{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T13:48:36Z","timestamp":1778680116576,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":40,"publisher":"ACM","license":[{"start":{"date-parts":[[2018,6,5]],"date-time":"2018-06-05T00:00:00Z","timestamp":1528156800000},"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":["61772116"],"award-info":[{"award-number":["61772116"]}]},{"name":"National Natural Science Foundation of China","award":["61632007"],"award-info":[{"award-number":["61632007"]}]},{"name":"National Natural Science Foundation of China","award":["61602089"],"award-info":[{"award-number":["61602089"]}]},{"name":"National Natural Science Foundation of China","award":["61572108"],"award-info":[{"award-number":["61572108"]}]},{"name":"The Telecommunications Foundation NII and NICT"},{"name":"LEADER of MEXT-Japan","award":["16809746"],"award-info":[{"award-number":["16809746"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2018,6,5]]},"DOI":"10.1145\/3206025.3206033","type":"proceedings-article","created":{"date-parts":[[2018,6,11]],"date-time":"2018-06-11T12:36:20Z","timestamp":1528720580000},"page":"46-54","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":44,"title":["Modal-adversarial Semantic Learning Network for Extendable Cross-modal Retrieval"],"prefix":"10.1145","author":[{"given":"Xing","family":"Xu","sequence":"first","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingkuan","family":"Song","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huimin","family":"Lu","sequence":"additional","affiliation":[{"name":"Kyushu Institute of Technology, Kitakyushu, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Yang","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fumin","family":"Shen","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zi","family":"Huang","sequence":"additional","affiliation":[{"name":"University of Queensland, Brisbane, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2018,6,5]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"G. Andrew R. Arora J. Bilmes and K. Livescu. 2013. Deep Canonical Correlation Analysis.. In ICML. 1247--1255.   G. Andrew R. Arora J. Bilmes and K. Livescu. 2013. Deep Canonical Correlation Analysis.. In ICML. 1247--1255."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2013.2281366"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.142"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654902"},{"key":"e_1_3_2_1_5_1","unstructured":"Y. Ganin and V. S. Lempitsky. 2015. Unsupervised Domain Adaptation by Backpropagation. ICML. 1180--1189.   Y. Ganin and V. S. Lempitsky. 2015. Unsupervised Domain Adaptation by Backpropagation. ICML. 1180--1189."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0658-4"},{"key":"e_1_3_2_1_7_1","unstructured":"I. Goodfellow J. Pouget-Abadie M. Mirza B. Xu D. Warde-Farley S. Ozair A. Courville and Y. Bengio. 2014. Generative Adversarial Nets. In NIPS. 2672--2680.   I. Goodfellow J. Pouget-Abadie M. Mirza B. Xu D. Warde-Farley S. Ozair A. Courville and Y. Bengio. 2014. Generative Adversarial Nets. In NIPS. 2672--2680."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1162\/0899766042321814"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2749147"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.5555\/3172077.3172151"},{"key":"e_1_3_2_1_11_1","volume-title":"2017 b. MHTN: Modal-adversarial Hybrid Transfer Network for Cross-modal Retrieval. CoRR","author":"Huang Xin","year":"2017","unstructured":"Xin Huang , Yuxin Peng , and Mingkuan Yuan . 2017 b. MHTN: Modal-adversarial Hybrid Transfer Network for Cross-modal Retrieval. CoRR Vol. abs\/ 1708 .04308 ( 2017 ). Xin Huang, Yuxin Peng, and Mingkuan Yuan. 2017 b. MHTN: Modal-adversarial Hybrid Transfer Network for Cross-modal Retrieval. CoRR Vol. abs\/1708.04308 (2017)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/957013.957143"},{"key":"e_1_3_2_1_13_1","volume-title":"A New Evaluation Protocol and Benchmarking Results for Extendable Cross-media Retrieval. CoRR","author":"Liu Ruoyu","year":"2017","unstructured":"Ruoyu Liu , Yao Zhao , Liang Zheng , Shikui Wei , and Yi Yang . 2017. A New Evaluation Protocol and Benchmarking Results for Extendable Cross-media Retrieval. CoRR Vol. abs\/ 1703 .03567 ( 2017 ). Ruoyu Liu, Yao Zhao, Liang Zheng, Shikui Wei, and Yi Yang. 2017. A New Evaluation Protocol and Benchmarking Results for Extendable Cross-media Retrieval. CoRR Vol. abs\/1703.03567 (2017)."},{"key":"e_1_3_2_1_14_1","unstructured":"J. Ngiam A. Khosla M. Kim J. Nam H. Lee and A. Ng. 2011. Multimodal deep learning. In ICML. 689--696.   J. Ngiam A. Khosla M. Kim J. Nam H. Lee and A. Ng. 2011. Multimodal deep learning. In ICML. 689--696."},{"key":"e_1_3_2_1_15_1","unstructured":"Mohammad Norouzi Tomas Mikolov Samy Bengio Yoram Singer Jonathon Shlens Andrea Frome Greg Corrado and Jeffrey Dean. 2013. Zero-Shot Learning by Convex Combination of Semantic Embeddings. (2013) 410--418.  Mohammad Norouzi Tomas Mikolov Samy Bengio Yoram Singer Jonathon Shlens Andrea Frome Greg Corrado and Jeffrey Dean. 2013. Zero-Shot Learning by Convex Combination of Semantic Embeddings. (2013) 410--418."},{"key":"e_1_3_2_1_16_1","unstructured":"Y. Peng X. Huang and J. Qi. 2016. Cross-media shared representation by hierarchical learning with multiple deep networks IJCAI. 3846--C3853.   Y. Peng X. Huang and J. Qi. 2016. Cross-media shared representation by hierarchical learning with multiple deep networks IJCAI. 3846--C3853."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2742704"},{"key":"e_1_3_2_1_18_1","volume-title":"2017 a. CM-GANs: Cross-modal Generative Adversarial Networks for Common Representation Learning. CoRR","author":"Peng Yuxin","year":"2017","unstructured":"Yuxin Peng , Jinwei Qi , and Yuxin Yuan . 2017 a. CM-GANs: Cross-modal Generative Adversarial Networks for Common Representation Learning. CoRR Vol. abs\/ 1710 .05106 ( 2017 ). Yuxin Peng, Jinwei Qi, and Yuxin Yuan. 2017 a. CM-GANs: Cross-modal Generative Adversarial Networks for Common Representation Learning. CoRR Vol. abs\/1710.05106 (2017)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"crossref","unstructured":"J. Pennington R. Socher and C. Manning. 2014. GloVe: Global Vectors for Word Representation. In EMNLP. 1532--1543.  J. Pennington R. Socher and C. Manning. 2014. GloVe: Global Vectors for Word Representation. In EMNLP. 1532--1543.","DOI":"10.3115\/v1\/D14-1162"},{"key":"e_1_3_2_1_20_1","unstructured":"C. Rashtchian M. Young P. Hodosh and J. Hockenmaier. 2010. Collecting Image Annotations Using Amazon's Mechanical Turk NAACL HLT 2010 Workshop on Creating Speech and Language Data with Amazon's Mechanical Turk.   C. Rashtchian M. Young P. Hodosh and J. Hockenmaier. 2010. Collecting Image Annotations Using Amazon's Mechanical Turk NAACL HLT 2010 Workshop on Creating Speech and Language Data with Amazon's Mechanical Turk."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1873987"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2699863"},{"key":"e_1_3_2_1_23_1","unstructured":"K. Simonyan and A. Zisserman. 2014. Very Deep Convolutional Networks for Large-Scale Image Recognition. CoRR Vol. abs\/1409.1556 (2014).  K. Simonyan and A. Zisserman. 2014. Very Deep Convolutional Networks for Large-Scale Image Recognition. CoRR Vol. abs\/1409.1556 (2014)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"crossref","unstructured":"Jingkuan Song Tao He Lianli Gao Xing Xu Alan Hajalic and Heng Tao Shen. 2018 b. Binary Generative Adversarial Networks for Image Retrieval. AAAI.  Jingkuan Song Tao He Lianli Gao Xing Xu Alan Hajalic and Heng Tao Shen. 2018 b. Binary Generative Adversarial Networks for Image Retrieval. AAAI.","DOI":"10.1609\/aaai.v32i1.11276"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"crossref","unstructured":"Jingkuan Song Tao He Lianli Gao Xing Xu and Heng Tao Shen. 2018 a. Deep Region Hashing for Efficient Large-scale Instance Search from Images. AAAI.  Jingkuan Song Tao He Lianli Gao Xing Xu and Heng Tao Shen. 2018 a. Deep Region Hashing for Efficient Large-scale Instance Search from Images. AAAI.","DOI":"10.1609\/aaai.v32i1.11277"},{"key":"e_1_3_2_1_26_1","unstructured":"N. Srivastava and R. Salakhutdinov. 2012. Learning representations for multimodal data with deep belief nets ICML Workshop.  N. Srivastava and R. Salakhutdinov. 2012. Learning representations for multimodal data with deep belief nets ICML Workshop."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123326"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2505311"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.261"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"crossref","unstructured":"L. Wang Y. Li and S. Lazebnik. 2016. Learning Deep Structure-Preserving Image-Text Embeddings CVPR. 5005--5013.  L. Wang Y. Li and S. Lazebnik. 2016. Learning Deep Structure-Preserving Image-Text Embeddings CVPR. 5005--5013.","DOI":"10.1109\/CVPR.2016.541"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-017-1027-5"},{"key":"e_1_3_2_1_32_1","unstructured":"W. Wang R. Arora K. Livescu and J. Bilmes. 2015. On deep multi-view representation learning. In ICML. 1083--1092.   W. Wang R. Arora K. Livescu and J. Bilmes. 2015. On deep multi-view representation learning. In ICML. 1083--1092."},{"key":"e_1_3_2_1_33_1","first-page":"449","article-title":"Cross-Modal Retrieval With CNN Visual Features: A New Baseline","volume":"47","author":"Wei Yunchao","year":"2017","unstructured":"Yunchao Wei , Yao Zhao , Canyi Lu , Shikui Wei , Luoqi Liu , Zhenfeng Zhu , and Shuicheng Yan . 2017 . Cross-Modal Retrieval With CNN Visual Features: A New Baseline . IEEE Trans. Cybernetics Vol. 47 , 2 (2017), 449 -- 460 . Yunchao Wei, Yao Zhao, Canyi Lu, Shikui Wei, Luoqi Liu, Zhenfeng Zhu, and Shuicheng Yan. 2017. Cross-Modal Retrieval With CNN Visual Features: A New Baseline. IEEE Trans. Cybernetics Vol. 47, 2 (2017), 449--460.","journal-title":"IEEE Trans. Cybernetics"},{"key":"e_1_3_2_1_34_1","volume-title":"Deep Adversarial Metric Learning for Cross-Modal Retrieval. World Wide Web","author":"Xu Xing","year":"2018","unstructured":"Xing Xu , Li He , Huimin Lu , Lianli Gao , and Yanli Ji. 2018. Deep Adversarial Metric Learning for Cross-Modal Retrieval. World Wide Web ( 2018 ). Xing Xu, Li He, Huimin Lu, Lianli Gao, and Yanli Ji. 2018. Deep Adversarial Metric Learning for Cross-Modal Retrieval. World Wide Web (2018)."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2967231"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2676345"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806346"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"crossref","unstructured":"F. Yan and K. Mikolajczyk. 2015. Deep correlation for matching images and text. In CVPR. 3441--3450.  F. Yan and K. Mikolajczyk. 2015. Deep correlation for matching images and text. In CVPR. 3441--3450.","DOI":"10.1109\/CVPR.2015.7298966"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2016.2516024"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"crossref","unstructured":"Li Zhang Tao Xiang and Shaogang Gong. 2017. Learning a Deep Embedding Model for Zero-Shot Learning CVPR. 3010--3019.  Li Zhang Tao Xiang and Shaogang Gong. 2017. Learning a Deep Embedding Model for Zero-Shot Learning CVPR. 3010--3019.","DOI":"10.1109\/CVPR.2017.321"}],"event":{"name":"ICMR '18: International Conference on Multimedia Retrieval","location":"Yokohama Japan","acronym":"ICMR '18","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 2018 ACM on International Conference on Multimedia Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3206025.3206033","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3206025.3206033","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T01:08:15Z","timestamp":1750208895000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3206025.3206033"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,6,5]]},"references-count":40,"alternative-id":["10.1145\/3206025.3206033","10.1145\/3206025"],"URL":"https:\/\/doi.org\/10.1145\/3206025.3206033","relation":{},"subject":[],"published":{"date-parts":[[2018,6,5]]},"assertion":[{"value":"2018-06-05","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}