{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T20:19:05Z","timestamp":1743020345082,"version":"3.40.3"},"publisher-location":"Cham","reference-count":32,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030602895"},{"type":"electronic","value":"9783030602901"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","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\/978-3-030-60290-1_26","type":"book-chapter","created":{"date-parts":[[2020,10,13]],"date-time":"2020-10-13T21:02:30Z","timestamp":1602622950000},"page":"327-341","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Multi-grained Cross-modal Similarity Query with Interpretability"],"prefix":"10.1007","author":[{"given":"Mingdong","family":"Zhu","sequence":"first","affiliation":[]},{"given":"Derong","family":"Shen","sequence":"additional","affiliation":[]},{"given":"Lixin","family":"Xu","sequence":"additional","affiliation":[]},{"given":"Gang","family":"Ren","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,10,14]]},"reference":[{"issue":"9","key":"26_CR1","doi-asserted-by":"publisher","first-page":"2372","DOI":"10.1109\/TCSVT.2017.2705068","volume":"28","author":"Y Peng","year":"2018","unstructured":"Peng, Y., Huang, X., Zhao, Y.: An over view of cross-media retrieval: concepts, methodologies, benchmarks, and challenges. IEEE Trans. Circuits Syst. Video Technol. 28(9), 2372\u20132385 (2018)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"26_CR2","doi-asserted-by":"crossref","unstructured":"He, X., Peng, Y., Xie, L.: A new benchmark and approach for fine-grained cross-media retrieval. In: 27th ACM International Conference on Multimedia, pp. 1740\u20131748. ACM (2019)","DOI":"10.1145\/3343031.3350974"},{"key":"26_CR3","doi-asserted-by":"crossref","unstructured":"Rasiwasia, N., Pereira, J., Coviello, E., et al.: A new approach to cross-modal multimedia retrieval. In: 18th International Conference on Multimedia, pp. 251\u2013260. ACM (2010)","DOI":"10.1145\/1873951.1873987"},{"issue":"6","key":"26_CR4","doi-asserted-by":"publisher","first-page":"965","DOI":"10.1109\/TCSVT.2013.2276704","volume":"24","author":"X Zhai","year":"2014","unstructured":"Zhai, X., Peng, Y., Xiao, J.: Learning cross-media joint representation with sparse and semisupervised regularization. IEEE Trans. Circuits Syst. Video Technol. 24(6), 965\u2013978 (2014)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"3","key":"26_CR5","doi-asserted-by":"publisher","first-page":"583","DOI":"10.1109\/TCSVT.2015.2400779","volume":"26","author":"Y Peng","year":"2016","unstructured":"Peng, Y., Zhai, X., Zhao, Y., Huang, X.: Semi-supervised cross-media feature learning with unified patch graph regularization. IEEE Trans. Circuits Syst. Video Technol. 26(3), 583\u2013596 (2016)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"26_CR6","doi-asserted-by":"crossref","unstructured":"Yan, F., Mikolajczyk, K.: Deep correlation for matching images and text. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 3441\u20133450. IEEE (2015)","DOI":"10.1109\/CVPR.2015.7298966"},{"key":"26_CR7","doi-asserted-by":"crossref","unstructured":"He, L., Xu, X., Lu, H., et al.: Unsupervised cross-modal retrieval through adversarial learning. In: IEEE International Conference on Multimedia and Expo, pp. 1153\u20131158. IEEE (2017)","DOI":"10.1109\/ICME.2017.8019549"},{"issue":"4","key":"26_CR8","doi-asserted-by":"publisher","first-page":"1173","DOI":"10.1109\/TCSVT.2019.2900171","volume":"30","author":"J Chi","year":"2020","unstructured":"Chi, J., Peng, Y.: Zero-shot cross-media embedding learning with dual adversarial distribution network. IEEE Trans. Circuits Syst. Video Technol. 30(4), 1173\u20131187 (2020)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"26_CR9","unstructured":"Andrej, K., Armand, J., Li, F.: Deep fragment embeddings for bidirectional image sentence mapping. In: 27th International Conference on Neural Information Processing Systems, pp. 1889\u20131897, ACM (2014)"},{"issue":"4","key":"26_CR10","doi-asserted-by":"publisher","first-page":"664","DOI":"10.1109\/TPAMI.2016.2598339","volume":"39","author":"K Andrej","year":"2017","unstructured":"Andrej, K., Li, F.: Deep visual-semantic alignments for generating image descriptions. IEEE Trans. Pattern Anal. Mach. Intell. 39(4), 664\u2013676 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"26_CR11","unstructured":"Xu, K., Ba, J., Kiros, R., et al.: Show, attend and tell: neural image caption generation with visual attention. In: 2015 International Conference on Machine Learning, pp. 2048\u20132057. IEEE (2015)"},{"key":"26_CR12","doi-asserted-by":"crossref","unstructured":"Wang, X., Wang, Y., Wan, W.: Watch, listen, and describe: globally and locally aligned cross-modal attentions for video captioning. In: Proceedings of 2018 Conference of the North American Chapter of the Association for Computational Linguistics, pp. 795\u2013801. ACL (2018)","DOI":"10.18653\/v1\/N18-2125"},{"key":"26_CR13","doi-asserted-by":"crossref","unstructured":"Jiang, Q., Li, W.: Deep cross-modal hashing. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition, pp. 3270\u20133278. IEEE (2017)","DOI":"10.1109\/CVPR.2017.348"},{"key":"26_CR14","doi-asserted-by":"crossref","unstructured":"Cao, Y., Long, M., Wang, J., et al.: Correlation autoencoder hashing for supervised cross-modal search. In: International Conference on Multimedia Retrieval, pp. 197\u2013204. ACM (2016)","DOI":"10.1145\/2911996.2912000"},{"key":"26_CR15","doi-asserted-by":"crossref","unstructured":"Cao, Y., Long, M., Wang, J.: Correlation hashing network for efficient cross-modal retrieval, In: 28th British Machine Vision Conference, pp. 1\u201312. BMVA (2017)","DOI":"10.5244\/C.31.128"},{"key":"26_CR16","doi-asserted-by":"crossref","unstructured":"Yang, E., Deng, C., Liu, W., et al.: Pairwise relationship guided deep hashing for cross-modal retrieval. In: 31st Conference on Artificial Intelligence, pp. 1618\u20131625. AAAI (2017)","DOI":"10.1609\/aaai.v31i1.10719"},{"key":"26_CR17","doi-asserted-by":"crossref","unstructured":"Zhang, J., Peng, Y., Yuan, M., et al.: Unsupervised generative adversarial cross-modal hashing. In: 32nd Conference on Artificial Intelligence, pp. 539\u2013546. AAAI (2018)","DOI":"10.1609\/aaai.v32i1.11263"},{"key":"26_CR18","doi-asserted-by":"crossref","unstructured":"Bennanismires, K., Musat, C., Hossmann, A., et al.: Simple unsupervised keyphrase extraction using sentence embeddings. In: Conference on Computational Natural Language Learning, pp. 221\u2013229. ACL (2018)","DOI":"10.18653\/v1\/K18-1022"},{"key":"26_CR19","doi-asserted-by":"crossref","unstructured":"Shen, Y., He, X., Gao, J., et al.: A latent semantic model with convolutional-pooling structure for information retrieval. In: Conference on Information and Knowledge Management. pp. 101\u2013110. ACM (2014)","DOI":"10.1145\/2661829.2661935"},{"key":"26_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"473","DOI":"10.1007\/978-3-030-01267-0_28","volume-title":"Computer Vision \u2013 ECCV 2018","author":"B Cheng","year":"2018","unstructured":"Cheng, B., Wei, Y., Shi, H., et al.: Revisiting RCNN: on awakening the classification power of faster RCNN. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11219, pp. 473\u2013490. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01267-0_28"},{"key":"26_CR21","unstructured":"Cer, D., Yang, Y., Kong, S., et al.: Universal sentence encoder. arXiv: Computation and Language, https:\/\/arxiv.org\/abs\/1803.11175v2. Accessed 12 Apr 2018"},{"key":"26_CR22","unstructured":"Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: 13th International Conference on Artificial Intelligence and Statistics, pp. 249\u2013256 JMLR (2010)"},{"issue":"1","key":"26_CR23","doi-asserted-by":"publisher","first-page":"853","DOI":"10.1613\/jair.3994","volume":"47","author":"M Hodosh","year":"2013","unstructured":"Hodosh, M., Young, P., Hockenmaier, J.: Framing image description as a ranking task: data, models and evaluation metrics. J. Artif. Intell. Res. 47(1), 853\u2013899 (2013)","journal-title":"J. Artif. Intell. Res."},{"issue":"2","key":"26_CR24","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1162\/tacl_a_00166","volume":"7","author":"P Young","year":"2014","unstructured":"Young, P., Lai, A., Hodosh, M., et al.: From image descriptions to visual denotations: new similarity metrics for semantic inference over event descriptions. Trans. Assoc. Comput. Linguist. 7(2), 67\u201378 (2014)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"26_CR25","doi-asserted-by":"crossref","unstructured":"Chua, T., Tang, J., Hong, R., et al.: NUS-WIDE: a real-world web image database from national university of Singapore. In: 8th Conference on Image and Video Retrieval, pp. 1\u20139. ACM (2009)","DOI":"10.1145\/1646396.1646452"},{"key":"26_CR26","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 Lin","year":"2014","unstructured":"Lin, T., Maire, M., Belongie, S.: 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). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"issue":"2","key":"26_CR27","doi-asserted-by":"publisher","first-page":"405","DOI":"10.1109\/TMM.2017.2742704","volume":"20","author":"Y Peng","year":"2018","unstructured":"Peng, Y., Qi, J., Huang, X., et al.: CCL: cross-modal correlation learning with multigrained fusion by hierarchical network. IEEE Trans. Multimedia 20(2), 405\u2013420 (2018)","journal-title":"IEEE Trans. Multimedia"},{"key":"26_CR28","doi-asserted-by":"crossref","unstructured":"Chen, T., Wu, W., Gao, Y., et al.: Fine-grained representation learning and recognition by exploiting hierarchical semantic embedding. In: 26th ACM Multimedia, pp. 2023\u20132031. ACM (2018)","DOI":"10.1145\/3240508.3240523"},{"key":"26_CR29","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"212","DOI":"10.1007\/978-3-030-01225-0_13","volume-title":"Computer Vision \u2013 ECCV 2018","author":"K Lee","year":"2018","unstructured":"Lee, K., Chen, X., Hua, G., et al.: Stacked cross attention for image-text matching. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11208, pp. 212\u2013228. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01225-0_13"},{"key":"26_CR30","doi-asserted-by":"crossref","unstructured":"Yan, F., Mikolajczyk, K.: Deep correlation for matching images and text. In: 2015 Computer Vision and Pattern Recognition, pp. 3441\u20133450. IEEE (2015)","DOI":"10.1109\/CVPR.2015.7298966"},{"issue":"3","key":"26_CR31","doi-asserted-by":"publisher","first-page":"370","DOI":"10.1109\/TMM.2015.2390499","volume":"17","author":"C Kang","year":"2015","unstructured":"Kang, C., Xiang, S., Liao, S., et al.: Learning consistent feature representation for cross-modal multimedia retrieval. IEEE Trans. Multimedia 17(3), 370\u2013381 (2015)","journal-title":"IEEE Trans. Multimedia"},{"key":"26_CR32","unstructured":"Abadi, M., Barham, P., Chen, J., et al.: TensorFlow: a system for large-scale machine learning. In: 12th USENIX Conference on Operating Systems Design and Implementation, pp. 265\u2013283. ACM (2016)"}],"container-title":["Lecture Notes in Computer Science","Web and Big Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-60290-1_26","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,23]],"date-time":"2022-11-23T04:46:32Z","timestamp":1669178792000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-60290-1_26"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030602895","9783030602901"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-60290-1_26","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"14 October 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"APWeb-WAIM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asia-Pacific Web (APWeb) and Web-Age Information Management (WAIM) Joint International Conference on Web and Big Data","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Tianjin","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","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":"12 August 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 August 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"apwebwaim2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.tjudb.cn\/apwebwaim2020\/","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":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"259","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":"68","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":"37","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":"26% - 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":"4.6","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Due to the COVID-19 pandemic the conference was organized as a fully online conference.","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)"}}]}}