{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T12:53:38Z","timestamp":1770296018253,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":37,"publisher":"ACM","license":[{"start":{"date-parts":[[2015,6,22]],"date-time":"2015-06-22T00:00:00Z","timestamp":1434931200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Basic Research Program of China","award":["2012CB316304"],"award-info":[{"award-number":["2012CB316304"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["91338202,61203277,91438105"],"award-info":[{"award-number":["91338202,61203277,91438105"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2015,6,22]]},"DOI":"10.1145\/2671188.2749341","type":"proceedings-article","created":{"date-parts":[[2015,6,22]],"date-time":"2015-06-22T15:37:08Z","timestamp":1434987428000},"page":"347-354","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":34,"title":["Image-Text Cross-Modal Retrieval via Modality-Specific Feature Learning"],"prefix":"10.1145","author":[{"given":"Jian","family":"Wang","sequence":"first","affiliation":[{"name":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}]},{"given":"Yonghao","family":"He","sequence":"additional","affiliation":[{"name":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}]},{"given":"Cuicui","family":"Kang","sequence":"additional","affiliation":[{"name":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}]},{"given":"Shiming","family":"Xiang","sequence":"additional","affiliation":[{"name":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}]},{"given":"Chunhong","family":"Pan","sequence":"additional","affiliation":[{"name":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2015,6,22]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.5555\/1886063.1886114"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.5555\/944919.944937"},{"key":"e_1_3_2_1_3_1","volume-title":"Proceedings of the Annual Meeting of the Association for Computational Linguistics","author":"Blunsom P.","year":"2014","unstructured":"P. Blunsom , E. Grefenstette , and N. Kalchbrenner . A convolutional neural network for modelling sentences . In Proceedings of the Annual Meeting of the Association for Computational Linguistics , 2014 . P. Blunsom, E. Grefenstette, and N. Kalchbrenner. A convolutional neural network for modelling sentences. In Proceedings of the Annual Meeting of the Association for Computational Linguistics, 2014."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/1646396.1646452"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654902"},{"key":"e_1_3_2_1_7_1","first-page":"13","volume-title":"International Workshop OntoImage","author":"Grubinger M.","year":"2006","unstructured":"M. Grubinger , P. Clough , H. Muller , and T. Deselaers . The iapr tc-12 benchmark: a new evaluation resource for visual information systems . In International Workshop OntoImage , pages 13 -- 23 , 2006 . M. Grubinger, P. Clough, H. Muller, and T. Deselaers. The iapr tc-12 benchmark: a new evaluation resource for visual information systems. In International Workshop OntoImage, pages 13--23, 2006."},{"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":"10.1126\/science.1127647"},{"key":"e_1_3_2_1_10_1","first-page":"1607","volume-title":"Advances in Neural Information Processing Systems","author":"Hinton G.","year":"2009","unstructured":"G. Hinton and R. Salakhutdinov . Replicated softmax: an undirected topic model . In Advances in Neural Information Processing Systems , pages 1607 -- 1614 , 2009 . G. Hinton and R. Salakhutdinov. Replicated softmax: an undirected topic model. In Advances in Neural Information Processing Systems, pages 1607--1614, 2009."},{"key":"e_1_3_2_1_11_1","first-page":"2042","volume-title":"Advances in Neural Information Processing Systems","author":"Hu B.","year":"2014","unstructured":"B. Hu , Z. Lu , H. Li , and Q. Chen . Convolutional neural network architectures for matching natural language sentences . In Advances in Neural Information Processing Systems , pages 2042 -- 2050 , 2014 . B. Hu, Z. Lu, H. Li, and Q. Chen. Convolutional neural network architectures for matching natural language sentences. In Advances in Neural Information Processing Systems, pages 2042--2050, 2014."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/2502081.2502283"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/2505515.2505665"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654889"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1181"},{"key":"e_1_3_2_1_16_1","volume-title":"International Conference on Machine Learning","author":"Kiros R.","year":"2014","unstructured":"R. Kiros , R. Salakhutdinov , and R. Zemel . Multimodal neural language models . In International Conference on Machine Learning , 2014 . R. Kiros, R. Salakhutdinov, and R. Zemel. Multimodal neural language models. In International Conference on Machine Learning, 2014."},{"key":"e_1_3_2_1_17_1","first-page":"1097","volume-title":"Advances in Neural Information Processing Systems","author":"Krizhevsky A.","year":"2012","unstructured":"A. Krizhevsky , I. Sutskever , and G. Hinton . Imagenet classification with deep convolutional neural networks . In Advances in Neural Information Processing Systems , pages 1097 -- 1105 , 2012 . A. Krizhevsky, I. Sutskever, and G. Hinton. Imagenet classification with deep convolutional neural networks. In Advances in Neural Information Processing Systems, pages 1097--1105, 2012."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000029664.99615.94"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/2484028.2484039"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/76.927424"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273577"},{"key":"e_1_3_2_1_23_1","first-page":"689","volume-title":"International Conference on Machine Learning","author":"Ngiam J.","year":"2011","unstructured":"J. Ngiam , A. Khosla , M. Kim , J. Nam , H. Lee , and A. Ng . Multimodal deep learning . In International Conference on Machine Learning , pages 689 -- 696 , 2011 . J. Ngiam, A. Khosla, M. Kim, J. Nam, H. Lee, and A. Ng. Multimodal deep learning. In International Conference on Machine Learning, pages 689--696, 2011."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1011139631724"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1873987"},{"key":"e_1_3_2_1_26_1","volume-title":"Cnn features off-the-shelf: an astounding baseline for recognition. arXiv preprint arXiv:1403.6382","author":"Razavian A.","year":"2014","unstructured":"A. Razavian , H. Azizpour , J. Sullivan , and S. Carlsson . Cnn features off-the-shelf: an astounding baseline for recognition. arXiv preprint arXiv:1403.6382 , 2014 . A. Razavian, H. Azizpour, J. Sullivan, and S. Carlsson. Cnn features off-the-shelf: an astounding baseline for recognition. arXiv preprint arXiv:1403.6382, 2014."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/11752790_2"},{"key":"e_1_3_2_1_28_1","first-page":"448","volume-title":"International Conference on Artificial Intelligence and Statistics","author":"Salakhutdinov R.","year":"2009","unstructured":"R. Salakhutdinov and G. Hinton . Deep boltzmann machines . In International Conference on Artificial Intelligence and Statistics , pages 448 -- 455 , 2009 . R. Salakhutdinov and G. Hinton. Deep boltzmann machines. In International Conference on Artificial Intelligence and Statistics, pages 448--455, 2009."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995350"},{"key":"e_1_3_2_1_30_1","first-page":"2222","volume-title":"Advances in Neural Information Processing Systems","author":"Srivastava N.","year":"2012","unstructured":"N. Srivastava and R. Salakhutdinov . Multimodal learning with deep boltzmann machines . In Advances in Neural Information Processing Systems , pages 2222 -- 2230 , 2012 . N. Srivastava and R. Salakhutdinov. Multimodal learning with deep boltzmann machines. In Advances in Neural Information Processing Systems, pages 2222--2230, 2012."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.446"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.261"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.14778\/2732296.2732301"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/2502081.2502097"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/2461466.2461497"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-27355-1_30"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2007.911822"}],"event":{"name":"ICMR '15: International Conference on Multimedia Retrieval","location":"Shanghai China","acronym":"ICMR '15","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 5th ACM on International Conference on Multimedia Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2671188.2749341","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2671188.2749341","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T06:12:35Z","timestamp":1750227155000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2671188.2749341"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,6,22]]},"references-count":37,"alternative-id":["10.1145\/2671188.2749341","10.1145\/2671188"],"URL":"https:\/\/doi.org\/10.1145\/2671188.2749341","relation":{},"subject":[],"published":{"date-parts":[[2015,6,22]]},"assertion":[{"value":"2015-06-22","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}