{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T16:14:12Z","timestamp":1772122452566,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":28,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,11,7]],"date-time":"2022-11-07T00:00:00Z","timestamp":1667779200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,11,7]]},"DOI":"10.1145\/3536221.3556575","type":"proceedings-article","created":{"date-parts":[[2022,11,4]],"date-time":"2022-11-04T15:54:14Z","timestamp":1667577254000},"page":"310-318","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Multi-level Fusion of Multi-modal Semantic Embeddings for Zero Shot Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8680-5376","authenticated-orcid":false,"given":"Zhe","family":"Kong","sequence":"first","affiliation":[{"name":"State Key Laboratory of Information Security, Institute of Information Engineering, CAS, China and School of Cyber Security, University of Chinese Academy of Sciences, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1069-4830","authenticated-orcid":false,"given":"Xin","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, CAS, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0870-5692","authenticated-orcid":false,"given":"Neng","family":"Gao","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Information Security, Institute of Information Engineering, CAS, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7068-1700","authenticated-orcid":false,"given":"Yifei","family":"Zhang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Information Security, Institute of Information Engineering, CAS, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3576-6666","authenticated-orcid":false,"given":"Yuhan","family":"Liu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Information Security, Institute of Information Engineering, CAS, China and School of Cyber Security, University of Chinese Academy of Sciences, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2130-0531","authenticated-orcid":false,"given":"Chenyang","family":"Tu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Information Security, Institute of Information Engineering, CAS, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2022,11,7]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.111"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298911"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.575"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.376"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00532"},{"key":"e_1_3_2_1_6_1","unstructured":"Georgiana Dinu Angeliki Lazaridou and Marco Baroni. 2014. Improving zero-shot learning by mitigating the hubness problem. arXiv preprint arXiv:1412.6568(2014).  Georgiana Dinu Angeliki Lazaridou and Marco Baroni. 2014. Improving zero-shot learning by mitigating the hubness problem. arXiv preprint arXiv:1412.6568(2014)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206772"},{"key":"e_1_3_2_1_8_1","volume-title":"Devise: A deep visual-semantic embedding model. Advances in neural information processing systems 26","author":"Frome Andrea","year":"2013","unstructured":"Andrea Frome , Greg\u00a0 S Corrado , Jon Shlens , Samy Bengio , Jeff Dean , Marc\u2019Aurelio Ranzato , and Tomas Mikolov . 2013 . Devise: A deep visual-semantic embedding model. Advances in neural information processing systems 26 (2013). Andrea Frome, Greg\u00a0S Corrado, Jon Shlens, Samy Bengio, Jeff Dean, Marc\u2019Aurelio Ranzato, and Tomas Mikolov. 2013. Devise: A deep visual-semantic embedding model. Advances in neural information processing systems 26 (2013)."},{"key":"e_1_3_2_1_9_1","unstructured":"Akshita Gupta Sanath Narayan Salman Khan Fahad\u00a0Shahbaz Khan Ling Shao and Joost van\u00a0de Weijer. 2021. Generative multi-label zero-shot learning. arXiv preprint arXiv:2101.11606(2021).  Akshita Gupta Sanath Narayan Salman Khan Fahad\u00a0Shahbaz Khan Ling Shao and Joost van\u00a0de Weijer. 2021. Generative multi-label zero-shot learning. arXiv preprint arXiv:2101.11606(2021)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.473"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206594"},{"key":"e_1_3_2_1_13_1","volume-title":"Attribute-based classification for zero-shot visual object categorization","author":"Lampert H","year":"2013","unstructured":"Christoph\u00a0 H Lampert , Hannes Nickisch , and Stefan Harmeling . 2013. Attribute-based classification for zero-shot visual object categorization . IEEE transactions on pattern analysis and machine intelligence 36, 3( 2013 ), 453\u2013465. Christoph\u00a0H Lampert, Hannes Nickisch, and Stefan Harmeling. 2013. Attribute-based classification for zero-shot visual object categorization. IEEE transactions on pattern analysis and machine intelligence 36, 3(2013), 453\u2013465."},{"key":"e_1_3_2_1_14_1","unstructured":"Hugo Larochelle Dumitru Erhan and Yoshua Bengio. 2008. Zero-data learning of new tasks.. In AAAI Vol.\u00a01. 3.  Hugo Larochelle Dumitru Erhan and Yoshua Bengio. 2008. Zero-data learning of new tasks.. In AAAI Vol.\u00a01. 3."},{"key":"e_1_3_2_1_15_1","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_1_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58542-6_29"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247998"},{"key":"e_1_3_2_1_18_1","volume-title":"International Conference on Machine Learning. PMLR, 8748\u20138763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford , Jong\u00a0Wook Kim , Chris Hallacy , Aditya Ramesh , Gabriel Goh , Sandhini Agarwal , Girish Sastry , Amanda Askell , Pamela Mishkin , Jack Clark , 2021 . Learning transferable visual models from natural language supervision . In International Conference on Machine Learning. PMLR, 8748\u20138763 . Alec Radford, Jong\u00a0Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, 2021. Learning transferable visual models from natural language supervision. In International Conference on Machine Learning. PMLR, 8748\u20138763."},{"key":"e_1_3_2_1_19_1","volume-title":"International conference on machine learning. PMLR, 2152\u20132161","author":"Romera-Paredes Bernardino","year":"2015","unstructured":"Bernardino Romera-Paredes and Philip Torr . 2015 . An embarrassingly simple approach to zero-shot learning . In International conference on machine learning. PMLR, 2152\u20132161 . Bernardino Romera-Paredes and Philip Torr. 2015. An embarrassingly simple approach to zero-shot learning. In International conference on machine learning. PMLR, 2152\u20132161."},{"key":"e_1_3_2_1_20_1","unstructured":"Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556(2014).  Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556(2014)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"e_1_3_2_1_22_1","volume-title":"Attention is all you need. Advances in neural information processing systems 30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani , Noam Shazeer , Niki Parmar , Jakob Uszkoreit , Llion Jones , Aidan\u00a0 N Gomez , \u0141ukasz Kaiser , and Illia Polosukhin . 2017. Attention is all you need. Advances in neural information processing systems 30 ( 2017 ). Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan\u00a0N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00717"},{"key":"e_1_3_2_1_24_1","unstructured":"Peter Welinder Steve Branson Takeshi Mita Catherine Wah Florian Schroff Serge Belongie and Pietro Perona. 2010. Caltech-UCSD birds 200. (2010).  Peter Welinder Steve Branson Takeshi Mita Catherine Wah Florian Schroff Serge Belongie and Pietro Perona. 2010. Caltech-UCSD birds 200. (2010)."},{"key":"e_1_3_2_1_25_1","volume-title":"Large scale image annotation: learning to rank with joint word-image embeddings. Machine learning 81, 1","author":"Weston Jason","year":"2010","unstructured":"Jason Weston , Samy Bengio , and Nicolas Usunier . 2010. Large scale image annotation: learning to rank with joint word-image embeddings. Machine learning 81, 1 ( 2010 ), 21\u201335. Jason Weston, Samy Bengio, and Nicolas Usunier. 2010. Large scale image annotation: learning to rank with joint word-image embeddings. Machine learning 81, 1 (2010), 21\u201335."},{"key":"e_1_3_2_1_26_1","volume-title":"Zero-shot learning\u2014a comprehensive evaluation of the good, the bad and the ugly","author":"Xian Yongqin","year":"2018","unstructured":"Yongqin Xian , Christoph\u00a0 H Lampert , Bernt Schiele , and Zeynep Akata . 2018. Zero-shot learning\u2014a comprehensive evaluation of the good, the bad and the ugly . IEEE transactions on pattern analysis and machine intelligence 41, 9( 2018 ), 2251\u20132265. Yongqin Xian, Christoph\u00a0H Lampert, Bernt Schiele, and Zeynep Akata. 2018. Zero-shot learning\u2014a comprehensive evaluation of the good, the bad and the ugly. IEEE transactions on pattern analysis and machine intelligence 41, 9(2018), 2251\u20132265."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01052"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.474"}],"event":{"name":"ICMI '22: INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION","location":"Bengaluru India","acronym":"ICMI '22","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction"]},"container-title":["Proceedings of the 2022 International Conference on Multimodal Interaction"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3536221.3556575","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3536221.3556575","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T17:48:52Z","timestamp":1750182532000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3536221.3556575"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,7]]},"references-count":28,"alternative-id":["10.1145\/3536221.3556575","10.1145\/3536221"],"URL":"https:\/\/doi.org\/10.1145\/3536221.3556575","relation":{},"subject":[],"published":{"date-parts":[[2022,11,7]]},"assertion":[{"value":"2022-11-07","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}