{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T04:11:32Z","timestamp":1750306292643,"version":"3.41.0"},"publisher-location":"New York, New York, USA","reference-count":35,"publisher":"ACM Press","license":[{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"IARPA","award":["D11PC20068"],"award-info":[{"award-number":["D11PC20068"]}]},{"name":"NSF","award":["OCI-1053575"],"award-info":[{"award-number":["OCI-1053575"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016]]},"DOI":"10.1145\/2872518.2888599","type":"proceedings-article","created":{"date-parts":[[2017,1,23]],"date-time":"2017-01-23T20:35:52Z","timestamp":1485203752000},"page":"311-316","source":"Crossref","is-referenced-by-count":3,"title":["Web-scale Multimedia Search for Internet Video Content"],"prefix":"10.1145","author":[{"given":"Lu","family":"Jiang","sequence":"first","affiliation":[{"name":"School of Computer Science, Carnegie Mellon University, Pittsburgh, PA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","reference":[{"key":"key-10.1145\/2872518.2888599-1","doi-asserted-by":"crossref","unstructured":"E. Apostolidis, V. Mezaris, M. Sahuguet, B. Huet, B.vCervenková, D. Stein, S. Eickeler, J. L. Redondo Garcia, R. Troncy, and L. Pikora. Automatic fine-grained hyperlinking of videos within a closed collection using scene segmentation. In MM, 2014.","DOI":"10.1145\/2647868.2655041"},{"key":"key-10.1145\/2872518.2888599-2","doi-asserted-by":"crossref","unstructured":"Y. Bengio, J. Louradour, R. Collobert, and J. Weston. Curriculum learning. In ICML, 2009.","DOI":"10.1145\/1553374.1553380"},{"key":"key-10.1145\/2872518.2888599-3","doi-asserted-by":"crossref","unstructured":"A. Brodersen, S. Scellato, and M. Wattenhofer. Youtube around the world: geographic popularity of videos. In WWW, 2012.","DOI":"10.1145\/2187836.2187870"},{"key":"key-10.1145\/2872518.2888599-4","doi-asserted-by":"crossref","unstructured":"P. Das, R. K. Srihari, and J. J. Corso. Translating related words to videos and back through latent topics. In WSDM, 2013.","DOI":"10.1145\/2433396.2433456"},{"key":"key-10.1145\/2872518.2888599-5","doi-asserted-by":"crossref","unstructured":"J. Davidson, B. Liebald, J. Liu, et al. The youtube video recommendation system. In RecSys, 2010.","DOI":"10.1145\/1864708.1864770"},{"key":"key-10.1145\/2872518.2888599-6","doi-asserted-by":"crossref","unstructured":"H. Jegou, M. Douze, and C. Schmid. Product quantization for nearest neighbor search. PAMI, 33(1):117--128, 2011.","DOI":"10.1109\/TPAMI.2010.57"},{"key":"key-10.1145\/2872518.2888599-7","doi-asserted-by":"crossref","unstructured":"L. Jiang, A. Hauptmann, and G. Xiang. Leveraging high-level and low-level features for multimedia event detection. In MM, 2012.","DOI":"10.1145\/2393347.2393412"},{"key":"key-10.1145\/2872518.2888599-8","doi-asserted-by":"crossref","unstructured":"L. Jiang, D. Meng, T. Mitamura, and A. G. Hauptmann. Easy samples first: Self-paced reranking for zero-example multimedia search. In MM, 2014.","DOI":"10.1145\/2647868.2654918"},{"key":"key-10.1145\/2872518.2888599-9","unstructured":"L. Jiang, D. Meng, S.-I. Yu, Z. Lan, S. Shan, and A. G. Hauptmann. Self-paced learning with diversity. In NIPS, 2014."},{"key":"key-10.1145\/2872518.2888599-10","doi-asserted-by":"crossref","unstructured":"L. Jiang, D. Meng, Q. Zhao, S. Shan, and A. G. Hauptmann. Self-paced curriculum learning. In AAAI, 2015.","DOI":"10.1609\/aaai.v29i1.9608"},{"key":"key-10.1145\/2872518.2888599-11","doi-asserted-by":"crossref","unstructured":"L. Jiang, T. Mitamura, S.-I. Yu, and A. G. Hauptmann. Zero-example event search using multimodal pseudo relevance feedback. In ICMR, 2014.","DOI":"10.1145\/2578726.2578764"},{"key":"key-10.1145\/2872518.2888599-12","doi-asserted-by":"crossref","unstructured":"L. Jiang, W. Tong, D. Meng, and A. G. Hauptmann. Towards efficient learning of optimal spatial bag-of-words representations. In ICMR, 2014.","DOI":"10.1145\/2578726.2578739"},{"key":"key-10.1145\/2872518.2888599-13","doi-asserted-by":"crossref","unstructured":"L. Jiang, S.-I. Yu, D. Meng, T. Mitamura, and A. G. Hauptmann. Bridging the ultimate semantic gap: A semantic search engine for internet videos. In ICMR, 2015.","DOI":"10.1145\/2671188.2749399"},{"key":"key-10.1145\/2872518.2888599-14","doi-asserted-by":"crossref","unstructured":"L. Jiang, S.-I. Yu, D. Meng, Y. Yang, T. Mitamura, and A. G. Hauptmann. Fast and accurate content-based semantic search in 100m internet videos. In MM, 2015.","DOI":"10.1145\/2733373.2806237"},{"key":"key-10.1145\/2872518.2888599-15","unstructured":"M. Kumar, B. Packer, and D. Koller. Self-paced learning for latent variable models. In NIPS, 2010."},{"key":"key-10.1145\/2872518.2888599-16","doi-asserted-by":"crossref","unstructured":"C. C. Marshall and F. M. Shipman. Saving, reusing, and remixing web video: using attitudes and practices to reveal social norms. In WWW, 2013.","DOI":"10.1145\/2488388.2488465"},{"key":"key-10.1145\/2872518.2888599-17","unstructured":"Y. Miao, M. Gowayyed, and F. Metze. Eesen: End-to-end speech recognition using deep rnn models and wfst-based decoding. arXiv preprint arXiv:1507.08240, 2015."},{"key":"key-10.1145\/2872518.2888599-18","doi-asserted-by":"crossref","unstructured":"Y. Miao, L. Jiang, H. Zhang, and F. Metze. Improvements to speaker adaptive training of deep neural networks. In SLT, 2014.","DOI":"10.1109\/SLT.2014.7078568"},{"key":"key-10.1145\/2872518.2888599-19","doi-asserted-by":"crossref","unstructured":"Y. Miao, F. Metze, and S. Rawat. Deep maxout networks for low-resource speech recognition. In ASRU, 2013.","DOI":"10.1109\/ASRU.2013.6707763"},{"key":"key-10.1145\/2872518.2888599-20","doi-asserted-by":"crossref","unstructured":"F. F.-H. Nah. A study on tolerable waiting time: how long are web users willing to wait? Behaviour & Information Technology, 23(3):153--163, 2004.","DOI":"10.1080\/01449290410001669914"},{"key":"key-10.1145\/2872518.2888599-21","doi-asserted-by":"crossref","unstructured":"M. R. Naphade and J. R. Smith. On the detection of semantic concepts at trecvid. In MM, 2004.","DOI":"10.1145\/1027527.1027680"},{"key":"key-10.1145\/2872518.2888599-22","doi-asserted-by":"crossref","unstructured":"R. J. Ordelman, M. Eskevich, R. Aly, B. Huet, and G. Jones. Defining and evaluating video hyperlinking for navigating multimedia archives. In Companion on WWW, 2015.","DOI":"10.1145\/2740908.2742915"},{"key":"key-10.1145\/2872518.2888599-23","unstructured":"P. Over, G. M. Awad, J. Fiscus, B. Antonishek, M. Michel, A. F. Smeaton, W. Kraaij, and G. Quénot. Trecvid 2010--an overview of the goals, tasks, data, evaluation mechanisms, and metrics. In TRECVID, 2011."},{"key":"key-10.1145\/2872518.2888599-24","doi-asserted-by":"crossref","unstructured":"R. Qumsiyeh and Y.-K. Ng. Predicting the ratings of multimedia items for making personalized recommendations. In SIGIR, 2012.","DOI":"10.1145\/2348283.2348349"},{"key":"key-10.1145\/2872518.2888599-25","unstructured":"O. Russakovsky, J. Deng, H. Su, J. Krause, S. Satheesh, S. Ma, Z. Huang, A. Karpathy, A. Khosla, M. Bernstein, et al. Imagenet large scale visual recognition challenge. IJCV, pages 1--42, 2014."},{"key":"key-10.1145\/2872518.2888599-26","doi-asserted-by":"crossref","unstructured":"J. Sivic and A. Zisserman. Video google: A text retrieval approach to object matching in videos. In ICCV, 2003.","DOI":"10.1109\/ICCV.2003.1238663"},{"key":"key-10.1145\/2872518.2888599-27","doi-asserted-by":"crossref","unstructured":"J. R. Smith. Riding the multimedia big data wave. In SIGIR, 2013.","DOI":"10.1145\/2484028.2494492"},{"key":"key-10.1145\/2872518.2888599-28","doi-asserted-by":"crossref","unstructured":"C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, and A. Rabinovich. Going deeper with convolutions. In CVPR 2015, 2015.","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"key-10.1145\/2872518.2888599-29","unstructured":"B. Thomee, D. A. Shamma, G. Friedland, B. Elizalde, K. Ni, D. Poland, D. Borth, and L.-J. Li. The new data and new challenges in multimedia research. arXiv preprint arXiv:1503.01817, 2015."},{"key":"key-10.1145\/2872518.2888599-30","unstructured":"B. Vandersmissen, F. Godin, A. Tomar, W. De Neve, and R. Van de Walle. The rise of mobile and social short-form video: an in-depth measurement study of vine. In Workshop on Social Multimedia and Storytelling, volume 1198, pages 1--10, 2014."},{"key":"key-10.1145\/2872518.2888599-31","unstructured":"B. Varadarajan, G. Toderici, S. Vijayanarasimhan, and A. Natsev. Efficient large scale video classification. arXiv preprint arXiv:1505.06250, 2015."},{"key":"key-10.1145\/2872518.2888599-32","unstructured":"S.-I. Yu, L. Jiang, Z. Xu, et al. Informedia @ trecvid 2014 med and mer. In TRECVID, 2014."},{"key":"key-10.1145\/2872518.2888599-33","doi-asserted-by":"crossref","unstructured":"S.-I. Yu, L. Jiang, Z. Xu, Y. Yang, and A. G. Hauptmann. Content-based video search over 1 million videos with 1 core in 1 second. In ICMR, 2015.","DOI":"10.1145\/2671188.2749398"},{"key":"key-10.1145\/2872518.2888599-34","doi-asserted-by":"crossref","unstructured":"Q. Zhao, D. Meng, L. Jiang, Q. Xie, Z. Xu, and A. G. Hauptmann. Self-paced learning for matrix factorization. In AAAI, 2015.","DOI":"10.1609\/aaai.v29i1.9584"},{"key":"key-10.1145\/2872518.2888599-35","doi-asserted-by":"crossref","unstructured":"C.-Z. Zhu and S. Satoh. Large vocabulary quantization for searching instances from videos. In ICMR, 2012.","DOI":"10.1145\/2324796.2324856"}],"event":{"number":"25","sponsor":["SIGWEB, ACM Special Interest Group on Hypertext, Hypermedia, and Web","IW3C2, International World Wide Web Conference Committee"],"acronym":"WWW '16 Companion","name":"the 25th International Conference Companion","start":{"date-parts":[[2016,4,11]]},"location":"Montréal, Québec, Canada","end":{"date-parts":[[2016,4,15]]}},"container-title":["Proceedings of the 25th International Conference Companion on World Wide Web - WWW '16 Companion"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2872518.2888599","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/dl.acm.org\/ft_gateway.cfm?id=2888599&ftid=1707824&dwn=1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:39:07Z","timestamp":1750221547000},"score":1,"resource":{"primary":{"URL":"http:\/\/dl.acm.org\/citation.cfm?doid=2872518.2888599"}},"subtitle":[],"proceedings-subject":"World Wide Web","short-title":[],"issued":{"date-parts":[[2016]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1145\/2872518.2888599","relation":{},"subject":[],"published":{"date-parts":[[2016]]}}}