{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T11:43:57Z","timestamp":1742989437978,"version":"3.40.3"},"publisher-location":"Cham","reference-count":38,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031441912"},{"type":"electronic","value":"9783031441929"}],"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\/978-3-031-44192-9_46","type":"book-chapter","created":{"date-parts":[[2023,9,21]],"date-time":"2023-09-21T05:01:41Z","timestamp":1695272501000},"page":"572-585","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["UIT: Unifying Pre-training Objectives for\u00a0Image-Text Understanding"],"prefix":"10.1007","author":[{"given":"Guoqiang","family":"Xu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shenggang","family":"Yan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,9,22]]},"reference":[{"key":"46_CR1","first-page":"23716","volume":"35","author":"JB Alayrac","year":"2022","unstructured":"Alayrac, J.B., et al.: Flamingo: a visual language model for few-shot learning. Adv. Neural. Inf. Process. Syst. 35, 23716\u201323736 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"46_CR2","unstructured":"Bao, H., et al.: UniLMv2: pseudo-masked language models for unified language model pre-training. In: International Conference on Machine Learning, pp. 642\u2013652. PMLR (2020)"},{"key":"46_CR3","unstructured":"Chang, H., et al.: Muse: text-to-image generation via masked generative transformers. arXiv preprint arXiv:2301.00704 (2023)"},{"key":"46_CR4","doi-asserted-by":"crossref","unstructured":"Chang, H., Zhang, H., Jiang, L., Liu, C., Freeman, W.T.: MaskGIT: masked generative image transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11315\u201311325 (2022)","DOI":"10.1109\/CVPR52688.2022.01103"},{"key":"46_CR5","unstructured":"Chen, X., et al.: PaLI: a jointly-scaled multilingual language-image model. arXiv preprint arXiv:2209.06794 (2022)"},{"key":"46_CR6","first-page":"19822","volume":"34","author":"M Ding","year":"2021","unstructured":"Ding, M., et al.: CogView: mastering text-to-image generation via transformers. Adv. Neural. Inf. Process. Syst. 34, 19822\u201319835 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"46_CR7","unstructured":"Ding, M., Zheng, W., Hong, W., Tang, J.: CogView2: faster and better text-to-image generation via hierarchical transformers. arXiv preprint arXiv:2204.14217 (2022)"},{"key":"46_CR8","unstructured":"Dong, L., et al.: Unified language model pre-training for natural language understanding and generation. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"46_CR9","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1007\/978-3-031-19784-0_6","volume-title":"Computer Vision-ECCV 2022","author":"O Gafni","year":"2022","unstructured":"Gafni, O., Polyak, A., Ashual, O., Sheynin, S., Parikh, D., Taigman, Y.: Make-a-scene: scene-based text-to-image generation with human priors. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13675, pp. 89\u2013106. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19784-0_6"},{"key":"46_CR10","unstructured":"Ho, J., Salimans, T.: Classifier-free diffusion guidance. arXiv preprint arXiv:2207.12598 (2022)"},{"key":"46_CR11","unstructured":"Jia, C., et al.: Scaling up visual and vision-language representation learning with noisy text supervision. In: International Conference on Machine Learning, pp. 4904\u20134916. PMLR (2021)"},{"key":"46_CR12","unstructured":"Lu, J., Clark, C., Zellers, R., Mottaghi, R., Kembhavi, A.: Unified-IO: a unified model for vision, language, and multi-modal tasks. arXiv preprint arXiv:2206.08916 (2022)"},{"key":"46_CR13","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1007\/978-3-031-19809-0_30","volume-title":"Computer Vision-ECCV 2022","author":"N Mu","year":"2022","unstructured":"Mu, N., Kirillov, A., Wagner, D., Xie, S.: SLIP: self-supervision meets language-image pre-training. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13686, pp. 529\u2013544. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19809-0_30"},{"key":"46_CR14","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"issue":"8","key":"46_CR15","first-page":"9","volume":"1","author":"A Radford","year":"2019","unstructured":"Radford, A., et al.: Language models are unsupervised multitask learners. OpenAI Blog 1(8), 9 (2019)","journal-title":"OpenAI Blog"},{"issue":"1","key":"46_CR16","first-page":"5485","volume":"21","author":"C Raffel","year":"2020","unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 21(1), 5485\u20135551 (2020)","journal-title":"J. Mach. Learn. Res."},{"key":"46_CR17","unstructured":"Ramesh, A., et al.: Zero-shot text-to-image generation. In: International Conference on Machine Learning, pp. 8821\u20138831. PMLR (2021)"},{"key":"46_CR18","first-page":"36479","volume":"35","author":"C Saharia","year":"2022","unstructured":"Saharia, C., et al.: Photorealistic text-to-image diffusion models with deep language understanding. Adv. Neural. Inf. Process. Syst. 35, 36479\u201336494 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"46_CR19","unstructured":"Tang, X., et al.: Hyperbolic code retrieval: a novel approach for efficient code search using hyperbolic space embeddings. arXiv preprint arXiv:2308.15234 (2023)"},{"key":"46_CR20","unstructured":"Tang, X., et al.: Multilevel semantic embedding of software patches: a fine-to-coarse grained approach towards security patch detection. arXiv preprint arXiv:2308.15233 (2023)"},{"key":"46_CR21","doi-asserted-by":"crossref","unstructured":"Tang, X., Sun, T., Zhu, R., Wang, S.: CKG: dynamic representation based on context and knowledge graph. In: 2020 25th International Conference on Pattern Recognition (ICPR), pp. 2889\u20132895. IEEE (2021)","DOI":"10.1109\/ICPR48806.2021.9412877"},{"key":"46_CR22","doi-asserted-by":"crossref","unstructured":"Tang, X., Tian, H., Kong, P., Liu, K., Klein, J., Bissyande, T.F.: App review driven collaborative bug finding. arXiv preprint arXiv:2301.02818 (2023)","DOI":"10.1007\/s10664-024-10489-x"},{"key":"46_CR23","doi-asserted-by":"crossref","unstructured":"Tang, X., Zhu, R., Sun, T., Wang, S.: Moto: enhancing embedding with multiple joint factors for Chinese text classification. In: 2020 25th International Conference on Pattern Recognition (ICPR), pp. 2882\u20132888. IEEE (2021)","DOI":"10.1109\/ICPR48806.2021.9412501"},{"key":"46_CR24","unstructured":"Tian, H., et al.: Is ChatGPT the ultimate programming assistant-how far is it? arXiv preprint arXiv:2304.11938 (2023)"},{"key":"46_CR25","doi-asserted-by":"crossref","unstructured":"Tian, H., et al.: Is this change the answer to that problem? correlating descriptions of bug and code changes for evaluating patch correctness. In: Proceedings of the 37th IEEE\/ACM International Conference on Automated Software Engineering, pp. 1\u201313 (2022)","DOI":"10.1145\/3551349.3556914"},{"key":"46_CR26","unstructured":"Van Den Oord, A., Vinyals, O., et al.: Neural discrete representation learning. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"46_CR27","unstructured":"Wang, J., et al.: GIT: a generative image-to-text transformer for vision and language. arXiv preprint arXiv:2205.14100 (2022)"},{"key":"46_CR28","doi-asserted-by":"publisher","unstructured":"Wang, L., et al.: Delving into commit-issue correlation to enhance commit message generation models. CoRR abs\/2308.00147 (2023). https:\/\/doi.org\/10.48550\/arXiv.2308.00147","DOI":"10.48550\/arXiv.2308.00147"},{"key":"46_CR29","unstructured":"Wang, P., et al.: Unifying architectures, tasks, and modalities through a simple sequence-to-sequence learning framework. arXiv preprint arXiv:2202.03052 (2022)"},{"key":"46_CR30","series-title":"Communications in Computer and Information Science","doi-asserted-by":"publisher","first-page":"494","DOI":"10.1007\/978-3-030-92310-5_57","volume-title":"Neural Information Processing","author":"S Wang","year":"2021","unstructured":"Wang, S., Tang, D., Zhang, L.: A large-scale hierarchical structure knowledge enhanced pre-training framework for\u00a0automatic ICD coding. In: Mantoro, T., Lee, M., Ayu, M.A., Wong, K.W., Hidayanto, A.N. (eds.) ICONIP 2021. CCIS, vol. 1517, pp. 494\u2013502. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-92310-5_57"},{"key":"46_CR31","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"523","DOI":"10.1007\/978-3-031-00126-0_38","volume-title":"Database Systems for Advanced Applications","author":"S Wang","year":"2022","unstructured":"Wang, S., Tang, D., Zhang, L., Li, H., Han, D.: HieNet: bidirectional hierarchy framework for automated ICD coding. In: Bhattacharya, A., et al. (eds.) DASFAA 2022. LNCS, vol. 13246, pp. 523\u2013539. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-00126-0_38"},{"key":"46_CR32","unstructured":"Wang, Z., Yu, J., Yu, A.W., Dai, Z., Tsvetkov, Y., Cao, Y.: SimVLM: simple visual language model pretraining with weak supervision. arXiv preprint arXiv:2108.10904 (2021)"},{"key":"46_CR33","unstructured":"Yao, L., et al.: FILIP: fine-grained interactive language-image pre-training. arXiv preprint arXiv:2111.07783 (2021)"},{"key":"46_CR34","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1007\/978-3-031-19812-0_5","volume-title":"Computer Vision-ECCV 2022","author":"H You","year":"2022","unstructured":"You, H., et al.: Learning visual representation from modality-shared contrastive language-image pre-training. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13687, pp. 69\u201387. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19812-0_5"},{"key":"46_CR35","unstructured":"Yu, J., et al.: Vector-quantized image modeling with improved VQGAN. arXiv preprint arXiv:2110.04627 (2021)"},{"key":"46_CR36","unstructured":"Yu, J., Wang, Z., Vasudevan, V., Yeung, L., Seyedhosseini, M., Wu, Y.: CoCa: contrastive captioners are image-text foundation models. arXiv preprint arXiv:2205.01917 (2022)"},{"key":"46_CR37","unstructured":"Yu, J., et al.: Scaling autoregressive models for content-rich text-to-image generation. arXiv preprint arXiv:2206.10789 (2022)"},{"key":"46_CR38","doi-asserted-by":"crossref","unstructured":"Zhou, L., Palangi, H., Zhang, L., Hu, H., Corso, J., Gao, J.: Unified vision-language pre-training for image captioning and VQA. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 13041\u201313049 (2020)","DOI":"10.1609\/aaai.v34i07.7005"}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks and Machine Learning \u2013 ICANN 2023"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-44192-9_46","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T15:02:47Z","timestamp":1730127767000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-44192-9_46"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031441912","9783031441929"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-44192-9_46","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":"22 September 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICANN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial Neural Networks","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Heraklion","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Greece","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":"26 September 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"32","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icann2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/e-nns.org\/icann2023\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"easyacademia.org","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"947","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":"426","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":"22","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":"45% - 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":"2.4","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)"}},{"value":"type of other papers accepted : 9 Abstract","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)"}}]}}