{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T01:33:59Z","timestamp":1777599239211,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":39,"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":"National Natural Science Foundation of China","award":["61571269"],"award-info":[{"award-number":["61571269"]}]},{"name":"National Key R&D Program of China","award":["2018YFC0806900"],"award-info":[{"award-number":["2018YFC0806900"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2019,10,15]]},"DOI":"10.1145\/3343031.3351055","type":"proceedings-article","created":{"date-parts":[[2019,10,21]],"date-time":"2019-10-21T16:32:26Z","timestamp":1571675546000},"page":"1749-1757","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":58,"title":["Cross-Modal Image-Text Retrieval with Semantic Consistency"],"prefix":"10.1145","author":[{"given":"Hui","family":"Chen","sequence":"first","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guiguang","family":"Ding","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zijia","family":"Lin","sequence":"additional","affiliation":[{"name":"Microsoft Research, Beijng, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sicheng","family":"Zhao","sequence":"additional","affiliation":[{"name":"University of California, Berkeley, Berkeley, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jungong","family":"Han","sequence":"additional","affiliation":[{"name":"University of Warwick, Coventry, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2019,10,15]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00051"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.5555\/3298239.3298253"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"e_1_3_2_1_5_1","unstructured":"Jan K Chorowski Dzmitry Bahdanau Dmitriy Serdyuk Kyunghyun Cho and Yoshua Bengio. 2015. Attention-based models for speech recognition. In Advances in neural information processing systems. 577--585.  Jan K Chorowski Dzmitry Bahdanau Dmitriy Serdyuk Kyunghyun Cho and Yoshua Bengio. 2015. Attention-based models for speech recognition. In Advances in neural information processing systems. 577--585."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2607421"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.201"},{"key":"e_1_3_2_1_9_1","volume-title":"Jamie Ryan Kiros, and Sanja Fidler","author":"Faghri Fartash","year":"2017","unstructured":"Fartash Faghri , David J Fleet , Jamie Ryan Kiros, and Sanja Fidler . 2017 . Vse Fartash Faghri, David J Fleet, Jamie Ryan Kiros, and Sanja Fidler. 2017. Vse"},{"key":"e_1_3_2_1_10_1","volume-title":"Improving visual-semantic embeddings with hard negatives. arXiv preprint arXiv:1707.05612","year":"2017","unstructured":": Improving visual-semantic embeddings with hard negatives. arXiv preprint arXiv:1707.05612 ( 2017 ). : Improving visual-semantic embeddings with hard negatives. arXiv preprint arXiv:1707.05612 (2017)."},{"key":"e_1_3_2_1_11_1","volume-title":"et almbox","author":"Frome Andrea","year":"2013","unstructured":"Andrea Frome , Greg S Corrado , Jon Shlens , Samy Bengio , Jeff Dean , Tomas Mikolov , et almbox . 2013 . Devise : A deep visual-semantic embedding model. In Advances in neural information processing systems. 2121--2129. Andrea Frome, Greg S Corrado, Jon Shlens, Samy Bengio, Jeff Dean, Tomas Mikolov, et almbox. 2013. Devise: A deep visual-semantic embedding model. In Advances in neural information processing systems. 2121--2129."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00750"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/s13735-017-0142-y"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.767"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00645"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/E17-2068"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"e_1_3_2_1_19_1","volume-title":"Unifying visual-semantic embeddings with multimodal neural language models. arXiv preprint arXiv:1411.2539","author":"Kiros Ryan","year":"2014","unstructured":"Ryan Kiros , Ruslan Salakhutdinov , and Richard S Zemel . 2014. Unifying visual-semantic embeddings with multimodal neural language models. arXiv preprint arXiv:1411.2539 ( 2014 ). Ryan Kiros, Ruslan Salakhutdinov, and Richard S Zemel. 2014. Unifying visual-semantic embeddings with multimodal neural language models. arXiv preprint arXiv:1411.2539 (2014)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"e_1_3_2_1_22_1","volume-title":"Cross-view retrieval via probability-based semantics-preserving hashing","author":"Lin Zijia","year":"2016","unstructured":"Zijia Lin , Guiguang Ding , Jungong Han , and Jianmin Wang . 2016. Cross-view retrieval via probability-based semantics-preserving hashing . IEEE transactions on cybernetics , Vol. 47 , 12 ( 2016 ), 4342--4355. Zijia Lin, Guiguang Ding, Jungong Han, and Jianmin Wang. 2016. Cross-view retrieval via probability-based semantics-preserving hashing. IEEE transactions on cybernetics , Vol. 47, 12 (2016), 4342--4355."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299011"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.301"},{"key":"e_1_3_2_1_25_1","unstructured":"Tomas Mikolov Ilya Sutskever Kai Chen Greg S Corrado and Jeff Dean. 2013. Distributed representations of words and phrases and their compositionality. In Advances in neural information processing systems. 3111--3119.  Tomas Mikolov Ilya Sutskever Kai Chen Greg S Corrado and Jeff Dean. 2013. Distributed representations of words and phrases and their compositionality. In Advances in neural information processing systems. 3111--3119."},{"key":"e_1_3_2_1_26_1","volume-title":"Proceedings of the 26th ACM International Conference on Multimedia (MM '18). 1856","author":"Mithun Niluthpol Chowdhury","year":"1864","unstructured":"Niluthpol Chowdhury Mithun , Rameswar Panda , Evangelos E. Papalexakis , and Amit K . Roy-Chowdhury. 2018. Webly Supervised Joint Embedding for Cross-Modal Image-Text Retrieval . In Proceedings of the 26th ACM International Conference on Multimedia (MM '18). 1856 -- 1864 . Niluthpol Chowdhury Mithun, Rameswar Panda, Evangelos E. Papalexakis, and Amit K. Roy-Chowdhury. 2018. Webly Supervised Joint Embedding for Cross-Modal Image-Text Retrieval. In Proceedings of the 26th ACM International Conference on Multimedia (MM '18). 1856--1864."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.232"},{"key":"e_1_3_2_1_28_1","volume-title":"Hierarchical Multimodal LSTM for Dense Visual-Semantic Embedding. In 2017 IEEE International Conference on Computer Vision (ICCV) . 1899--1907","author":"Niu Z.","year":"2017","unstructured":"Z. Niu , M. Zhou , L. Wang , X. Gao , and G. Hua . 2017 . Hierarchical Multimodal LSTM for Dense Visual-Semantic Embedding. In 2017 IEEE International Conference on Computer Vision (ICCV) . 1899--1907 . https:\/\/doi.org\/10.1109\/ICCV. 2017 .208 10.1109\/ICCV.2017.208 Z. Niu, M. Zhou , L. Wang, X. Gao, and G. Hua. 2017. Hierarchical Multimodal LSTM for Dense Visual-Semantic Embedding. In 2017 IEEE International Conference on Computer Vision (ICCV) . 1899--1907. https:\/\/doi.org\/10.1109\/ICCV.2017.208"},{"key":"e_1_3_2_1_29_1","unstructured":"Adam Paszke Sam Gross Soumith Chintala Gregory Chanan Edward Yang Zachary DeVito Zeming Lin Alban Desmaison Luca Antiga and Adam Lerer. 2017. Automatic differentiation in PyTorch. (2017).  Adam Paszke Sam Gross Soumith Chintala Gregory Chanan Edward Yang Zachary DeVito Zeming Lin Alban Desmaison Luca Antiga and Adam Lerer. 2017. Automatic differentiation in PyTorch. (2017)."},{"key":"e_1_3_2_1_30_1","volume-title":"CM-GANs: Cross-modal Generative Adversarial Networks for Common Representation Learning. arXiv preprint arXiv:1710.05106","author":"Peng Yuxin","year":"2017","unstructured":"Yuxin Peng , Jinwei Qi , and Yuxin Yuan . 2017. CM-GANs: Cross-modal Generative Adversarial Networks for Common Representation Learning. arXiv preprint arXiv:1710.05106 ( 2017 ). Yuxin Peng, Jinwei Qi, and Yuxin Yuan. 2017. CM-GANs: Cross-modal Generative Adversarial Networks for Common Representation Learning. arXiv preprint arXiv:1710.05106 (2017)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"e_1_3_2_1_32_1","unstructured":"Shaoqing Ren Kaiming He Ross Girshick and Jian Sun. 2015. Faster r-cnn: Towards real-time object detection with region proposal networks. In Advances in neural information processing systems. 91--99.  Shaoqing Ren Kaiming He Ross Girshick and Jian Sun. 2015. Faster r-cnn: Towards real-time object detection with region proposal networks. In Advances in neural information processing systems. 91--99."},{"key":"e_1_3_2_1_33_1","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N Gomez \u0141ukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. In Advances in Neural Information Processing Systems. 5998--6008.  Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N Gomez \u0141ukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. In Advances in Neural Information Processing Systems. 5998--6008."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123326"},{"key":"e_1_3_2_1_35_1","volume-title":"Bidirectional Retrieval Made Simple. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) .","author":"Wehrmann J\u00f4natas","unstructured":"J\u00f4natas Wehrmann and Rodrigo C. Barros . 2018 . Bidirectional Retrieval Made Simple. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) . J\u00f4natas Wehrmann and Rodrigo C. Barros. 2018. Bidirectional Retrieval Made Simple. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) ."},{"key":"e_1_3_2_1_36_1","unstructured":"Kelvin Xu Jimmy Ba Ryan Kiros Kyunghyun Cho Aaron Courville Ruslan Salakhudinov Rich Zemel and Yoshua Bengio. 2015. Show Attend and Tell: Neural Image Caption Generation with Visual Attention. In ICML . 2048--2057.  Kelvin Xu Jimmy Ba Ryan Kiros Kyunghyun Cho Aaron Courville Ruslan Salakhudinov Rich Zemel and Yoshua Bengio. 2015. Show Attend and Tell: Neural Image Caption Generation with Visual Attention. In ICML . 2048--2057."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"crossref","unstructured":"Xin Zhao Guiguang Ding Yuchen Guo Jungong Han and Yue Gao. 2017. TUCH: turning cross-view hashing into single-view hashing via generative adversarial nets. IJCAI.  Xin Zhao Guiguang Ding Yuchen Guo Jungong Han and Yue Gao. 2017. TUCH: turning cross-view hashing into single-view hashing via generative adversarial nets. IJCAI.","DOI":"10.24963\/ijcai.2017\/491"},{"key":"e_1_3_2_1_38_1","volume-title":"Dual-Path Convolutional Image-Text Embedding with Instance Loss. arXiv preprint arXiv:1711.05535","author":"Zheng Zhedong","year":"2017","unstructured":"Zhedong Zheng , Liang Zheng , Michael Garrett , Yi Yang , and Yi-Dong Shen . 2017. Dual-Path Convolutional Image-Text Embedding with Instance Loss. arXiv preprint arXiv:1711.05535 ( 2017 ). Zhedong Zheng, Liang Zheng, Michael Garrett, Yi Yang, and Yi-Dong Shen. 2017. Dual-Path Convolutional Image-Text Embedding with Instance Loss. arXiv preprint arXiv:1711.05535 (2017)."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/2600428.2609610"}],"event":{"name":"MM '19: The 27th ACM International Conference on Multimedia","location":"Nice France","acronym":"MM '19","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 27th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3343031.3351055","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3343031.3351055","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T23:13:12Z","timestamp":1750201992000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3343031.3351055"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,10,15]]},"references-count":39,"alternative-id":["10.1145\/3343031.3351055","10.1145\/3343031"],"URL":"https:\/\/doi.org\/10.1145\/3343031.3351055","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"}}]}}