{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T16:13:50Z","timestamp":1775578430988,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":34,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T00:00:00Z","timestamp":1698278400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Natural Science Foundation of China","award":["61972027"],"award-info":[{"award-number":["61972027"]}]},{"name":"Fundamental Research Funds for the Central Universities of China","award":["2022JBMC009"],"award-info":[{"award-number":["2022JBMC009"]}]},{"DOI":"10.13039\/501100005089","name":"Beijing Municipal Natural Science Foundation","doi-asserted-by":"publisher","award":["4212041"],"award-info":[{"award-number":["4212041"]}],"id":[{"id":"10.13039\/501100005089","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3612311","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:26:54Z","timestamp":1698391614000},"page":"4260-4268","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Hierarchical Reasoning Network with Contrastive Learning for Few-Shot Human-Object Interaction Recognition"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9335-0151","authenticated-orcid":false,"given":"Jiale","family":"Yu","sequence":"first","affiliation":[{"name":"Beijing Jiaotong University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2592-2354","authenticated-orcid":false,"given":"Baopeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Beijing Jiaotong University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6124-6197","authenticated-orcid":false,"given":"Qirui","family":"Li","sequence":"additional","affiliation":[{"name":"AFC Technology Co., LTD, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4796-4218","authenticated-orcid":false,"given":"Haoyang","family":"Chen","sequence":"additional","affiliation":[{"name":"AFC Technology Co., LTD, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1754-4878","authenticated-orcid":false,"given":"Zhu","family":"Teng","sequence":"additional","affiliation":[{"name":"Beijing Jiaotong University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.122"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00756"},{"key":"e_1_3_2_1_3_1","unstructured":"Chelsea Finn Pieter Abbeel and Sergey Levine. 2017. Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks. JMLR.org."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3093784"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00815"},{"key":"e_1_3_2_1_6_1","unstructured":"Saurabh Gupta and Jitendra Malik. 2015. Visual Semantic Role Labeling. arXiv:1505.04474 [cs.CV]"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3263660"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2021.3125343"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6764"},{"key":"e_1_3_2_1_14_1","volume-title":"Lin (Eds.)","volume":"33","author":"Khosla Prannay","year":"2020","unstructured":"Prannay Khosla, Piotr Teterwak, ChenWang, Aaron Sarna, Yonglong Tian, Phillip Isola, Aaron Maschinot, Ce Liu, and Dilip Krishnan. 2020. Supervised Contrastive Learning. In Advances in Neural Information Processing Systems, H. Larochelle, M. Ranzato, R. Hadsell, M.F. Balcan, and H. Lin (Eds.), Vol. 33. Curran Associates, Inc., 18661--18673. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2020\/file\/ d89a66c7c80a29b1bdbab0f2a1a94af8-Paper.pdf"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-5403"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2023"},{"key":"e_1_3_2_1_17_1","volume-title":"Proceedings of the 36th International Conference on Machine Learning (Proceedings of Machine Learning Research","volume":"3834","author":"Li Huaiyu","year":"2019","unstructured":"Huaiyu Li, Weiming Dong, Xing Mei, Chongyang Ma, Feiyue Huang, and Bao-Gang Hu. 2019. LGM-Net: Learning to Generate Matching Networks for Few-Shot Learning. In Proceedings of the 36th International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 97), Kamalika Chaudhuri and Ruslan Salakhutdinov (Eds.). PMLR, 3825--3834. https:\/\/proceedings.mlr.press\/ v97\/li19c.html"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00743"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00056"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3043268"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3049537"},{"key":"e_1_3_2_1_23_1","volume-title":"International Conference on Learning Representations.","author":"Liu Yanbin","year":"2018","unstructured":"Yanbin Liu, Juho Lee, Minseop Park, Saehoon Kim, Eunho Yang, Sung Ju Hwang, and Yi Yang. 2018. Learning to Propagate Labels: Transductive Propagation Network for Few-Shot Learning. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI"},{"key":"e_1_3_2_1_25_1","volume-title":"On First-Order Meta-Learning Algorithms. ArXiv abs\/1803.02999","author":"Nichol Alex","year":"2018","unstructured":"Alex Nichol, Joshua Achiam, and John Schulman. 2018. On First-Order Meta-Learning Algorithms. ArXiv abs\/1803.02999 (2018)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_25"},{"key":"e_1_3_2_1_28_1","unstructured":"Jake Snell Kevin Swersky and Richard Zemel. 2017. Prototypical Networks for Few-Shot Learning. (2017)."},{"key":"e_1_3_2_1_29_1","volume-title":"Computer Vision - ECCV","author":"Su Jong-Chyi","year":"2020","unstructured":"Jong-Chyi Su, Subhransu Maji, and Bharath Hariharan. 2020. When Does Selfsupervision Improve Few-Shot Learning?. In Computer Vision - ECCV 2020, Andrea Vedaldi, Horst Bischof, Thomas Brox, and Jan-Michael Frahm (Eds.). Springer International Publishing, Cham, 645--666."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00131"},{"key":"e_1_3_2_1_31_1","unstructured":"Oriol Vinyals Charles Blundell Timothy Lillicrap Koray Kavukcuoglu and Daan Wierstra. 2016. Matching Networks for One Shot Learning. (2016)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_15"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01307"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00093"}],"event":{"name":"MM '23: The 31st ACM International Conference on Multimedia","location":"Ottawa ON Canada","acronym":"MM '23","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 31st ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612311","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3612311","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T23:56:37Z","timestamp":1755820597000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612311"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":34,"alternative-id":["10.1145\/3581783.3612311","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3612311","relation":{},"subject":[],"published":{"date-parts":[[2023,10,26]]},"assertion":[{"value":"2023-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}