{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T17:38:02Z","timestamp":1758044282751,"version":"3.44.0"},"publisher-location":"Cham","reference-count":36,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032046130","type":"print"},{"value":"9783032046147","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,9,13]],"date-time":"2025-09-13T00:00:00Z","timestamp":1757721600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,13]],"date-time":"2025-09-13T00:00:00Z","timestamp":1757721600000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-04614-7_11","type":"book-chapter","created":{"date-parts":[[2025,9,12]],"date-time":"2025-09-12T12:22:41Z","timestamp":1757679761000},"page":"183-199","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["AI-Generated Lecture Slides for\u00a0Improving Slide Element Detection and\u00a0Retrieval"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-5882-4377","authenticated-orcid":false,"given":"Suyash","family":"Maniyar","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0004-5043-6766","authenticated-orcid":false,"given":"Vishvesh","family":"Trivedi","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4808-8860","authenticated-orcid":false,"given":"Ajoy","family":"Mondal","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7806-2557","authenticated-orcid":false,"given":"Anand","family":"Mishra","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6767-7057","authenticated-orcid":false,"given":"C.\u00a0V.","family":"Jawahar","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,9,13]]},"reference":[{"key":"11_CR1","doi-asserted-by":"crossref","unstructured":"Appalaraju, S., Jasani, B., Kota, B.U., Xie, Y., Manmatha, R.: DocFormer: end-to-end transformer for document understanding. In: ICCV, pp. 993\u20131003 (2021)","DOI":"10.1109\/ICCV48922.2021.00103"},{"key":"11_CR2","doi-asserted-by":"crossref","unstructured":"Araujo, A., Chaves, J., Lakshman, H., Angst, R., Girod, B.: Large-scale query-by-image video retrieval using bloom filters. arXiv preprint arXiv:1604.07939 (2016)","DOI":"10.1109\/ICIP.2015.7351054"},{"key":"11_CR3","unstructured":"Blanes, A.R.: Synthetic handwritten text generation. Univ. Aut\u00f2noma de Barcelona (2018)"},{"key":"11_CR4","unstructured":"Brown, T., et al.: Language models are few-shot learners. In: NeurIPS, vol. 33, pp. 1877\u20131901 (2020)"},{"key":"11_CR5","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: ECCV, pp. 213\u2013229 (2020)","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"11_CR6","doi-asserted-by":"crossref","unstructured":"Da, C., Luo, C., Zheng, Q., Yao, C.: Vision grid transformer for document layout analysis. In: ICCV, pp. 19462\u201319472 (2023)","DOI":"10.1109\/ICCV51070.2023.01783"},{"key":"11_CR7","doi-asserted-by":"crossref","unstructured":"Haurilet, M., Al-Halah, Z., Stiefelhagen, R.: Spase-multi-label page segmentation for presentation slides. In: WACV, pp. 726\u2013734 (2019)","DOI":"10.1109\/WACV.2019.00082"},{"key":"11_CR8","doi-asserted-by":"crossref","unstructured":"Haurilet, M., Roitberg, A., Martinez, M., Stiefelhagen, R.: Wise\u2014slide segmentation in the wild. In: ICDAR, pp. 343\u2013348 (2019)","DOI":"10.1109\/ICDAR.2019.00062"},{"key":"11_CR9","doi-asserted-by":"crossref","unstructured":"He, L., Lu, Y., Corring, J., Florencio, D., Zhang, C.: Diffusion-based document layout generation. In: ICDAR, pp. 361\u2013378 (2023)","DOI":"10.1007\/978-3-031-41676-7_21"},{"key":"11_CR10","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: GANs trained by a two time-scale update rule converge to a local Nash equilibrium. In: NeurIPS, pp. 6629\u20136640 (2017)"},{"key":"11_CR11","doi-asserted-by":"crossref","unstructured":"Huang, Y., Lv, T., Cui, L., Lu, Y., Wei, F.: LayoutLMV3: pre-training for document AI with unified text and image masking. In: ACM MM (2022)","DOI":"10.1145\/3503161.3548112"},{"key":"11_CR12","doi-asserted-by":"crossref","unstructured":"Jobin, K., Mishra, A., Jawahar, C.: Semantic labels-aware transformer model for searching over a large collection of lecture-slides. In: WACV (2024)","DOI":"10.1109\/WACV57701.2024.00591"},{"key":"11_CR13","doi-asserted-by":"crossref","unstructured":"Jobin, K., Mondal, A., Jawahar, C.: Classroom slide narration system. In: CVIP, pp. 135\u2013146 (2021)","DOI":"10.1007\/978-3-031-11349-9_12"},{"key":"11_CR14","doi-asserted-by":"crossref","unstructured":"Kim, J., Choi, Y., Kahng, M., Kim, J.: FitVid: responsive and flexible video content adaptation. In: ACM CHI, pp. 1\u201316 (2022)","DOI":"10.1145\/3491102.3501948"},{"key":"11_CR15","doi-asserted-by":"crossref","unstructured":"Lee, D.W., Ahuja, C., Liang, P.P., Natu, S., Morency, L.P.: Multimodal lecture presentations dataset: understanding multimodality in educational slides. arXiv (2022)","DOI":"10.1109\/ICCV51070.2023.01838"},{"key":"11_CR16","doi-asserted-by":"crossref","unstructured":"Li, I., Fabbri, A.R., Tung, R.R., Radev, D.R.: What should i learn first: introducing lecturebank for NLP education and prerequisite chain learning. In: AAAI, vol.\u00a033, pp. 6674\u20136681 (2019)","DOI":"10.1609\/aaai.v33i01.33016674"},{"key":"11_CR17","doi-asserted-by":"crossref","unstructured":"Li, M., et al.: DocBank: a benchmark dataset for document layout analysis. arXiv preprint arXiv:2006.01038 (2020)","DOI":"10.18653\/v1\/2020.coling-main.82"},{"key":"11_CR18","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., et al.: Microsoft COCO: common objects in context. In: ECCV, pp. 740\u2013755 (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"11_CR19","doi-asserted-by":"crossref","unstructured":"Osuala, R.: Enhancing the utility of privacy-preserving cancer classification using synthetic data. In: MICCAI Workshop, p.\u00a054 (2024)","DOI":"10.1007\/978-3-031-77789-9_6"},{"key":"11_CR20","doi-asserted-by":"crossref","unstructured":"Peng, Y.H., et al.: DreamStruct: understanding slides and user interfaces via synthetic data generation. In: ECCV, pp. 466\u2013485 (2024)","DOI":"10.1007\/978-3-031-72691-0_26"},{"key":"11_CR21","doi-asserted-by":"crossref","unstructured":"Pfitzmann, B., Auer, C., Dolfi, M., Nassar, A.S., Staar, P.: DocLayNet: a large human-annotated dataset for document-layout segmentation. In: ACM SIGKDD (2022)","DOI":"10.1145\/3534678.3539043"},{"key":"11_CR22","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1016\/j.patrec.2023.01.018","volume":"167","author":"L Pisaneschi","year":"2023","unstructured":"Pisaneschi, L., Gemelli, A., Marinai, S.: Automatic generation of scientific papers for data augmentation in document layout analysis. Pattern Recogn. Lett. 167, 38\u201344 (2023)","journal-title":"Pattern Recogn. Lett."},{"key":"11_CR23","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: ICML (2021)"},{"key":"11_CR24","doi-asserted-by":"crossref","unstructured":"Seng, T., Carlier, A., Forgione, T., Charvillat, V., Ooi, W.T.: SlideCraft: synthetic slides generation for robust slide analysis. In: ICDAR, pp. 79\u201396 (2024)","DOI":"10.1007\/978-3-031-70533-5_6"},{"key":"11_CR25","doi-asserted-by":"crossref","unstructured":"Shakeri, S., et al.: End-to-end synthetic data generation for domain adaptation of question answering systems. arXiv (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.439"},{"key":"11_CR26","doi-asserted-by":"crossref","unstructured":"Shao, Y., Jiang, Y., Kanell, T.A., Xu, P., Khattab, O., Lam, M.S.: Assisting in writing Wikipedia-like articles from scratch with large language models. arXiv preprint arXiv:2402.14207 (2024)","DOI":"10.18653\/v1\/2024.naacl-long.347"},{"key":"11_CR27","doi-asserted-by":"crossref","unstructured":"Shu, K., Li, Y., Ding, K., Liu, H.: Fact-enhanced synthetic news generation. In: AAAI, vol. 35, pp. 13825\u201313833 (2021)","DOI":"10.1609\/aaai.v35i15.17629"},{"key":"11_CR28","doi-asserted-by":"crossref","unstructured":"Singh, K., Navaratnam, T., Holmer, J., Schaub-Meyer, S., Roth, S.: Is synthetic data all we need? Benchmarking the robustness of models trained with synthetic images. In: CVPR, pp. 2505\u20132515 (2024)","DOI":"10.1109\/CVPRW63382.2024.00257"},{"key":"11_CR29","doi-asserted-by":"crossref","unstructured":"Song, Y., Soleymani, M.: Polysemous visual-semantic embedding for cross-modal retrieval. In: CVPR, pp. 1979\u20131988 (2019)","DOI":"10.1109\/CVPR.2019.00208"},{"issue":"5","key":"11_CR30","doi-asserted-by":"publisher","first-page":"264","DOI":"10.3390\/info15050264","volume":"15","author":"F Sufi","year":"2024","unstructured":"Sufi, F.: Addressing data scarcity in the medical domain: a GPT-based approach for synthetic data generation and feature extraction. Information 15(5), 264 (2024)","journal-title":"Information"},{"key":"11_CR31","doi-asserted-by":"crossref","unstructured":"Tanaka, R., Nishida, K., Nishida, K., Hasegawa, T., Saito, I., Saito, K.: SlideVQA: a dataset for document visual question answering on multiple images. In: AAAI, pp. 13636\u201313645 (2023)","DOI":"10.1609\/aaai.v37i11.26598"},{"key":"11_CR32","doi-asserted-by":"crossref","unstructured":"Tang, Z., et al.: Unifying vision, text, and layout for universal document processing. In: CVPR, pp. 19254\u201319264 (2023)","DOI":"10.1109\/CVPR52729.2023.01845"},{"key":"11_CR33","doi-asserted-by":"crossref","unstructured":"Wang, C.Y., Yeh, I.H., Mark\u00a0Liao, H.Y.: YOLOV9: learning what you want to learn using programmable gradient information. In: ECCV (2024)","DOI":"10.1007\/978-3-031-72751-1_1"},{"key":"11_CR34","unstructured":"Wei, J., et al.: Chain-of-thought prompting elicits reasoning in large language models. In: NeurIPS, vol. 35, pp. 24824\u201324837 (2022)"},{"key":"11_CR35","unstructured":"Yu, Z., Zhu, C., Culatana, S., Krishnamoorthi, R., Xiao, F., Lee, Y.J.: Diversify, don\u2019t fine-tune: Scaling up visual recognition training with synthetic images. arXiv preprint arXiv:2312.02253 (2023)"},{"key":"11_CR36","doi-asserted-by":"crossref","unstructured":"Zhong, X., Tang, J., Yepes, A.J.: PubLayNet: largest dataset ever for document layout analysis. In: ICDAR (2019)","DOI":"10.1109\/ICDAR.2019.00166"}],"container-title":["Lecture Notes in Computer Science","Document Analysis and Recognition \u2013 ICDAR 2025"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-04614-7_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,12]],"date-time":"2025-09-12T12:22:51Z","timestamp":1757679771000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-04614-7_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,13]]},"ISBN":["9783032046130","9783032046147"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-04614-7_11","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,13]]},"assertion":[{"value":"13 September 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"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":"Wuhan","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":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icdar2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iapr.org\/icdar2025","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}