{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T20:42:17Z","timestamp":1769632937229,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":35,"publisher":"ACM","license":[{"start":{"date-parts":[[2015,6,22]],"date-time":"2015-06-22T00:00:00Z","timestamp":1434931200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National 863 Program","award":["2014AA015101"],"award-info":[{"award-number":["2014AA015101"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61201387"],"award-info":[{"award-number":["61201387"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003399","name":"Science and Technology Commission of Shanghai Municipality","doi-asserted-by":"publisher","award":["13PJ1400400, 13511504503"],"award-info":[{"award-number":["13PJ1400400, 13511504503"]}],"id":[{"id":"10.13039\/501100003399","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2015,6,22]]},"DOI":"10.1145\/2671188.2749406","type":"proceedings-article","created":{"date-parts":[[2015,6,22]],"date-time":"2015-06-22T15:37:08Z","timestamp":1434987428000},"page":"435-442","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":86,"title":["Evaluating Two-Stream CNN for Video Classification"],"prefix":"10.1145","author":[{"given":"Hao","family":"Ye","sequence":"first","affiliation":[{"name":"Fudan University, Shanghai, China"}]},{"given":"Zuxuan","family":"Wu","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}]},{"given":"Rui-Wei","family":"Zhao","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}]},{"given":"Xi","family":"Wang","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}]},{"given":"Yu-Gang","family":"Jiang","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}]},{"given":"Xiangyang","family":"Xue","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}]}],"member":"320","published-online":{"date-parts":[[2015,6,22]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.50"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2134090"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.21236\/ADA623249"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"e_1_3_2_1_5_1","volume-title":"Separate Visual Pathways for Perception and Action. Trends in neurosciences","author":"Goodale M. A.","year":"1992","unstructured":"M. A. Goodale and A. D. Milner . Separate Visual Pathways for Perception and Action. Trends in neurosciences , 1992 . M. A. Goodale and A. D. Milner. Separate Visual Pathways for Perception and Action. Trends in neurosciences, 1992."},{"key":"e_1_3_2_1_6_1","volume-title":"University of amsterdam at thumos challenge","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 2014, 2014. M. Jain, J. van Gemert, and C. G. M. Snoek. University of amsterdam at thumos challenge 2014. In ECCV THUMOS Challenge 2014, 2014."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00138-013-0567-0"},{"key":"e_1_3_2_1_8_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_9_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_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/1991996.1992025"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P14-1062"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"e_1_3_2_1_13_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_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.272"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587756"},{"key":"e_1_3_2_1_16_1","volume-title":"Intelligent Signal Processing","author":"LeCun Y.","year":"2001","unstructured":"Y. LeCun , L. Bottou , Y. Bengio , and P. Haffner . Gradient-based learning applied to document recognition . In Intelligent Signal Processing , 2001 . Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner. Gradient-based learning applied to document recognition. In Intelligent Signal Processing, 2001."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.109"},{"key":"e_1_3_2_1_18_1","volume-title":"NIPS","author":"Mikolov T.","year":"2013","unstructured":"T. Mikolov , I. Sutskever , K. Chen , G. S. Corrado , and J. Dean . Distributed Representations of Words and Phrases and Their Compositionality . In NIPS , 2013 . T. Mikolov, I. Sutskever, K. Chen, G. S. Corrado, and J. Dean. Distributed Representations of Words and Phrases and Their Compositionality. In NIPS, 2013."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.228"},{"key":"e_1_3_2_1_20_1","volume-title":"CoRR","author":"Peng X.","year":"2014","unstructured":"X. Peng , L. Wang , X. Wang , and Y. Qiao . Bag of visual words and fusion methods for action recognition: Comprehensive study and good practice . CoRR , 2014 . X. Peng, L. Wang, X. Wang, and Y. Qiao. Bag of visual words and fusion methods for action recognition: Comprehensive study and good practice. CoRR, 2014."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2014.131"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587730"},{"key":"e_1_3_2_1_23_1","volume-title":"CoRR","author":"Schmidhuber J.","year":"2014","unstructured":"J. Schmidhuber . Deep learning in neural networks: An overview . CoRR , 2014 . J. Schmidhuber. Deep learning in neural networks: An overview. CoRR, 2014."},{"key":"e_1_3_2_1_24_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_25_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_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/1101149.1101236"},{"key":"e_1_3_2_1_27_1","volume-title":"ICML","author":"Socher R.","year":"2011","unstructured":"R. Socher , C. C.-Y. Lin , A. Y. Ng , and C. D. Manning . Parsing Natural Scenes and Natural Language with Recursive Neural Networks . In ICML , 2011 . R. Socher, C. C.-Y. Lin, A. Y. Ng, and C. D. Manning. Parsing Natural Scenes and Natural Language with Recursive Neural Networks. In ICML, 2011."},{"key":"e_1_3_2_1_28_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_29_1","volume-title":"NIPS","author":"Sutskever I.","year":"2014","unstructured":"I. Sutskever , O. Vinyals , and Q. V. Le . Sequence to Sequence Learning with Neural Networks . In NIPS , 2014 . I. Sutskever, O. Vinyals, and Q. V. Le. Sequence to Sequence Learning with Neural Networks. In NIPS, 2014."},{"key":"e_1_3_2_1_30_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_31_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_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.441"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654931"},{"key":"e_1_3_2_1_34_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_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126474"}],"event":{"name":"ICMR '15: International Conference on Multimedia Retrieval","location":"Shanghai China","acronym":"ICMR '15","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 5th ACM on International Conference on Multimedia Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2671188.2749406","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2671188.2749406","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T06:17:03Z","timestamp":1750227423000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2671188.2749406"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,6,22]]},"references-count":35,"alternative-id":["10.1145\/2671188.2749406","10.1145\/2671188"],"URL":"https:\/\/doi.org\/10.1145\/2671188.2749406","relation":{},"subject":[],"published":{"date-parts":[[2015,6,22]]},"assertion":[{"value":"2015-06-22","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}