{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T14:21:19Z","timestamp":1770819679500,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":52,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,10,10]],"date-time":"2022-10-10T00:00:00Z","timestamp":1665360000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2018AAA0102000"],"award-info":[{"award-number":["2018AAA0102000"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62022083, U21B2038, 61931008"],"award-info":[{"award-number":["62022083, U21B2038, 61931008"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,10,10]]},"DOI":"10.1145\/3503161.3548008","type":"proceedings-article","created":{"date-parts":[[2022,10,10]],"date-time":"2022-10-10T15:42:35Z","timestamp":1665416555000},"page":"5761-5772","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["Zero-shot Video Classification with Appropriate Web and Task Knowledge Transfer"],"prefix":"10.1145","author":[{"given":"Junbao","family":"Zhuo","sequence":"first","affiliation":[{"name":"Insititute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yan","family":"Zhu","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuhao","family":"Cui","sequence":"additional","affiliation":[{"name":"Meituan Inc., Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuhui","family":"Wang","sequence":"additional","affiliation":[{"name":"Insititute of Computing Technology, Chinese Academy of Sciences & Peng Cheng Laboratory, Beijing&Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bin","family":"M A","sequence":"additional","affiliation":[{"name":"Meituan Inc., Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qingming","family":"Huang","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences & Insititute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoming","family":"Wei","sequence":"additional","affiliation":[{"name":"Meituan Inc., Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaolin","family":"Wei","sequence":"additional","affiliation":[{"name":"Meituan Inc., Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2022,10,10]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298911"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00467"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475534"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00400"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01181"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10466"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v29i1.9800"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.17"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2969787"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240566"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00478"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018303"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2985708"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2985708"},{"key":"e_1_3_2_2_15_1","volume-title":"Action2vec: A crossmodal embedding approach to action learning. arXiv preprint arXiv:1901.00484","author":"Hahn Meera","year":"2019","unstructured":"Meera Hahn , Andrew Silva , and James M Rehg . 2019. Action2vec: A crossmodal embedding approach to action learning. arXiv preprint arXiv:1901.00484 ( 2019 ). Meera Hahn, Andrew Silva, and James M Rehg. 2019. Action2vec: A crossmodal embedding approach to action learning. arXiv preprint arXiv:1901.00484 (2019)."},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.521"},{"key":"e_1_3_2_2_18_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba . 2014 . Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014). Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_2_19_1","volume-title":"Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907","author":"Kipf Thomas N","year":"2016","unstructured":"Thomas N Kipf and Max Welling . 2016. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 ( 2016 ). Thomas N Kipf and Max Welling. 2016. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016)."},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.282"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206594"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995353"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01022"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.313"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/2911996.2912036"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00047"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15552-9_29"},{"key":"e_1_3_2_2_29_1","volume-title":"Proceedings of the International Conference on Learning Representations.","author":"Norouzi Mohammad","year":"2014","unstructured":"Mohammad Norouzi , Tomas Mikolov , Samy Bengio , Yoram Singer , Jonathon Shlens , Andrea Frome , Greg S Corrado , and Jeffrey Dean . 2014 . Zero-shot learning by convex combination of semantic embeddings . In Proceedings of the International Conference on Learning Representations. Mohammad Norouzi, Tomas Mikolov, Samy Bengio, Yoram Singer, Jonathon Shlens, Andrea Frome, Greg S Corrado, and Jeffrey Dean. 2014. Zero-shot learning by convex combination of semantic embeddings. In Proceedings of the International Conference on Learning Representations."},{"key":"e_1_3_2_2_30_1","unstructured":"Adam Paszke Sam Gross Soumith Chintala Gregory Chanan Edward Yang Zachary DeVito Zeming Lin Alban Desmaison Luca Antiga and Adam Lerer. 2017. Automatic differentiation in pytorch. (2017).  Adam Paszke Sam Gross Soumith Chintala Gregory Chanan Edward Yang Zachary DeVito Zeming Lin Alban Desmaison Luca Antiga and Adam Lerer. 2017. Automatic differentiation in pytorch. (2017)."},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.117"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0851-8"},{"key":"e_1_3_2_2_34_1","volume-title":"Proceedings of the International Conference on Machine Learning. 2152--2161","author":"Romera-Paredes Bernardino","year":"2015","unstructured":"Bernardino Romera-Paredes and Philip Torr . 2015 . An embarrassingly simple approach to zero-shot learning . In Proceedings of the International Conference on Machine Learning. 2152--2161 . Bernardino Romera-Paredes and Philip Torr. 2015. An embarrassingly simple approach to zero-shot learning. In Proceedings of the International Conference on Machine Learning. 2152--2161."},{"key":"e_1_3_2_2_35_1","volume-title":"Proceedings of the IEEE International Conference on Computer Vision","author":"Shizhe Chen Dong Huang","year":"2021","unstructured":"Dong Huang Shizhe Chen . 2021 . Elaborative Rehearsal for Zero-shot Action Recognition . Proceedings of the IEEE International Conference on Computer Vision (2021), 13638--13647. Dong Huang Shizhe Chen. 2021. Elaborative Rehearsal for Zero-shot Action Recognition. Proceedings of the IEEE International Conference on Computer Vision (2021), 13638--13647."},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00113"},{"key":"e_1_3_2_2_37_1","volume-title":"Amir Roshan Zamir, and Mubarak Shah","author":"Soomro Khurram","year":"2012","unstructured":"Khurram Soomro , Amir Roshan Zamir, and Mubarak Shah . 2012 . UCF101: A dataset of 101 human actions classes from videos in the wild. arXiv preprint arXiv:1212.0402 (2012). Khurram Soomro, Amir Roshan Zamir, and Mubarak Shah. 2012. UCF101: A dataset of 101 human actions classes from videos in the wild. arXiv preprint arXiv:1212.0402 (2012)."},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11164"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108563"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"e_1_3_2_2_41_1","volume-title":"Proceedings of Advances in Neural Information Processing Systems. 9972--9982","author":"Wan Ziyu","year":"2019","unstructured":"Ziyu Wan , Dongdong Chen , Yan Li , Xingguang Yan , Junge Zhang , Yizhou Yu , and Jing Liao . 2019 . Transductive zero-shot learning with visual structure constraint . In Proceedings of Advances in Neural Information Processing Systems. 9972--9982 . Ziyu Wan, Dongdong Chen, Yan Li, Xingguang Yan, Junge Zhang, Yizhou Yu, and Jing Liao. 2019. Transductive zero-shot learning with visual structure constraint. In Proceedings of Advances in Neural Information Processing Systems. 9972--9982."},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00717"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.339"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2015.7350760"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0983-5"},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_22"},{"key":"e_1_3_2_2_47_1","volume-title":"-F","author":"Jiang Y.-G.","year":"2018","unstructured":"Jiang Y.-G. , Wu Z., Wang J., Xue X., and Chang S . -F . 2018 . Exploiting feature and class relationships in video categorization with regu- larized deep neural networks. IEEE Transactions on Pattern Analysis and Machine Intelligence (2018), 352--364. Jiang Y.-G., Wu Z., Wang J., Xue X., and Chang S.-F. 2018. Exploiting feature and class relationships in video categorization with regu- larized deep neural networks. IEEE Transactions on Pattern Analysis and Machine Intelligence (2018), 352--364."},{"key":"e_1_3_2_2_48_1","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Fu Wu Z., Y.","year":"2016","unstructured":"Wu Z., Y. Fu , Jiang Y.-G., and Sigal L . 2016. Harnessing object and scene semantics for large-scale video understanding . Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition ( 2016 ), 3112--3121. Wu Z., Y. Fu, Jiang Y.-G., and Sigal L. 2016. Harnessing object and scene semantics for large-scale video understanding. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2016), 3112--3121."},{"key":"e_1_3_2_2_49_1","volume-title":"Proceedings of the International Conference on Learning Representations.","author":"Zhang Chiyuan","year":"2017","unstructured":"Chiyuan Zhang , Samy Bengio , Moritz Hardt , Benjamin Recht , and Oriol Vinyals . 2017 . Understanding deep learning requires rethinking generalization . In Proceedings of the International Conference on Learning Representations. Chiyuan Zhang, Samy Bengio, Moritz Hardt, Benjamin Recht, and Oriol Vinyals. 2017. Understanding deep learning requires rethinking generalization. In Proceedings of the International Conference on Learning Representations."},{"key":"e_1_3_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/157"},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00983"},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00084"}],"event":{"name":"MM '22: The 30th ACM International Conference on Multimedia","location":"Lisboa Portugal","acronym":"MM '22","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 30th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3503161.3548008","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3503161.3548008","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:02:29Z","timestamp":1750186949000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3503161.3548008"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,10]]},"references-count":52,"alternative-id":["10.1145\/3503161.3548008","10.1145\/3503161"],"URL":"https:\/\/doi.org\/10.1145\/3503161.3548008","relation":{},"subject":[],"published":{"date-parts":[[2022,10,10]]},"assertion":[{"value":"2022-10-10","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}