{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:25:55Z","timestamp":1750220755006,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":20,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,4,23]],"date-time":"2020-04-23T00:00:00Z","timestamp":1587600000000},"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":[[2020,4,23]]},"DOI":"10.1145\/3404555.3404610","type":"proceedings-article","created":{"date-parts":[[2020,8,20]],"date-time":"2020-08-20T17:01:06Z","timestamp":1597942866000},"page":"275-282","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Generalization or Instantiation?"],"prefix":"10.1145","author":[{"given":"Qibin","family":"Zheng","sequence":"first","affiliation":[{"name":"Army Engineering University of PLA, Nanjing, China"}]},{"given":"Ren","family":"Xiaoguang","sequence":"additional","affiliation":[{"name":"National Innovation Institute of Defense Technology, Beijing, China, Tianjin Artificial Intelligence Innovation Center, Tianjin, China"}]},{"given":"Yi","family":"Liu","sequence":"additional","affiliation":[{"name":"National Innovation Institute of Defense Technology, Beijing, China, Tianjin Artificial Intelligence Innovation Center, Tianjin, China"}]},{"given":"Wei","family":"Qin","sequence":"additional","affiliation":[{"name":"National Innovation Institute of Defense Technology, Beijing, China, Tianjin Artificial Intelligence Innovation Center, Tianjin, China"}]}],"member":"320","published-online":{"date-parts":[[2020,8,20]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2798607"},{"volume-title":"Image-Music-Text Hill and Wang","author":"Barthes R.","key":"e_1_3_2_1_2_1","unstructured":"Barthes , R. , 1978. The Rhetoric of the Image . In Image-Music-Text Hill and Wang , London , 32--51. Barthes, R., 1978. The Rhetoric of the Image. In Image-Music-Text Hill and Wang, London, 32--51."},{"volume-title":"Text and Image: A Critical Introduction to the Visual\/Verbal Divide","author":"Bateman J.","key":"e_1_3_2_1_3_1","unstructured":"Bateman , J. , 2014. Text and Image: A Critical Introduction to the Visual\/Verbal Divide . Routledge , New York . Bateman, J., 2014. Text and Image: A Critical Introduction to the Visual\/Verbal Divide. Routledge, New York."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"crossref","unstructured":"Cho K. Van Merri\u00ebnboer B. Gulcehre C. Bahdanau D. Bougares F. Schwenk H. and Bengio Y. 2014. Learning Phrase Representations Using RNN Encoder-Decoder for Statistical Machine Translation. In Empirical Methods on Natural Language Processing(EMNLP) ACL 1724--1734.  Cho K. Van Merri\u00ebnboer B. Gulcehre C. Bahdanau D. Bougares F. Schwenk H. and Bengio Y. 2014. Learning Phrase Representations Using RNN Encoder-Decoder for Statistical Machine Translation. In Empirical Methods on Natural Language Processing(EMNLP) ACL 1724--1734.","DOI":"10.3115\/v1\/D14-1179"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.18178\/ijmlc.2019.9.6.875"},{"volume-title":"Stack-Captioning: Coarse-to-Fine Learning for Image Captioning. In AAAI Conference on Artifcial Intelligence AAAI, 6837--6844","author":"Gu J.","key":"e_1_3_2_1_6_1","unstructured":"Gu , J. , Cai , J. , Wang , G. , and Chen , T ., 2018 . Stack-Captioning: Coarse-to-Fine Learning for Image Captioning. In AAAI Conference on Artifcial Intelligence AAAI, 6837--6844 . Gu, J., Cai, J., Wang, G., and Chen, T., 2018. Stack-Captioning: Coarse-to-Fine Learning for Image Captioning. In AAAI Conference on Artifcial Intelligence AAAI, 6837--6844."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/s13735-017-0142-y"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2598339"},{"volume-title":"International Conference on Learning Representations.","author":"Kingma D.P.","key":"e_1_3_2_1_9_1","unstructured":"Kingma , D.P. and Ba , J ., 2015. Adam: A method for stochastic optimization . In International Conference on Learning Representations. Kingma, D.P. and Ba, J., 2015. Adam: A method for stochastic optimization. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1108\/00220410310506303"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"crossref","unstructured":"Martinec R. and Salway A. 2005. A System for Image-text Relations in New (and old) Media. Visual communication 4 3 337--371.  Martinec R. and Salway A. 2005. A System for Image-text Relations in New (and old) Media. Visual communication 4 3 337--371.","DOI":"10.1177\/1470357205055928"},{"volume-title":"European Conference on Information Retrieval Springer, 711--725","author":"Otto C.","key":"e_1_3_2_1_12_1","unstructured":"Otto , C. , Holzki , S. , and Ewerth , R ., 2019. \"Is this an example image?\" -- Predicting the Relative Abstractness Level of Image and Text . In European Conference on Information Retrieval Springer, 711--725 . Otto, C., Holzki, S., and Ewerth, R., 2019. \"Is this an example image?\" -- Predicting the Relative Abstractness Level of Image and Text. In European Conference on Information Retrieval Springer, 711--725."},{"volume-title":"IEEE Conference on Computer Vision and Pattern Recognition IEEE, 1505--1514","author":"Qiao T.","key":"e_1_3_2_1_13_1","unstructured":"Qiao , T. , Zhang , J. , Xu , D. , and Tao , D ., 2019. MirrorGAN: Learning Text-to-image Generation by Redescription . In IEEE Conference on Computer Vision and Pattern Recognition IEEE, 1505--1514 . Qiao, T., Zhang, J., Xu, D., and Tao, D., 2019. MirrorGAN: Learning Text-to-image Generation by Redescription. In IEEE Conference on Computer Vision and Pattern Recognition IEEE, 1505--1514."},{"key":"e_1_3_2_1_14_1","volume-title":"Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks. In Proceedings of the International Conference on Learning Representations","author":"Radford A.","year":"2016","unstructured":"Radford , A. , Metz , L. , and Chintala , S ., 2016 . Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks. In Proceedings of the International Conference on Learning Representations ( San Juan, Puerto Rico , May 2-4 2016 ). Radford, A., Metz, L., and Chintala, S., 2016. Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks. In Proceedings of the International Conference on Learning Representations (San Juan, Puerto Rico, May 2-4 2016)."},{"key":"e_1_3_2_1_15_1","volume-title":"NAACL Hlt 2010 Workshop on Creating Speech and Language Data with Amazon's Mechanical Turk NAACL, 139--147","author":"Rashtchian C.","year":"1866","unstructured":"Rashtchian , C. , Young , P. , Hodosh , M. , and Hockenmaier , J ., 2010. Collecting Image Annotations Using Amazon's Mechanical Turk . In NAACL Hlt 2010 Workshop on Creating Speech and Language Data with Amazon's Mechanical Turk NAACL, 139--147 . 10.5555\/ 1866 696.1866717 Rashtchian, C., Young, P., Hodosh, M., and Hockenmaier, J., 2010. Collecting Image Annotations Using Amazon's Mechanical Turk. In NAACL Hlt 2010 Workshop on Creating Speech and Language Data with Amazon's Mechanical Turk NAACL, 139--147. 10.5555\/1866696.1866717"},{"volume-title":"Self-Critical Sequence Training for Image Captioning. In IEEE Conference on Computer Vision and Pattern Recognition IEEE, 7008--7024","author":"Rennie S.J.","key":"e_1_3_2_1_16_1","unstructured":"Rennie , S.J. , Marcheret , E. , Mroueh , Y. , Ross , J. , and Goel , V ., 2017 . Self-Critical Sequence Training for Image Captioning. In IEEE Conference on Computer Vision and Pattern Recognition IEEE, 7008--7024 . Rennie, S.J., Marcheret, E., Mroueh, Y., Ross, J., and Goel, V., 2017. Self-Critical Sequence Training for Image Captioning. In IEEE Conference on Computer Vision and Pattern Recognition IEEE, 7008--7024."},{"key":"e_1_3_2_1_17_1","volume-title":"International Systemic Functional Congress Springer, 1165--1205","author":"Unsworth L.","year":"2007","unstructured":"Unsworth , L. , 2007 . Image\/text Relations and Intersemiosis: Towards Multimodal Text Description for Multiliteracies Education . In International Systemic Functional Congress Springer, 1165--1205 . Unsworth, L., 2007. Image\/text Relations and Intersemiosis: Towards Multimodal Text Description for Multiliteracies Education. In International Systemic Functional Congress Springer, 1165--1205."},{"volume-title":"IEEE Conference on Computer Vision and Pattern Recognition IEEE, 1316--1324","author":"Xu T.","key":"e_1_3_2_1_18_1","unstructured":"Xu , T. , Zhang , P. , Huang , Q. , Zhang , H. , Gan , Z. , Huang , X. , and He , X ., 2018. Attngan: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks . In IEEE Conference on Computer Vision and Pattern Recognition IEEE, 1316--1324 . Xu, T., Zhang, P., Huang, Q., Zhang, H., Gan, Z., Huang, X., and He, X., 2018. Attngan: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks. In IEEE Conference on Computer Vision and Pattern Recognition IEEE, 1316--1324."},{"volume-title":"IEEE International Conference on Computer Vision IEEE, 5907--5915","author":"Zhang H.","key":"e_1_3_2_1_19_1","unstructured":"Zhang , H. , Xu , T. , Li , H. , Zhang , S. , Wang , X. , Huang , X. , and Metaxas , D.N ., 2017. Stackgan: Text to Photo-Realistic Image Synthesis with Stacked Generative Adversarial Networks . In IEEE International Conference on Computer Vision IEEE, 5907--5915 . Zhang, H., Xu, T., Li, H., Zhang, S., Wang, X., Huang, X., and Metaxas, D.N., 2017. Stackgan: Text to Photo-Realistic Image Synthesis with Stacked Generative Adversarial Networks. In IEEE International Conference on Computer Vision IEEE, 5907--5915."},{"volume-title":"Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks. In IEEE International Conference on Computer Vision IEEE, 2223--2232","author":"Zhu J.-Y.","key":"e_1_3_2_1_20_1","unstructured":"Zhu , J.-Y. , Park , T. , Isola , P. , and Efros , A.A ., 2017 . Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks. In IEEE International Conference on Computer Vision IEEE, 2223--2232 . Zhu, J.-Y., Park, T., Isola, P., and Efros, A.A., 2017. Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks. In IEEE International Conference on Computer Vision IEEE, 2223--2232."}],"event":{"name":"ICCAI '20: 2020 6th International Conference on Computing and Artificial Intelligence","sponsor":["University of Tsukuba University of Tsukuba"],"location":"Tianjin China","acronym":"ICCAI '20"},"container-title":["Proceedings of the 2020 6th International Conference on Computing and Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3404555.3404610","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3404555.3404610","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T22:38:59Z","timestamp":1750199939000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3404555.3404610"}},"subtitle":["Estimating the Relative Abstractness between Images and Text"],"short-title":[],"issued":{"date-parts":[[2020,4,23]]},"references-count":20,"alternative-id":["10.1145\/3404555.3404610","10.1145\/3404555"],"URL":"https:\/\/doi.org\/10.1145\/3404555.3404610","relation":{},"subject":[],"published":{"date-parts":[[2020,4,23]]},"assertion":[{"value":"2020-08-20","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}