{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T07:27:03Z","timestamp":1740122823980,"version":"3.37.3"},"reference-count":39,"publisher":"Springer Science and Business Media LLC","issue":"16","license":[{"start":{"date-parts":[[2021,7,29]],"date-time":"2021-07-29T00:00:00Z","timestamp":1627516800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,7,29]],"date-time":"2021-07-29T00:00:00Z","timestamp":1627516800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2022,7]]},"DOI":"10.1007\/s11042-021-11253-9","type":"journal-article","created":{"date-parts":[[2021,7,29]],"date-time":"2021-07-29T22:02:26Z","timestamp":1627596146000},"page":"23105-23121","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Enriching videos with automatic place recognition in google maps"],"prefix":"10.1007","volume":"81","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3288-044X","authenticated-orcid":false,"given":"Francesca","family":"Fallucchi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rosario","family":"Di Stabile","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Erasmo","family":"Purificato","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Romeo","family":"Giuliano","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ernesto William","family":"De Luca","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,7,29]]},"reference":[{"key":"11253_CR1","doi-asserted-by":"crossref","unstructured":"Basile P, Caputo A, Gentile AL, Rizzo G (2016) Overview of the evalita 2016 named entity recognition and linking in italian tweets (neel-it) task. In: the Final Workshop 7 December 2016, Naples, pp 40","DOI":"10.4000\/books.aaccademia.1935"},{"key":"11253_CR2","doi-asserted-by":"crossref","unstructured":"Ceccarelli M, di Bisceglie M, Galdi C, Giangregorio G, Ullo SL (2008) Image registration using non-linear diffusion. In: IGARSS 2008 - IEEE International Geoscience and Remote Sensing Symposium, 5, pp 220\u2013223","DOI":"10.1109\/IGARSS.2008.4780067"},{"key":"11253_CR3","doi-asserted-by":"crossref","unstructured":"Chiu C-C, Sainath TN, Wu Y, Prabhavalkar R, Nguyen P, Chen Z, Kannan A, Weiss RJ, Rao K, Gonina E et al (2018) State-of-the-art speech recognition with sequence-to-sequence models. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp 4774\u20134778. IEEE","DOI":"10.1109\/ICASSP.2018.8462105"},{"issue":"3","key":"11253_CR4","doi-asserted-by":"publisher","first-page":"16","DOI":"10.5120\/1462-1976","volume":"10","author":"SK Gaikwad","year":"2010","unstructured":"Gaikwad SK, Gawali BW, Yannawar P (2010) A review on speech recognition technique. International Journal of Computer Applications 10(3):16\u201324","journal-title":"International Journal of Computer Applications"},{"key":"11253_CR5","doi-asserted-by":"crossref","unstructured":"Giuliano R, Cardarilli GC, Cesarini C, Nunzio LD, Fallucchi F, Fazzolari R, Mazzenga F, Re M, Vizzarri A (2020) Indoor localization system based on bluetooth low energy for museum applications. Electronics, pp 1055","DOI":"10.3390\/electronics9061055"},{"key":"11253_CR6","doi-asserted-by":"crossref","unstructured":"Golubovic N, Krintz C, Wolski R, Lafia S, Hervey T, Kuhn W (2016) Extracting spatial information from social media in support of agricultural management decisions. In: Proceedings of the 10th Workshop on Geographic Information Retrieval, pp 1\u20132","DOI":"10.1145\/3003464.3003468"},{"key":"11253_CR7","unstructured":"Han KJ, Chandrashekaran A, Kim J, Lane I (2017) The capio 2017 conversational speech recognition system. arXiv preprint arXiv:1801.00059"},{"key":"11253_CR8","doi-asserted-by":"crossref","unstructured":"Hendricks AL, Wang O, Shechtman E, Sivic J, Darrell T, Russell B (2017) Localizing moments in video with natural language. In: Proceedings of the IEEE international conference on computer vision, pp 5803\u20135812","DOI":"10.1109\/ICCV.2017.618"},{"issue":"6","key":"11253_CR9","doi-asserted-by":"publisher","first-page":"797","DOI":"10.1109\/TSMCC.2011.2109710","volume":"41","author":"W Hu","year":"2011","unstructured":"Hu W, Xie N, Li L, Zeng X, Maybank S (2011) A survey on visual content-based video indexing and retrieval. IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews) 41(6):797\u2013819","journal-title":"IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews)"},{"issue":"9","key":"11253_CR10","doi-asserted-by":"publisher","first-page":"8066","DOI":"10.1016\/j.eswa.2012.01.136","volume":"39","author":"JJ Jung","year":"2012","unstructured":"Jung JJ (2012) Online named entity recognition method for microtexts in social networking services: A case study of twitter. Expert Syst Appl 39(9):8066\u20138070. https:\/\/doi.org\/10.1016\/j.eswa.2012.01.136, http:\/\/www.sciencedirect.com\/science\/article\/pii\/S0957417412001546","journal-title":"Expert Syst Appl"},{"key":"11253_CR11","doi-asserted-by":"publisher","unstructured":"Kelm P, Schmiedeke S, Sikora T (2012) Multimodal geo-tagging in social media websites using hierarchical spatial segmentation. LBSN \u201912: Proceedings of the 5th ACM SIGSPATIAL International Workshop on Location-Based Social Networks, pp 32\u201339. https:\/\/doi.org\/10.1145\/2442796.2442805","DOI":"10.1145\/2442796.2442805"},{"key":"11253_CR12","doi-asserted-by":"publisher","DOI":"10.1145\/777947.772545","volume-title":"Art and business of speech recognition: Creating the noble voice","author":"B Kotelly","year":"2003","unstructured":"Kotelly B (2003) Art and business of speech recognition: Creating the noble voice. Addison-Wesley Longman Publishing Co., Inc., USA"},{"key":"11253_CR13","unstructured":"Larson RR (1996) Geographic information retrieval and spatial browsing. Geographic information systems and libraries: patrons, maps, and spatial information [papers presented at the 1995 Clinic on Library Applications of Data Processing, April 10-12, 1995]"},{"key":"11253_CR14","unstructured":"Liu X, Zhang S, Wei F, Zhou M (2011) Recognizing named entities in tweets. In: Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, pp 359\u2013367. Association for Computational Linguistics, Portland, Oregon, USA. https:\/\/www.aclweb.org\/anthology\/P11-1037"},{"key":"11253_CR15","unstructured":"Liu Y, Albanie S, Nagrani A, Zisserman A (2019) Use what you have: Video retrieval using representations from collaborative experts. arXiv preprint arXiv:1907.13487"},{"key":"11253_CR16","doi-asserted-by":"crossref","unstructured":"Messina A, Borgotallo R, Dimino G, Gnota DA, Boch L (2008) Ants: A complete system for automatic news programme annotation based on multimodal analysis. In: 2008 Ninth International Workshop on Image Analysis for Multimedia Interactive Services, pp 219\u2013222","DOI":"10.1109\/WIAMIS.2008.15"},{"key":"11253_CR17","doi-asserted-by":"crossref","unstructured":"Miech A, Zhukov D, Alayrac J-B, Tapaswi M, Laptev I, Sivic J (2019) Howto100m: Learning a text-video embedding by watching hundred million narrated video clips. In: Proceedings of the IEEE International Conference on Computer Vision, pp 2630\u20132640","DOI":"10.1109\/ICCV.2019.00272"},{"key":"11253_CR18","doi-asserted-by":"crossref","unstructured":"Mithun NC, Li J, Metze F, Roy-Chowdhury AK (2018) Learning joint embedding with multimodal cues for cross-modal video-text retrieval. In: Proceedings of the 2018 ACM on International Conference on Multimedia Retrieval, pp 19\u201327","DOI":"10.1145\/3206025.3206064"},{"key":"11253_CR19","doi-asserted-by":"crossref","unstructured":"Mithun NC, Paul S, Roy-Chowdhury AK (2019) Weakly supervised video moment retrieval from text queries. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 11592\u201311601","DOI":"10.1109\/CVPR.2019.01186"},{"issue":"1","key":"11253_CR20","doi-asserted-by":"publisher","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. Linguisticae Investigationes 30(1):3\u201326. Publisher: John Benjamins Publishing Company","journal-title":"Linguisticae Investigationes"},{"key":"11253_CR21","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1016\/j.artint.2012.03.006","volume":"194","author":"J Nothman","year":"2013","unstructured":"Nothman J, Ringland N, Radford W, Murphy T, Curran JR (2013) Learning multilingual named entity recognition from wikipedia. Artif Intell 194:151\u2013175","journal-title":"Artif Intell"},{"issue":"2","key":"11253_CR22","doi-asserted-by":"publisher","first-page":"13","DOI":"10.5121\/iju.2012.3202","volume":"3","author":"BV Patel","year":"2012","unstructured":"Patel BV, Meshram BB (2012) Content based video retrieval systems. International Journal of UbiComp (IJU) 3(2):13\u201330","journal-title":"International Journal of UbiComp (IJU)"},{"issue":"20","key":"11253_CR23","doi-asserted-by":"publisher","first-page":"27447","DOI":"10.1007\/s11042-018-5931-7","volume":"77","author":"E Purificato","year":"2018","unstructured":"Purificato E, Rinaldi AM (2018) Multimedia and geographic data integration for cultural heritage information retrieval. Multimedia Tools and Applications 77(20):27447\u201327469","journal-title":"Multimedia Tools and Applications"},{"issue":"2-3","key":"11253_CR24","doi-asserted-by":"publisher","first-page":"164","DOI":"10.1561\/1500000034","volume":"12","author":"RS Purves","year":"2018","unstructured":"Purves RS, Clough P, Jones CB, Hall MH, Murdock V (2018) Geographic information retrieval: progress and challenges in spatial search of text. Foundations and Trends in Information Retrieval 12(2-3):164\u2013318","journal-title":"Foundations and Trends in Information Retrieval"},{"key":"11253_CR25","unstructured":"Rae A, Kelm P (2012) Working notes for the placing task at mediaeval 2012. Santa Croce in Fossabanda, Pisa, Italy, October 4-5. MediaEval 2012 Working Notes Proceedings, available at http:\/\/ceur-ws.org\/Vol-927\/, pp 32\u201339"},{"issue":"24","key":"11253_CR26","first-page":"14750","volume":"12","author":"N Raju","year":"2017","unstructured":"Raju N, Anita HB (2017) Text extraction from video images. Int J Appl Eng Res 12(24):14750\u201314754","journal-title":"Int J Appl Eng Res"},{"key":"11253_CR27","unstructured":"Ritter A, Clark S, Etzioni O, et al. (2011) Named entity recognition in tweets: an experimental study. In: Proceedings of the conference on empirical methods in natural language processing, pp 1524\u20131534. Association for Computational Linguistics"},{"key":"11253_CR28","unstructured":"Ritter A, Clark S, Mausam, Etzioni O (2011) Named entity recognition in tweets: An experimental study. In: Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing, pp 1524\u20131534. Association for Computational Linguistics. Edinburgh, Scotland, UK. https:\/\/www.aclweb.org\/anthology\/D11-1141"},{"issue":"4","key":"11253_CR29","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1561\/1500000014","volume":"2","author":"CGM Snoek","year":"2008","unstructured":"Snoek CGM, Worring M (2008) Concept-based video retrieval. Foundations and trends in information retrieval 2(4):215\u2013322","journal-title":"Foundations and trends in information retrieval"},{"key":"11253_CR30","unstructured":"Speranza M (2009) The named entity recognition task at evalita 2009. In: EVALITA 2009"},{"key":"11253_CR31","doi-asserted-by":"crossref","unstructured":"Sundheim BM (1995) Overview of results of the MUC-6 evaluation. In: Sixth Message Understanding Conference (MUC-6): Proceedings of a Conference Held in Columbia, Maryland, November 6-8, 1995. https:\/\/www.aclweb.org\/anthology\/M95-1002","DOI":"10.3115\/1072399.1072402"},{"key":"11253_CR32","doi-asserted-by":"crossref","unstructured":"Tjong Kim Sang EF, De Meulder F (2003) Introduction to the CoNLL-2003 shared task: Language-independent named entity recognition. In: Proceedings of the Seventh Conference on Natural Language Learning at HLT-NAACL 2003, pp 142\u2013147. https:\/\/www.aclweb.org\/anthology\/W03-0419","DOI":"10.3115\/1119176.1119195"},{"key":"11253_CR33","unstructured":"Torabi A, Tandon N, Sigal L (2016) Learning language-visual embedding for movie understanding with natural-language. arXiv preprint arXiv:1609.08124"},{"key":"11253_CR34","doi-asserted-by":"publisher","first-page":"124055","DOI":"10.1109\/ACCESS.2020.3006082","volume":"8","author":"SL Ullo","year":"2020","unstructured":"Ullo SL, Khare SK, Bajaj V, Sinha GR (2020) Hybrid computerized method for environmental sound classification. IEEE Access 8:124055\u2013124065","journal-title":"IEEE Access"},{"key":"11253_CR35","doi-asserted-by":"publisher","first-page":"3113","DOI":"10.3390\/s20113113","volume":"20","author":"SL Ullo","year":"2020","unstructured":"Ullo SL, Sinha GR (2020) Advances in smart environment monitoring systems using iot and sensors. Sensors 20:3113. https:\/\/doi.org\/10.3390\/s20113113","journal-title":"Sensors"},{"key":"11253_CR36","unstructured":"Veltkamp RC, Burkhardt H, Kriegel H-P (2013) State-of-the-art in content-based image and video retrieval. Springer Science & Business Media, 22"},{"key":"11253_CR37","doi-asserted-by":"crossref","unstructured":"Wilhelm-Stein T, Herms R, Ritter M, Eibl M (2014) Improving transcript-based video retrieval using unsupervised language model adaptation. In: Kanoulas E, Lupu M, Clough P, Sanderson M, Hall M, Hanbury A, Toms E (eds) Information Access Evaluation. Multilinguality, Multimodality, and Interaction, pp 110\u2013115. Springer International Publishing, Cham","DOI":"10.1007\/978-3-319-11382-1_11"},{"key":"11253_CR38","doi-asserted-by":"crossref","unstructured":"Xu R, Xiong C, Chen W, Corso JJ (2015) Jointly modeling deep video and compositional text to bridge vision and language in a unified framework. In: Twenty-Ninth AAAI Conference on Artificial Intelligence","DOI":"10.1609\/aaai.v29i1.9512"},{"issue":"1","key":"11253_CR39","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1007\/s11042-010-0630-z","volume":"51","author":"Y-T Zheng","year":"2011","unstructured":"Zheng Y-T, Zha Z-J, Chua T-S (2011) Research and applications on georeferenced multimedia: a survey. Multimedia Tools and Applications 51(1):77\u201398","journal-title":"Multimedia Tools and Applications"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-021-11253-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-021-11253-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-021-11253-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,5]],"date-time":"2023-01-05T22:05:00Z","timestamp":1672956300000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-021-11253-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,29]]},"references-count":39,"journal-issue":{"issue":"16","published-print":{"date-parts":[[2022,7]]}},"alternative-id":["11253"],"URL":"https:\/\/doi.org\/10.1007\/s11042-021-11253-9","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"type":"print","value":"1380-7501"},{"type":"electronic","value":"1573-7721"}],"subject":[],"published":{"date-parts":[[2021,7,29]]},"assertion":[{"value":"7 October 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 January 2021","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 July 2021","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 July 2021","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}