{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T01:19:09Z","timestamp":1742951949640,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":25,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819722402"},{"type":"electronic","value":"9789819722389"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-981-97-2238-9_5","type":"book-chapter","created":{"date-parts":[[2024,4,30]],"date-time":"2024-04-30T12:01:48Z","timestamp":1714478508000},"page":"59-71","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Semantic Completion: Enhancing Image-Text Retrieval with\u00a0Information Extraction and\u00a0Compression"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-6164-6784","authenticated-orcid":false,"given":"Xue","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6088-7198","authenticated-orcid":false,"given":"Yi","family":"Guo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,5,1]]},"reference":[{"key":"5_CR1","doi-asserted-by":"crossref","unstructured":"Chen, F., Chen, X., Xu, S., Xu, B.: Improving cross-modal understanding in visual dialog via contrastive learning. In: ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7937\u20137941 (2022). https:\/\/api.semanticscholar.org\/CorpusID:248218567","DOI":"10.1109\/ICASSP43922.2022.9747769"},{"key":"5_CR2","doi-asserted-by":"publisher","unstructured":"Chen, Y.-C., et al.: UNITER: UNiversal image-TExt representation learning. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12375, pp. 104\u2013120. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58577-8_7. https:\/\/api.semanticscholar.org\/CorpusID:216080982","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"5_CR3","doi-asserted-by":"crossref","unstructured":"Dou, Z.Y., et al.: An empirical study of training end-to-end vision-and-language transformers. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 18145\u201318155 (2021). https:\/\/api.semanticscholar.org\/CorpusID:241033425","DOI":"10.1109\/CVPR52688.2022.01763"},{"key":"5_CR4","unstructured":"Faghri, F., Fleet, D.J., Kiros, J.R., Fidler, S.: VSE++: improving visual-semantic embeddings with hard negatives. In: British Machine Vision Conference (2017). https:\/\/api.semanticscholar.org\/CorpusID:6095318"},{"key":"5_CR5","unstructured":"Gan, Z., Chen, Y.C., Li, L., Zhu, C., Cheng, Y., Liu, J.: Large-scale adversarial training for vision-and-language representation learning. ArXiv abs\/2006.06195 (2020). https:\/\/api.semanticscholar.org\/CorpusID:219573512"},{"key":"5_CR6","unstructured":"Gansbeke, W.V., Vandenhende, S., Georgoulis, S., Proesmans, M., Gool, L.V.: Learning to classify images without labels. ArXiv abs\/2005.12320 (2020). https:\/\/api.semanticscholar.org\/CorpusID:220347634"},{"key":"5_CR7","doi-asserted-by":"crossref","unstructured":"Huang, Z., Zeng, Z., Huang, Y., Liu, B., Fu, D., Fu, J.: Seeing out of the box: end-to-end pre-training for vision-language representation learning. In: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 12971\u201312980 (2021). https:\/\/api.semanticscholar.org\/CorpusID:233169113","DOI":"10.1109\/CVPR46437.2021.01278"},{"key":"5_CR8","doi-asserted-by":"crossref","unstructured":"Jain, A., et al.: MURAL: multimodal, multitask retrieval across languages. ArXiv abs\/2109.05125 (2021). https:\/\/api.semanticscholar.org\/CorpusID:237490989","DOI":"10.18653\/v1\/2021.findings-emnlp.293"},{"key":"5_CR9","unstructured":"Jia, C., et al.: Scaling up visual and vision-language representation learning with noisy text supervision. In: International Conference on Machine Learning (2021). https:\/\/api.semanticscholar.org\/CorpusID:231879586"},{"key":"5_CR10","unstructured":"Kim, W., Son, B., Kim, I.: ViLT: vision-and-language transformer without convolution or region supervision. In: International Conference on Machine Learning (2021). https:\/\/api.semanticscholar.org\/CorpusID:231839613"},{"key":"5_CR11","doi-asserted-by":"crossref","unstructured":"Li, G., Duan, N., Fang, Y., Jiang, D., Zhou, M.: Unicoder-VL: a universal encoder for vision and language by cross-modal pre-training. In: AAAI Conference on Artificial Intelligence (2019). https:\/\/api.semanticscholar.org\/CorpusID:201058752","DOI":"10.1609\/aaai.v34i07.6795"},{"key":"5_CR12","doi-asserted-by":"publisher","unstructured":"Li, X., et al.: Oscar: object-semantics aligned pre-training for vision-language tasks. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12375, pp. 121\u2013137. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58577-8_8. https:\/\/api.semanticscholar.org\/CorpusID:215754208","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"5_CR13","doi-asserted-by":"crossref","unstructured":"Lu, H., Fei, N., Huo, Y., Gao, Y., Lu, Z., Wen, J.: COTS: collaborative two-stream vision-language pre-training model for cross-modal retrieval. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 15671\u201315680 (2022). https:\/\/api.semanticscholar.org\/CorpusID:248218570","DOI":"10.1109\/CVPR52688.2022.01524"},{"key":"5_CR14","doi-asserted-by":"crossref","unstructured":"Luo, Z., et al.: LexLIP: lexicon-bottlenecked language-image pre-training for large-scale image-text retrieval. ArXiv abs\/2302.02908 (2023). https:\/\/api.semanticscholar.org\/CorpusID:256615217","DOI":"10.1109\/ICCV51070.2023.01029"},{"key":"5_CR15","doi-asserted-by":"crossref","unstructured":"Pena-Pereira, F., Wojnowski, W., Tobiszewski, M.: Agree-analytical greenness metric approach and software. Anal. Chem. 92, 10076\u201310082 (2020). https:\/\/api.semanticscholar.org\/CorpusID:219706533","DOI":"10.1021\/acs.analchem.0c01887"},{"key":"5_CR16","unstructured":"Qi, D., Su, L., Song, J., Cui, E., Bharti, T., Sacheti, A.: ImageBERT: cross-modal pre-training with large-scale weak-supervised image-text data. ArXiv abs\/2001.07966 (2020). https:\/\/api.semanticscholar.org\/CorpusID:210859480"},{"key":"5_CR17","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning (2021). https:\/\/api.semanticscholar.org\/CorpusID:231591445"},{"key":"5_CR18","unstructured":"Reed, S.E., Akata, Z., Yan, X., Logeswaran, L., Schiele, B., Lee, H.: Generative adversarial text to image synthesis. In: International Conference on Machine Learning (2016). https:\/\/api.semanticscholar.org\/CorpusID:1563370"},{"key":"5_CR19","unstructured":"Su, W., et al.: VL-BERT: pre-training of generic visual-linguistic representations. ArXiv abs\/1908.08530 (2019). https:\/\/api.semanticscholar.org\/CorpusID:201317624"},{"key":"5_CR20","doi-asserted-by":"crossref","unstructured":"Tan, H.H., Bansal, M.: LXMERT: learning cross-modality encoder representations from transformers. In: Conference on Empirical Methods in Natural Language Processing (2019). https:\/\/api.semanticscholar.org\/CorpusID:201103729","DOI":"10.18653\/v1\/D19-1514"},{"key":"5_CR21","unstructured":"Wang, W., Bao, H., Dong, L., Wei, F.: VLMo: unified vision-language pre-training with mixture-of-modality-experts. ArXiv abs\/2111.02358 (2021). https:\/\/api.semanticscholar.org\/CorpusID:241035439"},{"key":"5_CR22","doi-asserted-by":"crossref","unstructured":"Xu, J., Liu, Z., Pei, X., Wang, S., Gao, S.: FB-Net: dual-branch foreground-background fusion network with multi-scale semantic scanning for image-text retrieval. IEEE Access 11, 36516\u201336537 (2023). https:\/\/api.semanticscholar.org\/CorpusID:257897254","DOI":"10.1109\/ACCESS.2023.3263512"},{"key":"5_CR23","doi-asserted-by":"crossref","unstructured":"Yang, J., et al.: Vision-language pre-training with triple contrastive learning. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 15650\u201315659 (2022). https:\/\/api.semanticscholar.org\/CorpusID:247011309","DOI":"10.1109\/CVPR52688.2022.01522"},{"key":"5_CR24","unstructured":"Yao, L., et al.: FILIP: fine-grained interactive language-image pre-training. ArXiv abs\/2111.07783 (2021). https:\/\/api.semanticscholar.org\/CorpusID:244117525"},{"key":"5_CR25","doi-asserted-by":"crossref","unstructured":"Zhang, P., et al.: VinVL: revisiting visual representations in vision-language models. In: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5575\u20135584 (2021). https:\/\/api.semanticscholar.org\/CorpusID:235692795","DOI":"10.1109\/CVPR46437.2021.00553"}],"container-title":["Lecture Notes in Computer Science","Advances in Knowledge Discovery and Data Mining"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-2238-9_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,30]],"date-time":"2024-04-30T12:04:31Z","timestamp":1714478671000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-2238-9_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9789819722402","9789819722389"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-2238-9_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"1 May 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PAKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pacific-Asia Conference on Knowledge Discovery and Data Mining","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Taipei","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Taiwan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7 May 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 May 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pakdd2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/pakdd2024.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}