{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T06:25:40Z","timestamp":1743143140586,"version":"3.40.3"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030317225"},{"type":"electronic","value":"9783030317232"}],"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\/978-3-030-31723-2_35","type":"book-chapter","created":{"date-parts":[[2019,10,31]],"date-time":"2019-10-31T00:05:31Z","timestamp":1572480331000},"page":"416-428","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["One-Shot Video Object Segmentation Initialized with Referring Expression"],"prefix":"10.1007","author":[{"given":"XiaoQing","family":"Bu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianming","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiayu","family":"Liang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kunliang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yukuan","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guanghao","family":"Jin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,10,31]]},"reference":[{"key":"35_CR1","doi-asserted-by":"crossref","unstructured":"Andreas, J., Rohrbach, M., Darrell, T., Dan, K.: Learning to compose neural networks for question answering (2016)","DOI":"10.18653\/v1\/N16-1181"},{"key":"35_CR2","doi-asserted-by":"crossref","unstructured":"Andreas, J., Rohrbach, M., Darrell, T., Klein, D.: Neural module networks. In: IEEE Conference on Computer Vision and Pattern Recognition (2015)","DOI":"10.1109\/CVPR.2016.12"},{"key":"35_CR3","doi-asserted-by":"crossref","unstructured":"Avinash Ramakanth, S., Venkatesh Babu, R.: SeamSeg: video object segmentation using patch seams. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 376\u2013383 (2014)","DOI":"10.1109\/CVPR.2014.55"},{"key":"35_CR4","doi-asserted-by":"crossref","unstructured":"Caelles, S., Maninis, K.K., Pont-Tuset, J., Leal-Taix\u00e9, L., Cremers, D., Van\u00a0Gool,\u00a0L.: One-shot video object segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 221\u2013230 (2017)","DOI":"10.1109\/CVPR.2017.565"},{"key":"35_CR5","doi-asserted-by":"crossref","unstructured":"Chang, J., Wei, D., Fisher, J.W.: A video representation using temporal superpixels. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2051\u20132058 (2013)","DOI":"10.1109\/CVPR.2013.267"},{"key":"35_CR6","doi-asserted-by":"crossref","unstructured":"Fan, Q., Zhong, F., Lischinski, D., Cohen-Or, D., Chen, B.: JumpCut: non-successive mask transfer and interpolation for video cutout. ACM Trans. Graph. 34(6), Article No. 195 (2015)","DOI":"10.1145\/2816795.2818105"},{"key":"35_CR7","doi-asserted-by":"crossref","unstructured":"Grundmann, M., Kwatra, V., Han, M., Essa, I.: Efficient hierarchical graph-based video segmentation. In: 2010 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2141\u20132148. IEEE (2010)","DOI":"10.1109\/CVPR.2010.5539893"},{"key":"35_CR8","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":"35_CR9","unstructured":"Kan, C., Kovvuri, R., Nevatia, R.: Query-guided regression network with context policy for phrase grounding (2017)"},{"key":"35_CR10","doi-asserted-by":"crossref","unstructured":"Lee, Y.J., Kim, J., Grauman, K.: Key-segments for video object segmentation. In: 2011 IEEE International Conference on Computer Vision (ICCV), pp. 1995\u20132002. IEEE (2011)","DOI":"10.1109\/ICCV.2011.6126471"},{"key":"35_CR11","doi-asserted-by":"crossref","unstructured":"Li, F., Kim, T., Humayun, A., Tsai, D., Rehg, J.M.: Video segmentation by tracking many figure-ground segments. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2192\u20132199 (2013)","DOI":"10.1109\/ICCV.2013.273"},{"key":"35_CR12","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"649","DOI":"10.1007\/978-3-319-27194-1_64","volume-title":"Chinese Lexical Semantics","author":"J Li","year":"2015","unstructured":"Li, J., Mu, L., Zan, H., Zhang, K.: Research on Chinese parsing based on the improved compositional vector grammar. In: Lu, Q., Gao, H. (eds.) Chinese Lexical Semantics. LNCS (LNAI), vol. 9332, pp. 649\u2013658. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-27194-1_64"},{"key":"35_CR13","doi-asserted-by":"crossref","unstructured":"Liu, C., Zhe, L., Shen, X., Yang, J., Xin, L., Yuille, A.: Recurrent multimodal interaction for referring image segmentation (2017)","DOI":"10.1109\/ICCV.2017.143"},{"key":"35_CR14","doi-asserted-by":"crossref","unstructured":"Liu, J., Liang, W., Yang, M.H.: Referring expression generation and comprehension via attributes. In: IEEE International Conference on Computer Vision (2017)","DOI":"10.1109\/ICCV.2017.520"},{"key":"35_CR15","doi-asserted-by":"crossref","unstructured":"Mao, J., Huang, J., Toshev, A., Camburu, O., Yuille, A., Murphy, K.: Generation and comprehension of unambiguous object descriptions (2016)","DOI":"10.1109\/CVPR.2016.9"},{"key":"35_CR16","doi-asserted-by":"crossref","unstructured":"M\u00e4rki, N., Perazzi, F., Wang, O., Sorkine-Hornung, A.: Bilateral space video segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 743\u2013751 (2016)","DOI":"10.1109\/CVPR.2016.87"},{"key":"35_CR17","unstructured":"Mitchell, M., Deemter, K.V., Reiter, E.: Natural reference to objects in a visual domain. In: INLG - Sixth International Natural Language Generation Conference (2010)"},{"issue":"2","key":"35_CR18","first-page":"1","volume":"51","author":"I Paraboni","year":"2016","unstructured":"Paraboni, I., Galindo, M.R., Iacovelli, D.: Stars2: a corpus of object descriptions in a visual domain. Lang. Resour. Eval. 51(2), 1\u201324 (2016)","journal-title":"Lang. Resour. Eval."},{"key":"35_CR19","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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 724\u2013732 (2016)","DOI":"10.1109\/CVPR.2016.85"},{"key":"35_CR20","doi-asserted-by":"crossref","unstructured":"Perazzi, F., Wang, O., Gross, M., Sorkine-Hornung, A.: Fully connected object proposals for video segmentation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3227\u20133234 (2015)","DOI":"10.1109\/ICCV.2015.369"},{"key":"35_CR21","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, pp. 91\u201399 (2015)"},{"key":"35_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"817","DOI":"10.1007\/978-3-319-46448-0_49","volume-title":"Computer Vision \u2013 ECCV 2016","author":"A Rohrbach","year":"2016","unstructured":"Rohrbach, A., Rohrbach, M., Hu, R., Darrell, T., Schiele, B.: Grounding of textual phrases in images by reconstruction. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 817\u2013834. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_49"},{"key":"35_CR23","doi-asserted-by":"crossref","unstructured":"Wang, L., Yin, L., Lazebnik, S.: Learning deep structure-preserving image-text embeddings. In: Computer Vision and Pattern Recognition (2016)","DOI":"10.1109\/CVPR.2016.541"},{"key":"35_CR24","doi-asserted-by":"crossref","unstructured":"Xie, S., Tu, Z.: Holistically-nested edge detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1395\u20131403 (2015)","DOI":"10.1109\/ICCV.2015.164"},{"key":"35_CR25","doi-asserted-by":"crossref","unstructured":"Yu, L., Hao, T., Bansal, M., Berg, T.L.: A joint speaker-listener-reinforcer model for referring expressions (2016)","DOI":"10.1109\/CVPR.2017.375"},{"key":"35_CR26","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":"35_CR27","doi-asserted-by":"crossref","unstructured":"Yu, L., Zhe, L., Shen, X., Yang, J., Berg, T.L.: MAttNet: modular attention network for referring expression comprehension (2018)","DOI":"10.1109\/CVPR.2018.00142"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-31723-2_35","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T00:24:47Z","timestamp":1730334287000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-31723-2_35"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030317225","9783030317232"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-31723-2_35","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":"31 October 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Xi'an","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","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":"8 November 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 November 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.prcv2019.com\/en\/index.html","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":"412","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":"165","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":"40% - 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":"4","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":"4","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)"}}]}}