{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T18:33:45Z","timestamp":1772908425482,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":58,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,10,17]],"date-time":"2021-10-17T00:00:00Z","timestamp":1634428800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61872307"],"award-info":[{"award-number":["61872307"]}],"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":[[2021,10,17]]},"DOI":"10.1145\/3474085.3475253","type":"proceedings-article","created":{"date-parts":[[2021,10,18]],"date-time":"2021-10-18T22:11:38Z","timestamp":1634595098000},"page":"816-825","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":34,"title":["Semantic-Guided Relation Propagation Network for Few-shot Action Recognition"],"prefix":"10.1145","author":[{"given":"Xiao","family":"Wang","sequence":"first","affiliation":[{"name":"Xiamen University, Xiamen, China"}]},{"given":"Weirong","family":"Ye","sequence":"additional","affiliation":[{"name":"Xiamen University, Xiamen, China"}]},{"given":"Zhongang","family":"Qi","sequence":"additional","affiliation":[{"name":"Tencent PCG, Shenzhen, China"}]},{"given":"Xun","family":"Zhao","sequence":"additional","affiliation":[{"name":"Tencent PCG, Shenzhen, China"}]},{"given":"Guangge","family":"Wang","sequence":"additional","affiliation":[{"name":"Xiamen University, Xiamen, China"}]},{"given":"Ying","family":"Shan","sequence":"additional","affiliation":[{"name":"Tencent PCG, Shenzhen, China"}]},{"given":"Hanzi","family":"Wang","sequence":"additional","affiliation":[{"name":"Xiamen University, Xiamen, China"}]}],"member":"320","published-online":{"date-parts":[[2021,10,17]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.117"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00300"},{"key":"e_1_3_2_2_3_1","volume-title":"TARN: Temporal attentive relation network for few-shot and zero-shot action recognition. arXiv preprint arXiv:1907.09021","author":"Bishay Mina","year":"2019","unstructured":"Mina Bishay , Georgios Zoumpourlis , and Ioannis Patras . 2019 . TARN: Temporal attentive relation network for few-shot and zero-shot action recognition. arXiv preprint arXiv:1907.09021 (2019). Mina Bishay, Georgios Zoumpourlis, and Ioannis Patras. 2019. TARN: Temporal attentive relation network for few-shot and zero-shot action recognition. arXiv preprint arXiv:1907.09021 (2019)."},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00467"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413840"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01063"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240527"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00382"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58529-7_30"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2006.79"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.213"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.5555\/3305381.3305498"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351015"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413502"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240566"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00622"},{"key":"e_1_3_2_2_19_1","volume-title":"Weakly-supervised compositional feature aggregation for few-shot recognition. arXiv preprint arXiv:1906.04833","author":"Hu Ping","year":"2019","unstructured":"Ping Hu , Ximeng Sun , Kate Saenko , and Stan Sclaroff . 2019. Weakly-supervised compositional feature aggregation for few-shot recognition. arXiv preprint arXiv:1906.04833 ( 2019 ). Ping Hu, Ximeng Sun, Kate Saenko, and Stan Sclaroff. 2019. Weakly-supervised compositional feature aggregation for few-shot recognition. arXiv preprint arXiv:1906.04833 (2019)."},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"e_1_3_2_2_21_1","unstructured":"Will Kay Joao Carreira Karen Simonyan Brian Zhang Chloe Hillier Sudheendra Vijayanarasimhan Fabio Viola Tim Green Trevor Back Paul Natsev etal 2017. The kinetics human action video dataset. arXiv preprint arXiv:1705.06950 (2017).  Will Kay Joao Carreira Karen Simonyan Brian Zhang Chloe Hillier Sudheendra Vijayanarasimhan Fabio Viola Tim Green Trevor Back Paul Natsev et al. 2017. The kinetics human action video dataset. arXiv preprint arXiv:1705.06950 (2017)."},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00166"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413641"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00099"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240567"},{"key":"e_1_3_2_2_28_1","volume-title":"Temporal adaptive module for video recognition. arXiv preprint arXiv:2005.06803","author":"Liu Zhaoyang","year":"2020","unstructured":"Zhaoyang Liu , Limin Wang , Wayne Wu , Chen Qian , and Tong Lu Tam . 2020. Temporal adaptive module for video recognition. arXiv preprint arXiv:2005.06803 , Vol. 2 ( 2020 ). Zhaoyang Liu, Limin Wang, Wayne Wu, Chen Qian, and Tong Lu Tam. 2020. Temporal adaptive module for video recognition. arXiv preprint arXiv:2005.06803, Vol. 2 (2020)."},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/112"},{"key":"e_1_3_2_2_30_1","volume-title":"Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781","author":"Mikolov Tomas","year":"2013","unstructured":"Tomas Mikolov , Kai Chen , Greg Corrado , and Jeffrey Dean . 2013. Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781 ( 2013 ). Tomas Mikolov, Kai Chen, Greg Corrado, and Jeffrey Dean. 2013. Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781 (2013)."},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00020"},{"key":"e_1_3_2_2_32_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_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3416269"},{"key":"e_1_3_2_2_34_1","volume-title":"Baby steps towards few-shot learning with multiple semantics. arXiv preprint arXiv:1906.01905","author":"Schwartz Eli","year":"2019","unstructured":"Eli Schwartz , Leonid Karlinsky , Rogerio Feris , Raja Giryes , and Alex M Bronstein . 2019. Baby steps towards few-shot learning with multiple semantics. arXiv preprint arXiv:1906.01905 ( 2019 ). Eli Schwartz, Leonid Karlinsky, Rogerio Feris, Raja Giryes, and Alex M Bronstein. 2019. Baby steps towards few-shot learning with multiple semantics. arXiv preprint arXiv:1906.01905 (2019)."},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6872"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.5555\/2968826.2968890"},{"key":"e_1_3_2_2_37_1","volume-title":"Prototypical networks for few-shot learning. arXiv preprint arXiv:1703.05175","author":"Snell Jake","year":"2017","unstructured":"Jake Snell , Kevin Swersky , and Richard S Zemel . 2017. Prototypical networks for few-shot learning. arXiv preprint arXiv:1703.05175 ( 2017 ). Jake Snell, Kevin Swersky, and Richard S Zemel. 2017. Prototypical networks for few-shot learning. arXiv preprint arXiv:1703.05175 (2017)."},{"key":"e_1_3_2_2_38_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_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00151"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00131"},{"key":"e_1_3_2_2_41_1","volume-title":"Learning to learn: Meta-critic Networks for Sample Efficient Learning. arXiv preprint arXiv:1706.09529","author":"Sung Flood","year":"2017","unstructured":"Flood Sung , Li Zhang , Tao Xiang , Timothy Hospedales , and Yongxin Yang . 2017. Learning to learn: Meta-critic Networks for Sample Efficient Learning. arXiv preprint arXiv:1706.09529 ( 2017 ). Flood Sung, Li Zhang, Tao Xiang, Timothy Hospedales, and Yongxin Yang. 2017. Learning to learn: Meta-critic Networks for Sample Efficient Learning. arXiv preprint arXiv:1706.09529 (2017)."},{"key":"e_1_3_2_2_42_1","volume-title":"Rethinking few-shot image classification: a good embedding is all you need? arXiv preprint arXiv:2003.11539","author":"Tian Yonglong","year":"2020","unstructured":"Yonglong Tian , Yue Wang , Dilip Krishnan , Joshua B Tenenbaum , and Phillip Isola . 2020. Rethinking few-shot image classification: a good embedding is all you need? arXiv preprint arXiv:2003.11539 ( 2020 ). Yonglong Tian, Yue Wang, Dilip Krishnan, Joshua B Tenenbaum, and Phillip Isola. 2020. Rethinking few-shot image classification: a good embedding is all you need? arXiv preprint arXiv:2003.11539 (2020)."},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.5555\/3157382.3157504"},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295446"},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350891"},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"e_1_3_2_2_50_1","volume-title":"Adaptive cross-modal few-shot learning. arXiv preprint arXiv:1902.07104","author":"Xing Chen","year":"2019","unstructured":"Chen Xing , Negar Rostamzadeh , Boris N Oreshkin , and Pedro O Pinheiro . 2019. Adaptive cross-modal few-shot learning. arXiv preprint arXiv:1902.07104 ( 2019 ). Chen Xing, Negar Rostamzadeh, Boris N Oreshkin, and Pedro O Pinheiro. 2019. Adaptive cross-modal few-shot learning. arXiv preprint arXiv:1902.07104 (2019)."},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3206025.3206028"},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3416301"},{"key":"e_1_3_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01222"},{"key":"e_1_3_2_2_54_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_31"},{"key":"e_1_3_2_2_55_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_49"},{"key":"e_1_3_2_2_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2018.8545710"},{"key":"e_1_3_2_2_57_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_46"},{"key":"e_1_3_2_2_58_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_43"}],"event":{"name":"MM '21: ACM Multimedia Conference","location":"Virtual Event China","acronym":"MM '21","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 29th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3474085.3475253","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3474085.3475253","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:48:17Z","timestamp":1750193297000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3474085.3475253"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,17]]},"references-count":58,"alternative-id":["10.1145\/3474085.3475253","10.1145\/3474085"],"URL":"https:\/\/doi.org\/10.1145\/3474085.3475253","relation":{},"subject":[],"published":{"date-parts":[[2021,10,17]]},"assertion":[{"value":"2021-10-17","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}