{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T08:01:06Z","timestamp":1777104066583,"version":"3.51.4"},"publisher-location":"Cham","reference-count":41,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319105895","type":"print"},{"value":"9783319105901","type":"electronic"}],"license":[{"start":{"date-parts":[[2014,1,1]],"date-time":"2014-01-01T00:00:00Z","timestamp":1388534400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2014]]},"DOI":"10.1007\/978-3-319-10590-1_7","type":"book-chapter","created":{"date-parts":[[2014,8,13]],"date-time":"2014-08-13T21:50:08Z","timestamp":1407966608000},"page":"95-110","source":"Crossref","is-referenced-by-count":50,"title":["Linking People in Videos with \u201cTheir\u201d Names Using Coreference Resolution"],"prefix":"10.1007","author":[{"given":"Vignesh","family":"Ramanathan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Armand","family":"Joulin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Percy","family":"Liang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li","family":"Fei-Fei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"7_CR1","unstructured":"Cisco visual networking index: Global mobile data traffic forecast update. Tech. rep., Cisco (February 2014)"},{"key":"7_CR2","unstructured":"Bach, F., Harchaoui, Z.: Diffrac: A discriminative and flexible framework for clustering. In: NIPS (2007)"},{"key":"7_CR3","first-page":"1107","volume":"3","author":"K. Barnard","year":"2003","unstructured":"Barnard, K., Duygulu, P., Forsyth, D., de Freitas, N., Blei, D.M., Jordan, M.I.: Matching words and pictures. Journal of Machine Learning Research\u00a03, 1107\u20131135 (2003)","journal-title":"Journal of Machine Learning Research"},{"key":"7_CR4","doi-asserted-by":"crossref","unstructured":"B\u00e4uml, M., Tapaswi, M., Stiefelhagen, R.: Semi-supervised Learning with Constraints for Person Identification in Multimedia Data. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR (June 2013)","DOI":"10.1109\/CVPR.2013.462"},{"key":"7_CR5","doi-asserted-by":"crossref","unstructured":"Berg, T.L., Berg, A.C., Edwards, J., Maire, M., White, R., Teh, Y.W., Learned-Miller, E.G., Forsyth, D.A.: Names and faces in the news. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), vol.\u00a02, pp. 848\u2013854 (2004)","DOI":"10.1109\/CVPR.2004.1315253"},{"key":"7_CR6","doi-asserted-by":"crossref","unstructured":"Bojanowski, P., Bach, F., Laptev, I., Ponce, J., Schmid, C., Sivic, J.: Finding actors and actions in movies. In: ICCV (2013)","DOI":"10.1109\/ICCV.2013.283"},{"key":"7_CR7","doi-asserted-by":"crossref","unstructured":"Cour, T., Sapp, B., Jordan, C., Taskar, B.: Learning from ambiguously labeled images. In: CVPR (2009)","DOI":"10.1109\/CVPR.2009.5206667"},{"key":"7_CR8","doi-asserted-by":"crossref","unstructured":"Das, P., Xu, C., Doell, R.F., Corso, J.J.: A thousand frames in just a few words: Lingual description of videos through latent topics and sparse object stitching. In: CVPR (2013)","DOI":"10.1109\/CVPR.2013.340"},{"key":"7_CR9","doi-asserted-by":"crossref","unstructured":"Duchenne, O., Laptev, I., Sivic, J., Bach, F., Ponce, J.: Automatic annotation of human actions in video. In: ICCV (2009)","DOI":"10.1109\/ICCV.2009.5459279"},{"key":"7_CR10","unstructured":"Duda, R.O., Hart, P.E., Stork, D.G.: Pattern classification. John Wiley & Sons (2012)"},{"key":"7_CR11","doi-asserted-by":"crossref","unstructured":"Everingham, M., Sivic, J., Zisserman, A.: Hello! my name is... buffy automatic naming of characters in tv video. In: BMVC (2006)","DOI":"10.5244\/C.20.92"},{"key":"7_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1007\/978-3-642-15561-1_2","volume-title":"Computer Vision \u2013 ECCV 2010","author":"A. Farhadi","year":"2010","unstructured":"Farhadi, A., Hejrati, M., Sadeghi, M., Young, P., Rashtchian, C., Hockenmaier, J., Forsyth, D.: Every picture tells a story: Generating sentences from images. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part IV. LNCS, vol.\u00a06314, pp. 15\u201329. Springer, Heidelberg (2010)"},{"key":"7_CR13","doi-asserted-by":"crossref","unstructured":"Fidler, S., Sharma, A., Urtasun, R.: A sentence is worth a thousand pixels. In: CVPR. IEEE (2013)","DOI":"10.1109\/CVPR.2013.260"},{"key":"7_CR14","doi-asserted-by":"crossref","unstructured":"Guillaumin, M., Mensink, T., Verbeek, J., Schmid, C.: Tagprop: Discriminative metric learning in nearest neighbor models for image auto-annotation. In: CVPR (2009)","DOI":"10.1109\/ICCV.2009.5459266"},{"key":"7_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1007\/978-3-540-88682-2_3","volume-title":"Computer Vision \u2013 ECCV 2008","author":"A. Gupta","year":"2008","unstructured":"Gupta, A., Davis, L.S.: Beyond nouns: Exploiting prepositions and comparative adjectives for learning visual classifiers. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part I. LNCS, vol.\u00a05302, pp. 16\u201329. Springer, Heidelberg (2008)"},{"key":"7_CR16","doi-asserted-by":"crossref","unstructured":"Gupta, A., Srinivasan, P., Shi, J., Davis, L.S.: Understanding videos, constructing plots learning a visually grounded storyline model from annotated videos. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009, pp. 2012\u20132019. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206492"},{"key":"7_CR17","unstructured":"Haghighi, A., Klein, D.: Coreference resolution in a modular, entity-centered model. In: HLT-NAACL (2010)"},{"key":"7_CR18","doi-asserted-by":"crossref","unstructured":"Han, X., Sun, L., Zhao, J.: Collective entity linking in web text: a graph-based method. In: ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 765\u2013774 (2011)","DOI":"10.1145\/2009916.2010019"},{"key":"7_CR19","unstructured":"Hobbs, J.R., Mulkar-Mehta, R.: Using abduction for video-text coreference. In: Proceedings of BOEMIE 2008 Workshop on Ontology Evolution and Multimedia Information Extraction (2008)"},{"key":"7_CR20","unstructured":"Hodosh, M., Young, P., Rashtchian, C., Hockenmaier, J.: Cross-caption coreference resolution for automatic image understanding. In: Conference on Computational Natural Language Learning (2010)"},{"key":"7_CR21","unstructured":"Jie, L., Caputo, B., Ferrari, V.: Who\u2019s doing what: Joint modeling of names and verbs for simultaneous face and pose annotation. In: NIPS (2009)"},{"issue":"7","key":"7_CR22","doi-asserted-by":"publisher","first-page":"1409","DOI":"10.1109\/TPAMI.2011.239","volume":"34","author":"Z. Kalal","year":"2012","unstructured":"Kalal, Z., Mikolajczyk, K., Matas, J.: Tracking-learning-detection. IEEE Transactions on Pattern Analysis and Machine Intelligence\u00a034(7), 1409\u20131422 (2012)","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"7_CR23","doi-asserted-by":"crossref","unstructured":"Kong, C., Lin, D., Bansal, M., Urtasun, R., Fidler, S.: What are you talking about? text-to-image coreference. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.455"},{"key":"7_CR24","doi-asserted-by":"crossref","unstructured":"Kulkarni, G., Premraj, V., Dhar, S., Li, S., Choi, Y., Berg, A.C., Berg, T.L.: Baby talk: Understanding and generating simple image descriptions. In: CVPR (2011)","DOI":"10.1109\/CVPR.2011.5995466"},{"key":"7_CR25","doi-asserted-by":"crossref","unstructured":"Kummerfeld, J.K., Klein, D.: Error-driven analysis of challenges in coreference resolution. In: Proceedings of EMNLP (2013)","DOI":"10.18653\/v1\/D13-1027"},{"key":"7_CR26","doi-asserted-by":"crossref","unstructured":"Laptev, I., Marsza\u0142ek, M., Schmid, C., Rozenfeld, B.: Learning realistic human actions from movies. In: CVPR (2008)","DOI":"10.1109\/CVPR.2008.4587756"},{"key":"7_CR27","unstructured":"Lee, H., Peirsman, Y., Chang, A., Chambers, N., Surdeanu, M., Jurafsky, D.: Stanford\u2019s mulit-pass sieve coreference resolution system at the conll-2011 shared task. In: CoNLL 2011 Shared Task (2011)"},{"key":"7_CR28","doi-asserted-by":"crossref","unstructured":"Marsza\u0142ek, M., Laptev, I., Schmid, C.: Actions in context. In: CVPR (2009)","DOI":"10.1109\/CVPRW.2009.5206557"},{"key":"7_CR29","unstructured":"Matuszek, C., FitzGerald, N., Zettlemoyer, L., Bo, L., Fox, D.: A joint model of language and perception for grounded attribute learning. In: ICML (2012)"},{"key":"7_CR30","unstructured":"Motwani, T.S., Mooney, R.J.: Improving video activity recognition using object recognition and text mining. In: ECAI (2012)"},{"key":"7_CR31","unstructured":"Ordonez, V., Kulkarni, G., Berg, T.L.: Im2text: Describing images using 1 million captioned photographs. In: NIPS (2011)"},{"key":"7_CR32","unstructured":"Pham, P., Moens, M.F., Tuytelaars, T.: Linking names and faces: Seeing the problem in different ways. In: Proceedings of the 10th European Conference on Computer Vision: Workshop Faces in \u2018Real-life\u2019 Images: Detection, Alignment, and Recognition, pp. 68\u201381 (2008)"},{"key":"7_CR33","doi-asserted-by":"crossref","unstructured":"Ramanathan, V., Liang, P., Fei-Fei, L.: Video event understanding using natural language descriptions. In: ICCV (2013)","DOI":"10.1109\/ICCV.2013.117"},{"key":"7_CR34","doi-asserted-by":"crossref","unstructured":"Rohrbach, M., Stark, M., Szarvas, G., Schiele, B.: What helps where \u2013 and why? semantic relatedness for knowledge transfer. In: CVPR (2010)","DOI":"10.1109\/CVPR.2010.5540121"},{"key":"7_CR35","doi-asserted-by":"crossref","unstructured":"Rohrbach, M., Wei, Q., Titov, I., Thater, S., Pinkal, M., Schiele, B.: Translating video content to natural language descriptions. In: ICCV (2013)","DOI":"10.1109\/ICCV.2013.61"},{"key":"7_CR36","unstructured":"Silberer, C., Ferrari, V., Lapata, M.: Models of semantic representation with visual attributes. In: ACL (2013)"},{"key":"7_CR37","doi-asserted-by":"crossref","unstructured":"Sivic, J., Everingham, M., Zisserman, A.: \u201cWho are you?\u201d - learning person specific classifiers from video. In: CVPR (2009)","DOI":"10.1109\/CVPR.2009.5206513"},{"key":"7_CR38","doi-asserted-by":"crossref","unstructured":"Tapaswi, M., B\u00e4uml, M., Stiefelhagen, R.: \u201cKnock! Knock! Who is it?\u201d Probabilistic Person Identification in TV Series. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR (June 2012)","DOI":"10.1109\/CVPR.2012.6247986"},{"key":"7_CR39","doi-asserted-by":"crossref","unstructured":"Tellex, S., Kollar, T., Dickerson, S., Walter, M.R., Banerjee, A.G., Teller, S., Roy, N.: Understanding natural language commands for robotic navigation and mobile manipulation. AAAI (2011)","DOI":"10.1609\/aaai.v25i1.7979"},{"key":"7_CR40","doi-asserted-by":"crossref","unstructured":"Vijayanarasimhan, S., Grauman, K.: Keywords to visual categories: Multiple-instance learning for weakly supervised object categorization. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2008, pp. 1\u20138. IEEE (2008)","DOI":"10.1109\/CVPR.2008.4587632"},{"key":"7_CR41","unstructured":"Wang, Y., Mori, G.: A discriminative latent model of image region and object tag correspondence. In: NIPS (2010)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2014"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-10590-1_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,4]],"date-time":"2025-05-04T05:26:47Z","timestamp":1746336407000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-10590-1_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014]]},"ISBN":["9783319105895","9783319105901"],"references-count":41,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-10590-1_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2014]]}}}