{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T20:46:04Z","timestamp":1743021964808,"version":"3.40.3"},"publisher-location":"Cham","reference-count":30,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030377335"},{"type":"electronic","value":"9783030377342"}],"license":[{"start":{"date-parts":[[2019,12,24]],"date-time":"2019-12-24T00:00:00Z","timestamp":1577145600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-37734-2_55","type":"book-chapter","created":{"date-parts":[[2019,12,26]],"date-time":"2019-12-26T19:03:00Z","timestamp":1577386980000},"page":"681-693","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Multi-hop Interactive Cross-Modal Retrieval"],"prefix":"10.1007","author":[{"given":"Xuecheng","family":"Ning","sequence":"first","affiliation":[]},{"given":"Xiaoshan","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Changsheng","family":"Xu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,12,24]]},"reference":[{"issue":"3","key":"55_CR1","doi-asserted-by":"publisher","first-page":"179","DOI":"10.1007\/BF00393937","volume":"3","author":"P Aigrain","year":"1996","unstructured":"Aigrain, P., Zhang, H., Petkovic, D.: Content-based representation and retrieval of visual media: a state-of-the-art review. Multimedia Tools Appl. 3(3), 179\u2013202 (1996)","journal-title":"Multimedia Tools Appl."},{"doi-asserted-by":"crossref","unstructured":"Anderson, P., et al.: Bottom-up and top-down attention for image captioning and visual question answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6077\u20136086 (2018)","key":"55_CR2","DOI":"10.1109\/CVPR.2018.00636"},{"unstructured":"Andrew, G., Arora, R., Bilmes, J., Livescu, K.: Deep canonical correlation analysis. In: International Conference on Machine Learning, pp. 1247\u20131255 (2013)","key":"55_CR3"},{"doi-asserted-by":"crossref","unstructured":"Cao, Y., Long, M., Wang, J., Yang, Q., Yu, P.S.: Deep visual-semantic hashing for cross-modal retrieval. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1445\u20131454. ACM (2016)","key":"55_CR4","DOI":"10.1145\/2939672.2939812"},{"doi-asserted-by":"crossref","unstructured":"Cho, K., et al.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv preprint \narXiv:1406.1078\n\n (2014)","key":"55_CR5","DOI":"10.3115\/v1\/D14-1179"},{"issue":"Dec","key":"55_CR6","first-page":"651","volume":"3","author":"DR Dooly","year":"2002","unstructured":"Dooly, D.R., Zhang, Q., Goldman, S.A., Amar, R.A.: Multiple-instance learning of real-valued data. J. Mach. Learn. Res. 3(Dec), 651\u2013678 (2002)","journal-title":"J. Mach. Learn. Res."},{"unstructured":"Faghri, F., Fleet, D.J., Kiros, J.R., Fidler, S.: VSE++: improving visual-semantic embeddings with hard negatives. arXiv preprint \narXiv:1707.05612\n\n (2017)","key":"55_CR7"},{"issue":"2","key":"55_CR8","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1023\/B:VISI.0000022288.19776.77","volume":"59","author":"PF Felzenszwalb","year":"2004","unstructured":"Felzenszwalb, P.F., Huttenlocher, D.P.: Efficient graph-based image segmentation. Int. J. Comput. Vis. 59(2), 167\u2013181 (2004)","journal-title":"Int. J. Comput. Vis."},{"unstructured":"Frome, A., Corrado, G.S., Shlens, J., Bengio, S., Dean, J., Mikolov, T., et al.: DeViSE: a deep visual-semantic embedding model. In: Advances in Neural Information Processing Systems, pp. 2121\u20132129 (2013)","key":"55_CR9"},{"doi-asserted-by":"crossref","unstructured":"Karpathy, A., Fei-Fei, L.: Deep visual-semantic alignments for generating image descriptions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3128\u20133137 (2015)","key":"55_CR10","DOI":"10.1109\/CVPR.2015.7298932"},{"unstructured":"Karpathy, A., Joulin, A., Fei-Fei, L.F.: Deep fragment embeddings for bidirectional image sentence mapping. In: Advances in Neural Information Processing Systems, pp. 1889\u20131897 (2014)","key":"55_CR11"},{"unstructured":"Kiros, R., Salakhutdinov, R., Zemel, R.S.: Unifying visual-semantic embeddings with multimodal neural language models. arXiv preprint \narXiv:1411.2539\n\n (2014)","key":"55_CR12"},{"doi-asserted-by":"crossref","unstructured":"Klein, B., Lev, G., Sadeh, G., Wolf, L.: Associating neural word embeddings with deep image representations using fisher vectors. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4437\u20134446 (2015)","key":"55_CR13","DOI":"10.1109\/CVPR.2015.7299073"},{"unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097\u20131105 (2012)","key":"55_CR14"},{"key":"55_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). \nhttps:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"doi-asserted-by":"crossref","unstructured":"Ma, L., Lu, Z., Shang, L., Li, H.: Multimodal convolutional neural networks for matching image and sentence. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2623\u20132631 (2015)","key":"55_CR16","DOI":"10.1109\/ICCV.2015.301"},{"unstructured":"Mao, J., Xu, W., Yang, Y., Wang, J., Yuille, A.L.: Explain images with multimodal recurrent neural networks. arXiv preprint \narXiv:1410.1090\n\n (2014)","key":"55_CR17"},{"doi-asserted-by":"crossref","unstructured":"Ray, A., Christie, G., Bansal, M., Batra, D., Parikh, D.: Question relevance in VQA: identifying non-visual and false-premise questions. arXiv preprint \narXiv:1606.06622\n\n (2016)","key":"55_CR18","DOI":"10.18653\/v1\/D16-1090"},{"doi-asserted-by":"crossref","unstructured":"Rennie, S.J., Marcheret, E., Mroueh, Y., Ross, J., Goel, V.: Self-critical sequence training for image captioning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7008\u20137024 (2017)","key":"55_CR19","DOI":"10.1109\/CVPR.2017.131"},{"issue":"12","key":"55_CR20","doi-asserted-by":"publisher","first-page":"5610","DOI":"10.1109\/TIP.2016.2612883","volume":"25","author":"F Shen","year":"2016","unstructured":"Shen, F., Zhou, X., Yang, Y., Song, J., Shen, H.T., Tao, D.: A fast optimization method for general binary code learning. IEEE Trans. Image Process. 25(12), 5610\u20135621 (2016)","journal-title":"IEEE Trans. Image Process."},{"unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint \narXiv:1409.1556\n\n (2014)","key":"55_CR21"},{"key":"55_CR22","doi-asserted-by":"publisher","first-page":"207","DOI":"10.1162\/tacl_a_00177","volume":"2","author":"R Socher","year":"2014","unstructured":"Socher, R., Karpathy, A., Le, Q.V., Manning, C.D., Ng, A.Y.: Grounded compositional semantics for finding and describing images with sentences. Trans. Assoc. Comput. Linguist. 2, 207\u2013218 (2014)","journal-title":"Trans. Assoc. Comput. Linguist."},{"unstructured":"Vendrov, I., Kiros, R., Fidler, S., Urtasun, R.: Order-embeddings of images and language. arXiv preprint \narXiv:1511.06361\n\n (2015)","key":"55_CR23"},{"doi-asserted-by":"crossref","unstructured":"Wan, J., et al.: Deep learning for content-based image retrieval: a comprehensive study. In: Proceedings of the 22nd ACM International Conference on Multimedia, pp. 157\u2013166. ACM (2014)","key":"55_CR24","DOI":"10.1145\/2647868.2654948"},{"issue":"15","key":"55_CR25","doi-asserted-by":"publisher","first-page":"9255","DOI":"10.1007\/s11042-016-3380-8","volume":"75","author":"C Wang","year":"2016","unstructured":"Wang, C., Yang, H., Meinel, C.: A deep semantic framework for multimodal representation learning. Multimedia Tools Appl. 75(15), 9255\u20139276 (2016)","journal-title":"Multimedia Tools Appl."},{"doi-asserted-by":"crossref","unstructured":"Wang, D., Nyberg, E.: A long short-term memory model for answer sentence selection in question answering. In: Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pp. 707\u2013712 (2015)","key":"55_CR26","DOI":"10.3115\/v1\/P15-2116"},{"doi-asserted-by":"crossref","unstructured":"Wang, L., Li, Y., Lazebnik, S.: Learning deep structure-preserving image-text embeddings. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5005\u20135013 (2016)","key":"55_CR27","DOI":"10.1109\/CVPR.2016.541"},{"issue":"5","key":"55_CR28","doi-asserted-by":"publisher","first-page":"2494","DOI":"10.1109\/TIP.2017.2676345","volume":"26","author":"X Xu","year":"2017","unstructured":"Xu, X., Shen, F., Yang, Y., Shen, H.T., Li, X.: Learning discriminative binary codes for large-scale cross-modal retrieval. IEEE Trans. Image Process. 26(5), 2494\u20132507 (2017)","journal-title":"IEEE Trans. Image Process."},{"doi-asserted-by":"crossref","unstructured":"You, Q., Jin, H., Wang, Z., Fang, C., Luo, J.: Image captioning with semantic attention. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4651\u20134659 (2016)","key":"55_CR29","DOI":"10.1109\/CVPR.2016.503"},{"key":"55_CR30","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1162\/tacl_a_00166","volume":"2","author":"P Young","year":"2014","unstructured":"Young, P., Lai, A., Hodosh, M., Hockenmaier, J.: From image descriptions to visual denotations: new similarity metrics for semantic inference over event descriptions. Trans. Assoc. Comput. Linguist. 2, 67\u201378 (2014)","journal-title":"Trans. Assoc. Comput. Linguist."}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-37734-2_55","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,2,6]],"date-time":"2020-02-06T13:14:18Z","timestamp":1580994858000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-37734-2_55"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,12,24]]},"ISBN":["9783030377335","9783030377342"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-37734-2_55","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2019,12,24]]},"assertion":[{"value":"24 December 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MMM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Multimedia Modeling","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Daejeon","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Korea (Republic of)","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 January 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 January 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mmm2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.mmm2020.kr\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"171","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"40","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"23% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Of the 171 submissions, 46 were accepted as poster papers; of the 49 special session paper submissions, 28 were accepted for oral presentation and 8 for poster presentation; 9 demo papers and 10 VBS papers were also accepted.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}