{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T03:57:31Z","timestamp":1773719851265,"version":"3.50.1"},"publisher-location":"Cham","reference-count":23,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030057152","type":"print"},{"value":"9783030057169","type":"electronic"}],"license":[{"start":{"date-parts":[[2018,12,11]],"date-time":"2018-12-11T00:00:00Z","timestamp":1544486400000},"content-version":"tdm","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":[[2019]]},"DOI":"10.1007\/978-3-030-05716-9_55","type":"book-chapter","created":{"date-parts":[[2018,12,10]],"date-time":"2018-12-10T14:17:32Z","timestamp":1544451452000},"page":"616-621","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":35,"title":["Deep Learning-Based Concept Detection in vitrivr"],"prefix":"10.1007","author":[{"given":"Luca","family":"Rossetto","sequence":"first","affiliation":[]},{"given":"Mahnaz","family":"Amiri Parian","sequence":"additional","affiliation":[]},{"given":"Ralph","family":"Gasser","sequence":"additional","affiliation":[]},{"given":"Ivan","family":"Giangreco","sequence":"additional","affiliation":[]},{"given":"Silvan","family":"Heller","sequence":"additional","affiliation":[]},{"given":"Heiko","family":"Schuldt","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,12,11]]},"reference":[{"key":"55_CR1","unstructured":"Abadi, M., Barham, P., Chen, J., et al.: Tensorflow: a system for large-scale machine learning. In: Proceedings of the USENIX Symposium on Operating Systems Design and Implementation (OSDI), vol. 16, pp. 265\u2013283. USENIX, Savannah, GA, USA (2016)"},{"key":"55_CR2","doi-asserted-by":"crossref","unstructured":"Chen, L.-C., Zhu, Y., Papandreou, G., Schroff, F., Adam, H.: Encoder-decoder with atrous separable convolution for semantic image segmentation. In: Proceedings of the 15th European Conference on Computer Vision (ECCV), Munich, Germany (2018, page to appear)","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"55_CR3","doi-asserted-by":"crossref","unstructured":"Cob\u00e2rzan, C., et al.: Interactive video search tools: a detailed analysis of the video browser showdown 2015. Multimedia Tools and Appl. (MTAP) 76(4), 5539\u20135571 (2017)","DOI":"10.1007\/s11042-016-3661-2"},{"key":"55_CR4","doi-asserted-by":"crossref","unstructured":"Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3213\u20133223. IEEE, Las Vegas (2016)","DOI":"10.1109\/CVPR.2016.350"},{"issue":"1","key":"55_CR5","doi-asserted-by":"crossref","first-page":"98","DOI":"10.1007\/s11263-014-0733-5","volume":"111","author":"SM Mark Everingham","year":"2015","unstructured":"Mark Everingham, S.M., Eslami, A., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The Pascal visual object classes challenge: a retrospective. Int. J. Comput. Vis. (IJCV) 111(1), 98\u2013136 (2015)","journal-title":"Int. J. Comput. Vis. (IJCV)"},{"key":"55_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"190","DOI":"10.1007\/978-3-319-73603-7_16","volume-title":"MultiMedia Modeling","author":"R Furuta","year":"2018","unstructured":"Furuta, R., Inoue, N., Yamasaki, T.: Efficient and interactive spatial-semantic image retrieval. In: Schoeffmann, K., et al. (eds.) MMM 2018. LNCS, vol. 10704, pp. 190\u2013202. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-319-73603-7_16"},{"issue":"1","key":"55_CR7","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1007\/s13222-015-0209-y","volume":"16","author":"I Giangreco","year":"2016","unstructured":"Giangreco, I., Schuldt, H.: ADAM$$_{pro}$$: database support for big multimedia retrieval. Datenbank-Spektrum 16(1), 17\u201326 (2016)","journal-title":"Datenbank-Spektrum"},{"key":"55_CR8","unstructured":"Jaderberg, M., Simonyan, K., Vedaldi, A., Zisserman, A.: Synthetic data and artificial neural networks for natural scene text recognition. arXiv preprint arXiv:1406.2227 , pp. 1\u201310 (2014)"},{"key":"55_CR9","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Toderici, G., Shetty, S., Leung, T., Sukthankar, R., Li, F.-F.: Large-scale video classification with convolutional neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1725\u20131732. IEEE, Columbus (2014)","DOI":"10.1109\/CVPR.2014.223"},{"key":"55_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"issue":"Nov","key":"55_CR11","first-page":"2579","volume":"9","author":"L Maaten van der","year":"2008","unstructured":"van der Maaten, L., Hinton, G.: Visualizing data using t-SNE. J. Mach. Learn. Res. (JMLR) 9(Nov), 2579\u20132605 (2008)","journal-title":"J. Mach. Learn. Res. (JMLR)"},{"key":"55_CR12","unstructured":"Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781 , pp. 1\u201312 (2013)"},{"key":"55_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"403","DOI":"10.1007\/978-3-319-73600-6_41","volume-title":"MultiMedia Modeling","author":"L Rossetto","year":"2018","unstructured":"Rossetto, L., Giangreco, I., Gasser, R., Schuldt, H.: Competitive video retrieval with vitrivr. In: Schoeffmann, K., et al. (eds.) MMM 2018. LNCS, vol. 10705, pp. 403\u2013406. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-319-73600-6_41"},{"key":"55_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"377","DOI":"10.1007\/978-3-319-27674-8_36","volume-title":"MultiMedia Modeling","author":"L Rossetto","year":"2016","unstructured":"Rossetto, L., et al.: IMOTION \u2013 searching for video sequences using multi-shot sketch queries. In: Tian, Q., Sebe, N., Qi, G.-J., Huet, B., Hong, R., Liu, X. (eds.) MMM 2016. LNCS, vol. 9517, pp. 377\u2013382. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-27674-8_36"},{"key":"55_CR15","doi-asserted-by":"crossref","unstructured":"Rossetto, L., Giangreco, I., Schuldt, H.: Cineast: a multi-feature sketch-based video retrieval engine. In: Proceedings of the International Symposium on Multimedia (ISM), pp. 18\u201323. IEEE, Taichung, December 2014","DOI":"10.1109\/ISM.2014.38"},{"key":"55_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"255","DOI":"10.1007\/978-3-319-14442-9_24","volume-title":"MultiMedia Modeling","author":"L Rossetto","year":"2015","unstructured":"Rossetto, L., et al.: IMOTION \u2014 a content-based video retrieval engine. In: He, X., Luo, S., Tao, D., Xu, C., Yang, J., Hasan, M.A. (eds.) MMM 2015. LNCS, vol. 8936, pp. 255\u2013260. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-14442-9_24"},{"key":"55_CR17","doi-asserted-by":"crossref","unstructured":"Rossetto, L., Giangreco, I., T\u0103nase, C., Schuldt, H.: vitrivr: a flexible retrieval stack supporting multiple query modesfor searching in multimedia collections. In: Proceedings of the ACM Conference on Multimedia Conference (ACM MM), pp. 1183\u20131186. ACM, Amsterdam, October 2016","DOI":"10.1145\/2964284.2973797"},{"key":"55_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"469","DOI":"10.1007\/978-3-319-51814-5_43","volume-title":"MultiMedia Modeling","author":"L Rossetto","year":"2017","unstructured":"Rossetto, L., Giangreco, I., T\u0103nase, C., Schuldt, H., Dupont, S., Seddati, O.: Enhanced retrieval and browsing in the IMOTION system. In: Amsaleg, L., Gu\u00f0mundsson, G.\u00de., Gurrin, C., J\u00f3nsson, B.\u00de., Satoh, S. (eds.) MMM 2017. LNCS, vol. 10133, pp. 469\u2013474. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-51814-5_43"},{"issue":"11","key":"55_CR19","doi-asserted-by":"crossref","first-page":"2298","DOI":"10.1109\/TPAMI.2016.2646371","volume":"39","author":"B Shi","year":"2017","unstructured":"Shi, B., Bai, X., Yao, C.: An end-to-end trainable neural network for image-based sequence recognition and its application to scene text recognition. IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI) 39(11), 2298\u20132304 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI)"},{"key":"55_CR20","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3D convolutional networks. In: Proceedings of the International Conference on Computer Vision (ICCV), pp. 4489\u20134497. IEEE, Santiago (2015)","DOI":"10.1109\/ICCV.2015.510"},{"issue":"4","key":"55_CR21","doi-asserted-by":"crossref","first-page":"652","DOI":"10.1109\/TPAMI.2016.2587640","volume":"39","author":"O Vinyals","year":"2017","unstructured":"Vinyals, O., Toshev, A., Bengio, S., Erhan, D.: Show and tell: lessons learned from the 2015 MSCOCO image captioning challenge. IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI) 39(4), 652\u2013663 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI)"},{"key":"55_CR22","doi-asserted-by":"crossref","unstructured":"Zhou, B., Zhao, H., Puig, X., Fidler, S., Barriuso, A., Torralba, A.: Scene parsing through ADE20K dataset. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), vol. 1, p. 4. IEEE, Honolulu (2017)","DOI":"10.1109\/CVPR.2017.544"},{"key":"55_CR23","doi-asserted-by":"crossref","unstructured":"Zhou, X., et al.: East: an efficient and accurate scene text detector. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2642\u20132651. IEEE, Honolulu (2017)","DOI":"10.1109\/CVPR.2017.283"}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-05716-9_55","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,11,6]],"date-time":"2019-11-06T23:53:25Z","timestamp":1573084405000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-05716-9_55"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,12,11]]},"ISBN":["9783030057152","9783030057169"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-05716-9_55","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,12,11]]},"assertion":[{"value":"MMM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Multimedia Modeling","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Thessaloniki","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Greece","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 January 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 January 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mmm2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/mmm2019.iti.gr\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double blind for full papers and workshop papers, single blind for other paper types","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"204","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"96","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"47% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"2.67","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"3","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"6 demonstration papers, 5 industry papers, 6 workshop papers, and 6 Video Browser Showdown papers were also accepted.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}}]}}