{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T15:57:08Z","timestamp":1783439828690,"version":"3.54.6"},"publisher-location":"New York, NY, USA","reference-count":47,"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":"National Natural Science Foundation of China","award":["61832017"],"award-info":[{"award-number":["61832017"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61976206"],"award-info":[{"award-number":["61976206"]}],"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":[[2023,10,26]]},"DOI":"10.1145\/3581783.3611888","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:12Z","timestamp":1698391632000},"page":"5302-5310","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":26,"title":["Zero-shot Skeleton-based Action Recognition via Mutual Information Estimation and Maximization"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9161-8620","authenticated-orcid":false,"given":"Yujie","family":"Zhou","sequence":"first","affiliation":[{"name":"Renmin University of China, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7985-5743","authenticated-orcid":false,"given":"Wenwen","family":"Qiang","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences & Institute of Software, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1004-7753","authenticated-orcid":false,"given":"Anyi","family":"Rao","sequence":"additional","affiliation":[{"name":"Stanford University, Stanford, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8883-7005","authenticated-orcid":false,"given":"Ning","family":"Lin","sequence":"additional","affiliation":[{"name":"Renmin University of China, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8560-1910","authenticated-orcid":false,"given":"Bing","family":"Su","sequence":"additional","affiliation":[{"name":"Renmin University of China & Beijing Key Laboratory of Big Data Management and Analysis Methods, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6877-5353","authenticated-orcid":false,"given":"Jiaqi","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Rethinking Zero-Shot Video Classification: End-to-End Training for Realistic Applications. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR).","author":"Brattoli Biagio","year":"2020","unstructured":"Biagio Brattoli, Joseph Tighe, Fedor Zhdanov, Pietro Perona, and Krzysztof Chalupka. 2020. Rethinking Zero-Shot Video Classification: End-to-End Training for Realistic Applications. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.143"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"e_1_3_2_1_4_1","volume-title":"Skeleton-Based Action Recognition With Shift Graph Convolutional Network. CVPR","author":"Cheng Ke","year":"2020","unstructured":"Ke Cheng, Yifan Zhang, Xiangyu He, Weihan Chen, Jian Cheng, and Hanqing Lu. 2020. Skeleton-Based Action Recognition With Shift Graph Convolutional Network. CVPR (2020), 180--189."},{"key":"e_1_3_2_1_5_1","volume-title":"IEEE Conference on Computer Vision and Pattern Recognition","author":"Du Yong","year":"2015","unstructured":"Yong Du, Wei Wang, and Liang Wang. 2015. Hierarchical recurrent neural network for skeleton based action recognition. IEEE Conference on Computer Vision and Pattern Recognition (2015)."},{"key":"e_1_3_2_1_6_1","volume-title":"DeViSE: A Deep Visual-Semantic Embedding Model. NIPS","author":"Frome Andrea","year":"2013","unstructured":"Andrea Frome, S. Gregory Corrado, Jonathon Shlens, Samy Bengio, Jeffrey Dean, Marc'Aurelio Ranzato, and Tomas Mikolov. 2013. DeViSE: A Deep Visual-Semantic Embedding Model. NIPS (2013)."},{"key":"e_1_3_2_1_7_1","volume-title":"Exploring Semantic Inter-Class Relationships (SIR) for Zero-Shot Action Recognition. AAAI","author":"Gan Chuang","year":"2015","unstructured":"Chuang Gan, Ming Lin, Yi Yang, Yueting Zhuang, and G. Alexander Hauptmann. 2015. Exploring Semantic Inter-Class Relationships (SIR) for Zero-Shot Action Recognition. AAAI (2015), 3769--3775."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19957"},{"key":"e_1_3_2_1_9_1","volume-title":"Syntactically Guided Generative Embeddings for Zero-Shot Skeleton Action Recognition. 2021 IEEE International Conference on Image Processing (ICIP)","author":"Gupta Pranay","year":"2021","unstructured":"Pranay Gupta, Divyanshu Sharma, and Kiran Ravi Sarvadevabhatla. 2021. Syntactically Guided Generative Embeddings for Zero-Shot Skeleton Action Recognition. 2021 IEEE International Conference on Image Processing (ICIP) (2021), 439--443."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01288"},{"key":"e_1_3_2_1_11_1","unstructured":"Kaiming He Xiangyu Zhang Shaoqing Ren and Jian Sun. 2016. Deep residual learning for image recognition. In CVPR."},{"key":"e_1_3_2_1_12_1","volume-title":"Learning deep representations by mutual information estimation and maximization. arXiv preprint arXiv:1808.06670","author":"Hjelm R Devon","year":"2018","unstructured":"R Devon Hjelm, Alex Fedorov, Samuel Lavoie-Marchildon, Karan Grewal, Phil Bachman, Adam Trischler, and Yoshua Bengio. 2018. Learning deep representations by mutual information estimation and maximization. arXiv preprint arXiv:1808.06670 (2018)."},{"key":"e_1_3_2_1_13_1","volume-title":"Weakly-supervised 3D Human Pose Estimation with Cross-view U-shaped Graph Convolutional Network","author":"Hua Guoliang","year":"2022","unstructured":"Guoliang Hua, Hong Liu, Wenhao Li, Qian Zhang, Runwei Ding, and Xin Xu. 2022. Weakly-supervised 3D Human Pose Estimation with Cross-view U-shaped Graph Convolutional Network. IEEE Transactions on Multimedia (2022)."},{"key":"e_1_3_2_1_14_1","volume-title":"Skeleton based zero shot action recognition in joint pose-language semantic space. arXiv preprint arXiv:1911.11344","author":"Jasani Bhavan","year":"2019","unstructured":"Bhavan Jasani and Afshaan Mazagonwalla. 2019. Skeleton based zero shot action recognition in joint pose-language semantic space. arXiv preprint arXiv:1911.11344 (2019)."},{"key":"e_1_3_2_1_15_1","volume-title":"Ahmed Ferdous Sohel, and Farid Boussa\u00efd","author":"Ke Qiuhong","year":"2017","unstructured":"Qiuhong Ke, Mohammed Bennamoun, Senjian An, Ahmed Ferdous Sohel, and Farid Boussa\u00efd. 2017. A New Representation of Skeleton Sequences for 3D Action Recognition. CVPR (2017)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.207"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.282"},{"key":"e_1_3_2_1_18_1","volume-title":"Renqiang Martin Min, and Yun Fu","author":"Li Kai","year":"2019","unstructured":"Kai Li, Renqiang Martin Min, and Yun Fu. 2019. Rethinking Zero-Shot Learning - A Conditional Visual Classification Perspective. ICCV (2019)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00471"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413548"},{"key":"e_1_3_2_1_21_1","volume-title":"Gang Wang, Ling-Yu Duan, and Kot Alex Chichung.","author":"Liu Jun","year":"2019","unstructured":"Jun Liu, Amir Shahroudy, Lisboa Mauricio Perez, Gang Wang, Ling-Yu Duan, and Kot Alex Chichung. 2019. NTU RGBD 120: A Large-Scale Benchmark for 3D Human Activity Understanding. IEEE Transactions on Pattern Analysis and Machine Intelligence (2019)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3418212"},{"key":"e_1_3_2_1_23_1","volume-title":"Distributed Representations of Words and Phrases and their Compositionality. Neural Information Processing Systems","author":"Mikolov Tomas","year":"2013","unstructured":"Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg Corrado, and Jeffrey Dean. 2013. Distributed Representations of Words and Phrases and their Compositionality. Neural Information Processing Systems (2013)."},{"key":"e_1_3_2_1_24_1","volume-title":"f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization. NIPS","author":"Nowozin Sebastian","year":"2016","unstructured":"Sebastian Nowozin, Botond Cseke, and Ryota Tomioka. 2016. f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization. NIPS (2016)."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3112815"},{"key":"e_1_3_2_1_26_1","volume-title":"International Conference on Machine Learning. PMLR","author":"Qiang Wenwen","year":"2022","unstructured":"Wenwen Qiang, Jiangmeng Li, Changwen Zheng, Bing Su, and Hui Xiong. 2022. Interventional contrastive learning with meta semantic regularizer. In International Conference on Machine Learning. PMLR, 18018--18030."},{"key":"e_1_3_2_1_27_1","volume-title":"International conference on machine learning. PMLR, 8748--8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PMLR, 8748--8763."},{"key":"e_1_3_2_1_28_1","volume-title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks. EMNLP\/IJCNLP","author":"Reimers Nils","year":"2019","unstructured":"Nils Reimers and Iryna Gurevych. 2019. Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks. EMNLP\/IJCNLP (2019)."},{"key":"e_1_3_2_1_29_1","volume-title":"Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoders. CVPR","author":"Sch\u00f6nfeld Edgar","year":"2019","unstructured":"Edgar Sch\u00f6nfeld, Sayna Ebrahimi, Samarth Sinha, Trevor Darrell, and Zeynep Akata. 2019. Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoders. CVPR (2019)."},{"key":"e_1_3_2_1_30_1","volume-title":"NTU RGBD: A Large Scale Dataset for 3D Human Activity Analysis. CVPR","author":"Shahroudy Amir","year":"2016","unstructured":"Amir Shahroudy, Jun Liu, Tian-Tsong Ng, and Gang Wang. 2016. NTU RGBD: A Large Scale Dataset for 3D Human Activity Analysis. CVPR (2016)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01230"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995316"},{"key":"e_1_3_2_1_33_1","volume-title":"Locality and Compositionality in Zero-Shot Learning. ICLR","author":"Sylvain Tristan","year":"2020","unstructured":"Tristan Sylvain, Linda Petrini, and Devon Hjelm. 2020. Locality and Compositionality in Zero-Shot Learning. ICLR (2020)."},{"key":"e_1_3_2_1_34_1","volume-title":"Zero-shot learning by mutual information estimation and maximization. Knowledge-Based Systems","author":"Tang Chenwei","year":"2020","unstructured":"Chenwei Tang, Xue Yang, Jiancheng Lv, and Zhenan He. 2020. Zero-shot learning by mutual information estimation and maximization. Knowledge-Based Systems (2020)."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475307"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"e_1_3_2_1_37_1","volume-title":"Learning Robust Visual-Semantic Embeddings. ICCV","author":"Yao-Hung Tsai Hubert","year":"2017","unstructured":"Hubert Yao-Hung Tsai, Liang-Kang Huang, and Ruslan Salakhutdinov. 2017. Learning Robust Visual-Semantic Embeddings. ICCV (2017)."},{"key":"e_1_3_2_1_38_1","volume-title":"On Mutual Information Maximization for Representation Learning. ICLR","author":"Tschannen Michael","year":"2020","unstructured":"Michael Tschannen, Josip Djolonga, K. Paul Rubenstein, Sylvain Gelly, and Mario Lucic. 2020. On Mutual Information Maximization for Representation Learning. ICLR (2020)."},{"key":"e_1_3_2_1_39_1","volume-title":"Spatio-Temporal Branching for Motion Prediction using Motion Increments. arXiv preprint arXiv:2308.01097","author":"Wang Jiexin","year":"2023","unstructured":"Jiexin Wang, Yujie Zhou, Wenwen Qiang, Ying Ba, Bing Su, and Ji-Rong Wen. 2023. Spatio-Temporal Branching for Motion Prediction using Motion Increments. arXiv preprint arXiv:2308.01097 (2023)."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-017-1027-5"},{"key":"e_1_3_2_1_41_1","volume-title":"Fine-Grained Action Retrieval Through Multiple Parts-of-Speech Embeddings. International Conference on Computer Vision","author":"Wray Michael","year":"2019","unstructured":"Michael Wray, Diane Larlus, Gabriela Csurka, and Dima Damen. 2019. Fine-Grained Action Retrieval Through Multiple Parts-of-Speech Embeddings. International Conference on Computer Vision (2019)."},{"key":"e_1_3_2_1_42_1","volume-title":"Multi-Task Zero-Shot Action Recognition with Prioritised Data Augmentation. ECCV","author":"Xu Xun","year":"2016","unstructured":"Xun Xu, M. Timothy Hospedales, and Shaogang Gong. 2016. Multi-Task Zero-Shot Action Recognition with Prioritised Data Augmentation. ECCV (2016), 343--359."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00119"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/MMUL.2012.24"},{"key":"e_1_3_2_1_46_1","volume-title":"Self-supervised Action Representation Learning from Partial Spatio-Temporal Skeleton Sequences. arXiv preprint arXiv:2302.09018","author":"Zhou Yujie","year":"2023","unstructured":"Yujie Zhou, Haodong Duan, Anyi Rao, Bing Su, and Jiaqi Wang. 2023. Self-supervised Action Representation Learning from Partial Spatio-Temporal Skeleton Sequences. arXiv preprint arXiv:2302.09018 (2023)."},{"key":"e_1_3_2_1_47_1","volume-title":"Towards Universal Representation for Unseen Action Recognition. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR).","author":"Zhu Yi","year":"2018","unstructured":"Yi Zhu, Yang Long, Yu Guan, Shawn Newsam, and Ling Shao. 2018. Towards Universal Representation for Unseen Action Recognition. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR)."}],"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\/3581783.3611888","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3611888","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:00:37Z","timestamp":1755820837000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3611888"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":47,"alternative-id":["10.1145\/3581783.3611888","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3611888","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"}}]}}