{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T18:17:30Z","timestamp":1780424250105,"version":"3.54.1"},"reference-count":35,"publisher":"Springer Science and Business Media LLC","issue":"21","license":[{"start":{"date-parts":[[2018,5,8]],"date-time":"2018-05-08T00:00:00Z","timestamp":1525737600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100006548","name":"K\u00e4rntner Wirtschaftsf\u00f6rderungsfonds","doi-asserted-by":"publisher","award":["KWF 20214 u. 3520\/ 26336\/38165"],"award-info":[{"award-number":["KWF 20214 u. 3520\/ 26336\/38165"]}],"id":[{"id":"10.13039\/501100006548","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2018,11]]},"DOI":"10.1007\/s11042-018-6016-3","type":"journal-article","created":{"date-parts":[[2018,5,7]],"date-time":"2018-05-07T20:03:36Z","timestamp":1525723416000},"page":"28817-28842","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Binary convolutional neural network features off-the-shelf for image to video linking in endoscopic multimedia databases"],"prefix":"10.1007","volume":"77","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2791-7110","authenticated-orcid":false,"given":"Stefan","family":"Petscharnig","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Klaus","family":"Sch\u00f6ffmann","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2018,5,8]]},"reference":[{"key":"6016_CR1","unstructured":"Awad G, Fiscus J, Michel M, Joy D, Kraaij W, Smeaton AF, Qu\u00e9not G, Eskevich M, Aly R, Ordelman R (2016) Trecvid 2016: evaluating video search, video event detection, localization, and hyperlinking. In: Proceedings of TRECVID, vol 2016"},{"key":"6016_CR2","first-page":"584","volume-title":"Neural codes for image retrieval","author":"A Babenko","year":"2014","unstructured":"Babenko A, Slesarev A, Chigorin A, Lempitsky V (2014) Neural codes for image retrieval. Springer International Publishing, Cham, pp 584\u2013599"},{"key":"6016_CR3","doi-asserted-by":"crossref","unstructured":"Beecks C, Schoeffmann K, Lux M, Uysal MS, Seidl T (2015) Endoscopic video retrieval: a signature-based approach for linking endoscopic images with video segments. In: Del Bimbo A, Chen SC, Wang H, Yu H, Zimmermann R (eds) Proceedings of the IEEE international symposium on multimedia 2015 (ISM 2015). IEEE, Los Alamitos, pp 1\u20136","DOI":"10.1109\/ISM.2015.21"},{"key":"6016_CR4","first-page":"185","volume-title":"Exploiting multimodality in video hyperlinking to improve target diversity","author":"R Bois","year":"2017","unstructured":"Bois R, Vukoti\u0107 V, Simon AR, Sicre R, Raymond C, S\u00e9billot P, Gravier G (2017) Exploiting multimodality in video hyperlinking to improve target diversity. Springer International Publishing, Cham, pp 185\u2013197"},{"key":"6016_CR5","doi-asserted-by":"crossref","unstructured":"Bosch A, Zisserman A, Munoz X (2007) Representing shape with a spatial pyramid kernel. In: Proceedings of the 6th ACM international conference on image and video retrieval. ACM, pp 401\u2013408","DOI":"10.1145\/1282280.1282340"},{"key":"6016_CR6","unstructured":"BVLC (2016) Caffe model zoo. \n                    http:\/\/caffe.berkeleyvision.org\/model_zoo.html"},{"key":"6016_CR7","doi-asserted-by":"crossref","unstructured":"Carlos JR, Lux M, Giro-i Nieto X, Munoz P, Anagnostopoulos N (2015) Visual information retrieval in endoscopic video archives. In: 2015 13th international workshop on content-based multimedia indexing (CBMI). IEEE, pp 1\u20136","DOI":"10.1109\/CBMI.2015.7153618"},{"key":"6016_CR8","doi-asserted-by":"publisher","first-page":"426","DOI":"10.1016\/j.sigpro.2016.05.021","volume":"128","author":"V Chandrasekhar","year":"2016","unstructured":"Chandrasekhar V, Lin J, Mor\u00e8re O, Goh H, Veillard A (2016) A practical guide to CNNs and fisher vectors for image instance retrieval. Signal Process 128:426\u2013439","journal-title":"Signal Process"},{"key":"6016_CR9","unstructured":"Chatzichristofis SA, Boutalis YS (2008) Cedd: color and edge directivity descriptor: a compact descriptor for image indexing and retrieval. In: International conference on computer vision systems. Springer, pp 312\u2013322"},{"key":"6016_CR10","unstructured":"Cheng Z, Li X, Shen J, Hauptmann AG (2015) Cmu-smu@ trecvid 2015: video hyperlinking"},{"issue":"11","key":"6016_CR11","doi-asserted-by":"publisher","first-page":"2521","DOI":"10.1109\/TMM.2017.2697824","volume":"19","author":"S Ercoli","year":"2017","unstructured":"Ercoli S, Bertini M, Bimbo AD (2017) Compact hash codes for efficient visual descriptors retrieval in large scale databases. IEEE Trans Multimedia 19(11):2521\u20132532. \n                    https:\/\/doi.org\/10.1109\/TMM.2017.2697824","journal-title":"IEEE Trans Multimedia"},{"key":"6016_CR12","unstructured":"Eskevich M, Aly R, Racca D, Ordelman R, Chen S, Jones GJ (2014) The search and hyperlinking task at mediaeval 2014"},{"key":"6016_CR13","doi-asserted-by":"publisher","unstructured":"Galu\u0161\u010d\u00e1kov\u00e1 P, Batko M, \u010cech J, Matas J, Nov\u00e1k D, Pecina P (2017) Visual descriptors in methods for video hyperlinking. In: Proceedings of the 2017 ACM on international conference on multimedia retrieval, ICMR \u201917. ACM, New York, pp 294\u2013300. \n                    https:\/\/doi.org\/10.1145\/3078971.3079026","DOI":"10.1145\/3078971.3079026"},{"key":"6016_CR14","unstructured":"Guo J, Li J (2015) Cnn based hashing for image retrieval. arXiv:\n                    1509.01354"},{"key":"6016_CR15","unstructured":"He K, Zhang X, Ren S, Sun J (2015) Deep residual learning for image recognition. arXiv:\n                    1512.03385"},{"key":"6016_CR16","doi-asserted-by":"crossref","unstructured":"Huang J, Kumar SR, Mitra M, Zhu WJ, Zabih R (1997) Image indexing using color correlograms. In: 1997 IEEE computer society conference on computer vision and pattern recognition, 1997. Proceedings. IEEE, pp 762\u2013768","DOI":"10.1109\/CVPR.1997.609412"},{"key":"6016_CR17","doi-asserted-by":"crossref","unstructured":"Iakovidou C, Anagnostopoulos N, Kapoutsis AC, Boutalis Y, Chatzichristofis SA (2014) Searching images with mpeg-7 (& mpeg-7-like) powered localized descriptors: the simple answer to effective content based image retrieval. In: 2014 12th international workshop on content-based multimedia indexing (CBMI), pp 1\u20136","DOI":"10.1109\/CBMI.2014.6849821"},{"key":"6016_CR18","doi-asserted-by":"crossref","unstructured":"Jia Y, Shelhamer E, Donahue J, Karayev S, Long J, Girshick R, Guadarrama S, Darrell T (2014) Caffe: convolutional architecture for fast feature embedding. In: Proceedings of the 22nd ACM international conference on multimedia, MM \u201914. ACM, New York, pp 675\u2013678","DOI":"10.1145\/2647868.2654889"},{"key":"6016_CR19","unstructured":"Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: Bartlett P, Pereira F, Burges C, Bottou L, Weinberger K (eds) Advances in neural information processing systems 25, pp 1106\u20131114"},{"key":"6016_CR20","doi-asserted-by":"crossref","unstructured":"Loko\u010d J, Hetland ML, Skopal T, Beecks C (2011) Ptolemaic indexing of the signature quadratic form distance. In: Proceedings of the fourth international conference on similarity search and applications, SISAP \u201911. ACM, New York, pp 9\u201316","DOI":"10.1145\/1995412.1995417"},{"key":"6016_CR21","doi-asserted-by":"crossref","unstructured":"Lux M, Chatzichristofis SA (2008) Lire: lucene image retrieval: an extensible java cbir library. In: Proceedings of the 16th ACM international conference on multimedia. ACM, pp 1085\u20131088","DOI":"10.1145\/1459359.1459577"},{"key":"6016_CR22","doi-asserted-by":"publisher","unstructured":"M\u00fcnzer B, Schoeffmann K, B\u00f6sz\u00f6rmenyi L (2013) Relevance segmentation of laparoscopic videos. In: 2013 IEEE international symposium on multimedia, pp 84\u201391. \n                    https:\/\/doi.org\/10.1109\/ISM.2013.22","DOI":"10.1109\/ISM.2013.22"},{"key":"6016_CR23","unstructured":"OpenCV (2015) Open source computer vision library. \n                    https:\/\/github.com\/itseez\/opencv"},{"issue":"7","key":"6016_CR24","doi-asserted-by":"publisher","first-page":"8061","DOI":"10.1007\/s11042-017-4699-5","volume":"77","author":"Stefan Petscharnig","year":"2017","unstructured":"Petscharnig S, Schoeffmann K (2017) Learning laparoscopic video shot classification for gynecological surgery. Multimedia Tools and Applications:1\u201319. \n                    https:\/\/doi.org\/10.1007\/s11042-017-4699-5","journal-title":"Multimedia Tools and Applications"},{"key":"6016_CR25","doi-asserted-by":"publisher","unstructured":"Petscharnig S, Lux M, Chatzichristofis S (2017) Dimensionality reduction for image features using deep learning and autoencoders. In: Proceedings of the 15th international workshop on content-based multimedia indexing, CBMI \u201917. ACM, New York, pp 23:1\u201323:6. \n                    https:\/\/doi.org\/10.1145\/3095713.3095737","DOI":"10.1145\/3095713.3095737"},{"key":"6016_CR26","doi-asserted-by":"crossref","unstructured":"Razavian AS, Azizpour H, Sullivan J, Carlsson S (2014) Cnn features off-the-shelf: an astounding baseline for recognition. In: Proceedings of the 2014 IEEE conference on computer vision and pattern recognition workshops, CVPRW \u201914. IEEE Computer Society, Washington, pp 512\u2013519","DOI":"10.1109\/CVPRW.2014.131"},{"key":"6016_CR27","doi-asserted-by":"crossref","unstructured":"Schoeffmann K, Beecks C, Lux M, Uysal MS, Seidl T (2016) Content-based retrieval in videos from laparoscopic surgery, pp 97,861V\u201397,861V\u201310","DOI":"10.1117\/12.2216864"},{"key":"6016_CR28","doi-asserted-by":"publisher","unstructured":"Schoeffmann K, M\u00fcnzer B, Riegler M, Halvorsen P (2017) Medical multimedia information systems (mmis). In: Proceedings of the 2017 ACM on multimedia conference, MM \u201917. \n                    https:\/\/doi.org\/10.1145\/3123266.3130142\n                    \n                  . ACM, New York, pp 1957\u20131958","DOI":"10.1145\/3123266.3130142"},{"key":"6016_CR29","unstructured":"Simon AR, Sicre R, Bois R, Gravier G, S\u00e9billot P (2015) IRISA at TrecVid2015: leveraging multimodal LDA for video hyperlinking. In: TRECVid 2015 workshop, working notes of the TRECVid 2015 workshop. Gaithersburg, United States. \n                    https:\/\/hal.archives-ouvertes.fr\/hal-01403726"},{"issue":"4","key":"6016_CR30","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1109\/MMUL.2011.71","volume":"18","author":"I Sodagar","year":"2011","unstructured":"Sodagar I (2011) The MPEG-DASH standard for multimedia streaming over the internet. IEEE MultiMedia 18(4):62\u201367","journal-title":"IEEE MultiMedia"},{"key":"6016_CR31","doi-asserted-by":"crossref","unstructured":"Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A (2015) Going deeper with convolutions. In: The IEEE conference on computer vision and pattern recognition (CVPR)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"6016_CR32","doi-asserted-by":"crossref","unstructured":"Vukoti\u0107 V, Raymond C, Gravier G (2016) Bidirectional joint representation learning with symmetrical deep neural networks for multimodal and crossmodal applications. In: Proceedings of the 2016 ACM on international conference on multimedia retrieval, ICMR \u201916. ACM, New York, pp 343\u2013346","DOI":"10.1145\/2911996.2912064"},{"key":"6016_CR33","doi-asserted-by":"publisher","unstructured":"Vukoti\u0107 V, Raymond C, Gravier G (2016) Multimodal and crossmodal representation learning from textual and visual features with bidirectional deep neural networks for video hyperlinking. In: Proceedings of the 2016 ACM workshop on vision and language integration meets multimedia fusion, iV&L-MM \u201916. ACM, New York, pp 37\u201344. \n                    https:\/\/doi.org\/10.1145\/2983563.2983567","DOI":"10.1145\/2983563.2983567"},{"key":"6016_CR34","doi-asserted-by":"publisher","unstructured":"Vukoti\u0107 V, Raymond C, Gravier G (2017) Generative adversarial networks for multimodal representation learning in video hyperlinking. In: Proceedings of the 2017 ACM on international conference on multimedia retrieval, ICMR \u201917. ACM, New York, pp 416\u2013419. \n                    https:\/\/doi.org\/10.1145\/3078971.3079038","DOI":"10.1145\/3078971.3079038"},{"issue":"4","key":"6016_CR35","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1109\/TIP.2003.819861","volume":"13","author":"Z. Wang","year":"2004","unstructured":"Wang Z, Bovik A, Sheikh H, Simoncelli E (2004) Image quality assessment: from error visibility to structural similarity. In: IEEE transactions on image processing, vol 13, pp 600\u2013612","journal-title":"IEEE Transactions on Image Processing"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11042-018-6016-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-018-6016-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-018-6016-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,9]],"date-time":"2019-05-09T16:34:28Z","timestamp":1557419668000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11042-018-6016-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,5,8]]},"references-count":35,"journal-issue":{"issue":"21","published-print":{"date-parts":[[2018,11]]}},"alternative-id":["6016"],"URL":"https:\/\/doi.org\/10.1007\/s11042-018-6016-3","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,5,8]]},"assertion":[{"value":"29 May 2017","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 April 2018","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 April 2018","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 May 2018","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}