{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T09:41:25Z","timestamp":1766137285560,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":35,"publisher":"ACM","license":[{"start":{"date-parts":[[2019,10,15]],"date-time":"2019-10-15T00:00:00Z","timestamp":1571097600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"CMU Portugal","award":["CMUP-ERI\/TIC\/0046\/2014"],"award-info":[{"award-number":["CMUP-ERI\/TIC\/0046\/2014"]}]},{"name":"H2020 ICT","award":["687605"],"award-info":[{"award-number":["687605"]}]},{"name":"FCT","award":["UID\/CEC\/04516\/2013"],"award-info":[{"award-number":["UID\/CEC\/04516\/2013"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2019,10,15]]},"DOI":"10.1145\/3343031.3351030","type":"proceedings-article","created":{"date-parts":[[2019,10,21]],"date-time":"2019-10-21T16:32:26Z","timestamp":1571675546000},"page":"75-83","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["Cross-Modal Subspace Learning with Scheduled Adaptive Margin Constraints"],"prefix":"10.1145","author":[{"given":"David","family":"Semedo","sequence":"first","affiliation":[{"name":"Universidade NOVA de Lisboa, Caparica, Portugal"}]},{"given":"Joao","family":"Magalhaes","sequence":"additional","affiliation":[{"name":"Universidade NOVA de Lisboa, Caparica, Portugal"}]}],"member":"320","published-online":{"date-parts":[[2019,10,15]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/1646396.1646452"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123369"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654902"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0658-4"},{"volume-title":"Deep Learning","author":"Goodfellow Ian","key":"e_1_3_2_1_5_1","unstructured":"Ian Goodfellow , Yoshua Bengio , and Aaron Courville . 2016. Deep Learning . The MIT Press . Ian Goodfellow, Yoshua Bengio, and Aaron Courville. 2016. Deep Learning .The MIT Press."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1162\/0899766042321814"},{"volume-title":"Advances in Large Margin Classifiers","author":"Herbrich Ralf","key":"e_1_3_2_1_7_1","unstructured":"Ralf Herbrich , Thore Graepel , and Klaus Obermayer . 2000. Large Margin Rank Boundaries for Ordinal Regression . In Advances in Large Margin Classifiers , , P. J. Bartlett, B. Sch\u00f6lkopf, D. Schuurmans, and A. J. Smola (Eds.). MIT Press , 115--132. Ralf Herbrich, Thore Graepel, and Klaus Obermayer. 2000. Large Margin Rank Boundaries for Ordinal Regression. In Advances in Large Margin Classifiers , , P. J. Bartlett, B. Sch\u00f6lkopf, D. Schuurmans, and A. J. Smola (Eds.). MIT Press, 115--132."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/28.3-4.321"},{"key":"e_1_3_2_1_9_1","volume-title":"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 . MHTN: Modal-adversarial Hybrid Transfer Network for Cross-modal Retrieval. CoRR , Vol. abs\/ 1708 .04308 (2017). arxiv: 1708.04308 http:\/\/arxiv.org\/abs\/1708.04308 Xin Huang, Yuxin Peng, and Mingkuan Yuan. 2017. MHTN: Modal-adversarial Hybrid Transfer Network for Cross-modal Retrieval. CoRR , Vol. abs\/1708.04308 (2017). arxiv: 1708.04308 http:\/\/arxiv.org\/abs\/1708.04308"},{"key":"e_1_3_2_1_10_1","volume-title":"Proceedings of the Ninth Asian Conference on Machine Learning (Proceedings of Machine Learning Research), Min-Ling Zhang and Yung-Kyun Noh (Eds.)","volume":"77","author":"Kang Cuicui","year":"2017","unstructured":"Cuicui Kang , Shengcai Liao , Zhen Li , Zigang Cao , and Gang Xiong . 2017 . Learning Deep Semantic Embeddings for Cross-Modal Retrieval . In Proceedings of the Ninth Asian Conference on Machine Learning (Proceedings of Machine Learning Research), Min-Ling Zhang and Yung-Kyun Noh (Eds.) , Vol. 77 . PMLR, 471--486. http:\/\/proceedings.mlr.press\/v77\/kang17a.html Cuicui Kang, Shengcai Liao, Zhen Li, Zigang Cao, and Gang Xiong. 2017. Learning Deep Semantic Embeddings for Cross-Modal Retrieval. In Proceedings of the Ninth Asian Conference on Machine Learning (Proceedings of Machine Learning Research), Min-Ling Zhang and Yung-Kyun Noh (Eds.), Vol. 77. PMLR, 471--486. http:\/\/proceedings.mlr.press\/v77\/kang17a.html"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2390499"},{"key":"e_1_3_2_1_12_1","volume-title":"Kingma and Jimmy Ba","author":"Diederik","year":"2014","unstructured":"Diederik P. Kingma and Jimmy Ba . 2014 . Adam : A Method for Stochastic Optimization. CoRR , Vol. abs\/ 1412 .6980 (2014). arxiv: 1412.6980 http:\/\/arxiv.org\/abs\/1412.6980 Diederik P. Kingma and Jimmy Ba. 2014. Adam: A Method for Stochastic Optimization. CoRR , Vol. abs\/1412.6980 (2014). arxiv: 1412.6980 http:\/\/arxiv.org\/abs\/1412.6980"},{"volume-title":"Proceedings of the Eleventh ACM International Conference on Multimedia (MULTIMEDIA '03)","author":"Li Dongge","key":"e_1_3_2_1_13_1","unstructured":"Dongge Li , Nevenka Dimitrova , Mingkun Li , and Ishwar K. Sethi . 2003. Multimedia Content Processing Through Cross-modal Association . In Proceedings of the Eleventh ACM International Conference on Multimedia (MULTIMEDIA '03) . ACM, New York, NY, USA, 604--611. https:\/\/doi.org\/10.1145\/957013.957143 10.1145\/957013.957143 Dongge Li, Nevenka Dimitrova, Mingkun Li, and Ishwar K. Sethi. 2003. Multimedia Content Processing Through Cross-modal Association. In Proceedings of the Eleventh ACM International Conference on Multimedia (MULTIMEDIA '03). ACM, New York, NY, USA, 604--611. https:\/\/doi.org\/10.1145\/957013.957143"},{"key":"e_1_3_2_1_14_1","volume-title":"2015 IEEE International Conference on Computer Vision, ICCV 2015","author":"Li Sijin","year":"2015","unstructured":"Sijin Li , Weichen Zhang , and Antoni B. Chan . 2015. Maximum-Margin Structured Learning with Deep Networks for 3D Human Pose Estimation . In 2015 IEEE International Conference on Computer Vision, ICCV 2015 , Santiago, Chile, December 7--13 , 2015 . IEEE Computer Society, 2848--2856. https:\/\/doi.org\/10.1109\/ICCV.2015.326 10.1109\/ICCV.2015.326 Sijin Li, Weichen Zhang, and Antoni B. Chan. 2015. Maximum-Margin Structured Learning with Deep Networks for 3D Human Pose Estimation. In 2015 IEEE International Conference on Computer Vision, ICCV 2015, Santiago, Chile, December 7--13, 2015. IEEE Computer Society, 2848--2856. https:\/\/doi.org\/10.1109\/ICCV.2015.326"},{"volume-title":"Proceedings of the 28th International Conference on International Conference on Machine Learning (ICML'11)","author":"Ngiam Jiquan","key":"e_1_3_2_1_15_1","unstructured":"Jiquan Ngiam , Aditya Khosla , Mingyu Kim , Juhan Nam , Honglak Lee , and Andrew Y. Ng . 2011. Multimodal Deep Learning . In Proceedings of the 28th International Conference on International Conference on Machine Learning (ICML'11) . Omnipress, USA, 689--696. http:\/\/dl.acm.org\/citation.cfm?id=3104482.3104569 Jiquan Ngiam, Aditya Khosla, Mingyu Kim, Juhan Nam, Honglak Lee, and Andrew Y. Ng. 2011. Multimodal Deep Learning. In Proceedings of the 28th International Conference on International Conference on Machine Learning (ICML'11). Omnipress, USA, 689--696. http:\/\/dl.acm.org\/citation.cfm?id=3104482.3104569"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.5555\/3061053.3061157"},{"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":"Multi-label Cross-Modal Retrieval. In 2015 IEEE International Conference on Computer Vision (ICCV). 4094--4102","author":"Ranjan V.","year":"2015","unstructured":"V. Ranjan , N. Rasiwasia , and C. V. Jawahar . 2015 . Multi-label Cross-Modal Retrieval. In 2015 IEEE International Conference on Computer Vision (ICCV). 4094--4102 . https:\/\/doi.org\/10.1109\/ICCV. 2015 .466 10.1109\/ICCV.2015.466 V. Ranjan, N. Rasiwasia, and C. V. Jawahar. 2015. Multi-label Cross-Modal Retrieval. In 2015 IEEE International Conference on Computer Vision (ICCV). 4094--4102. https:\/\/doi.org\/10.1109\/ICCV.2015.466"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.5555\/1866696.1866717"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1873987"},{"key":"e_1_3_2_1_21_1","first-page":"1503","volume-title":"Article arXiv:1503.03832 (March","author":"Schroff Florian","year":"2015","unstructured":"Florian Schroff , Dmitry Kalenichenko , and James Philbin . 2015. FaceNet: A Unified Embedding for Face Recognition and Clustering . arXiv e-prints , Article arXiv:1503.03832 (March 2015 ), bibinfonumpagesarXiv: 1503 .03832 pages.arxiv: cs.CV\/1503.03832 Florian Schroff, Dmitry Kalenichenko, and James Philbin. 2015. FaceNet: A Unified Embedding for Face Recognition and Clustering . arXiv e-prints, Article arXiv:1503.03832 (March 2015), bibinfonumpagesarXiv:1503.03832 pages.arxiv: cs.CV\/1503.03832"},{"key":"e_1_3_2_1_22_1","volume-title":"Temporal Cross-Media Retrieval with Soft-Smoothing. In 2018 ACM Multimedia Conference on Multimedia Conference (MM '18)","author":"Semedo David","year":"2018","unstructured":"David Semedo and Joao Magalhaes . 2018 . Temporal Cross-Media Retrieval with Soft-Smoothing. In 2018 ACM Multimedia Conference on Multimedia Conference (MM '18) . ACM, New York, NY, USA, 1038--1046. https:\/\/doi.org\/10.1145\/3240508.3240665 10.1145\/3240508.3240665 David Semedo and Joao Magalhaes. 2018. Temporal Cross-Media Retrieval with Soft-Smoothing. In 2018 ACM Multimedia Conference on Multimedia Conference (MM '18). ACM, New York, NY, USA, 1038--1046. https:\/\/doi.org\/10.1145\/3240508.3240665"},{"key":"e_1_3_2_1_23_1","volume-title":"Very Deep Convolutional Networks for Large-Scale Image Recognition. CoRR","author":"Simonyan Karen","year":"2014","unstructured":"Karen Simonyan and Andrew Zisserman . 2014. Very Deep Convolutional Networks for Large-Scale Image Recognition. CoRR , Vol. abs\/ 1409 .1556 ( 2014 ). arxiv: 1409.1556 http:\/\/arxiv.org\/abs\/1409.1556 Karen Simonyan and Andrew Zisserman. 2014. Very Deep Convolutional Networks for Large-Scale Image Recognition. CoRR , Vol. abs\/1409.1556 (2014). arxiv: 1409.1556 http:\/\/arxiv.org\/abs\/1409.1556"},{"key":"e_1_3_2_1_24_1","volume-title":"Mach. Learn. Res.","volume":"6","author":"Tsochantaridis Ioannis","year":"2005","unstructured":"Ioannis Tsochantaridis , Thorsten Joachims , Thomas Hofmann , and Yasemin Altun . 2005 . Large Margin Methods for Structured and Interdependent Output Variables. J . Mach. Learn. Res. , Vol. 6 (Dec. 2005), 1453--1484. http:\/\/dl.acm.org\/citation.cfm?id=1046920.1088722 Ioannis Tsochantaridis, Thorsten Joachims, Thomas Hofmann, and Yasemin Altun. 2005. Large Margin Methods for Structured and Interdependent Output Variables. J. Mach. Learn. Res. , Vol. 6 (Dec. 2005), 1453--1484. http:\/\/dl.acm.org\/citation.cfm?id=1046920.1088722"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123326"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2505311"},{"key":"e_1_3_2_1_27_1","volume-title":"A Comprehensive Survey on Cross-modal Retrieval. CoRR","author":"Wang Kaiye","year":"2016","unstructured":"Kaiye Wang , Qiyue Yin , Wei Wang , Shu Wu , and Liang Wang . 2016c. A Comprehensive Survey on Cross-modal Retrieval. CoRR , Vol. abs\/ 1607 .06215 ( 2016 ). Kaiye Wang, Qiyue Yin, Wei Wang, Shu Wu, and Liang Wang. 2016c. A Comprehensive Survey on Cross-modal Retrieval. CoRR , Vol. abs\/1607.06215 (2016)."},{"key":"e_1_3_2_1_28_1","volume-title":"Learning Deep Structure-Preserving Image-Text Embeddings. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 5005--5013","author":"Wang L.","year":"2016","unstructured":"L. Wang , Y. Li , and S. Lazebnik . 2016b . Learning Deep Structure-Preserving Image-Text Embeddings. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 5005--5013 . https:\/\/doi.org\/10.1109\/CVPR. 2016 .541 10.1109\/CVPR.2016.541 L. Wang, Y. Li, and S. Lazebnik. 2016b. Learning Deep Structure-Preserving Image-Text Embeddings. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 5005--5013. https:\/\/doi.org\/10.1109\/CVPR.2016.541"},{"key":"e_1_3_2_1_29_1","volume-title":"Cross-Modal Retrieval With CNN Visual Features: A New Baseline","author":"Wei Yunchao","year":"2016","unstructured":"Yunchao Wei , Yao Zhao , Canyi Lu , Shikui Wei , Luoqi Liu , Zhenfeng Zhu , and Shuicheng Yan . 2016. Cross-Modal Retrieval With CNN Visual Features: A New Baseline . IEEE Transactions on Cybernetics ( 2016 ). Yunchao Wei, Yao Zhao, Canyi Lu, Shikui Wei, Luoqi Liu, Zhenfeng Zhu, and Shuicheng Yan. 2016. Cross-Modal Retrieval With CNN Visual Features: A New Baseline. IEEE Transactions on Cybernetics (2016)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240521"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2017.8019528"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3206025.3206033"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298966"},{"key":"e_1_3_2_1_34_1","volume-title":"Learning Query and Image Similarities with Ranking Canonical Correlation Analysis. In 2015 IEEE International Conference on Computer Vision (ICCV) . 28--36","author":"Yao T.","year":"2015","unstructured":"T. Yao , T. Mei , and C. W. Ngo . 2015 . Learning Query and Image Similarities with Ranking Canonical Correlation Analysis. In 2015 IEEE International Conference on Computer Vision (ICCV) . 28--36 . https:\/\/doi.org\/10.1109\/ICCV. 2015 .12 10.1109\/ICCV.2015.12 T. Yao, T. Mei, and C. W. Ngo. 2015. Learning Query and Image Similarities with Ranking Canonical Correlation Analysis. In 2015 IEEE International Conference on Computer Vision (ICCV) . 28--36. https:\/\/doi.org\/10.1109\/ICCV.2015.12"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2013.2276704"}],"event":{"name":"MM '19: The 27th ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Nice France","acronym":"MM '19"},"container-title":["Proceedings of the 27th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3343031.3351030","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3343031.3351030","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T23:13:11Z","timestamp":1750201991000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3343031.3351030"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,10,15]]},"references-count":35,"alternative-id":["10.1145\/3343031.3351030","10.1145\/3343031"],"URL":"https:\/\/doi.org\/10.1145\/3343031.3351030","relation":{},"subject":[],"published":{"date-parts":[[2019,10,15]]},"assertion":[{"value":"2019-10-15","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}