{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2023,6,9]],"date-time":"2023-06-09T21:50:23Z","timestamp":1686347423292},"reference-count":45,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2014,5,23]],"date-time":"2014-05-23T00:00:00Z","timestamp":1400803200000},"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":["Multimed Tools Appl"],"published-print":{"date-parts":[[2015,2]]},"DOI":"10.1007\/s11042-014-2056-5","type":"journal-article","created":{"date-parts":[[2014,5,22]],"date-time":"2014-05-22T01:41:13Z","timestamp":1400722873000},"page":"1291-1315","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Best practices for learning video concept detectors from social media examples"],"prefix":"10.1007","volume":"74","author":[{"given":"Svetlana","family":"Kordumova","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xirong","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cees G. M.","family":"Snoek","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2014,5,23]]},"reference":[{"key":"2056_CR1","doi-asserted-by":"crossref","unstructured":"Ballan L, Bertini M, Del Bimbo A, Serra G (2011) Enriching and localizing semantic tags in internet videos. In: MM 1541\u20131544","DOI":"10.1145\/2072298.2072060"},{"key":"2056_CR2","unstructured":"Chang S-F, Ellis D, Jiang W, Lee K, Yanagawa A, Loui AC, Luo J (2007) Large-scale multimodal semantic concept detection for consumer video. In: MIR 255\u2013264"},{"key":"2056_CR3","doi-asserted-by":"crossref","unstructured":"Fan J, Shen Y, Zhou N, Gao Y (2010) Harvesting large-scale weakly-tagged image databases from the web. In: CVPR 802\u2013809","DOI":"10.1109\/CVPR.2010.5540135"},{"key":"2056_CR4","doi-asserted-by":"crossref","unstructured":"Heikkila M, Pietikainen M, Schmid C (2009) Description of interest regions with local binary patterns. In: PR 42(3):425\u2013436","DOI":"10.1016\/j.patcog.2008.08.014"},{"key":"2056_CR5","unstructured":"Hu Y, Li M, Yu N (2008) Multiple-instance ranking: learning to rank images for image retrieval. In: CVPR 1\u20138"},{"key":"2056_CR6","unstructured":"Hwang SJ, Grauman K (2012) Learning the relative importance of objects from tagged images for retrieval and cross-modal search. In: IJCV 100(2):134\u2013153"},{"key":"2056_CR7","doi-asserted-by":"crossref","unstructured":"Jain V, Varma M (2011) Learning to re-rank: query-dependent image re-ranking using click data. In: WWW 277\u2013286","DOI":"10.1145\/1963405.1963447"},{"key":"2056_CR8","doi-asserted-by":"crossref","unstructured":"Jiang W, Cotton CV, Chang S-F, Ellis D, Loui AC (2009) Short-term audio-visual atoms for generic video concept classification. In: MM. doi: 10.1145\/1631272.1631277","DOI":"10.1145\/1631272.1631277"},{"key":"2056_CR9","unstructured":"Jiang Y-G, Yang J, Ngo C-W, Hauptmann A (2010) Representations of keypoint-based semantic concept detection: a comprehensive study. In: TMM 12(1):42\u201353"},{"key":"2056_CR10","doi-asserted-by":"crossref","unstructured":"Joachims T (2002) Optimizing search engines using clickthrough data. In: SIGKDD 133\u2013142","DOI":"10.1145\/775047.775067"},{"key":"2056_CR11","doi-asserted-by":"crossref","unstructured":"Kennedy LS, Chang S-F, Kozintsev IV (2006) To search or to label?: predicting the performance of search-based automatic image classifiers. In: MIR 249\u2013258","DOI":"10.1145\/1178677.1178712"},{"key":"2056_CR12","unstructured":"Kim J, Pavlovic V (2012) Attribute rating for classification of visual objects. In: ICPR 1611\u20131614"},{"key":"2056_CR13","doi-asserted-by":"crossref","unstructured":"Kordumova S, Li X, Snoek CGM (2013) Evaluating sources and strategies for learning video concepts from social media. In: CBMI 91\u201396","DOI":"10.1109\/CBMI.2013.6576561"},{"key":"2056_CR14","doi-asserted-by":"crossref","unstructured":"Li M (2007) Texture moment for content-based image retrieval. In: ICME 508\u2013511","DOI":"10.1109\/ICME.2007.4284698"},{"key":"2056_CR15","unstructured":"Li X, Snoek CGM, Worring M (2009) Learning social tag relevance by neighbor voting. In: TMM 11(7):1310\u20131322"},{"key":"2056_CR16","doi-asserted-by":"crossref","unstructured":"Li X, Snoek CGM, Worring M (2010) Unsupervised multi-feature tag relevance learning for social image retrieval. In: CIVR 10\u201317","DOI":"10.1145\/1816041.1816044"},{"key":"2056_CR17","unstructured":"Li X, Snoek CGM, Worring M, Koelma DC, Smeulders AWM (2013) Bootstrapping visual categorization with relevant negatives. In: TMM 15(4):933\u2013945"},{"key":"2056_CR18","doi-asserted-by":"crossref","unstructured":"Li X, Snoek CGM, Worring M, Smeulders AWM (2012) Harvesting social images for bi-concept search. In: TMM 14(4):1091\u20131104","DOI":"10.1109\/TMM.2012.2191943"},{"key":"2056_CR19","doi-asserted-by":"crossref","unstructured":"Li G, Wang M, Zheng Y-T, Li H, Zha Z-J, Chua T-S (2011) Shottagger: tag location for internet videos. In: ICMR. doi: 10.1145\/1991996.1992033","DOI":"10.1145\/1991996.1992033"},{"key":"2056_CR20","doi-asserted-by":"crossref","unstructured":"Liu D, Hua X, Yang L, Wang M, Zhang H (2009) Tag ranking. In: WWW 351\u2013360","DOI":"10.1145\/1526709.1526757"},{"key":"2056_CR21","unstructured":"Liu Y, Xu D, Tsang IW-H, Luo J (2011) Textual query of personal photos facilitated by large-scale web data. In: PAMI 33(5):1022\u20131036"},{"key":"2056_CR22","unstructured":"Lowe DG (2003) Distinctive image features from scale-invariant keypoints. In: IJCV 60(2):91\u2013110"},{"key":"2056_CR23","doi-asserted-by":"crossref","unstructured":"Maji S, Berg A, Malik J (2008) Classification using intersection kernel support vector machines is efficient. In: CVPR 1\u20138","DOI":"10.1109\/CVPR.2008.4587630"},{"key":"2056_CR24","doi-asserted-by":"crossref","unstructured":"Oliva A, Torralba A (2001) Modeling the shape of the scene: a holistic representation of the spatial envelope. In: IJCV 42(3):145\u2013175","DOI":"10.1023\/A:1011139631724"},{"key":"2056_CR25","doi-asserted-by":"crossref","unstructured":"Ray S, Craven M (2005) Supervised versus multiple instance learning: an empirical comparison. In ICML 697\u2013704","DOI":"10.1145\/1102351.1102439"},{"key":"2056_CR26","doi-asserted-by":"crossref","unstructured":"Schindler G, Zitnick L, Brown M (2008) Internet video category recognition. CVPR. doi: 10.1109\/CVPRW.2008.4562960","DOI":"10.1109\/CVPRW.2008.4562960"},{"key":"2056_CR27","doi-asserted-by":"crossref","unstructured":"Schroff F, Criminisi A, Zisserman A (2007) Harvesting image databases from the web. In: ICCV 33(4):754\u201366","DOI":"10.1109\/ICCV.2007.4409099"},{"key":"2056_CR28","unstructured":"Settles B, Craven M, Ray S (2008) Multiple-instance active learning. In: NIPS 1289\u20131296"},{"key":"2056_CR29","doi-asserted-by":"crossref","unstructured":"Setz A, Snoek CGM (2009) Can social tagged images aid concept-based video search? In: ICME 1460\u20131463","DOI":"10.1109\/ICME.2009.5202778"},{"key":"2056_CR30","doi-asserted-by":"crossref","unstructured":"Sigurbj\u00f6rnsson B, van Zwol R (2008) Flickr tag recommendation based on collective knowledge. In: WWW 327\u2013336","DOI":"10.1145\/1367497.1367542"},{"key":"2056_CR31","doi-asserted-by":"crossref","unstructured":"Sivic J, Zisserman A (2003) Video google: a text retrieval approach to object matching in videos. In: ICCV 2:1470\u20131477","DOI":"10.1109\/ICCV.2003.1238663"},{"key":"2056_CR32","doi-asserted-by":"crossref","unstructured":"Smeaton AF, Over P, Kraaij W (2006) Evaluation campaigns and TRECVid. In: MIR 321\u2013330","DOI":"10.1145\/1178677.1178722"},{"key":"2056_CR33","doi-asserted-by":"crossref","unstructured":"Sun Y, Kojima A (2011) A novel method for semantic video concept learning using web images. In: MM 1081\u20131084","DOI":"10.1145\/2072298.2071943"},{"key":"2056_CR34","doi-asserted-by":"crossref","unstructured":"Ulges A, Koch M, Borth D (2012) Linking visual concept detection with viewer demographics. In: ICMR. doi: 10.1145\/2324796.2324827","DOI":"10.1145\/2324796.2324827"},{"key":"2056_CR35","doi-asserted-by":"crossref","unstructured":"Ulges A, Schulze C, Keysers D, Breuel T (2008) A system that learns to tag videos by watching youtube. In: ICVS 5008:415\u2013424","DOI":"10.1007\/978-3-540-79547-6_40"},{"key":"2056_CR36","doi-asserted-by":"crossref","unstructured":"Ulges A, Schulze C, Keysers D, Breuel T (2008) Identifying relevant frames in weakly labeled videos for training concept detectors. In: CIVR 9\u201316","DOI":"10.1145\/1386352.1386358"},{"key":"2056_CR37","doi-asserted-by":"crossref","unstructured":"Uricchio T, Ballan L, Bertini M, Del Bimbo A (2013) An evaluation of nearest-neighbor methods for tag refinement. In: ICME 1\u20136","DOI":"10.1109\/ICME.2013.6607547"},{"key":"2056_CR38","doi-asserted-by":"crossref","unstructured":"van de Sande K, Gevers T, Snoek CGM (2010) Evaluating color descriptors for object and scene recognition. In: PAMI 32(9):1582\u20131596","DOI":"10.1109\/TPAMI.2009.154"},{"key":"2056_CR39","volume-title":"Statistical learning theory","author":"VN Vapnik","year":"1998","unstructured":"Vapnik VN (1998) Statistical learning theory. Wiley, New York"},{"key":"2056_CR40","doi-asserted-by":"crossref","unstructured":"Wang H, Schmid C (2013) Action recognition with improved trajectories. In: ICCV 3551\u20133558","DOI":"10.1109\/ICCV.2013.441"},{"key":"2056_CR41","doi-asserted-by":"crossref","unstructured":"Wang Z, Zhao M, Song Y, Kumar S, Li B (2010) Youtubecat: learning to categorize wild web videos. In: CVPR","DOI":"10.1109\/CVPR.2010.5540125"},{"key":"2056_CR42","doi-asserted-by":"crossref","unstructured":"Yan R, Hauptmann AG, Jin R (2003) Negative pseudo-relevance feedback in content-based video retrieval. I:n MM 343\u2013346","DOI":"10.1145\/957013.957087"},{"key":"2056_CR43","doi-asserted-by":"crossref","unstructured":"Yang J, Hauptmann A (2008) (Un)reliability of video concept detection. In: CIVR 85\u201394","DOI":"10.1145\/1386352.1386367"},{"key":"2056_CR44","unstructured":"Zhao W-L, Wu X, Ngo C-W (2010) On the annotation of web videos by efficient near-duplicate search. In: TMM 12(5):448\u2013461"},{"key":"2056_CR45","doi-asserted-by":"crossref","unstructured":"Zhu S, Ngo C-W, Jiang Y-G (2012) Sampling and ontologically pooling web images for visual concept learning. In: TMM 14(4):1068\u20131078","DOI":"10.1109\/TMM.2012.2190387"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-014-2056-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11042-014-2056-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-014-2056-5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,8,10]],"date-time":"2019-08-10T14:40:05Z","timestamp":1565448005000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11042-014-2056-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,5,23]]},"references-count":45,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2015,2]]}},"alternative-id":["2056"],"URL":"https:\/\/doi.org\/10.1007\/s11042-014-2056-5","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2014,5,23]]}}}