted-by":"crossref","unstructured":"Balajee Vasudevan, A., Dai, D., Van Gool, L.: Object referring in videos with language and human gaze. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00434"},{"key":"8_CR2","unstructured":"Benard, A., Gygli, M.: Interactive video object segmentation in the wild. arXiv:1801.00269 (2017)"},{"key":"8_CR3","doi-asserted-by":"crossref","unstructured":"Caelles, S., Maninis, K.K., Pont-Tuset, J., Leal-Taixe, L., Cremers, D., Gool, L.V.: One-shot video object segmentation. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.565"},{"key":"8_CR4","doi-asserted-by":"crossref","unstructured":"Chen, K., Kovvuri, R., Nevatia, R.: Query-guided regression network with context policy for phrase grounding. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.95"},{"key":"8_CR5","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. arXiv:1606.00915 (2016)"},{"key":"8_CR6","doi-asserted-by":"crossref","unstructured":"Cheng, J., Tsai, Y.H., Wang, S., Yang, M.H.: SegFlow: joint learning for video object segmentation and optical flow. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.81"},{"key":"8_CR7","doi-asserted-by":"publisher","first-page":"569","DOI":"10.1109\/TPAMI.2014.2345401","volume":"37","author":"MM Cheng","year":"2015","unstructured":"Cheng, M.M., Mitra, N.J., Huang, X., Torr, P.H.S., Hu, S.M.: Global contrast based salient region detection. PAMI 37, 569\u2013582 (2015)","journal-title":"PAMI"},{"key":"8_CR8","doi-asserted-by":"publisher","first-page":"1558","DOI":"10.1109\/TPAMI.2014.2377715","volume":"37","author":"P Doll\u00e1r","year":"2015","unstructured":"Doll\u00e1r, P., Zitnick, C.L.: Fast edge detection using structured forests. PAMI. 37, 1558\u20131570 (2015)","journal-title":"PAMI."},{"key":"8_CR9","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":"8_CR10","doi-asserted-by":"crossref","unstructured":"Gavrilyuk, K., Ghodrati, A., Li, Z., Snoek, C.G.: Actor and action video segmentation from a sentence. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00624"},{"key":"8_CR11","unstructured":"Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: AISTATS (2010)"},{"key":"8_CR12","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.B.: Mask R-CNN. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"8_CR13","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"8_CR14","doi-asserted-by":"crossref","unstructured":"Hu, R., Rohrbach, M., Andreas, J., Darrell, T., Saenko, K.: Modeling relationships in referential expressions with compositional modular networks. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.470"},{"key":"8_CR15","unstructured":"Hu, Y.T., Huang, J., Schwing, A.G.: MaskRNN: instance level video object segmentation. In: NIPS (2017)"},{"key":"8_CR16","doi-asserted-by":"crossref","unstructured":"Ilg, E., Mayer, N., Saikia, T., Keuper, M., Dosovitskiy, A., Brox, T.: FlowNet 2.0: evolution of optical flow estimation with deep networks. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.179"},{"key":"8_CR17","doi-asserted-by":"crossref","unstructured":"Jain, S.D., Xiong, B., Grauman, K.: FusionSeg: learning to combine motion and appearance for fully automatic segmentation of generic objects in videos. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.228"},{"key":"8_CR18","unstructured":"Khoreva, A., Benenson, R., Ilg, E., Brox, T., Schiele, B.: Lucid data dreaming for multiple object tracking. arXiv:1703.09554 (2017)"},{"key":"8_CR19","doi-asserted-by":"crossref","unstructured":"Koh, Y., Kim, C.: Primary object segmentation in videos based on region augmentation and reduction. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.784"},{"key":"8_CR20","unstructured":"Krishna, R., et al.: Visual genome: connecting language and vision using crowdsourced dense image annotations. arXiv:1602.07332 (2016)"},{"key":"8_CR21","doi-asserted-by":"crossref","unstructured":"Li, R., et al.: Referring image segmentation via recurrent refinement networks. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00602"},{"key":"8_CR22","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: CVPR (2017)","DOI":"10.1109\/CVPR.2017.777"},{"key":"8_CR23","doi-asserted-by":"crossref","unstructured":"Lin, D., Dai, J., Jia, J., He, K., Sun, J.: ScribbleSup: scribble-supervised convolutional networks for semantic segmentation. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.344"},{"key":"8_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":"TY 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":"8_CR25","doi-asserted-by":"crossref","unstructured":"Liu, C., Lin, Z., Shen, X., Yang, J., Lu, X., Yuille, A.: Recurrent multimodal interaction for referring image segmentation. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.143"},{"key":"8_CR26","unstructured":"Liu, W., Rabinovich, A., Berg, A.C.: ParseNet: looking wider to see better. arxiv:1506.04579 (2015)"},{"key":"8_CR27","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"8_CR28","doi-asserted-by":"crossref","unstructured":"Luo, R., Shakhnarovich, G.: Comprehension-guided referring expressions. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.333"},{"key":"8_CR29","doi-asserted-by":"crossref","unstructured":"Maninis, K., Caelles, S., Pont-Tuset, J., Gool, L.V.: Deep extreme cut: from extreme points to object segmentation. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00071"},{"key":"8_CR30","unstructured":"Maninis, K., et al.: Video object segmentation without temporal information. arxiv:1709.06031 (2017)"},{"key":"8_CR31","doi-asserted-by":"crossref","unstructured":"Mao, J., Jonathan, H., Toshev, A., Camburu, O., Yuille, A., Murphy, K.: Generation and comprehension of unambiguous object descriptions. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.9"},{"key":"8_CR32","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"792","DOI":"10.1007\/978-3-319-46493-0_48","volume-title":"Computer Vision \u2013 ECCV 2016","author":"VK Nagaraja","year":"2016","unstructured":"Nagaraja, V.K., Morariu, V.I., Davis, L.S.: Modeling context between objects for referring expression understanding. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 792\u2013807. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_48"},{"key":"8_CR33","doi-asserted-by":"crossref","unstructured":"Papazoglou, A., Ferrari, V.: Fast object segmentation in unconstrained video. In: ICCV (2013)","DOI":"10.1109\/ICCV.2013.223"},{"key":"8_CR34","doi-asserted-by":"crossref","unstructured":"Perazzi, F., Pont-Tuset, J., McWilliams, B., Gool, L.V., Gross, M., Sorkine-Hornung, A.: A benchmark dataset and evaluation methodology for video object segmentation. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.85"},{"key":"8_CR35","doi-asserted-by":"crossref","unstructured":"Perazzi, F., Khoreva, A., Benenson, R., Schiele, B., Sorkine-Hornung, A.: Learning video object segmentation from static images. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.372"},{"key":"8_CR36","doi-asserted-by":"crossref","unstructured":"Perazzi, F., Wang, O., Gross, M., Sorkine-Hornung, A.: Fully connected object proposals for video segmentation. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.369"},{"key":"8_CR37","unstructured":"Pont-Tuset, J., et al.: The 2018 DAVIS challenge on video object segmentation. arXiv:1803.00557 (2018)"},{"key":"8_CR38","unstructured":"Pont-Tuset, J., Perazzi, F., Caelles, S., Arbel\u00e1ez, P., Sorkine-Hornung, A., Van Gool, L.: The 2017 DAVIS challenge on video object segmentation. arXiv:1704.00675 (2017)"},{"key":"8_CR39","doi-asserted-by":"crossref","unstructured":"Thomee, B., et al.: YFCC100M: the new data in multimedia research. Commun. ACM (2016)","DOI":"10.1145\/2812802"},{"key":"8_CR40","doi-asserted-by":"crossref","unstructured":"Tokmakov, P., Alahari, K., Schmid, C.: Learning video object segmentation with visual memory. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.480"},{"key":"8_CR41","doi-asserted-by":"crossref","unstructured":"Tsai, Y.H., Yang, M.H., Black, M.J.: Video segmentation via object flow. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.423"},{"key":"8_CR42","doi-asserted-by":"crossref","unstructured":"Voigtlaender, P., Leibe, B.: Online adaptation of convolutional neural networks for the 2017 DAVIS challenge on video object segmentation. In: DAVIS Challenge - CVPR Workshops (2017)","DOI":"10.5244\/C.31.116"},{"key":"8_CR43","doi-asserted-by":"crossref","unstructured":"Voigtlaender, P., Leibe, B.: Online adaptation of convolutional neural networks for video object segmentation. In: BMVC (2017)","DOI":"10.5244\/C.31.116"},{"key":"8_CR44","doi-asserted-by":"crossref","unstructured":"Wang, P., et al.: Understanding convolution for semantic segmentation. arXiv:1702.08502 (2017)","DOI":"10.1109\/WACV.2018.00163"},{"key":"8_CR45","doi-asserted-by":"crossref","unstructured":"Wang, W., Shen, J.: Super-trajectory for video segmentation. arXiv:1702.08634 (2017)","DOI":"10.1109\/ICCV.2017.185"},{"key":"8_CR46","doi-asserted-by":"crossref","unstructured":"Wen, L., Du, D., Lei, Z., Li, S.Z., Yang, M.H.: JOTS: joint online tracking and segmentation. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298835"},{"key":"8_CR47","doi-asserted-by":"crossref","unstructured":"Xiao, F., Lee, Y.J.: Track and segment: an iterative unsupervised approach for video object proposals. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.107"},{"key":"8_CR48","unstructured":"Yeh, R., Xiong, J., Hwu, W.M., Do, M., Schwing, A.: Interpretable and globally optimal prediction for textual grounding using image concepts. In: NIPS (2017)"},{"key":"8_CR49","doi-asserted-by":"crossref","unstructured":"Yu, L., et al.: MAttNet: modular attention network for referring expression comprehension. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00142"},{"key":"8_CR50","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":"8_CR51","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Yuan, L., Guo, Y., He, Z., Huang, I.A., Lee, H.: Discriminative bimodal networks for visual localization and detection with natural language queries. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.122"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2018"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-20870-7_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,10,5]],"date-time":"2021-10-05T11:15:52Z","timestamp":1633432552000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-20870-7_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030208691","9783030208707"],"references-count":51,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-20870-7_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"25 May 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Perth, WA","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australia","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":"2 December 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 December 2018","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":"accv2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/accv2018.net\/","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":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"979","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":"274","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":"28% - 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":"2.7","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}