{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,27]],"date-time":"2025-08-27T15:48:47Z","timestamp":1756309727999,"version":"3.40.3"},"publisher-location":"Cham","reference-count":41,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031438486"},{"type":"electronic","value":"9783031438493"}],"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\/978-3-031-43849-3_16","type":"book-chapter","created":{"date-parts":[[2023,9,21]],"date-time":"2023-09-21T21:01:25Z","timestamp":1695330085000},"page":"182-191","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Classification of\u00a0Visualization Types and\u00a0Perspectives in\u00a0Patents"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9248-5444","authenticated-orcid":false,"given":"Junaid Ahmed","family":"Ghauri","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6802-1241","authenticated-orcid":false,"given":"Eric","family":"M\u00fcller-Budack","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0918-6297","authenticated-orcid":false,"given":"Ralph","family":"Ewerth","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,9,22]]},"reference":[{"key":"16_CR1","unstructured":"Chen, G., Yao, W., Song, X., Li, X., Rao, Y., Zhang, K.: PLOT: prompt learning with optimal transport for vision-language models. In: International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, 1\u20135 May 2023. OpenReview.net (2023). https:\/\/openreview.net\/pdf?id=zqwryBoXYnh"},{"key":"16_CR2","unstructured":"Chen, X., et al.: PaLI: a jointly-scaled multilingual language-image model. In: International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, 1\u20135 May 2023. OpenReview.net (2023). https:\/\/openreview.net\/pdf?id=mWVoBz4W0u"},{"key":"16_CR3","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, 3\u20137 May 2021. OpenReview.net (2021). https:\/\/openreview.net\/forum?id=YicbFdNTTy"},{"key":"16_CR4","unstructured":"Gralinski, F., et al.: Kleister: a novel task for Information Extraction involving Long Documents with Complex Layout. arXiv preprint abs\/2003.02356 (2020). https:\/\/arxiv.org\/abs\/2003.02356"},{"key":"16_CR5","doi-asserted-by":"publisher","unstructured":"Hanbury, A., et al.: Patent image retrieval: a survey. In: Workshop on Patent Information Retrieval, PaIR 2011, Glasgow, Scotland, UK, 24 October 2011. ACM (2011). https:\/\/doi.org\/10.1145\/2064975.2064979","DOI":"10.1145\/2064975.2064979"},{"key":"16_CR6","doi-asserted-by":"publisher","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016, Las Vegas, NV, USA, 27\u201330 June 2016. IEEE Computer Society (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"16_CR7","unstructured":"Houlsby, N., et al.: Parameter-efficient transfer learning for NLP. In: International Conference on Machine Learning, ICML 2019, 9\u201315 June 2019, Long Beach, California, USA. PMLR (2019)"},{"key":"16_CR8","unstructured":"Hu, X., Zhang, L., Liu, J., Fan, J., You, Y., Wu, Y.: GPTR: Gestalt-Perception Transformer for Diagram Object Detection. arXiv preprint abs\/2212.14232 (2022). https:\/\/doi.org\/10.48550\/arXiv.2212.14232"},{"key":"16_CR9","doi-asserted-by":"publisher","unstructured":"Jiang, S., Luo, J., Pava, G.R., Hu, J., Magee, C.L.: A convolutional neural network-based patent image retrieval method for design ideation. In: International Design Engineering Technical Conferences & Computers and Information in Engineering Conference, IDETC-CIE 2020, Online, Virtual, 17\u201319 August 2020. The American Society of Mechanical Engineers (ASME) (2020). https:\/\/doi.org\/10.1115\/DETC2020-22048","DOI":"10.1115\/DETC2020-22048"},{"key":"16_CR10","doi-asserted-by":"publisher","unstructured":"Jobin, K.V., Mondal, A., Jawahar, C.V.: DocFigure: a dataset for scientific document figure classification. In: IAPR International Workshop on Graphics Recognition co-located with International Conference on Document Analysis and Recognition, GREC@ICDAR 2019, Sydney, Australia, 22\u201325 September 2019. IEEE (2019). https:\/\/doi.org\/10.1109\/ICDARW.2019.00018","DOI":"10.1109\/ICDARW.2019.00018"},{"key":"16_CR11","doi-asserted-by":"publisher","unstructured":"Joho, H., Azzopardi, L., Vanderbauwhede, W.: A survey of patent users: an analysis of tasks, behavior, search functionality and system requirements. In: Information Interaction in Context Symposium, IIiX 2010, New Brunswick, NJ, USA, 18\u201321 August 2010. ACM (2010). https:\/\/doi.org\/10.1145\/1840784.1840789","DOI":"10.1145\/1840784.1840789"},{"key":"16_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"235","DOI":"10.1007\/978-3-319-46493-0_15","volume-title":"Computer Vision \u2013 ECCV 2016","author":"A Kembhavi","year":"2016","unstructured":"Kembhavi, A., Salvato, M., Kolve, E., Seo, M., Hajishirzi, H., Farhadi, A.: A diagram is worth a dozen images. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 235\u2013251. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_15"},{"key":"16_CR13","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, 7\u20139 May 2015 (2015)"},{"key":"16_CR14","doi-asserted-by":"publisher","DOI":"10.1016\/j.wpi.2021.102035","volume":"65","author":"R Krestel","year":"2021","unstructured":"Krestel, R., Chikkamath, R., Hewel, C., Risch, J.: A survey on deep learning for patent analysis. World Pat. Inf. 65, 102035 (2021). https:\/\/doi.org\/10.1016\/j.wpi.2021.102035","journal-title":"World Pat. Inf."},{"key":"16_CR15","doi-asserted-by":"publisher","unstructured":"Kucer, M., Oyen, D., Castorena, J., Wu, J.: DeepPatent: large scale patent drawing recognition and retrieval. In: IEEE\/CVF Winter Conference on Applications of Computer Vision, WACV 2022, Waikoloa, HI, USA, 3\u20138 January 2022. IEEE (2022). https:\/\/doi.org\/10.1109\/WACV51458.2022.00063","DOI":"10.1109\/WACV51458.2022.00063"},{"key":"16_CR16","unstructured":"Lee, K., et al.: Pix2Struct: Screenshot Parsing as Pretraining for Visual Language understanding. arXiv preprint abs\/2210.03347 (2022). https:\/\/doi.org\/10.48550\/arXiv.2210.03347"},{"key":"16_CR17","doi-asserted-by":"crossref","unstructured":"Li, X.L., Liang, P.: Prefix-tuning: optimizing continuous prompts for generation. In: Annual Meeting of the Association for Computational Linguistics and the International Joint Conference on Natural Language Processing, ACL\/IJCNLP 2021, Virtual Event, 1\u20136 August 2021. Association for Computational Linguistics (2021)","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"16_CR18","unstructured":"Lian, D., Zhou, D., Feng, J., Wang, X.: Scaling & shifting your features: a new baseline for efficient model tuning. In: Conference on Neural Information Processing Systems, NeurIPS 2022, New Orleans, Louisiana, 28 Nov 2022 \u2013 9 Dec 2022 (2022)"},{"issue":"2","key":"16_CR19","doi-asserted-by":"publisher","first-page":"491","DOI":"10.1002\/smj.3441","volume":"44","author":"M Miric","year":"2022","unstructured":"Miric, M., Jia, N., Huang, K.G.: Using supervised machine learning for large-scale classification in management research: the case for identifying artificial intelligence patents. Strateg. Manag. J. 44(2), 491\u2013519 (2022)","journal-title":"Strateg. Manag. J."},{"key":"16_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"289","DOI":"10.1007\/978-3-030-45442-5_36","volume-title":"Advances in Information Retrieval","author":"D Morris","year":"2020","unstructured":"Morris, D., M\u00fcller-Budack, E., Ewerth, R.: SlideImages: a dataset for educational image classification. In: Jose, J.M., et al. (eds.) ECIR 2020. LNCS, vol. 12036, pp. 289\u2013296. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-45442-5_36"},{"key":"16_CR21","doi-asserted-by":"publisher","unstructured":"Nazir, D., Hashmi, K.A., Pagani, A., Liwicki, M., Stricker, D., Afzal, M.Z.: HybridTabNet: towards better table detection in scanned document images. Appl. Sci. 11(18), 8396 (2021). https:\/\/doi.org\/10.3390\/app11188396","DOI":"10.3390\/app11188396"},{"key":"16_CR22","doi-asserted-by":"publisher","unstructured":"Paliwal, S.S., Vishwanath, D., Rahul, R., Sharma, M., Vig, L.: TableNet: deep learning model for end-to-end table detection and tabular data extraction from scanned document images. In: International Conference on Document Analysis and Recognition, ICDAR 2019, Sydney, Australia, 20\u201325 September 2019. IEEE (2019). https:\/\/doi.org\/10.1109\/ICDAR.2019.00029","DOI":"10.1109\/ICDAR.2019.00029"},{"key":"16_CR23","unstructured":"Pan, J., Lin, Z., Zhu, X., Shao, J., Li, H.: ST-adapter: parameter-efficient image-to-video transfer learning. In: Conference on Neural Information Processing Systems, NeurIPS 2022, New Orleans, Louisiana, 28 Nov 2022 - 9 Dec 2022 (2022)"},{"key":"16_CR24","unstructured":"Piroi, F., Lupu, M., Hanbury, A., Zenz, V.: CLEF-IP 2011: Retrieval in the Intellectual Property Domain. In: CLEF 2011 Labs and Workshop, Notebook Papers, 19\u201322 September 2011, Amsterdam, The Netherlands. CEUR Workshop Proceedings. vol. 1177. CEUR-WS.org (2011). https:\/\/ceur-ws.org\/Vol-1177\/CLEF2011wn-CLEF-IP-PiroiEt2011.pdf"},{"key":"16_CR25","unstructured":"Pustu-Iren, K., Bruns, G., Ewerth, R.: A multimodal approach for semantic patent image retrieval. In: Workshop on Patent Text Mining and Semantic Technologies co-located with International Conference on Research and Development in Information Retrieval, PatentSemTech@SIGIR 2021, July 11\u201315, 2021. ACM (2021)"},{"key":"16_CR26","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, ICML 2021, Virtual Event, 18\u201324 July 2021. PMLR (2021). http:\/\/proceedings.mlr.press\/v139\/radford21a.html"},{"key":"16_CR27","doi-asserted-by":"publisher","unstructured":"Radosavovic, I., Kosaraju, R.P., Girshick, R.B., He, K., Doll\u00e1r, P.: Designing network design spaces. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020, Seattle, WA, USA, 13\u201319 June 2020. Computer Vision Foundation\/IEEE (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.01044","DOI":"10.1109\/CVPR42600.2020.01044"},{"key":"16_CR28","doi-asserted-by":"publisher","unstructured":"Schreiber, S., Agne, S., Wolf, I., Dengel, A., Ahmed, S.: DeepDeSRT: deep learning for detection and structure recognition of tables in document images. In: IAPR International Conference on Document Analysis and Recognition, ICDAR 2017 (2017). https:\/\/doi.org\/10.1109\/ICDAR.2017.192","DOI":"10.1109\/ICDAR.2017.192"},{"key":"16_CR29","unstructured":"Song, K., Ran, C., Yang, L.: A digital analysis system of patents integrating natural language processing and machine learning. Technol. Anal. Strateg. Manag. 34, 1\u201317 (2022)"},{"key":"16_CR30","doi-asserted-by":"crossref","unstructured":"Sung, Y.L., Cho, J., Bansal, M.: VL-adapter: parameter-efficient transfer learning for vision-and-language tasks. In: Conference on Computer Vision and Pattern Recognition, CVPR 2022, 19 Jun 2022 - 24 Jun 2022. IEEE\/CVF (2022)","DOI":"10.1109\/CVPR52688.2022.00516"},{"key":"16_CR31","unstructured":"Tan, M., Le, Q.V.: EfficientNetV2: smaller models and faster training. In: Proceedings of the International Conference on Machine Learning, ICML 2021, 18\u201324 July 2021, Virtual Event. PMLR (2021)"},{"issue":"4","key":"16_CR32","doi-asserted-by":"publisher","first-page":"292","DOI":"10.1016\/j.wpi.2012.07.002","volume":"34","author":"S Vrochidis","year":"2012","unstructured":"Vrochidis, S., Moumtzidou, A., Kompatsiaris, I.: Concept-based patent image retrieval. World Pat. Inf. 34(4), 292\u2013303 (2012). https:\/\/doi.org\/10.1016\/j.wpi.2012.07.002","journal-title":"World Pat. Inf."},{"key":"16_CR33","unstructured":"Wang, S., Zhang, L., Luo, X., Yang, Y., Hu, X., Liu, J.: RL-CSDia: Representation Learning of Computer Science Diagrams. arXiv preprint abs\/2103.05900 (2021), https:\/\/arxiv.org\/abs\/2103.05900"},{"key":"16_CR34","doi-asserted-by":"publisher","unstructured":"Wei, X., Wu, J., Ajayi, K., Oyen, D.: Visual descriptor extraction from patent figure captions: a case study of data efficiency between BiLSTM and transformer. In: Joint Conference on Digital Libraries, JCDL 2022, Cologne, Germany, 20\u201324 June 2022. ACM\/IEEE (2022), https:\/\/doi.org\/10.1145\/3529372.3533299","DOI":"10.1145\/3529372.3533299"},{"key":"16_CR35","unstructured":"WIPO Statistics Database: IP Facts and Figures (2023). https:\/\/www.wipo.int\/en\/ipfactsandfigures\/patents. Accessed 24 July 2023"},{"key":"16_CR36","unstructured":"Wortsman, M., et al.: Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time. In: International Conference on Machine Learning, ICML 2022, 17\u201323 July 2022, Baltimore, Maryland, USA. PMLR (2022). https:\/\/proceedings.mlr.press\/v162\/wortsman22a.html"},{"key":"16_CR37","doi-asserted-by":"publisher","unstructured":"Xie, S., Girshick, R.B., Doll\u00e1r, P., Tu, Z., He, K.: Aggregated residual transformations for deep neural networks. In: Conference on Computer Vision and Pattern Recognition, CVPR 2017, Honolulu, HI, USA, 21\u201326 July 2017. IEEE Computer Society (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.634","DOI":"10.1109\/CVPR.2017.634"},{"key":"16_CR38","doi-asserted-by":"publisher","unstructured":"Yang, L., Gong, M., Asari, V.K.: Diagram image retrieval and analysis: challenges and opportunities. In: Conference on Computer Vision and Pattern Recognition, CVPR Workshops 2020, Seattle, WA, USA, 14\u201319 June 2020. IEEE\/CVF (2020). https:\/\/doi.org\/10.1109\/CVPRW50498.2020.00098","DOI":"10.1109\/CVPRW50498.2020.00098"},{"key":"16_CR39","unstructured":"Yu, J., Wang, Z., Vasudevan, V., Yeung, L., Seyedhosseini, M., Wu, Y.: CoCa: contrastive captioners are image-text foundation models. Trans. Mach. Learn. Res. 2022, 2835\u20138856 (2022). https:\/\/openreview.net\/forum?id=Ee277P3AYC"},{"key":"16_CR40","doi-asserted-by":"publisher","unstructured":"Zhou, K., Yang, J., Loy, C.C., Liu, Z.: Conditional prompt learning for vision-language models. In: Conference on Computer Vision and Pattern Recognition, CVPR 2022, New Orleans, LA, USA, 18\u201324 June 2022. IEEE\/CVF (2022). https:\/\/doi.org\/10.1109\/CVPR52688.2022.01631","DOI":"10.1109\/CVPR52688.2022.01631"},{"issue":"9","key":"16_CR41","doi-asserted-by":"publisher","first-page":"2337","DOI":"10.1007\/s11263-022-01653-1","volume":"130","author":"K Zhou","year":"2022","unstructured":"Zhou, K., Yang, J., Loy, C.C., Liu, Z.: Learning to prompt for vision-language models. Int. J. Comput. Vis. (IJCV) 130(9), 2337\u20132348 (2022)","journal-title":"Int. J. Comput. Vis. (IJCV)"}],"container-title":["Lecture Notes in Computer Science","Linking Theory and Practice of Digital Libraries"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-43849-3_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T16:04:06Z","timestamp":1710345846000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-43849-3_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031438486","9783031438493"],"references-count":41,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-43849-3_16","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":"TPDL","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Theory and Practice of Digital Libraries","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Zadar","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Croatia","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":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"tpdl2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/tpdl2023.dei.unipd.it\/","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":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"69","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":"13","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":"17","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":"19% - 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":"2","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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3 invited papers","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)"}}]}}