{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T06:16:49Z","timestamp":1775283409903,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":59,"publisher":"ACM","license":[{"start":{"date-parts":[[2018,2,2]],"date-time":"2018-02-02T00:00:00Z","timestamp":1517529600000},"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":[[2018,2,2]]},"DOI":"10.1145\/3159652.3159735","type":"proceedings-article","created":{"date-parts":[[2018,2,6]],"date-time":"2018-02-06T18:12:23Z","timestamp":1517940743000},"page":"28-36","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":11,"title":["Deep Neural Architecture for Multi-Modal Retrieval based on Joint Embedding Space for Text and Images"],"prefix":"10.1145","author":[{"given":"Saeid","family":"Balaneshin-kordan","sequence":"first","affiliation":[{"name":"Wayne State University, Detroit, MI, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexander","family":"Kotov","sequence":"additional","affiliation":[{"name":"Wayne State University, Detroit, MI, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2018,2,2]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/2746539.2746553"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3077136.3080764"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939812"},{"key":"e_1_3_2_1_4_1","volume-title":"Transitive Hashing Network for Heterogeneous Multimedia Retrieval. arXiv preprint arXiv:1608.04307","author":"Cao Zhangjie","year":"2016"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/1646396.1646452"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","unstructured":"Guillem Collell Ted Zhang and Marie-Francine Moens. 2017. Imagined Visual Representations as Multimodal Embeddings Proceedings of AAAI. 4378--4384.  Guillem Collell Ted Zhang and Marie-Francine Moens. 2017. Imagined Visual Representations as Multimodal Embeddings Proceedings of AAAI. 4378--4384.","DOI":"10.1609\/aaai.v31i1.11155"},{"key":"e_1_3_2_1_7_1","volume-title":"Indexing by latent semantic analysis. Journal of the Association for Information Science and Technology","author":"Deerwester Scott","year":"1990"},{"key":"e_1_3_2_1_8_1","volume-title":"Imagenet: A large-scale hierarchical image database Proceedings of IEEE CVPR. 248--255.","author":"Deng Jia","year":"2009"},{"key":"e_1_3_2_1_9_1","volume-title":"Query expansion with locally-trained word embeddings. arXiv preprint arXiv:1605.07891","author":"Diaz Fernando","year":"2016"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298754"},{"key":"e_1_3_2_1_11_1","volume-title":"Proceedings of NIPS. 2121--2129","author":"Frome Andrea","year":"2013"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/2766462.2767780"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0658-4"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"crossref","unstructured":"Yunchao Gong Liwei Wang Micah Hodosh Julia Hockenmaier and Svetlana Lazebnik. 2014. Improving image-sentence embeddings using large weakly annotated photo collections Proceedings of ECCV. 529--545.  Yunchao Gong Liwei Wang Micah Hodosh Julia Hockenmaier and Svetlana Lazebnik. 2014. Improving image-sentence embeddings using large weakly annotated photo collections Proceedings of ECCV. 529--545.","DOI":"10.1007\/978-3-319-10593-2_35"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/2983323.2983769"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.5555\/2283516.2283615"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1162\/0899766042321814"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1032"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.5555\/2566972.2566993"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/2505515.2505665"},{"key":"e_1_3_2_1_23_1","volume-title":"Deep Cross-Modal Hashing. arXiv preprint arXiv:1602.02255","author":"Jiang Qing-Yuan","year":"2016"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"crossref","unstructured":"Andrej Karpathy and Li Fei-Fei. 2015. Deep visual-semantic alignments for generating image descriptions Proceedings of IEEE CVPR. 3128--3137.  Andrej Karpathy and Li Fei-Fei. 2015. Deep visual-semantic alignments for generating image descriptions Proceedings of IEEE CVPR. 3128--3137.","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"e_1_3_2_1_25_1","unstructured":"Andrej Karpathy Armand Joulin and Fei Fei Li. 2014. Deep fragment embeddings for bidirectional image sentence mapping Proceedings of NIPS. 1889--1897.   Andrej Karpathy Armand Joulin and Fei Fei Li. 2014. Deep fragment embeddings for bidirectional image sentence mapping Proceedings of NIPS. 1889--1897."},{"key":"e_1_3_2_1_26_1","volume-title":"Proceedings of ICML. 595--603","author":"Kiros Ryan","year":"2014"},{"key":"e_1_3_2_1_27_1","volume-title":"Unifying visual-semantic embeddings with multimodal neural language models. arXiv preprint arXiv:1411.2539","author":"Kiros Ryan","year":"2014"},{"key":"e_1_3_2_1_28_1","volume-title":"Reddy","author":"Kotov Alexander","year":"2015"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/2487788.2487861"},{"key":"e_1_3_2_1_30_1","volume-title":"Hinton","author":"Krizhevsky Alex","year":"2012"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/2983323.2983876"},{"key":"e_1_3_2_1_32_1","volume-title":"Nghia The Pham, and Marco Baroni","author":"Lazaridou Angeliki","year":"2015"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/2911451.2911493"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.301"},{"key":"e_1_3_2_1_36_1","volume-title":"Yuille","author":"Mao Junhua","year":"2014"},{"key":"e_1_3_2_1_37_1","unstructured":"Tomas Mikolov Ilya Sutskever Kai Chen Greg S. Corrado and Jeff Dean. 2013. Distributed representations of words and phrases and their compositionality Proceedings of NIPS. 3111--3119.   Tomas Mikolov Ilya Sutskever Kai Chen Greg S. Corrado and Jeff Dean. 2013. Distributed representations of words and phrases and their compositionality Proceedings of NIPS. 3111--3119."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3038912.3052579"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/2766462.2767738"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/2661829.2661935"},{"key":"e_1_3_2_1_43_1","volume-title":"Proceedings of NIPS. 935--943","author":"Socher Richard","year":"2013"},{"key":"e_1_3_2_1_44_1","volume-title":"Ng","author":"Socher Richard","year":"2014"},{"key":"e_1_3_2_1_45_1","volume-title":"Proceedings of NIPS. 2377--2385","author":"Srivastava Rupesh K.","year":"2015"},{"key":"e_1_3_2_1_46_1","volume-title":"inception-resnet and the impact of residual connections on learning. arXiv preprint arXiv:1602.07261","author":"Szegedy Christian","year":"2016"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"crossref","unstructured":"Christian Szegedy Vincent Vanhoucke Sergey Ioffe Jonathon Shlens and Zbigniew Wojna. 2016. Rethinking the inception architecture for computer vision Proceedings of IEEE CVPR. 2818--2826.  Christian Szegedy Vincent Vanhoucke Sergey Ioffe Jonathon Shlens and Zbigniew Wojna. 2016. Rethinking the inception architecture for computer vision Proceedings of IEEE CVPR. 2818--2826.","DOI":"10.1109\/CVPR.2016.308"},{"key":"e_1_3_2_1_48_1","volume-title":"Proceedings of ICLR","author":"Tan Ming","year":"2016"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2587640"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/2766462.2767752"},{"key":"e_1_3_2_1_51_1","unstructured":"Di Wang and Eric Nyberg. 2015. A long short-term memory model for answer sentence selection in question answering Proceedings of ACL. 707--712.  Di Wang and Eric Nyberg. 2015. A long short-term memory model for answer sentence selection in question answering Proceedings of ACL. 707--712."},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"crossref","unstructured":"Liwei Wang Yin Li and Svetlana Lazebnik. 2016. Learning deep structure-preserving image-text embeddings Proceedings of IEEE CVPR. 5005--5013.  Liwei Wang Yin Li and Svetlana Lazebnik. 2016. Learning deep structure-preserving image-text embeddings Proceedings of IEEE CVPR. 5005--5013.","DOI":"10.1109\/CVPR.2016.541"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00778-015-0391-4"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/1148170.1148204"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/2623330.2623688"},{"key":"e_1_3_2_1_56_1","first-page":"449","article-title":"Cross-modal retrieval with cnn visual features: A new baseline","volume":"47","author":"Wei Yunchao","year":"2016","journal-title":"IEEE Transactions on Cybernetics"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-010-5198-3"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2013.2291214"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1145\/3077136.3080831"}],"event":{"name":"WSDM 2018: The Eleventh ACM International Conference on Web Search and Data Mining","location":"Marina Del Rey CA USA","acronym":"WSDM 2018","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data","SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the Eleventh ACM International Conference on Web Search and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3159652.3159735","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3159652.3159735","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T02:26:12Z","timestamp":1750213572000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3159652.3159735"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,2,2]]},"references-count":59,"alternative-id":["10.1145\/3159652.3159735","10.1145\/3159652"],"URL":"https:\/\/doi.org\/10.1145\/3159652.3159735","relation":{},"subject":[],"published":{"date-parts":[[2018,2,2]]},"assertion":[{"value":"2018-02-02","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}