{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T09:04:15Z","timestamp":1783587855449,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":54,"publisher":"ACM","license":[{"start":{"date-parts":[[2015,10,13]],"date-time":"2015-10-13T00:00:00Z","timestamp":1444694400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National 863 Program of China","award":["2014AA015101"],"award-info":[{"award-number":["2014AA015101"]}]},{"name":"NSFC","award":["61201387"],"award-info":[{"award-number":["61201387"]}]},{"name":"STCSM","award":["13PJ1400400"],"award-info":[{"award-number":["13PJ1400400"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2015,10,13]]},"DOI":"10.1145\/2733373.2806222","type":"proceedings-article","created":{"date-parts":[[2016,2,26]],"date-time":"2016-02-26T19:09:21Z","timestamp":1456513761000},"page":"461-470","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":360,"title":["Modeling Spatial-Temporal Clues in a Hybrid Deep Learning Framework for Video Classification"],"prefix":"10.1145","author":[{"given":"Zuxuan","family":"Wu","sequence":"first","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xi","family":"Wang","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu-Gang","family":"Jiang","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Ye","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiangyang","family":"Xue","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2015,10,13]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.5555\/2354409.2355123"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015424"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-35289-8_26"},{"key":"e_1_3_2_1_4_1","volume-title":"CoRR","author":"Chung J.","year":"2015","unstructured":"J. Chung , \u00c7. G\u00fcl\u00e7ehre, K. Cho , and Y. Bengio . Gated feedback recurrent neural networks . CoRR , 2015 . J. Chung, \u00c7. G\u00fcl\u00e7ehre, K. Cho, and Y. Bengio. Gated feedback recurrent neural networks. CoRR, 2015."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2134090"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.21236\/ADA623249"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2005.06.042"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.5244\/C.2.23"},{"key":"e_1_3_2_1_11_1","volume-title":"ECCV THUMOS Challenge Workshop","author":"Jain M.","year":"2014","unstructured":"M. Jain , J. van Gemert , and C. G. M. Snoek . University of amsterdam at thumos challenge 2014 . In ECCV THUMOS Challenge Workshop , 2014 . M. Jain, J. van Gemert, and C. G. M. Snoek. University of amsterdam at thumos challenge 2014. In ECCV THUMOS Challenge Workshop, 2014."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00138-013-0567-0"},{"key":"e_1_3_2_1_13_1","volume-title":"ICML","author":"Ji S.","year":"2010","unstructured":"S. Ji , W. Xu , M. Yang , and K. Yu . 3d convolutional neural networks for human action recognition . In ICML , 2010 . S. Ji, W. Xu, M. Yang, and K. Yu. 3d convolutional neural networks for human action recognition. In ICML, 2010."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654889"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/1631272.1631277"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/s13735-012-0024-2"},{"key":"e_1_3_2_1_17_1","unstructured":"Y.-G. Jiang J. Liu A. Roshan Zamir G. Toderici I. Laptev M. Shah and R. Sukthankar. THUMOS challenge: Action recognition with a large number of classes. http:\/\/crcv.ucf.edu\/THUMOS14\/ 2014.  Y.-G. Jiang J. Liu A. Roshan Zamir G. Toderici I. Laptev M. Shah and R. Sukthankar. THUMOS challenge: Action recognition with a large number of classes. http:\/\/crcv.ucf.edu\/THUMOS14\/ 2014."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/1991996.1992025"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.5244\/C.22.99"},{"key":"e_1_3_2_1_21_1","author":"Kloft M.","year":"2011","unstructured":"M. Kloft , U. Brefeld , S. Sonnenburg , and A. Zien . Lp-norm multiple kernel learning. The Journal of Machine Learning Research , 2011 . M. Kloft, U. Brefeld, S. Sonnenburg, and A. Zien. Lp-norm multiple kernel learning. The Journal of Machine Learning Research, 2011.","journal-title":"Lp-norm multiple kernel learning. The Journal of Machine Learning Research"},{"key":"e_1_3_2_1_22_1","volume-title":"NIPS","author":"Krizhevsky A.","year":"2012","unstructured":"A. Krizhevsky , I. Sutskever , and G. E. Hinton . Imagenet classification with deep convolutional neural networks . In NIPS , 2012 . A. Krizhevsky, I. Sutskever, and G. E. Hinton. Imagenet classification with deep convolutional neural networks. In NIPS, 2012."},{"key":"e_1_3_2_1_23_1","volume-title":"CoRR","author":"Lan Z.","year":"2014","unstructured":"Z. Lan , M. Lin , X. Li , A. G. Hauptmann , and B. Raj . Beyond gaussian pyramid: Multi-skip feature stacking for action recognition . CoRR , 2014 . Z. Lan, M. Lin, X. Li, A. G. Hauptmann, and B. Raj. Beyond gaussian pyramid: Multi-skip feature stacking for action recognition. CoRR, 2014."},{"key":"e_1_3_2_1_24_1","volume-title":"IJCV","author":"Laptev I.","year":"2007","unstructured":"I. Laptev . On space-time interest points . IJCV , 2007 . I. Laptev. On space-time interest points. IJCV, 2007."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2008.2005597"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.109"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000029664.99615.94"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0723-7"},{"key":"e_1_3_2_1_29_1","volume-title":"ICML","author":"Ngiam J.","year":"2011","unstructured":"J. Ngiam , A. Khosla , M. Kim , J. Nam , H. Lee , and A. Ng . Multimodal deep learning . In ICML , 2011 . J. Ngiam, A. Khosla, M. Kim, J. Nam, H. Lee, and A. Ng. Multimodal deep learning. In ICML, 2011."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.228"},{"key":"e_1_3_2_1_31_1","volume-title":"CoRR","author":"Ranzato M.","year":"2014","unstructured":"M. Ranzato , A. Szlam , J. Bruna , M. Mathieu , R. Collobert , and S. Chopra . Video (language) modeling: a baseline for generative models of natural videos . CoRR , 2014 . M. Ranzato, A. Szlam, J. Bruna, M. Mathieu, R. Collobert, and S. Chopra. Video (language) modeling: a baseline for generative models of natural videos. CoRR, 2014."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2014.131"},{"key":"e_1_3_2_1_33_1","volume-title":"NIPS","author":"Simonyan K.","year":"2014","unstructured":"K. Simonyan and A. Zisserman . Two-stream convolutional networks for action recognition in videos . In NIPS , 2014 . K. Simonyan and A. Zisserman. Two-stream convolutional networks for action recognition in videos. In NIPS, 2014."},{"key":"e_1_3_2_1_34_1","volume-title":"CoRR","author":"Simonyan K.","year":"2014","unstructured":"K. Simonyan and A. Zisserman . Very deep convolutional networks for large-scale image recognition . CoRR , 2014 . K. Simonyan and A. Zisserman. Very deep convolutional networks for large-scale image recognition. CoRR, 2014."},{"key":"e_1_3_2_1_35_1","volume-title":"CoRR","author":"Soomro K.","year":"2012","unstructured":"K. Soomro , A. R. Zamir , and M. Shah . UCF101: A dataset of 101 human actions classes from videos in the wild . CoRR , 2012 . K. Soomro, A. R. Zamir, and M. Shah. UCF101: A dataset of 101 human actions classes from videos in the wild. CoRR, 2012."},{"key":"e_1_3_2_1_36_1","volume-title":"CoRR","author":"Srivastava N.","year":"2015","unstructured":"N. Srivastava , E. Mansimov , and R. Salakhutdinov . Unsupervised learning of video representations using LSTMs . CoRR , 2015 . N. Srivastava, E. Mansimov, and R. Salakhutdinov. Unsupervised learning of video representations using LSTMs. CoRR, 2015."},{"key":"e_1_3_2_1_37_1","volume-title":"NIPS","author":"Srivastava N.","year":"2012","unstructured":"N. Srivastava and R. Salakhutdinov . Multimodal learning with deep boltzmann machines . In NIPS , 2012 . N. Srivastava and R. Salakhutdinov. Multimodal learning with deep boltzmann machines. In NIPS, 2012."},{"key":"e_1_3_2_1_38_1","volume-title":"CoRR","author":"Szegedy C.","year":"2014","unstructured":"C. Szegedy , W. Liu , Y. Jia , P. Sermanet , S. Reed , D. Anguelov , D. Erhan , V. Vanhoucke , and A. Rabinovich . Going Deeper with Convolutions . CoRR , 2014 . C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, and A. Rabinovich. Going Deeper with Convolutions. CoRR, 2014."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.5555\/2354409.2354961"},{"key":"e_1_3_2_1_40_1","volume-title":"CoRR","author":"Tran D.","year":"2014","unstructured":"D. Tran , L. Bourdev , R. Fergus , L. Torresani , and M. Paluri . C3d: Generic features for video analysis . CoRR , 2014 . D. Tran, L. Bourdev, R. Fergus, L. Torresani, and M. Paluri. C3d: Generic features for video analysis. CoRR, 2014."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/1329125.1329409"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459183"},{"key":"e_1_3_2_1_43_1","volume-title":"CoRR","author":"Venugopalan S.","year":"2014","unstructured":"S. Venugopalan , H. Xu , J. Donahue , M. Rohrbach , R. J. Mooney , and K. Saenko . Translating videos to natural language using deep recurrent neural networks . CoRR , 2014 . S. Venugopalan, H. Xu, J. Donahue, M. Rohrbach, R. J. Mooney, and K. Saenko. Translating videos to natural language using deep recurrent neural networks. CoRR, 2014."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.441"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.5244\/C.23.124"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206709"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654931"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.427"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/2499907.2499909"},{"key":"e_1_3_2_1_50_1","volume-title":"CVPR","author":"Ye G.","year":"2012","unstructured":"G. Ye , D. Liu , I.-H. Jhuo , and S.-F. Chang . Robust late fusion with rank minimization . In CVPR , 2012 . G. Ye, D. Liu, I.-H. Jhuo, and S.-F. Chang. Robust late fusion with rank minimization. In CVPR, 2012."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/2671188.2749406"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.5555\/1888212.1888253"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.5244\/C.29.60"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-006-9794-4"}],"event":{"name":"MM '15: ACM Multimedia Conference","location":"Brisbane Australia","acronym":"MM '15","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 23rd ACM international conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2733373.2806222","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2733373.2806222","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T06:16:47Z","timestamp":1750227407000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2733373.2806222"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,10,13]]},"references-count":54,"alternative-id":["10.1145\/2733373.2806222","10.1145\/2733373"],"URL":"https:\/\/doi.org\/10.1145\/2733373.2806222","relation":{},"subject":[],"published":{"date-parts":[[2015,10,13]]},"assertion":[{"value":"2015-10-13","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}