{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:09:58Z","timestamp":1776888598407,"version":"3.51.2"},"publisher-location":"Cham","reference-count":58,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031705328","type":"print"},{"value":"9783031705335","type":"electronic"}],"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\/978-3-031-70533-5_21","type":"book-chapter","created":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T05:02:25Z","timestamp":1725685345000},"page":"349-366","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["AltChart: Enhancing VLM-Based Chart Summarization Through Multi-pretext Tasks"],"prefix":"10.1007","author":[{"given":"Omar","family":"Moured","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiaming","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"M. Saquib","family":"Sarfraz","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rainer","family":"Stiefelhagen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,9,8]]},"reference":[{"issue":"100","key":"21_CR1","first-page":"71","volume":"30","author":"P Ackland","year":"2017","unstructured":"Ackland, P., Resnikoff, S., Bourne, R.: World blindness and visual impairment: despite many successes, the problem is growing. Commun. Eye Health 30(100), 71 (2017)","journal-title":"Commun. Eye Health"},{"key":"21_CR2","doi-asserted-by":"crossref","unstructured":"Alam, M.Z.I., Islam, S., Hoque, E.: SeeChart: enabling accessible visualizations through interactive natural language interface for people with visual impairments. In: Proceedings of the 28th International Conference on Intelligent User Interfaces, pp. 46\u201364 (2023)","DOI":"10.1145\/3581641.3584099"},{"key":"21_CR3","unstructured":"Bansal, H., Grover, A.: Leaving reality to imagination: Robust classification via generated datasets. In: ICLR 2023 Workshop on Trustworthy and Reliable Large-Scale Machine Learning Models (2023)"},{"key":"21_CR4","unstructured":"Blecher, L., Cucurull, G., Scialom, T., Stojnic, R.: Nougat: neural optical understanding for academic documents. In: The Twelfth International Conference on Learning Representations (2023)"},{"key":"21_CR5","doi-asserted-by":"crossref","unstructured":"Cascante-Bonilla, P., et\u00a0al.: Going beyond nouns with vision & language models using synthetic data. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 20155\u201320165 (2023)","DOI":"10.1109\/ICCV51070.2023.01844"},{"key":"21_CR6","doi-asserted-by":"crossref","unstructured":"Chen, S., Hou, Y., Cui, Y., Che, W., Liu, T., Yu, X.: Recall and learn: Fine-tuning deep pretrained language models with less forgetting. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 7870\u20137881 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.634"},{"key":"21_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"104","DOI":"10.1007\/978-3-030-58577-8_7","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y-C Chen","year":"2020","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"},{"key":"21_CR8","doi-asserted-by":"crossref","unstructured":"Cheng, Z.Q., Dai, Q., Hauptmann, A.G.: ChartReader: a unified framework for chart derendering and comprehension without heuristic rules. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 22202\u201322213 (2023)","DOI":"10.1109\/ICCV51070.2023.02029"},{"key":"21_CR9","doi-asserted-by":"crossref","unstructured":"Chintalapati, S.S., Bragg, J., Wang, L.L.: A dataset of alt texts from HCI publications: Analyses and uses towards producing more descriptive alt texts of data visualizations in scientific papers. In: Proceedings of the 24th International ACM SIGACCESS Conference on Computers and Accessibility, pp. 1\u201312 (2022)","DOI":"10.1145\/3517428.3544796"},{"key":"21_CR10","unstructured":"Commission, D.R.: The Web: Access and Inclusion for Disabled People; A Formal Investigation. The Stationery Office (2004)"},{"key":"21_CR11","doi-asserted-by":"crossref","unstructured":"Deshpande, A., Rock, J., Forsyth, D.: Learning large-scale automatic image colorization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 567\u2013575 (2015)","DOI":"10.1109\/ICCV.2015.72"},{"key":"21_CR12","doi-asserted-by":"publisher","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Burstein, J., Doran, C., Solorio, T. (eds.) Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pp. 4171\u20134186. Association for Computational Linguistics, Minneapolis, Minnesota (2019). https:\/\/doi.org\/10.18653\/v1\/N19-1423, https:\/\/aclanthology.org\/N19-1423","DOI":"10.18653\/v1\/N19-1423"},{"key":"21_CR13","unstructured":"Diagram center: specific guidelines - graphs. http:\/\/diagramcenter.org\/specific-guidelines-e.html (2022)"},{"key":"21_CR14","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16$$\\times $$16 words: transformers for image recognition at scale. In: International Conference on Learning Representations (2020)"},{"key":"21_CR15","doi-asserted-by":"crossref","unstructured":"Farahani, A.M., Adibi, P., Darvishy, A., Ehsani, M.S., Hutter, H.P.: Automatic chart understanding: a review. IEEE Access (2023)","DOI":"10.1109\/ACCESS.2023.3298050"},{"issue":"4","key":"21_CR16","doi-asserted-by":"publisher","first-page":"681","DOI":"10.1007\/s11023-020-09548-1","volume":"30","author":"L Floridi","year":"2020","unstructured":"Floridi, L., Chiriatti, M.: GPT-3: Its nature, scope, limits, and consequences. Minds Mach. 30(4), 681\u2013694 (2020). https:\/\/doi.org\/10.1007\/s11023-020-09548-1","journal-title":"Minds Mach."},{"key":"21_CR17","unstructured":"Gidaris, S., Singh, P., Komodakis, N.: Unsupervised representation learning by predicting image rotations (2018)"},{"key":"21_CR18","unstructured":"Han, Y., et al.: ChartLlama: a multimodal LLM for chart understanding and generation. arXiv preprint arXiv:2311.16483 (2023)"},{"key":"21_CR19","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"21_CR20","doi-asserted-by":"crossref","unstructured":"Isola, P., Zhu, J.Y., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks (2018)","DOI":"10.1109\/CVPR.2017.632"},{"issue":"1","key":"21_CR21","doi-asserted-by":"publisher","first-page":"2","DOI":"10.3390\/technologies9010002","volume":"9","author":"A Jaiswal","year":"2020","unstructured":"Jaiswal, A., Babu, A.R., Zadeh, M.Z., Banerjee, D., Makedon, F.: A survey on contrastive self-supervised learning. Technologies 9(1), 2 (2020)","journal-title":"Technologies"},{"key":"21_CR22","doi-asserted-by":"crossref","unstructured":"Jung, C., Mehta, S., Kulkarni, A., Zhao, Y., Kim, Y.S.: Communicating visualizations without visuals: investigation of visualization alternative text for people with visual impairments (2021)","DOI":"10.1109\/TVCG.2021.3114846"},{"key":"21_CR23","doi-asserted-by":"crossref","unstructured":"Kantharaj, S., et al.: Chart-to-text: a large-scale benchmark for chart summarization. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 4005\u20134023 (2022)","DOI":"10.18653\/v1\/2022.acl-long.277"},{"key":"21_CR24","doi-asserted-by":"crossref","unstructured":"Kim, G., et al.: OCR-free document understanding transformer. In: European Conference on Computer Vision, pp. 498\u2013517 (2022)","DOI":"10.1007\/978-3-031-19815-1_29"},{"key":"21_CR25","unstructured":"Lee, K., et al.: Pix2Struct: screenshot parsing as pretraining for visual language understanding. In: International Conference on Machine Learning, pp. 18893\u201318912. PMLR (2023)"},{"key":"21_CR26","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.: BLIP: bootstrapping language-image pre-training for unified vision-language understanding and generation. In: International Conference on Machine Learning, pp. 12888\u201312900. PMLR (2022)"},{"key":"21_CR27","doi-asserted-by":"crossref","unstructured":"Liu, F., et al.: MatCha: enhancing visual language pretraining with math reasoning and chart derendering (2023)","DOI":"10.18653\/v1\/2023.acl-long.714"},{"key":"21_CR28","unstructured":"Liu, H., et al.: A survey on hallucination in large vision-language models. arXiv preprint arXiv:2402.00253 (2024)"},{"key":"21_CR29","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Li, Y., Lee, Y.J.: Improved baselines with visual instruction tuning (2023)","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"21_CR30","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"issue":"1","key":"21_CR31","doi-asserted-by":"publisher","first-page":"1073","DOI":"10.1109\/TVCG.2021.3114770","volume":"28","author":"A Lundgard","year":"2021","unstructured":"Lundgard, A., Satyanarayan, A.: Accessible visualization via natural language descriptions: a four-level model of semantic content. IEEE Trans. Visual Comput. Graphics 28(1), 1073\u20131083 (2021)","journal-title":"IEEE Trans. Visual Comput. Graphics"},{"key":"21_CR32","doi-asserted-by":"crossref","unstructured":"Mack, K., Cutrell, E., Lee, B., Morris, M.R.: Designing tools for high-quality alt text authoring. In: Proceedings of the 23rd International ACM SIGACCESS Conference on Computers and Accessibility, pp. 1\u201314 (2021)","DOI":"10.1145\/3441852.3471207"},{"key":"21_CR33","doi-asserted-by":"crossref","unstructured":"Masry, A., Do, X.L., Tan, J.Q., Joty, S., Hoque, E.: ChartQA: a benchmark for question answering about charts with visual and logical reasoning. In: Findings of the Association for Computational Linguistics: ACL 2022, pp. 2263\u20132279 (2022)","DOI":"10.18653\/v1\/2022.findings-acl.177"},{"key":"21_CR34","doi-asserted-by":"crossref","unstructured":"Masry, A., Kavehzadeh, P., Do, X.L., Hoque, E., Joty, S.: UniChart: a universal vision-language pretrained model for chart comprehension and reasoning. In: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pp. 14662\u201314684 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.906"},{"key":"21_CR35","doi-asserted-by":"crossref","unstructured":"Meng, F., et al.: ChartAssisstant: a universal chart multimodal language model via chart-to-table pre-training and multitask instruction tuning. arXiv preprint arXiv:2401.02384 (2024)","DOI":"10.18653\/v1\/2024.findings-acl.463"},{"key":"21_CR36","doi-asserted-by":"crossref","unstructured":"Misra, I., Maaten, L.v.d.: Self-supervised learning of pretext-invariant representations. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6707\u20136717 (2020)","DOI":"10.1109\/CVPR42600.2020.00674"},{"key":"21_CR37","doi-asserted-by":"crossref","unstructured":"Moured, O., Alzalabny, S., Schwarz, T., Rapp, B., Stiefelhagen, R.: Accessible document layout: an interface for 2D tactile displays. In: Proceedings of the 16th International Conference on PErvasive Technologies Related to Assistive Environments, pp. 265\u2013271 (2023)","DOI":"10.1145\/3594806.3594811"},{"key":"21_CR38","doi-asserted-by":"crossref","unstructured":"Moured, O., Baumgarten-Egemole, M., M\u00fcller, K., Roitberg, A., Schwarz, T., Stiefelhagen, R.: Chart4Blind: an intelligent interface for chart accessibility conversion. In: Proceedings of the 29th International Conference on Intelligent User Interfaces, pp. 504\u2013514 (2024)","DOI":"10.1145\/3640543.3645175"},{"key":"21_CR39","doi-asserted-by":"publisher","unstructured":"Moured, O., Zhang, J., Roitberg, A., Schwarz, T., Stiefelhagen, R.: Line graphics digitization: a step towards full automation. In: Fink, G.A., Jain, R., Kise, K., Zanibbi, R. (eds.) International Conference on Document Analysis and Recognition, vol. 14191, pp. 438\u2013453. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-41734-4_27","DOI":"10.1007\/978-3-031-41734-4_27"},{"key":"21_CR40","doi-asserted-by":"crossref","unstructured":"Noroozi, M., Favaro, P.: Unsupervised learning of visual representations by solving jigsaw puzzles (2017)","DOI":"10.1007\/978-3-319-46466-4_5"},{"key":"21_CR41","doi-asserted-by":"crossref","unstructured":"Post, M.: A call for clarity in reporting bleu scores. In: Proceedings of the Third Conference on Machine Translation: Research Papers, pp. 186\u2013191 (2018)","DOI":"10.18653\/v1\/W18-6319"},{"key":"21_CR42","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"issue":"1","key":"21_CR43","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":"21_CR44","unstructured":"Rahman, R., Hasan, R., Farhad, A.A.: ChartSumm: a large scale benchmark for Chart to Text Summarization. Ph.D. thesis, Department of Computer Science and Engineering (CSE), Islamic University (2022)"},{"issue":"4","key":"21_CR45","doi-asserted-by":"publisher","first-page":"2761","DOI":"10.1007\/s11831-023-09884-2","volume":"30","author":"V Rani","year":"2023","unstructured":"Rani, V., Nabi, S.T., Kumar, M., Mittal, A., Kumar, K.: Self-supervised learning: a succinct review. Arch. Comput. Methods Eng. 30(4), 2761\u20132775 (2023)","journal-title":"Arch. Comput. Methods Eng."},{"key":"21_CR46","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, vol. 28 (2015)"},{"key":"21_CR47","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015","author":"O Ronneberger","year":"2015","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234\u2013241. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28"},{"issue":"2","key":"21_CR48","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3485766","volume":"55","author":"AB Sai","year":"2022","unstructured":"Sai, A.B., Mohankumar, A.K., Khapra, M.M.: A survey of evaluation metrics used for NLG systems. ACM Comput. Surv. (CSUR) 55(2), 1\u201339 (2022)","journal-title":"ACM Comput. Surv. (CSUR)"},{"issue":"13s","key":"21_CR49","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3577925","volume":"55","author":"MC Schiappa","year":"2023","unstructured":"Schiappa, M.C., Rawat, Y.S., Shah, M.: Self-supervised learning for videos: a survey. ACM Comput. Surv. 55(13s), 1\u201337 (2023)","journal-title":"ACM Comput. Surv."},{"key":"21_CR50","doi-asserted-by":"crossref","unstructured":"Tang, B., Boggust, A., Satyanarayan, A.: VisText: a benchmark for semantically rich chart captioning. In: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 7268\u20137298 (2023)","DOI":"10.18653\/v1\/2023.acl-long.401"},{"key":"21_CR51","unstructured":"Touvron, H., et\u00a0al.: Llama 2: open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)"},{"key":"21_CR52","unstructured":"W3C: Standards (2022). https:\/\/www.w3.org\/standards\/"},{"key":"21_CR53","doi-asserted-by":"crossref","unstructured":"Wang, Z., et al.: Scaling data generation in vision-and-language navigation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 12009\u201312020 (2023)","DOI":"10.1109\/ICCV51070.2023.01103"},{"key":"21_CR54","unstructured":"Web Content Accessibility Guidelines (WCAG): complex images (2022). https:\/\/www.w3.org\/WAI\/tutorials\/images\/complex\/"},{"key":"21_CR55","unstructured":"WebAIM: Screen reader user survey 9 results (2021). https:\/\/webaim.org\/projects\/screenreadersurvey9\/"},{"key":"21_CR56","doi-asserted-by":"crossref","unstructured":"Xu, Y., Zhong, X., Yepes, A.J.J., Lau, J.H.: Forget me not: reducing catastrophic forgetting for domain adaptation in reading comprehension. In: 2020 International Joint Conference on Neural Networks (IJCNN), pp.\u00a01\u20138. IEEE (2020)","DOI":"10.1109\/IJCNN48605.2020.9206891"},{"key":"21_CR57","doi-asserted-by":"crossref","unstructured":"Zhang, R., Isola, P., Efros, A.A.: Colorful image colorization (2016)","DOI":"10.1007\/978-3-319-46487-9_40"},{"key":"21_CR58","doi-asserted-by":"crossref","unstructured":"Zhu, J., Ran, J., Lee, R.K.W., Li, Z., Choo, K.: AutoChart: a dataset for chart-to-text generation task. In: Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021), pp. 1636\u20131644 (2021)","DOI":"10.26615\/978-954-452-072-4_183"}],"container-title":["Lecture Notes in Computer Science","Document Analysis and Recognition - ICDAR 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-70533-5_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T21:46:11Z","timestamp":1732743971000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-70533-5_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031705328","9783031705335"],"references-count":58,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-70533-5_21","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"8 September 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The first author has received a fund grant from the European Union\u2019s Horizon 2020 research and innovation program under the Marie Sklodowska-Curie Grant No.861166.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"ICDAR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Document Analysis and Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Athens","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":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 August 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 September 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icdar2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icdar2024.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}