{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:18:58Z","timestamp":1750220338230,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":30,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,12,4]],"date-time":"2021-12-04T00:00:00Z","timestamp":1638576000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,12,4]]},"DOI":"10.1145\/3507548.3507599","type":"proceedings-article","created":{"date-parts":[[2022,3,9]],"date-time":"2022-03-09T23:12:40Z","timestamp":1646867560000},"page":"331-336","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Adaptive Margin Ranking for Supervised Cross-modal Retrieval"],"prefix":"10.1145","author":[{"given":"Tianyuan","family":"Xu","sequence":"first","affiliation":[{"name":"Hefei University of Technology, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xueliang","family":"Liu","sequence":"additional","affiliation":[{"name":"Hefei University of Technology, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2022,3,9]]},"reference":[{"volume-title":"PMLR","author":"Andrew G","key":"e_1_3_2_1_1_1","unstructured":"Andrew G , Arora R , Bilmes J , Deep canonical correlation analysis[C]\/\/International conference on machine learning . PMLR , 2013: 1247-1255. Andrew G, Arora R, Bilmes J, Deep canonical correlation analysis[C]\/\/International conference on machine learning. PMLR, 2013: 1247-1255."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"crossref","unstructured":"Chua T S Tang J Hong R Nus-wide: a real-world web image database from national university of singapore[C]\/\/Proceedings of the ACM international conference on image and video retrieval. 2009: 1-9.  Chua T S Tang J Hong R Nus-wide: a real-world web image database from national university of singapore[C]\/\/Proceedings of the ACM international conference on image and video retrieval. 2009: 1-9.","DOI":"10.1145\/1646396.1646452"},{"volume-title":"Cross-modal retrieval with correspondence autoencoder[C]\/\/Proceedings of the 22nd ACM international conference on Multimedia. 2014: 7-16","author":"Feng F","key":"e_1_3_2_1_3_1","unstructured":"Feng F , Wang X , Li R. Cross-modal retrieval with correspondence autoencoder[C]\/\/Proceedings of the 22nd ACM international conference on Multimedia. 2014: 7-16 . Feng F, Wang X, Li R. Cross-modal retrieval with correspondence autoencoder[C]\/\/Proceedings of the 22nd ACM international conference on Multimedia. 2014: 7-16."},{"key":"e_1_3_2_1_4_1","volume-title":"Canonical correlation analysis: An overview with application to learning methods[J]. Neural computation","author":"Hardoon D R","year":"2004","unstructured":"Hardoon D R , Szedmak S , Shawe-Taylor J. Canonical correlation analysis: An overview with application to learning methods[J]. Neural computation , 2004 , 16(12): 2639-2664. Hardoon D R, Szedmak S, Shawe-Taylor J. Canonical correlation analysis: An overview with application to learning methods[J]. Neural computation, 2004, 16(12): 2639-2664."},{"key":"e_1_3_2_1_5_1","volume-title":"Relations between two sets of variates[M]\/\/Breakthroughs in statistics","author":"Hotelling H.","year":"1992","unstructured":"Hotelling H. Relations between two sets of variates[M]\/\/Breakthroughs in statistics . Springer , New York, NY , 1992 : 162-190. Hotelling H. Relations between two sets of variates[M]\/\/Breakthroughs in statistics. Springer, New York, NY, 1992: 162-190."},{"key":"e_1_3_2_1_6_1","volume-title":"Multi-view discriminant analysis[J]","author":"Kan M","year":"2015","unstructured":"Kan M , Shan S , Zhang H , Multi-view discriminant analysis[J] . IEEE transactions on pattern analysis and machine intelligence, 2015 , 38(1): 188-194. Kan M, Shan S, Zhang H, Multi-view discriminant analysis[J]. IEEE transactions on pattern analysis and machine intelligence, 2015, 38(1): 188-194."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2020.08.009"},{"key":"e_1_3_2_1_8_1","volume-title":"GitHub","author":"Rakhlin A.","year":"2016","unstructured":"Rakhlin A. Convolutional neural networks for sentence classification[J] . GitHub , 2016 . Rakhlin A. Convolutional neural networks for sentence classification[J]. GitHub, 2016."},{"key":"e_1_3_2_1_9_1","volume-title":"Ba J. Adam: A method for stochastic optimization[J]. arXiv preprint arXiv:1412.6980","author":"Kingma D P","year":"2014","unstructured":"Kingma D P , Ba J. Adam: A method for stochastic optimization[J]. arXiv preprint arXiv:1412.6980 , 2014 . Kingma D P, Ba J. Adam: A method for stochastic optimization[J]. arXiv preprint arXiv:1412.6980, 2014."},{"key":"e_1_3_2_1_10_1","volume-title":"Imagenet classification with deep convolutional neural networks[J]. Advances in neural information processing systems","author":"Krizhevsky A","year":"2012","unstructured":"Krizhevsky A , Sutskever I , Hinton G E . Imagenet classification with deep convolutional neural networks[J]. Advances in neural information processing systems , 2012 , 25: 1097-1105. Krizhevsky A, Sutskever I, Hinton G E. Imagenet classification with deep convolutional neural networks[J]. Advances in neural information processing systems, 2012, 25: 1097-1105."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"crossref","unstructured":"Li D Dimitrova N Li M Multimedia content processing through cross-modal association[C]\/\/Proceedings of the eleventh ACM international conference on Multimedia. 2003: 604-611.  Li D Dimitrova N Li M Multimedia content processing through cross-modal association[C]\/\/Proceedings of the eleventh ACM international conference on Multimedia. 2003: 604-611.","DOI":"10.1145\/957013.957143"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"crossref","unstructured":"Li S Zhang W Chan A B. Maximum-margin structured learning with deep networks for 3d human pose estimation[C]\/\/Proceedings of the IEEE international conference on computer vision. 2015: 2848-2856.  Li S Zhang W Chan A B. Maximum-margin structured learning with deep networks for 3d human pose estimation[C]\/\/Proceedings of the IEEE international conference on computer vision. 2015: 2848-2856.","DOI":"10.1109\/ICCV.2015.326"},{"key":"e_1_3_2_1_13_1","unstructured":"Mikolov T Sutskever I Chen K Distributed representations of words and phrases and their compositionality[C]\/\/Advances in neural information processing systems. 2013: 3111-3119.  Mikolov T Sutskever I Chen K Distributed representations of words and phrases and their compositionality[C]\/\/Advances in neural information processing systems. 2013: 3111-3119."},{"key":"e_1_3_2_1_14_1","volume-title":"Multimodal deep learning[C]\/\/ICML","author":"Ngiam J","year":"2011","unstructured":"Ngiam J , Khosla A , Kim M , Multimodal deep learning[C]\/\/ICML . 2011 . Ngiam J, Khosla A, Kim M, Multimodal deep learning[C]\/\/ICML. 2011."},{"key":"e_1_3_2_1_15_1","unstructured":"Peng Y Huang X Qi J. Cross-media shared representation by hierarchical learning with multiple deep networks[C]\/\/IJCAI. 2016: 3846-3853.  Peng Y Huang X Qi J. Cross-media shared representation by hierarchical learning with multiple deep networks[C]\/\/IJCAI. 2016: 3846-3853."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2742704"},{"key":"e_1_3_2_1_17_1","unstructured":"Rashtchian C Young P Hodosh M Collecting image annotations using amazon's mechanical turk[C]\/\/Proceedings of the NAACL HLT 2010 Workshop on Creating Speech and Language Data with Amazon's Mechanical Turk. 2010: 139-147.  Rashtchian C Young P Hodosh M Collecting image annotations using amazon's mechanical turk[C]\/\/Proceedings of the NAACL HLT 2010 Workshop on Creating Speech and Language Data with Amazon's Mechanical Turk. 2010: 139-147."},{"volume-title":"A new approach to cross-modal multimedia retrieval[C]\/\/Proceedings of the 18th ACM international conference on Multimedia. 2010: 251-260","author":"Rasiwasia N","key":"e_1_3_2_1_18_1","unstructured":"Rasiwasia N , Costa Pereira J , Coviello E , A new approach to cross-modal multimedia retrieval[C]\/\/Proceedings of the 18th ACM international conference on Multimedia. 2010: 251-260 . Rasiwasia N, Costa Pereira J, Coviello E, A new approach to cross-modal multimedia retrieval[C]\/\/Proceedings of the 18th ACM international conference on Multimedia. 2010: 251-260."},{"volume-title":"Cross-Modal Subspace Learning with Scheduled Adaptive Margin Constraints[C]\/\/Proceedings of the 27th ACM International Conference on Multimedia. 2019: 75-83","author":"Semedo D","key":"e_1_3_2_1_19_1","unstructured":"Semedo D , Magalh\u00e3es J. Cross-Modal Subspace Learning with Scheduled Adaptive Margin Constraints[C]\/\/Proceedings of the 27th ACM International Conference on Multimedia. 2019: 75-83 . Semedo D, Magalh\u00e3es J. Cross-Modal Subspace Learning with Scheduled Adaptive Margin Constraints[C]\/\/Proceedings of the 27th ACM International Conference on Multimedia. 2019: 75-83."},{"key":"e_1_3_2_1_20_1","volume-title":"Very deep convolutional networks for large-scale image recognition[J]. arXiv preprint arXiv:1409.1556","author":"Simonyan K","year":"2014","unstructured":"Simonyan K , Zisserman A. Very deep convolutional networks for large-scale image recognition[J]. arXiv preprint arXiv:1409.1556 , 2014 . Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition[J]. arXiv preprint arXiv:1409.1556, 2014."},{"key":"e_1_3_2_1_21_1","volume-title":"Visualizing data using t-SNE[J]. Journal of machine learning research","author":"Van der Maaten L","year":"2008","unstructured":"Van der Maaten L , Hinton G. Visualizing data using t-SNE[J]. Journal of machine learning research , 2008 , 9(11). Van der Maaten L, Hinton G. Visualizing data using t-SNE[J]. Journal of machine learning research, 2008, 9(11)."},{"volume-title":"Adversarial cross-modal retrieval[C]\/\/Proceedings of the 25th ACM international conference on Multimedia. 2017: 154-162","author":"Wang B","key":"e_1_3_2_1_22_1","unstructured":"Wang B , Yang Y , Xu X , Adversarial cross-modal retrieval[C]\/\/Proceedings of the 25th ACM international conference on Multimedia. 2017: 154-162 . Wang B, Yang Y, Xu X, Adversarial cross-modal retrieval[C]\/\/Proceedings of the 25th ACM international conference on Multimedia. 2017: 154-162."},{"key":"e_1_3_2_1_23_1","volume-title":"Deep semantic mapping for cross-modal retrieval[C]\/\/2015 IEEE 27th International conference on tools with artificial intelligence (ICTAI)","author":"Wang C","year":"2015","unstructured":"Wang C , Yang H , Meinel C. Deep semantic mapping for cross-modal retrieval[C]\/\/2015 IEEE 27th International conference on tools with artificial intelligence (ICTAI) . IEEE , 2015 : 234-241. Wang C, Yang H, Meinel C. Deep semantic mapping for cross-modal retrieval[C]\/\/2015 IEEE 27th International conference on tools with artificial intelligence (ICTAI). IEEE, 2015: 234-241."},{"key":"e_1_3_2_1_24_1","volume-title":"A comprehensive survey on cross-modal retrieval[J]. arXiv preprint arXiv:1607.06215","author":"Wang K","year":"2016","unstructured":"Wang K , Yin Q , Wang W , A comprehensive survey on cross-modal retrieval[J]. arXiv preprint arXiv:1607.06215 , 2016 . Wang K, Yin Q, Wang W, A comprehensive survey on cross-modal retrieval[J]. arXiv preprint arXiv:1607.06215, 2016."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"crossref","unstructured":"Wang K He R Wang W Learning coupled feature spaces for cross-modal matching[C]\/\/Proceedings of the IEEE International Conference on Computer Vision. 2013: 2088-2095.  Wang K He R Wang W Learning coupled feature spaces for cross-modal matching[C]\/\/Proceedings of the IEEE International Conference on Computer Vision. 2013: 2088-2095.","DOI":"10.1109\/ICCV.2013.261"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"crossref","unstructured":"Wang L Li Y Lazebnik S. Learning deep structure-preserving image-text embeddings[C]\/\/Proceedings of the IEEE conference on computer vision and pattern recognition. 2016: 5005-5013.  Wang L Li Y Lazebnik S. Learning deep structure-preserving image-text embeddings[C]\/\/Proceedings of the IEEE conference on computer vision and pattern recognition. 2016: 5005-5013.","DOI":"10.1109\/CVPR.2016.541"},{"key":"e_1_3_2_1_27_1","volume-title":"Online low-rank similarity function learning with adaptive relative margin for cross-modal retrieval[C]\/\/2017 IEEE International Conference on Multimedia and Expo (ICME)","author":"Wu Y","year":"2017","unstructured":"Wu Y , Wang S , Zhang W , Online low-rank similarity function learning with adaptive relative margin for cross-modal retrieval[C]\/\/2017 IEEE International Conference on Multimedia and Expo (ICME) . IEEE , 2017 : 823-828. Wu Y, Wang S, Zhang W, Online low-rank similarity function learning with adaptive relative margin for cross-modal retrieval[C]\/\/2017 IEEE International Conference on Multimedia and Expo (ICME). IEEE, 2017: 823-828."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"crossref","unstructured":"Yan F Mikolajczyk K. Deep correlation for matching images and text[C]\/\/Proceedings of the IEEE conference on computer vision and pattern recognition. 2015: 3441-3450.  Yan F Mikolajczyk K. Deep correlation for matching images and text[C]\/\/Proceedings of the IEEE conference on computer vision and pattern recognition. 2015: 3441-3450.","DOI":"10.1109\/CVPR.2015.7298966"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2013.2276704"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"crossref","unstructured":"Zhen L Hu P Wang X Deep supervised cross-modal retrieval[C]\/\/Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2019: 10394-10403.  Zhen L Hu P Wang X Deep supervised cross-modal retrieval[C]\/\/Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2019: 10394-10403.","DOI":"10.1109\/CVPR.2019.01064"}],"event":{"name":"CSAI 2021: 2021 5th International Conference on Computer Science and Artificial Intelligence","acronym":"CSAI 2021","location":"Beijing China"},"container-title":["2021 5th International Conference on Computer Science and Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3507548.3507599","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3507548.3507599","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:12:26Z","timestamp":1750191146000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3507548.3507599"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,4]]},"references-count":30,"alternative-id":["10.1145\/3507548.3507599","10.1145\/3507548"],"URL":"https:\/\/doi.org\/10.1145\/3507548.3507599","relation":{},"subject":[],"published":{"date-parts":[[2021,12,4]]},"assertion":[{"value":"2022-03-09","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}