{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T16:53:29Z","timestamp":1768323209271,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":26,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,10,18]],"date-time":"2021-10-18T00:00:00Z","timestamp":1634515200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"USA National Science Foundation","award":["Grants NSF 2038029, 1564097"],"award-info":[{"award-number":["Grants NSF 2038029, 1564097"]}]},{"DOI":"10.13039\/501100004543","name":"China Scholarship Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004543","id-type":"DOI","asserted-by":"publisher"}]},{"name":"IBM faculty award"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,10,18]]},"DOI":"10.1145\/3462244.3479892","type":"proceedings-article","created":{"date-parts":[[2021,10,15]],"date-time":"2021-10-15T14:41:47Z","timestamp":1634308907000},"page":"43-51","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Efficient Deep Feature Calibration for Cross-Modal Joint Embedding Learning"],"prefix":"10.1145","author":[{"given":"Zhongwei","family":"Xie","sequence":"first","affiliation":[{"name":"School of Computer Science, Georgia Institute of Technology, USA and School of Computer Science and Technology, Wuhan University of Technology, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ling","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer Science, Georgia Institute of Technology, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lin","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Wuhan University of Technology, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Luo","family":"Zhong","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Wuhan University of Technology, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2021,10,18]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3210036"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240627"},{"key":"e_1_3_2_2_4_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805(2018).","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin , Ming-Wei Chang , Kenton Lee , and Kristina Toutanova . 2018 . Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805(2018). Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805(2018)."},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01458"},{"key":"e_1_3_2_2_6_1","unstructured":"Ian Goodfellow Jean Pouget-Abadie Mehdi Mirza Bing Xu David Warde-Farley Sherjil Ozair Aaron Courville and Yoshua Bengio. 2014. Generative adversarial nets. In Advances in neural information processing systems. 2672\u20132680.  Ian Goodfellow Jean Pouget-Abadie Mehdi Mirza Bing Xu David Warde-Farley Sherjil Ozair Aaron Courville and Yoshua Bengio. 2014. Generative adversarial nets. In Advances in neural information processing systems. 2672\u20132680."},{"key":"e_1_3_2_2_7_1","unstructured":"Ishaan Gulrajani Faruk Ahmed Martin Arjovsky Vincent Dumoulin and Aaron\u00a0C Courville. 2017. Improved training of wasserstein gans. In Advances in neural information processing systems. 5767\u20135777.  Ishaan Gulrajani Faruk Ahmed Martin Arjovsky Vincent Dumoulin and Aaron\u00a0C Courville. 2017. Improved training of wasserstein gans. In Advances in neural information processing systems. 5767\u20135777."},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_2_9_1","unstructured":"Alexander Hermans Lucas Beyer and Bastian Leibe. 2017. In defense of the triplet loss for person re-identification. arXiv preprint arXiv:1703.07737(2017).  Alexander Hermans Lucas Beyer and Bastian Leibe. 2017. In defense of the triplet loss for person re-identification. arXiv preprint arXiv:1703.07737(2017)."},{"key":"e_1_3_2_2_10_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980(2014).","author":"Kingma P","year":"2014","unstructured":"Diederik\u00a0 P Kingma and Jimmy Ba . 2014 . Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980(2014). Diederik\u00a0P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980(2014)."},{"key":"e_1_3_2_2_11_1","unstructured":"Ryan Kiros Yukun Zhu Russ\u00a0R Salakhutdinov Richard Zemel Raquel Urtasun Antonio Torralba and Sanja Fidler. 2015. Skip-thought vectors. In Advances in neural information processing systems. 3294\u20133302.  Ryan Kiros Yukun Zhu Russ\u00a0R Salakhutdinov Richard Zemel Raquel Urtasun Antonio Torralba and Sanja Fidler. 2015. Skip-thought vectors. In Advances in neural information processing systems. 3294\u20133302."},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.5120\/20752-3148"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401244"},{"key":"e_1_3_2_2_14_1","volume-title":"Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692(2019).","author":"Liu Yinhan","year":"2019","unstructured":"Yinhan Liu , Myle Ott , Naman Goyal , Jingfei Du , Mandar Joshi , Danqi Chen , Omer Levy , Mike Lewis , Luke Zettlemoyer , and Veselin Stoyanov . 2019 . Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692(2019). Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692(2019)."},{"key":"e_1_3_2_2_15_1","volume-title":"Proceedings of the 2004 conference on empirical methods in natural language processing. 404\u2013411","author":"Mihalcea Rada","year":"2004","unstructured":"Rada Mihalcea and Paul Tarau . 2004 . Textrank: Bringing order into text . In Proceedings of the 2004 conference on empirical methods in natural language processing. 404\u2013411 . Rada Mihalcea and Paul Tarau. 2004. Textrank: Bringing order into text. In Proceedings of the 2004 conference on empirical methods in natural language processing. 404\u2013411."},{"key":"e_1_3_2_2_16_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_2_17_1","unstructured":"Tomas Mikolov Ilya Sutskever Kai Chen Greg\u00a0S Corrado and Jeff Dean. 2013. Distributed representations of words and phrases and their compositionality. In Advances in neural information processing systems. 3111\u20133119.  Tomas Mikolov Ilya Sutskever Kai Chen Greg\u00a0S Corrado and Jeff Dean. 2013. Distributed representations of words and phrases and their compositionality. In Advances in neural information processing systems. 3111\u20133119."},{"key":"e_1_3_2_2_18_1","volume-title":"Term-weighting approaches in automatic text retrieval. Information processing & management 24, 5","author":"Salton Gerard","year":"1988","unstructured":"Gerard Salton and Christopher Buckley . 1988. Term-weighting approaches in automatic text retrieval. Information processing & management 24, 5 ( 1988 ), 513\u2013523. Gerard Salton and Christopher Buckley. 1988. Term-weighting approaches in automatic text retrieval. Information processing & management 24, 5 (1988), 513\u2013523."},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.327"},{"key":"e_1_3_2_2_20_1","unstructured":"Victor Sanh Lysandre Debut Julien Chaumond and Thomas Wolf. 2019. DistilBERT a distilled version of BERT: smaller faster cheaper and lighter. arXiv preprint arXiv:1910.01108(2019).  Victor Sanh Lysandre Debut Julien Chaumond and Thomas Wolf. 2019. DistilBERT a distilled version of BERT: smaller faster cheaper and lighter. arXiv preprint arXiv:1910.01108(2019)."},{"key":"e_1_3_2_2_21_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_2_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123326"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01184"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298966"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"crossref","unstructured":"Sergey Zagoruyko and Nikos Komodakis. 2016. Wide residual networks. arXiv preprint arXiv:1605.07146(2016).  Sergey Zagoruyko and Nikos Komodakis. 2016. Wide residual networks. arXiv preprint arXiv:1605.07146(2016).","DOI":"10.5244\/C.30.87"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01174"}],"event":{"name":"ICMI '21: INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION","location":"Montr\u00e9al QC Canada","acronym":"ICMI '21","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction"]},"container-title":["Proceedings of the 2021 International Conference on Multimodal Interaction"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3462244.3479892","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3462244.3479892","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:48:54Z","timestamp":1750193334000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3462244.3479892"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,18]]},"references-count":26,"alternative-id":["10.1145\/3462244.3479892","10.1145\/3462244"],"URL":"https:\/\/doi.org\/10.1145\/3462244.3479892","relation":{},"subject":[],"published":{"date-parts":[[2021,10,18]]},"assertion":[{"value":"2021-10-18","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}