{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T19:06:35Z","timestamp":1742929595653,"version":"3.40.3"},"publisher-location":"Cham","reference-count":22,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319703527"},{"type":"electronic","value":"9783319703534"}],"license":[{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"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":[],"published-print":{"date-parts":[[2017]]},"DOI":"10.1007\/978-3-319-70353-4_33","type":"book-chapter","created":{"date-parts":[[2017,11,21]],"date-time":"2017-11-21T23:37:40Z","timestamp":1511307460000},"page":"386-395","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Visual versus Textual Embedding for\u00a0Video\u00a0Retrieval"],"prefix":"10.1007","author":[{"given":"Danny","family":"Francis","sequence":"first","affiliation":[]},{"given":"Paul","family":"Pidou","sequence":"additional","affiliation":[]},{"given":"Bernard","family":"Merialdo","sequence":"additional","affiliation":[]},{"given":"Beno\u00eet","family":"Huet","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2017,11,23]]},"reference":[{"key":"33_CR1","unstructured":"Awad, G., Fiscus, J., Michel, M., Joy, D., Kraaij, W., Smeaton, A.F., Qu\u00e9not, G., Eskevich, M., Aly, R., Ordelman, R.: Trecvid 2016: evaluating video search, video event detection, localization, and hyperlinking. In: Proceedings of TRECVID, vol. 2016, November 2016"},{"key":"33_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"187","DOI":"10.1007\/978-3-540-78646-7_19","volume-title":"Advances in Information Retrieval","author":"S Ayache","year":"2008","unstructured":"Ayache, S., Qu\u00e9not, G.: Video corpus annotation using active learning. In: Macdonald, C., Ounis, I., Plachouras, V., Ruthven, I., White, R.W. (eds.) ECIR 2008. LNCS, vol. 4956, pp. 187\u2013198. Springer, Heidelberg (2008). https:\/\/doi.org\/10.1007\/978-3-540-78646-7_19"},{"key":"33_CR3","unstructured":"Blacoe, W., Lapata, M.: A comparison of vector-based representations for semantic composition. In: Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, pp. 546\u2013556. Association for Computational Linguistics, July 2012"},{"key":"33_CR4","doi-asserted-by":"crossref","unstructured":"Dalton, J., Allan, J., Mirajkar, P.: Zero-shot video retrieval using content and concepts. In: Proceedings of the 22nd ACM International Conference on Information & Knowledge Management, pp. 1857\u20131860. ACM, October 2013","DOI":"10.1145\/2505515.2507880"},{"key":"33_CR5","doi-asserted-by":"crossref","unstructured":"Francis, D., Pidou, P., Merialdo, B., Huet, B.: Natural language access to video databases. In: 3rd International Conference on Multimedia Big Data, BIGMM 2017, April 2017. http:\/\/www.eurecom.fr\/publication\/5199","DOI":"10.1109\/BigMM.2017.34"},{"key":"33_CR6","doi-asserted-by":"crossref","unstructured":"Habibian, A., Mensink, T., Snoek, C.G.: Composite concept discovery for zero-shot video event detection. In: Proceedings of International Conference on Multimedia Retrieval, p. 17. ACM, April 2014","DOI":"10.1145\/2578726.2578746"},{"issue":"7","key":"33_CR7","doi-asserted-by":"crossref","first-page":"1583","DOI":"10.1109\/TMM.2017.2671414","volume":"19","author":"X Han","year":"2017","unstructured":"Han, X., Singh, B., Morariu, V., Davis, L.S.: VRFP: on-the-fly video retrieval using web images and fast fisher vector products. IEEE Trans. Multimed. 19(7), 1583\u20131595 (2017)","journal-title":"IEEE Trans. Multimed."},{"key":"33_CR8","doi-asserted-by":"crossref","unstructured":"Johnson, J., Karpathy, A., Fei-Fei, L.: DenseCap: fully convolutional localization networks for dense captioning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4565\u20134574 (2016)","DOI":"10.1109\/CVPR.2016.494"},{"key":"33_CR9","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Fei-Fei, L.: Deep visual-semantic alignments for generating image descriptions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3128\u20133137 (2015)","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"33_CR10","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097\u20131105 (2012)"},{"key":"33_CR11","doi-asserted-by":"crossref","unstructured":"Mettes, P., Koelma, D.C., Snoek, C.G.: The imagenet shuffle: reorganized pre-training for video event detection. In: Proceedings of the 2016 ACM on International Conference on Multimedia Retrieval, pp. 175\u2013182. ACM, June 2016","DOI":"10.1145\/2911996.2912036"},{"key":"33_CR12","doi-asserted-by":"crossref","unstructured":"Mikolov, T., Karafi\u00e1t, M., Burget, L., Cernock\u00fd, J., Khudanpur, S.: Recurrent neural network based language model. In: Interspeech, vol. 2, p. 3, September 2010","DOI":"10.1109\/ICASSP.2011.5947611"},{"key":"33_CR13","unstructured":"Mikolov, T., Sutskever, I., Chen, K., Corrado, G.S., Dean, J.: Distributed representations of words and phrases and their compositionality. In: Advances in Neural Information Processing Systems, pp. 3111\u20133119 (2013)"},{"key":"33_CR14","unstructured":"Niaz, U., Merialdo, B., Tanase, C.: EURECOM at TrecVid 2014: the semantic indexing task. TRECVID, February 2014"},{"key":"33_CR15","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., Manning, C.D.: GloVe: global vectors for word representation. In: EMNLP, vol. 14, pp. 1532\u20131543, October 2014","DOI":"10.3115\/v1\/D14-1162"},{"key":"33_CR16","doi-asserted-by":"crossref","unstructured":"Safadi, B., Sahuguet, M., Huet, B.: When textual and visual information join forces for multimedia retrieval. In: Proceedings of International Conference on Multimedia Retrieval, p. 265. ACM, April 2014","DOI":"10.1145\/2578726.2578760"},{"key":"33_CR17","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"33_CR18","unstructured":"Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. In: Advances in Neural Information Processing Systems, pp. 3104\u20133112 (2014)"},{"key":"33_CR19","doi-asserted-by":"crossref","unstructured":"Vinyals, O., Toshev, A., Bengio, S., Erhan, D.: Show and tell: a neural image caption generator. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3156\u20133164 (2015)","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"33_CR20","doi-asserted-by":"crossref","unstructured":"Wang, C., Yang, H., Bartz, C., Meinel, C.: Image captioning with deep bidirectional LSTMs. In: Proceedings of the 2016 ACM on Multimedia Conference, pp. 988\u2013997. ACM, October 2016","DOI":"10.1145\/2964284.2964299"},{"key":"33_CR21","unstructured":"Wieting, J., Bansal, M., Gimpel, K., Livescu, K.: Towards universal paraphrastic sentence embeddings. arXiv preprint arXiv:1511.08198 (2015)"},{"key":"33_CR22","unstructured":"Google Images Search Engine. https:\/\/www.google.fr\/imghp?"}],"container-title":["Lecture Notes in Computer Science","Advanced Concepts for Intelligent Vision Systems"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-70353-4_33","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,10,6]],"date-time":"2019-10-06T11:24:04Z","timestamp":1570361044000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-70353-4_33"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017]]},"ISBN":["9783319703527","9783319703534"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-70353-4_33","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2017]]}}}