{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T03:18:00Z","timestamp":1740107880901,"version":"3.37.3"},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2016,4,13]],"date-time":"2016-04-13T00:00:00Z","timestamp":1460505600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Nature Science Foundation of China","doi-asserted-by":"crossref","award":["61173054"],"award-info":[{"award-number":["61173054"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"crossref","award":["4152050"],"award-info":[{"award-number":["4152050"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"crossref"}]},{"name":"863 Project","award":["2014AA015202"],"award-info":[{"award-number":["2014AA015202"]}]},{"name":"the Funds for Creative Research Groups of China under Grant","award":["61421061"],"award-info":[{"award-number":["61421061"]}]},{"name":"the Cosponsored Project of Beijing Committee of Education"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2017,11]]},"DOI":"10.1007\/s00530-016-0506-9","type":"journal-article","created":{"date-parts":[[2016,4,14]],"date-time":"2016-04-14T05:01:38Z","timestamp":1460610098000},"page":"713-724","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Multi-modal tag localization for mobile video search"],"prefix":"10.1007","volume":"23","author":[{"given":"Rui","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sheng","family":"Tang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wu","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongdong","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jintao","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2016,4,13]]},"reference":[{"issue":"8","key":"506_CR1","doi-asserted-by":"crossref","first-page":"2242","DOI":"10.1109\/TMM.2014.2359332","volume":"16","author":"W Liu","year":"2014","unstructured":"Liu, W., Mei, T., Zhang, Y.: Instant mobile video search with layered audio-video indexing and progressive transmission. IEEE Trans. Multimed. 16(8), 2242\u20132255 (2014)","journal-title":"IEEE Trans. Multimed."},{"key":"506_CR2","doi-asserted-by":"crossref","unstructured":"Ballan, L., Bertini, M., Del Bimbo, A., Meoni, M., Serra, G.: Tag suggestion and localization in user-generated videos based on social knowledge. In: ACM SIGMM workshop on social media, pp. 3\u20138 (2010)","DOI":"10.1145\/1878151.1878155"},{"key":"506_CR3","doi-asserted-by":"crossref","unstructured":"Chu, W.-T., Li, C.-J., Chou, Y.-K.: Tag suggestion and localization for web videos by bipartite graph matching. In: ACM SIGMM workshop on Social media, pp. 35\u201340 (2011)","DOI":"10.1145\/2072609.2072621"},{"key":"506_CR4","unstructured":"Ulges, A., Schulze, C., Breuel, T.: Multiple instance learning from weakly labeled videos. In: SAMT workshop on cross-media information analysis and retrieval (2008)"},{"key":"506_CR5","doi-asserted-by":"crossref","unstructured":"Li, G., Wang, M., Zheng, Y., Li, H., Zha, Z., Chua, T.: Shottagger: tag location for internet videos. In: ICMR, p. 37 (2011)","DOI":"10.1145\/1991996.1992033"},{"key":"506_CR6","doi-asserted-by":"crossref","unstructured":"Fergus, R., Li, F., Perona, P., Zisserman, A.: Learning object categories from google\u2019s image search. In: ICCV, pp. 1816\u20131823 (2005)","DOI":"10.1109\/ICCV.2005.142"},{"key":"506_CR7","unstructured":"Li, H., Yi, L., Liu, B., Wang, Y.: Localizing relevant frames in web videos using topic model and relevance filtering. Mach. Vis. Appl. 25(7), 1661\u20131670 (2014)"},{"key":"506_CR8","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: NIPS, pp. 1106\u20131114 (2012)"},{"key":"506_CR9","doi-asserted-by":"crossref","unstructured":"Zhang, R., Tang, S., Liu, W., Li, J.: Multimodal tag localization based on deep learning. In: Proceedings of the 7th international conference on internet multimedia computing and service, ICIMCS 2015, Zhangjiajie, August 19\u201321, pp. 50:1\u201350:4 (2015)","DOI":"10.1145\/2808492.2808542"},{"key":"506_CR10","doi-asserted-by":"crossref","unstructured":"Girshick, R.B.: Fast R-CNN. CoRR, vol. abs\/1504.08083 (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"506_CR11","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. CoRR, vol. abs\/1409.1556 (2014)"},{"key":"506_CR12","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L., Li, K., Li, F.: Imagenet: a large-scale hierarchical image database. In: CVPR, pp. 248\u2013255 (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"506_CR13","unstructured":"Srivastava, N., Hinton, G.E., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res 15(1), 1929\u20131958 (2014)"},{"key":"506_CR14","doi-asserted-by":"crossref","unstructured":"Girshick, R.B., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: CVPR, pp. 580\u2013587 (2014)","DOI":"10.1109\/CVPR.2014.81"},{"key":"506_CR15","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. CoRR, vol. abs\/1411.4038 (2014)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"506_CR16","unstructured":"Farabet, C., Couprie, C., Najman, L., LeCun, Y.: Learning hierarchical features for scene labeling. IEEE Trans. Pattern Anal. Mach. Intell. 35(8), 1915\u20131929 (2013)"},{"key":"506_CR17","unstructured":"Donahue, J., Jia, Y., Vinyals, O., Hoffman, J., Zhang, N., Tzeng, E., Darrell, T.: Decaf: a deep convolutional activation feature for generic visual recognition. In: ICML, pp. 647\u2013655 (2014)"},{"key":"506_CR18","unstructured":"Ji, S., Xu, W., Yang, M., Yu, K.: 3d convolutional neural networks for human action recognition. IEEE Trans. Pattern Anal. Mach. Intell. 35(1), 221\u2013231 (2013)"},{"key":"506_CR19","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Toderici, G., Shetty, S., Leung, T., Sukthankar, R., Li, F.: Large-scale video classification with convolutional neural networks. In: CVPR, pp. 1725\u20131732 (2014)","DOI":"10.1109\/CVPR.2014.223"},{"issue":"4","key":"506_CR20","doi-asserted-by":"crossref","first-page":"833","DOI":"10.1109\/TMM.2013.2238909","volume":"15","author":"D Tao","year":"2013","unstructured":"Tao, D., Jin, L., Liu, W., Li, X.: Hessian regularized support vector machines for mobile image annotation on the cloud. IEEE Trans. Multimed. 15(4), 833\u2013844 (2013)","journal-title":"IEEE Trans. Multimed."},{"key":"506_CR21","unstructured":"Mei, T., Wang, Y., Hua, X., Gong, S., Li, S.: Coherent image annotation by learning semantic distance. In: CVPR, 24\u201326 June, Anchorage (2008)"},{"issue":"2","key":"506_CR22","first-page":"10","volume":"29","author":"T Mei","year":"2011","unstructured":"Mei, T., Yang, B., Hua, X., Li, S.: Contextual video recommendation by multimodal relevance and user feedback. ACM Trans. Inf. Syst. 29(2), 10 (2011)","journal-title":"ACM Trans. Inf. Syst."},{"issue":"7","key":"506_CR23","doi-asserted-by":"crossref","first-page":"2676","DOI":"10.1109\/TIP.2013.2255302","volume":"22","author":"W Liu","year":"2013","unstructured":"Liu, W., Tao, D.: Multiview hessian regularization for image annotation. IEEE Trans. Image Process. 22(7), 2676\u20132687 (2013)","journal-title":"IEEE Trans. Image Process."},{"key":"506_CR24","doi-asserted-by":"crossref","first-page":"50","DOI":"10.1016\/j.cviu.2013.03.007","volume":"118","author":"W Liu","year":"2014","unstructured":"Liu, W., Tao, D., Cheng, J., Tang, Y.: Multiview hessian discriminative sparse coding for image annotation. Comput. Vis. Image Underst. 118, 50\u201360 (2014)","journal-title":"Comput. Vis. Image Underst."},{"issue":"12","key":"506_CR25","doi-asserted-by":"crossref","first-page":"2531","DOI":"10.1109\/TPAMI.2015.2417578","volume":"37","author":"C Xu","year":"2015","unstructured":"Xu, C., Tao, D., Xu, C.: Multi-view intact space learning. IEEE Trans. Pattern Anal. Mach. Intell. 37(12), 2531\u20132544 (2015)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"8","key":"506_CR26","doi-asserted-by":"crossref","first-page":"1559","DOI":"10.1109\/TPAMI.2013.2296528","volume":"36","author":"X Chang","year":"2014","unstructured":"Chang, X., Dacheng, T., Chao, X.: Large-margin multi-view information bottleneck. Pattern Anal. Mach. Intell. IEEE Trans. 36(8), 1559\u20131572 (2014)","journal-title":"Pattern Anal. Mach. Intell. IEEE Trans."},{"key":"506_CR27","unstructured":"Ngiam, J., Khosla, A., Kim, M., Nam, J., Lee, H., Ng, A.Y.: Multimodal deep learning. In: ICML, pp. 689\u2013696 (2011)"},{"issue":"1","key":"506_CR28","first-page":"2949","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava, N., Salakhutdinov, R.: Multimodal learning with deep boltzmann machines. J. Mach. Learn. Res. 15(1), 2949\u20132980 (2014)","journal-title":"J. Mach. Learn. Res."},{"key":"506_CR29","unstructured":"Frome, A., Corrado, G.S., Shlens, J., Bengio, S., Dean, J., Ranzato, M., Mikolov, T.: Devise: a deep visual-semantic embedding model. In: NIPS, pp. 2121\u20132129 (2013)"},{"key":"506_CR30","doi-asserted-by":"crossref","unstructured":"W. Liu, T. Mei, Y. Zhang, C. Che, and J. Luo, \u201cMulti-task deep visual-semantic embedding for video thumbnail selection,\u201d in CVPR, 2015, pp. 3707\u20133715","DOI":"10.1109\/CVPR.2015.7298994"},{"key":"506_CR31","doi-asserted-by":"crossref","unstructured":"Pan, Y., Mei, T., Yao, T., Li, H., Rui, Y.: Jointly modeling embedding and translation to bridge video and language. CoRR, vol. abs\/1505.01861 (2015)","DOI":"10.1109\/CVPR.2016.497"},{"key":"506_CR32","unstructured":"Mikolov, T., Sutskever, I., Chen, K., Corrado, G.S., Dean, J.: Distributed representations of words and phrases and their compositionality. In: NIPS, pp. 3111\u20133119 (2013)"},{"key":"506_CR33","doi-asserted-by":"crossref","unstructured":"Kang, H., Hua, X.: To learn representativeness of video frames. In: ACM MM, pp. 423\u2013426 (2005)","DOI":"10.1145\/1101149.1101242"},{"issue":"2","key":"506_CR34","doi-asserted-by":"crossref","first-page":"289","DOI":"10.1109\/TCSVT.2008.2009241","volume":"19","author":"J Luo","year":"2009","unstructured":"Luo, J., Papin, C., Costello, K.: Towards extracting semantically meaningful key frames from personal video clips: from humans to computers. IEEE Trans. Circ. Syst. Video Technol. 19(2), 289\u2013301 (2009)","journal-title":"IEEE Trans. Circ. Syst. Video Technol."},{"key":"506_CR35","doi-asserted-by":"crossref","unstructured":"Li, H., Yi, L., Guan, Y., Zhang, H.: DUT-WEBV: a benchmark dataset for performance evaluation of tag localization for web video. In: MMM, pp. 305\u2013315 (2013)","DOI":"10.1007\/978-3-642-35728-2_29"},{"key":"506_CR36","unstructured":"Word2vec [Online]. https:\/\/code.google.com\/p\/word2vec\/"},{"key":"506_CR37","doi-asserted-by":"crossref","unstructured":"Ulges, A., Schulze, C., Keysers, D., Breuel, T.M.: Identifying relevant frames in weakly labeled videos for training concept detectors. In: CIVR, pp. 9\u201316 (2008)","DOI":"10.1145\/1386352.1386358"},{"key":"506_CR38","unstructured":"Ballan, L., Bertini, M., Serra, G., Bimbo, A.D.: A data-driven approach for tag refinement and localization in web videos. CoRR, vol. abs\/1407.0623 (2014)"}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00530-016-0506-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-016-0506-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-016-0506-9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-016-0506-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,9,6]],"date-time":"2019-09-06T13:20:49Z","timestamp":1567776049000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00530-016-0506-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,4,13]]},"references-count":38,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2017,11]]}},"alternative-id":["506"],"URL":"https:\/\/doi.org\/10.1007\/s00530-016-0506-9","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"type":"print","value":"0942-4962"},{"type":"electronic","value":"1432-1882"}],"subject":[],"published":{"date-parts":[[2016,4,13]]}}}