{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T06:37:18Z","timestamp":1783665438317,"version":"3.55.0"},"reference-count":44,"publisher":"Springer Science and Business Media LLC","issue":"21","license":[{"start":{"date-parts":[[2017,5,9]],"date-time":"2017-05-09T00:00:00Z","timestamp":1494288000000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2017,11]]},"DOI":"10.1007\/s11042-017-4732-8","type":"journal-article","created":{"date-parts":[[2017,5,9]],"date-time":"2017-05-09T01:42:24Z","timestamp":1494294144000},"page":"22599-22622","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Entity linking across vision and language"],"prefix":"10.1007","volume":"76","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2063-6773","authenticated-orcid":false,"given":"Aparna Nurani","family":"Venkitasubramanian","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tinne","family":"Tuytelaars","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marie-Francine","family":"Moens","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2017,5,9]]},"reference":[{"key":"4732_CR1","doi-asserted-by":"crossref","unstructured":"Afkham HM, Targhi AT, Eklundh JO, Pronobis A (2008) Joint visual vocabulary for animal classification. In: 19th International conference on pattern recognition. IEEE, pp 1\u20134","DOI":"10.1109\/ICPR.2008.4761710"},{"key":"4732_CR2","unstructured":"Alfonseca E, Manandhar S (2002) An unsupervised method for general named entity recognition and automated concept discovery. In: Proceedings of the 1st international conference on general WordNet. Mysore, pp 34\u201343"},{"key":"4732_CR3","unstructured":"Bagga A, Baldwin B (1998) Algorithms for scoring coreference chains. In: The first international conference on language resources and evaluation workshop on linguistics coreference, vol 1. Citeseer, pp 563\u2013566"},{"key":"4732_CR4","doi-asserted-by":"crossref","unstructured":"Berg TL, Forsyth DA (2006) Animals on the web. In: 2006 IEEE Computer society conference on computer vision and pattern recognition, vol 2. IEEE, pp 1463\u20131470","DOI":"10.1109\/CVPR.2006.57"},{"key":"4732_CR5","doi-asserted-by":"crossref","unstructured":"Chatfield K, Simonyan K, Vedaldi A, Zisserman A (2014) Return of the devil in the details: delving deep into convolutional nets. arXiv preprint arXiv: 1405.3531","DOI":"10.5244\/C.28.6"},{"issue":"5-6","key":"4732_CR6","doi-asserted-by":"crossref","first-page":"441","DOI":"10.1007\/BF00136985","volume":"26","author":"S Coates-Stephens","year":"1992","unstructured":"Coates-Stephens S (1992) The analysis and acquisition of proper names for the understanding of free text. Comput Hum 26(5-6):441\u2013456","journal-title":"Comput Hum"},{"key":"4732_CR7","doi-asserted-by":"crossref","unstructured":"Coughlan JM, Ferreira SJ (2002) Finding deformable shapes using loopy belief propagation. In: European Conference on computer vision. Springer, pp 453\u2013468","DOI":"10.1007\/3-540-47977-5_30"},{"key":"4732_CR8","doi-asserted-by":"crossref","unstructured":"Deng J, Dong W, Socher R, Li L J, Li K, Fei-Fei L (2009) Imagenet: a large-scale hierarchical image database. In: IEEE Conference on computer vision and pattern recognition, 2009. CVPR 2009. IEEE, pp 248\u2013255","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"4732_CR9","doi-asserted-by":"crossref","unstructured":"Durrett G, Klein D (2013) Easy victories and uphill battles in coreference resolution. In: Proceedings of the conference on empirical methods in natural language processing. Association for Computational Linguistics. Seattle","DOI":"10.18653\/v1\/D13-1203"},{"key":"4732_CR10","doi-asserted-by":"crossref","unstructured":"Durrett G, Klein D (2014) A joint model for entity analysis: coreference, typing, and linking. In: Transactions of the association for computational linguistics","DOI":"10.1162\/tacl_a_00197"},{"key":"4732_CR11","doi-asserted-by":"crossref","unstructured":"Dusart T, Nurani Venkitasubramanian A, Moens M F (2013) Cross-modal alignment for wildlife recognition. In: Proceedings of the 2nd ACM international workshop on multimedia analysis for ecological data. ACM, pp 9\u201314","DOI":"10.1145\/2509896.2509905"},{"key":"4732_CR12","unstructured":"Everingham M, Van Gool L, Williams CKI, Winn J, Zisserman A The PASCAL visual object classes challenge 2012 (VOC2012) results. http:\/\/www.pascal-network.org\/challenges\/VOC\/voc2012\/workshop\/index.html"},{"key":"4732_CR13","unstructured":"Fang H, Gupta S, Iandola F, Srivastava R, Deng L, Doll\u00e1r P., Gao J, He X, Mitchell M, Platt J et al (2014) From captions to visual concepts and back. arXiv preprint arXiv: 1411.4952"},{"key":"4732_CR14","unstructured":"Gomez A, Salazar A (2016) Towards automatic wild animal monitoring: Identification of animal species in camera-trap images using very deep convolutional neural networks. arXiv preprint arXiv: 1603.06169"},{"key":"4732_CR15","doi-asserted-by":"crossref","unstructured":"Guadarrama S, Krishnamoorthy N, Malkarnenkar G, Venugopalan S, Mooney R, Darrell T, Saenko K (2013) Youtube2text: recognizing and describing arbitrary activities using semantic hierarchies and zero-shot recognition. In: 2013 IEEE International conference on computer vision (ICCV). IEEE, pp 2712\u20132719","DOI":"10.1109\/ICCV.2013.337"},{"key":"4732_CR16","doi-asserted-by":"crossref","unstructured":"Guillaumin M, Mensink T, Verbeek J, Schmid C (2008) Automatic face naming with caption-based supervision. In: IEEE Conference on computer vision and pattern recognition, 2008. CVPR 2008. IEEE, pp 1\u20138","DOI":"10.1109\/CVPR.2008.4587603"},{"key":"4732_CR17","unstructured":"Hariharan B, Girshick R (2016) Low-shot visual object recognition. arXiv preprint arXiv: 1606.02819"},{"key":"4732_CR18","doi-asserted-by":"crossref","unstructured":"Hellier P, Demoulin V, Oisel L, P\u00e9rez P. (2012) A contrario shot detection. In: 2012 19th IEEE international conference on image processing. IEEE, pp 3085\u20133088","DOI":"10.1109\/ICIP.2012.6467552"},{"key":"4732_CR19","doi-asserted-by":"crossref","unstructured":"Joly A, Go\u00ebau H, Glotin H, Spampinato C, Bonnet P, Vellinga WP, Planqu\u00e9 R, Rauber A, Palazzo S, Fisher B et al (2015) Lifeclef 2015: multimedia life species identification challenges. In: International conference of the cross-language evaluation forum for European languages. Springer, pp 462\u2013483","DOI":"10.1007\/978-3-319-24027-5_46"},{"key":"4732_CR20","unstructured":"Karpathy A, Fei-Fei L (2014) Deep visual-semantic alignments for generating image descriptions. arXiv preprint arXiv: 1412.2306"},{"key":"4732_CR21","doi-asserted-by":"crossref","unstructured":"Kazemzadeh S, Ordonez V, Matten M, Berg TL (2014) Referit game: referring to objects in photographs of natural scenes. In: EMNLP","DOI":"10.3115\/v1\/D14-1086"},{"key":"4732_CR22","unstructured":"Khosla A, Jayadevaprakash N, Yao B, Li FFL (2011) Novel dataset for fine-grained image categorization. In: First workshop on fine-grained visual categorization, CVPR (2011). Citeseer"},{"key":"4732_CR23","doi-asserted-by":"crossref","unstructured":"Kong C, Lin D, Bansal M, Urtasun R, Fidler S (2014) What are you talking about? Text-to-image coreference. In: 2014 IEEE Conference on computer vision and pattern recognition. IEEE, pp 3558\u20133565","DOI":"10.1109\/CVPR.2014.455"},{"issue":"4","key":"4732_CR24","doi-asserted-by":"crossref","first-page":"885","DOI":"10.1162\/COLI_a_00152","volume":"39","author":"H Lee","year":"2013","unstructured":"Lee H, Chang A, Peirsman Y, Chambers N, Surdeanu M, Jurafsky D (2013) Deterministic coreference resolution based on entity-centric, precision-ranked rules. Comput Linguist 39(4):885\u2013916","journal-title":"Comput Linguist"},{"issue":"4","key":"4732_CR25","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1093\/bib\/6.4.357","volume":"6","author":"U Leser","year":"2005","unstructured":"Leser U, Hakenberg J (2005) What makes a gene name? Named entity recognition in the biomedical literature. Brief Bioinf 6(4):357\u2013369","journal-title":"Brief Bioinf"},{"key":"4732_CR26","unstructured":"Liu X, Li Y, Wu H, Zhou M, Wei F, Lu Y (2013) Entity linking for tweets. In: ACL, vol 1, pp 1304\u20131311"},{"key":"4732_CR27","doi-asserted-by":"crossref","unstructured":"Luo X (2005) On coreference resolution performance metrics. In: Proceedings of the conference on human language technology and empirical methods in natural language processing. Association for Computational Linguistics, , pp 25\u201332","DOI":"10.3115\/1220575.1220579"},{"key":"4732_CR28","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1145\/219717.219748","volume":"38","author":"GA Miller","year":"1995","unstructured":"Miller GA (1995) WordNet: a lexical database for English. Commun ACM 38:39\u201341","journal-title":"Commun ACM"},{"issue":"1","key":"4732_CR29","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1075\/li.30.1.03nad","volume":"30","author":"D Nadeau","year":"2007","unstructured":"Nadeau D, Sekine S (2007) A survey of named entity recognition and classification. Lingvisticae Investigationes 30(1):3\u201326","journal-title":"Lingvisticae Investigationes"},{"key":"4732_CR30","unstructured":"Pearl J (2014) Probabilistic reasoning in intelligent systems: networks of plausible inference. Morgan Kaufmann"},{"issue":"1","key":"4732_CR31","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1109\/TMM.2009.2036232","volume":"12","author":"PT Pham","year":"2010","unstructured":"Pham PT, Moens MF, Tuytelaars T (2010) Cross-media alignment of names and faces. IEEE Trans Multimed 12(1):13\u201327","journal-title":"IEEE Trans Multimed"},{"issue":"3","key":"4732_CR32","doi-asserted-by":"crossref","first-page":"44","DOI":"10.1109\/MMUL.2011.22","volume":"18","author":"PT Pham","year":"2011","unstructured":"Pham PT, Tuytelaars T, Moens MF (2011) Naming people in news videos with label propagation. IEEE Multimed 18(3):44\u201355","journal-title":"IEEE Multimed"},{"key":"4732_CR33","doi-asserted-by":"crossref","unstructured":"Pradhan S, Luo X, Recasens M, Hovy E, Ng V, Strube M (2014) Scoring coreference partitions of predicted mentions: a reference implementation","DOI":"10.3115\/v1\/P14-2006"},{"key":"4732_CR34","unstructured":"Pradhan S, Ramshaw L, Marcus M, Palmer M, Weischedel R, Xue N (2011) Conll-2011 shared task: modeling unrestricted coreference in ontonotes. In: Proceedings of the Fifteenth conference on computational natural language learning: shared task. Association for Computational Linguistics, pp 1\u201327"},{"issue":"8","key":"4732_CR35","doi-asserted-by":"crossref","first-page":"1319","DOI":"10.1109\/TPAMI.2006.155","volume":"28","author":"D Ramanan","year":"2006","unstructured":"Ramanan D, Forsyth DA, Barnard K (2006) Building models of animals from video. IEEE Trans Pattern Anal Mach Intell 28(8):1319\u20131334","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"4732_CR36","doi-asserted-by":"crossref","unstructured":"Ramanathan V, Joulin A, Liang P, Fei-Fei L (2014) Linking people in videos with \u201ctheir\u201d names using coreference resolution. In: European conference on computer vision. Springer, pp 95\u2013110","DOI":"10.1007\/978-3-319-10590-1_7"},{"key":"4732_CR37","doi-asserted-by":"crossref","unstructured":"Roth D, Yih WT (2002) Probabilistic reasoning for entity & relation recognition. In: Proceedings of the 19th international conference on computational linguistics, vol 1. Association for Computational Linguistics, , pp 1\u20137","DOI":"10.3115\/1072228.1072379"},{"key":"4732_CR38","doi-asserted-by":"crossref","unstructured":"Schmid C (2001) Constructing models for content-based image retrieval. In: Proceedings of the 2001 IEEE computer society conference on computer vision and pattern recognition, 2001. CVPR 2001, vol 2. IEEE, pp II\u201339","DOI":"10.1109\/CVPR.2001.990922"},{"key":"4732_CR39","unstructured":"Schmidt M (2012) UGM: Matlab code for undirected graphical models"},{"key":"4732_CR40","unstructured":"Seitner J, Bizer C, Eckert K, Faralli S, Meusel R, Paulheim H, Ponzetto S (2016) A large database of hypernymy relations extracted from the web. In: Proceedings of the 10th edition of the language resources and evaluation conference. Portoroz"},{"issue":"2","key":"4732_CR41","doi-asserted-by":"crossref","first-page":"443","DOI":"10.1109\/TKDE.2014.2327028","volume":"27","author":"W Shen","year":"2015","unstructured":"Shen W, Wang J, Han J (2015) Entity linking with a knowledge base: issues, techniques, and solutions. IEEE Trans Knowl Data Eng 27(2):443\u2013460","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"4732_CR42","doi-asserted-by":"crossref","unstructured":"Venkitasubramanian AN, Tuytelaars T, Moens MF (2016) Wildlife recognition in nature documentaries with weak supervision from subtitles and external data. Pattern Recogn Lett Elsev","DOI":"10.1016\/j.patrec.2016.01.025"},{"key":"4732_CR43","doi-asserted-by":"crossref","unstructured":"Vilain M, Burger J, Aberdeen J, Connolly D, Hirschman L (1995) A model-theoretic coreference scoring scheme. In: Proceedings of the 6th conference on message understanding. Association for Computational Linguistics, pp 45\u201352","DOI":"10.3115\/1072399.1072405"},{"key":"4732_CR44","unstructured":"Wah C, Branson S, Welinder P, Perona P, Belongie S (2011) The Caltech-UCSD birds-200-2011 dataset, Technical Report CNS-TR-2011-001 California Institute of Technology"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11042-017-4732-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-017-4732-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-017-4732-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T09:36:45Z","timestamp":1750239405000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11042-017-4732-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,5,9]]},"references-count":44,"journal-issue":{"issue":"21","published-print":{"date-parts":[[2017,11]]}},"alternative-id":["4732"],"URL":"https:\/\/doi.org\/10.1007\/s11042-017-4732-8","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,5,9]]}}}