{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T04:49:34Z","timestamp":1743137374687,"version":"3.40.3"},"publisher-location":"Cham","reference-count":24,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031446955"},{"type":"electronic","value":"9783031446962"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-3-031-44696-2_36","type":"book-chapter","created":{"date-parts":[[2023,10,7]],"date-time":"2023-10-07T09:03:59Z","timestamp":1696669439000},"page":"457-468","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Text-Image Pair Is Not Enough: Language-Vision Relation Inference with\u00a0Auxiliary Modality Translation"],"prefix":"10.1007","author":[{"given":"Wenjie","family":"Lu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dong","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shoushan","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guodong","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,10,8]]},"reference":[{"key":"36_CR1","doi-asserted-by":"crossref","unstructured":"Alikhani, M., Sharma, P., Li, S., Soricut, R., Stone, M.: Cross-modal coherence modeling for caption generation. In: Proceedings of ACL 2020, pp. 6525\u20136535","DOI":"10.18653\/v1\/2020.acl-main.583"},{"key":"36_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"N Carion","year":"2020","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 213\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13"},{"key":"36_CR3","doi-asserted-by":"crossref","unstructured":"Ive, J., Li, A.M., Miao, Y., Caglayan, O., Madhyastha, P., Specia, L.: Exploiting multimodal reinforcement learning for simultaneous machine translation. In: Proceedings of EACL 2021, pp. 3222\u20133233","DOI":"10.18653\/v1\/2021.eacl-main.281"},{"key":"36_CR4","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2021.104518","volume":"107","author":"K Jin","year":"2022","unstructured":"Jin, K., Sun, S., Li, H., Zhang, F.: A novel multi-modal analysis model with baidu search index for subway passenger flow forecasting. Eng. Appl. Artif. Intell. 107, 104518 (2022). https:\/\/doi.org\/10.1016\/j.engappai.2021.104518","journal-title":"Eng. Appl. Artif. Intell."},{"key":"36_CR5","doi-asserted-by":"crossref","unstructured":"Ju, X., et al.: Joint multi-modal aspect-sentiment analysis with auxiliary cross-modal relation detection. In: Proceedings of EMNLP 2021, pp. 4395\u20134405","DOI":"10.18653\/v1\/2021.emnlp-main.360"},{"key":"36_CR6","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)","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"36_CR7","doi-asserted-by":"crossref","unstructured":"Khan, Z., Fu, Y.: Exploiting BERT for multimodal target sentiment classification through input space translation. In: Proceedings of ACM MM 2021, pp. 3034\u20133042","DOI":"10.1145\/3474085.3475692"},{"key":"36_CR8","unstructured":"Kiela, D., Bhooshan, S., Firooz, H., Testuggine, D.: Supervised multimodal bitransformers for classifying images and text. In: Proceedings of ViGIL@NeurIPS 2019"},{"key":"36_CR9","unstructured":"Li, L.H., Yatskar, M., Yin, D., Hsieh, C., Chang, K.: Visualbert: a simple and performant baseline for vision and language. CoRR (2019), http:\/\/arxiv.org\/abs\/1908.03557"},{"key":"36_CR10","doi-asserted-by":"crossref","unstructured":"Li, Z., Wei, Z., Fan, Z., Shan, H., Huang, X.: An unsupervised sampling approach for image-sentence matching using document-level structural information. In: Proceedings of AAAI 2021, pp. 13324\u201313332","DOI":"10.1609\/aaai.v35i15.17573"},{"key":"36_CR11","doi-asserted-by":"crossref","unstructured":"Li, Z., Ling, F., Xu, C., Zhang, C., Ma, H.: Cross-media hash retrieval using multi-head attention network. In: Proceedings of ICPR 2020, pp. 1290\u20131297","DOI":"10.1109\/ICPR48806.2021.9413130"},{"key":"36_CR12","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). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"36_CR13","doi-asserted-by":"crossref","unstructured":"Lu, W., Zhang, D.: Unified multi-modal multi-task joint learning for language-vision relation inference. In: Proceedings of ICME 2022, pp. 1\u20136","DOI":"10.1109\/ICME52920.2022.9859683"},{"key":"36_CR14","doi-asserted-by":"crossref","unstructured":"Mai, S., Hu, H., Xing, S.: Modality to modality translation: An adversarial representation learning and graph fusion network for multimodal fusion. In: Proceedings of AAAI 2020, pp. 164\u2013172","DOI":"10.1609\/aaai.v34i01.5347"},{"issue":"1","key":"36_CR15","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1007\/s13735-019-00187-6","volume":"9","author":"C Otto","year":"2020","unstructured":"Otto, C., Springstein, M., Anand, A., Ewerth, R.: Characterization and classification of semantic image-text relations. Inter. J. Multimedia Inform. Retrieval 9(1), 31\u201345 (2020). https:\/\/doi.org\/10.1007\/s13735-019-00187-6","journal-title":"Inter. J. Multimedia Inform. Retrieval"},{"key":"36_CR16","doi-asserted-by":"crossref","unstructured":"Sun, L., et al.: RIVA: a pre-trained tweet multimodal model based on text-image relation for multimodal NER. In: Proceedings of COLING 2020, pp. 1852\u20131862","DOI":"10.18653\/v1\/2020.coling-main.168"},{"key":"36_CR17","doi-asserted-by":"crossref","unstructured":"Sun, L., Wang, J., Zhang, K., Su, Y., Weng, F.: Rpbert: a text-image relation propagation-based BERT model for multimodal NER. In: Proceedings of AAAI 2021, pp. 13860\u201313868","DOI":"10.1609\/aaai.v35i15.17633"},{"key":"36_CR18","doi-asserted-by":"crossref","unstructured":"Vempala, A., Preotiuc-Pietro, D.: Categorizing and inferring the relationship between the text and image of twitter posts. In: Proceedings of ACL 2019, pp. 2830\u20132840","DOI":"10.18653\/v1\/P19-1272"},{"issue":"12","key":"36_CR19","doi-asserted-by":"publisher","first-page":"4070","DOI":"10.1007\/s10803-018-3702-y","volume":"48","author":"RJ Walsh","year":"2018","unstructured":"Walsh, R.J., Krabbendam, L., Dewinter, J., Begeer, S.: Brief report: gender identity differences in autistic adults: associations with perceptual and socio-cognitive profiles. J. Autism Dev. Disord. 48(12), 4070\u20134078 (2018)","journal-title":"J. Autism Dev. Disord."},{"key":"36_CR20","doi-asserted-by":"publisher","first-page":"130","DOI":"10.1016\/j.neucom.2021.09.041","volume":"467","author":"B Yang","year":"2022","unstructured":"Yang, B., Shao, B., Wu, L., Lin, X.: Multimodal sentiment analysis with unidirectional modality translation. Neurocomputing 467, 130\u2013137 (2022). https:\/\/doi.org\/10.1016\/j.neucom.2021.09.041","journal-title":"Neurocomputing"},{"key":"36_CR21","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2020.104048","volume":"97","author":"J Yang","year":"2021","unstructured":"Yang, J., Zou, X., Zhang, W., Han, H.: Microblog sentiment analysis via embedding social contexts into an attentive LSTM. Eng. Appl. Artif. Intell. 97, 104048 (2021). https:\/\/doi.org\/10.1016\/j.engappai.2020.104048","journal-title":"Eng. Appl. Artif. Intell."},{"key":"36_CR22","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3035277","author":"X Yang","year":"2020","unstructured":"Yang, X., Feng, S., Wang, D., Zhang, Y.: Image-text multimodal emotion classification via multi-view attentional network. IEEE Trans. Multimedia (2020). https:\/\/doi.org\/10.1109\/TMM.2020.3035277","journal-title":"IEEE Trans. Multimedia"},{"key":"36_CR23","first-page":"67","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. Lingu. 2, 67\u201378 (2014)","journal-title":"Trans. Assoc. Comput. Lingu."},{"key":"36_CR24","doi-asserted-by":"publisher","unstructured":"Zhang, S., Song, L., Jin, L., Xu, K., Yu, D., Luo, J.: Video-aided unsupervised grammar induction. In: Proceedings of NAACL-HLT 2021, pp. 1513\u20131524. https:\/\/doi.org\/10.18653\/v1\/2021.naacl-main.119","DOI":"10.18653\/v1\/2021.naacl-main.119"}],"container-title":["Lecture Notes in Computer Science","Natural Language Processing and Chinese Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-44696-2_36","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T09:00:59Z","timestamp":1730278859000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-44696-2_36"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031446955","9783031446962"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-44696-2_36","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"8 October 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"NLPCC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"CCF International Conference on Natural Language Processing and Chinese Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Foshan","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":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 October 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 October 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"nlpcc2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/tcci.ccf.org.cn\/conference\/2023\/index.php","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":"Softconf","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"478","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":"143","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":"30% - 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","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)"}}]}}