{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T09:34:18Z","timestamp":1789205658379,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":48,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319464862","type":"print"},{"value":"9783319464879","type":"electronic"}],"license":[{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"vor","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":[[2016]]},"DOI":"10.1007\/978-3-319-46487-9_52","type":"book-chapter","created":{"date-parts":[[2016,9,16]],"date-time":"2016-09-16T14:50:47Z","timestamp":1474037447000},"page":"849-866","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":55,"title":["Webly-Supervised Video Recognition by Mutually Voting for Relevant Web Images and Web Video Frames"],"prefix":"10.1007","author":[{"given":"Chuang","family":"Gan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chen","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lixin","family":"Duan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Boqing","family":"Gong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2016,9,17]]},"reference":[{"key":"52_CR1","doi-asserted-by":"crossref","unstructured":"Chang, C.C., Lin, C.J.: LIBSVM: a library for support vector machines. ACM Trans. Intell. Syst. Technol. (2011)","DOI":"10.1145\/1961189.1961199"},{"key":"52_CR2","doi-asserted-by":"crossref","unstructured":"Chen, J., Cui, Y., Ye, G., Liu, D., Chang, S.: Event-driven semantic concept discovery by exploiting weakly tagged internet images. In: ICMR (2014)","DOI":"10.1145\/2578726.2578729"},{"key":"52_CR3","doi-asserted-by":"crossref","unstructured":"Chen, X., Gupta, A.: Webly supervised learning of convolutional networks. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.168"},{"key":"52_CR4","doi-asserted-by":"crossref","unstructured":"Chen, X., Shrivastava, A., Gupta, A.: NEIL: extracting visual knowledge from web data. In: ICCV, pp. 1409\u20131416 (2013)","DOI":"10.1109\/ICCV.2013.178"},{"key":"52_CR5","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: CVPR (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"52_CR6","doi-asserted-by":"crossref","unstructured":"Divvala, S.K., Farhadi, A., Guestrin, C.: Learning everything about anything: webly-supervised visual concept learning. In: CVPR, pp. 3270\u20133277 (2014)","DOI":"10.1109\/CVPR.2014.412"},{"key":"52_CR7","doi-asserted-by":"crossref","unstructured":"Donahue, J., Hendricks, L.A., Guadarrama, S., Rohrbach, M., Venugopalan, S., Saenko, K., Darrell, T.: Long-term recurrent convolutional networks for visual recognition and description. In: CVPR (2015)","DOI":"10.21236\/ADA623249"},{"key":"52_CR8","doi-asserted-by":"crossref","unstructured":"Duan, L., Tsang, I.W., Xu, D., Chua, T.S.: Domain adaptation from multiple sources via auxiliary classifiers. In: Proceedings of the 26th Annual International Conference on Machine Learning, pp. 289\u2013296. ACM (2009)","DOI":"10.1145\/1553374.1553411"},{"issue":"9","key":"52_CR9","doi-asserted-by":"publisher","first-page":"1667","DOI":"10.1109\/TPAMI.2011.265","volume":"34","author":"L Duan","year":"2012","unstructured":"Duan, L., Xu, D., Tsang, I.H., Luo, J.: Visual event recognition in videos by learning from web data. IEEE Trans. Pattern Anal. Mach. Intell. 34(9), 1667\u20131680 (2012)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"52_CR10","first-page":"1871","volume":"9","author":"RE Fan","year":"2008","unstructured":"Fan, R.E., Chang, K.W., Hsieh, C.J., Wang, X.R., Lin, C.J.: Liblinear: a library for large linear classification. J. Mach. Learn. Res. 9, 1871\u20131874 (2008)","journal-title":"J. Mach. Learn. Res."},{"key":"52_CR11","doi-asserted-by":"crossref","unstructured":"Gan, C., Wang, N., Yang, Y., Yeung, D.Y., Hauptmann, A.G.: Devnet: a deep event network for multimedia event detection and evidence recounting. In: CVPR, pp. 2568\u20132577 (2015)","DOI":"10.1109\/CVPR.2015.7298872"},{"key":"52_CR12","doi-asserted-by":"crossref","unstructured":"Gan, C., Yao, T., Yang, K., Yang, Y., Mei, T.: You lead, we exceed: labor-free video concept learning by jointly exploiting web videos and images. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.106"},{"key":"52_CR13","unstructured":"Gong, B., Grauman, K., Sha, F.: Connecting the dots with landmarks: discriminatively learning domain-invariant features for unsupervised domain adaptation. In: ICML, pp. 222\u2013230 (2013)"},{"key":"52_CR14","doi-asserted-by":"crossref","unstructured":"Habibian, A., Mensink, T., Snoek, C.G.: Composite concept discovery for zero-shot video event detection. In: ICMR, p. 17 (2014)","DOI":"10.1145\/2578726.2578746"},{"key":"52_CR15","doi-asserted-by":"crossref","unstructured":"Habibian, A., Mensink, T., Snoek, C.G.: Videostory: a new multimedia embedding for few-example recognition and translation of events. In: ACM Multimedia, pp. 17\u201326 (2014)","DOI":"10.1145\/2647868.2654913"},{"issue":"8","key":"52_CR16","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"52_CR17","doi-asserted-by":"crossref","unstructured":"Huang, J., Gretton, A., Borgwardt, K.M., Sch\u00f6lkopf, B., Smola, A.J.: Correcting sample selection bias by unlabeled data. In: NIPS, pp. 601\u2013608 (2006)","DOI":"10.7551\/mitpress\/7503.003.0080"},{"key":"52_CR18","doi-asserted-by":"crossref","unstructured":"Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R.B., Guadarrama, S., Darrell, T.: Caffe: convolutional architecture for fast feature embedding. In: ACM Multimedia, vol. 2, p. 4 (2014)","DOI":"10.1145\/2647868.2654889"},{"issue":"2","key":"52_CR19","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1007\/s13735-012-0024-2","volume":"2","author":"YG Jiang","year":"2013","unstructured":"Jiang, Y.G., Bhattacharya, S., Chang, S.F., Shah, M.: High-level event recognition in unconstrained videos. Int. J. Multimedia Inf. Retrieval 2(2), 73\u2013101 (2013)","journal-title":"Int. J. Multimedia Inf. Retrieval"},{"key":"52_CR20","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Toderici, G., Shetty, S., Leung, T., Sukthankar, R., Fei-Fei, L.: Large-scale video classification with convolutional neural networks. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.223"},{"key":"52_CR21","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: NIPS (2012)"},{"key":"52_CR22","unstructured":"Lan, Z., Lin, M., Li, X., Hauptmann, A.G., Raj, B.: Beyond gaussian pyramid: multi-skip feature stacking for action recognition. In: CVPR (2015)"},{"key":"52_CR23","doi-asserted-by":"crossref","unstructured":"Liu, W., Hua, G., Smith, J.R.: Unsupervised one-class learning for automatic outlier removal. In: CVPR, pp. 3826\u20133833 (2014)","DOI":"10.1109\/CVPR.2014.483"},{"key":"52_CR24","unstructured":"Ng, J.Y.H., Hausknecht, M., Vijayanarasimhan, S., Vinyals, O., Monga, R., Toderici, G.: Beyond short snippets: deep networks for video classification. In: CVPR (2015)"},{"key":"52_CR25","doi-asserted-by":"crossref","unstructured":"Oneata, D., Verbeek, J., Schmid, C., et al.: Action and event recognition with fisher vectors on a compact feature set. In: ICCV (2013)","DOI":"10.1109\/ICCV.2013.228"},{"issue":"2","key":"52_CR26","doi-asserted-by":"publisher","first-page":"199","DOI":"10.1109\/TNN.2010.2091281","volume":"22","author":"SJ Pan","year":"2011","unstructured":"Pan, S.J., Tsang, I.W., Kwok, J.T., Yang, Q.: Domain adaptation via transfer component analysis. IEEE Trans. Neural Netw. 22(2), 199\u2013210 (2011)","journal-title":"IEEE Trans. Neural Netw."},{"issue":"10","key":"52_CR27","doi-asserted-by":"publisher","first-page":"1345","DOI":"10.1109\/TKDE.2009.191","volume":"22","author":"SJ Pan","year":"2010","unstructured":"Pan, S.J., Yang, Q.: A survey on transfer learning. IEEE Trans. Knowl. Data Eng. 22(10), 1345\u20131359 (2010)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"52_CR28","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-642-15561-1_16","volume-title":"Computer Vision \u2013 ECCV 2010","author":"K Saenko","year":"2010","unstructured":"Saenko, K., Kulis, B., Fritz, M., Darrell, T.: Adapting visual category models to new domains. In: Maragos, P., Paragios, N., Daniilidis, K. (eds.) ECCV 2010, Part IV. LNCS, vol. 6314, pp. 213\u2013226. Springer, Heidelberg (2010)"},{"key":"52_CR29","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: NIPS (2014)"},{"key":"52_CR30","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: ICLR (2015)"},{"key":"52_CR31","doi-asserted-by":"crossref","unstructured":"Singh, B., Han, X., Wu, Z., Morariu, V.I., Davis, L.S.: Selecting relevant web trained concepts for automated event retrieval. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.518"},{"key":"52_CR32","unstructured":"Soomro, K., Zamir, A.R., Shah, M.: UCF101: a dataset of 101 human actions classes from videos in the wild. arXiv preprint arXiv:1212.0402 (2012)"},{"key":"52_CR33","first-page":"1517","volume":"11","author":"BK Sriperumbudur","year":"2010","unstructured":"Sriperumbudur, B.K., Gretton, A., Fukumizu, K., Sch\u00f6lkopf, B., Lanckriet, G.R.: Hilbert space embeddings and metrics on probability measures. J. Mach. Learn. Res. 11, 1517\u20131561 (2010)","journal-title":"J. Mach. Learn. Res."},{"key":"52_CR34","unstructured":"Srivastava, N., Mansimov, E., Salakhutdinov, R.: Unsupervised learning of video representations using lstms. In: ICML (2015)"},{"key":"52_CR35","unstructured":"Sukhbaatar, S., Fergus, R.: Learning from noisy labels with deep neural networks. 2(3), 4 (2014). arXiv preprint arXiv:1406.2080"},{"key":"52_CR36","doi-asserted-by":"crossref","unstructured":"Sun, C., Gan, C., Nevatia, R.: Automatic concept discovery from parallel text and visual corpora. In: ICCV, pp. 2596\u20132604 (2015)","DOI":"10.1109\/ICCV.2015.298"},{"key":"52_CR37","doi-asserted-by":"crossref","unstructured":"Sun, C., Nevatia, R.: Large-scale web video event classification by use of fisher vectors. In: WACV (2013)","DOI":"10.1109\/WACV.2013.6474994"},{"key":"52_CR38","doi-asserted-by":"crossref","unstructured":"Sun, C., Shetty, S., Sukthankar, R., Nevatia, R.: Temporal localization of fine-grained actions in videos by domain transfer from web images. In: ACM Multimedia, pp. 371\u2013380 (2015)","DOI":"10.1145\/2733373.2806226"},{"key":"52_CR39","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., Rabinovich, A.: Going deeper with convolutions. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"52_CR40","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: C3D: generic features for video analysis. In: ICCV (2015)"},{"key":"52_CR41","doi-asserted-by":"crossref","unstructured":"Wang, H., Schmid, C.: Action recognition with improved trajectories. In: ICCV (2013)","DOI":"10.1109\/ICCV.2013.441"},{"key":"52_CR42","doi-asserted-by":"crossref","unstructured":"Wang, L., Qiao, Y., Tang, X.: Action recognition with trajectory-pooled deep-convolutional descriptors. In: CVPR, pp. 4305\u20134314 (2015)","DOI":"10.1109\/CVPR.2015.7299059"},{"key":"52_CR43","doi-asserted-by":"crossref","unstructured":"Wang, L., Xiong, Y., Wang, Z., Qiao, Y., Lin, D., Tang, X., Gool, L.V.: Temporal segment networks: towards good practices for deep action recognition. In: ECCV (2016)","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"52_CR44","unstructured":"Xiao, T., Xia, T., Yang, Y., Huang, C., Wang, X.: Learning from massive noisy labeled data for image classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2691\u20132699 (2015)"},{"key":"52_CR45","doi-asserted-by":"crossref","unstructured":"Yan, Z., Zhang, H., Piramuthu, R., Jagadeesh, V., DeCoste, D., Di, W., Yu, Y.: HD-CNN: Hierarchical deep convolutional neural networks for large scale visual recognition. In: ICCV, pp. 2740\u20132748 (2015)","DOI":"10.1109\/ICCV.2015.314"},{"key":"52_CR46","doi-asserted-by":"crossref","unstructured":"Ye, G., Li, Y., Xu, H., Liu, D., Chang, S.F.: Eventnet: a large scale structured concept library for complex event detection in video. In: ACM Multimedia, pp. 471\u2013480 (2015)","DOI":"10.1145\/2733373.2806221"},{"key":"52_CR47","doi-asserted-by":"crossref","unstructured":"Zha, S., Luisier, F., Andrews, W., Srivastava, N., Salakhutdinov, R.: Exploiting image-trained CNN architectures for unconstrained video classification. In: BMVC (2015)","DOI":"10.5244\/C.29.60"},{"key":"52_CR48","doi-asserted-by":"crossref","unstructured":"Zhang, H., Hu, Z., Deng, Y., Sachan, M., Yan, Z., Xing, E.P.: Learning concept taxonomies from multi-modal data. In: ACL (2016)","DOI":"10.18653\/v1\/P16-1169"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2016"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-46487-9_52","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,20]],"date-time":"2023-08-20T04:37:07Z","timestamp":1692506227000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-46487-9_52"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319464862","9783319464879"],"references-count":48,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-46487-9_52","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016]]},"assertion":[{"value":"17 September 2016","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Amsterdam","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"The Netherlands","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2016","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 October 2016","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 October 2016","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2016","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.eccv2016.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}