{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T15:49:08Z","timestamp":1780501748926,"version":"3.54.1"},"reference-count":52,"publisher":"American Society of Civil Engineers (ASCE)","issue":"6","content-domain":{"domain":["ascelibrary.org"],"crossmark-restriction":true},"short-container-title":["J. Comput. Civ. Eng."],"published-print":{"date-parts":[[2025,11]]},"DOI":"10.1061\/jccee5.cpeng-6500","type":"journal-article","created":{"date-parts":[[2025,8,13]],"date-time":"2025-08-13T11:47:32Z","timestamp":1755085652000},"update-policy":"https:\/\/doi.org\/10.1061\/do.news.20190416.0001","source":"Crossref","is-referenced-by-count":1,"title":["Enhanced Semantic Recognition of Architectural Floor Plan Recognition Using CLIP and Advanced Sampling Strategy"],"prefix":"10.1061","volume":"39","author":[{"given":"Yumeng","family":"Wang","sequence":"first","affiliation":[{"name":"China Univ. of Geosciences","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jici","family":"Xing","sequence":"additional","affiliation":[{"name":"China Univ. of Geosciences","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Longyong","family":"Wu","sequence":"additional","affiliation":[{"name":"China Univ. of Geosciences","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianga","family":"Shang","sequence":"additional","affiliation":[{"name":"China Univ. of Geosciences","place":["China"]},{"name":"China Univ. of Geosciences","place":["China"]},{"name":"China Univ. of Geosciences","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"30","reference":[{"key":"e_1_3_4_2_1","doi-asserted-by":"crossref","unstructured":"Ahmed S. M. Liwicki M. Weber and A. Dengel. 2011. \u201cImproved automatic analysis of architectural floor plans.\u201d In Proc. 2011 Int. Conf. on Document Analysis and Recognition 864\u2013869. New York: IEEE.","DOI":"10.1109\/ICDAR.2011.177"},{"key":"e_1_3_4_3_1","doi-asserted-by":"crossref","unstructured":"Aoki Y. A. Shio H. Arai and K. Odaka. 1996. \u201cA prototype system for interpreting hand-sketched floor plans.\u201d In Vol.\u00a03 of Proc. 13th Int. Conf. on Pattern Recognition 747\u2013751. New York: IEEE.","DOI":"10.1109\/ICPR.1996.547268"},{"key":"e_1_3_4_4_1","unstructured":"Barducci A. and S. Marinai. 2012. \u201cObject recognition in floor plans by graphs of white connected components.\u201d In Proc. 21st Int. Conf. on Pattern Recognition (ICPR2012) 298\u2013301. New York: IEEE."},{"key":"e_1_3_4_5_1","unstructured":"Brown T. et\u00a0al. 2020. \u201cLanguage models are few-shot learners.\u201d Preprint submitted May 28 2020. https:\/\/arxiv.org\/abs\/2005.14165."},{"key":"e_1_3_4_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF01580842"},{"key":"e_1_3_4_7_1","doi-asserted-by":"crossref","unstructured":"De P. 2019. \u201cVectorization of architectural floor plans.\u201d In Proc. 2019 12h Int. Conf. on Contemporary Computing (IC3) 1\u20135. New York: IEEE.","DOI":"10.1109\/IC3.2019.8844930"},{"key":"e_1_3_4_8_1","unstructured":"Devlin J. 2018. \u201cBert: Pre-training of deep bidirectional transformers for language understanding.\u201d Preprint submitted October 11 2018. https:\/\/arxiv.org\/abs\/1810.04805."},{"key":"e_1_3_4_9_1","doi-asserted-by":"crossref","unstructured":"Dodge S. J. Xu and B. Stenger. 2017. \u201cParsing floor plan images.\u201d In Proc. 2017 15th IAPR Int. Conf. on Machine Vision Applications (MVA) 358\u2013361. New York: IEEE.","DOI":"10.23919\/MVA.2017.7986875"},{"key":"e_1_3_4_10_1","unstructured":"Dosovitskiy A. 2020. \u201cAn image is worth 16x16 words: Transformers for image recognition at scale.\u201d Preprint submitted October 22 2020. https:\/\/arxiv.org\/abs\/2010.11929."},{"key":"e_1_3_4_11_1","unstructured":"Du Y. et\u00a0al. 2021. \u201cPP-OCRv2: Bag of tricks for ultra lightweight OCR system.\u201d Preprint submitted September 7 2021. https:\/\/arxiv.org\/abs\/2109.03144."},{"key":"e_1_3_4_12_1","doi-asserted-by":"crossref","unstructured":"Dupont E. K. Cherenkova D. Mallis G. Gusev A. Kacem and D. Aouada. 2024. \u201cTransCAD: A hierarchical transformer for CAD sequence inference from point clouds.\u201d In Proc. European Conf. on Computer Vision 19\u201336. Cham Switzerland: Springer.","DOI":"10.1007\/978-3-031-73030-6_2"},{"key":"e_1_3_4_13_1","doi-asserted-by":"crossref","unstructured":"Egiazarian V. O. Voynov A. Artemov D. Volkhonskiy A. Safin M. Taktasheva D. Zorin and E. Burnaev. 2020. \u201cDeep vectorization of technical drawings.\u201d In Proc. European Conf. on Computer Vision 582\u2013598. Cham Switzerland: Springer.","DOI":"10.1007\/978-3-030-58601-0_35"},{"key":"e_1_3_4_14_1","doi-asserted-by":"crossref","unstructured":"Fan Z. T. Chen P. Wang and Z. Wang. 2022. \u201cCADTransformer: Panoptic symbol spotting transformer for cad drawings.\u201d In Proc. IEEE\/CVF Conf. on Computer Vision and Pattern Recognition 10986\u201310996. New York: IEEE.","DOI":"10.1109\/CVPR52688.2022.01071"},{"key":"e_1_3_4_15_1","doi-asserted-by":"crossref","unstructured":"Fayyaz M. S. A. Koohpayegani F. R. Jafari S. Sengupta H. R. V. Joze E. Sommerlade H. Pirsiavash and J. Gall. 2022. \u201cAdaptive token sampling for efficient vision transformers.\u201d In Proc. European Conf. on Computer Vision 396\u2013414. Cham Switzerland: Springer.","DOI":"10.1007\/978-3-031-20083-0_24"},{"key":"e_1_3_4_16_1","unstructured":"Galanos T. A. Liapis and G. N. Yannakakis. 2023. \u201cArchitext: Language-driven generative architecture design.\u201d Preprint submitted March 13 2023. https:\/\/arxiv.org\/abs\/2303.07519."},{"key":"e_1_3_4_17_1","unstructured":"Gao H. H. Yuan Z. Wang and S. Ji. 2017. \u201cPixel deconvolutional networks.\u201d Preprint submitted May 18 2017. https:\/\/arxiv.org\/abs\/1705.06820."},{"key":"e_1_3_4_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.autcon.2015.12.008"},{"key":"e_1_3_4_19_1","doi-asserted-by":"crossref","unstructured":"Goncu C. A. Madugalla S. Marinai and K. Marriott. 2015. \u201cAccessible on-line floor plans.\u201d In Proc. 24th Int. Conf. on World Wide Web 388\u2013398. New York: Association for Computing Machinery. https:\/\/doi.org\/10.1145\/2736277.2741660.","DOI":"10.1145\/2736277.2741660"},{"key":"e_1_3_4_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"e_1_3_4_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3152247"},{"key":"e_1_3_4_22_1","doi-asserted-by":"crossref","unstructured":"He K. G. Gkioxari P. Doll\u00e1r and R. Girshick. 2017. \u201cMask R-CNN.\u201d In Proc. IEEE Int. Conf. on Computer Vision 2961\u20132969. New York: IEEE.","DOI":"10.1109\/ICCV.2017.322"},{"key":"e_1_3_4_23_1","doi-asserted-by":"crossref","unstructured":"Hori O. and S. Tanigawa. 1993. \u201cRaster-to-vector conversion by line fitting based on contours and skeletons.\u201d In Proc. 2nd Int. Conf. on Document Analysis and Recognition (ICDAR\u201993) 353\u2013358. New York: IEEE.","DOI":"10.1109\/ICDAR.1993.395716"},{"key":"e_1_3_4_24_1","doi-asserted-by":"crossref","unstructured":"Huang Y. T. Lv L. Cui Y. Lu and F. Wei. 2022. \u201cLayoutLMv3: Pre-training for document AI with unified text and image masking.\u201d In Proc. 30th ACM Int. Conf. on Multimedia 4083\u20134091. New York: Association for Computing Machinery.","DOI":"10.1145\/3503161.3548112"},{"key":"e_1_3_4_25_1","doi-asserted-by":"crossref","unstructured":"Kalervo A. J. Ylioinas M. H\u00e4iki\u00f6 A. Karhu and J. Kannala. 2019. \u201cCubiCasa5K: A dataset and an improved multi-task model for floorplan image analysis.\u201d In Proc. Image Analysis: 21st Scandinavian Conf. SCIA 2019 28\u201340. Cham Switzerland: Springer.","DOI":"10.1007\/978-3-030-20205-7_3"},{"key":"e_1_3_4_26_1","doi-asserted-by":"crossref","unstructured":"Law H. and J. Deng. 2018. \u201cCornerNet: Detecting objects as paired keypoints.\u201d In Proc. European Conf. on Computer Vision (ECCV) 734\u2013750. Berlin: Springer.","DOI":"10.1007\/978-3-030-01264-9_45"},{"key":"e_1_3_4_27_1","doi-asserted-by":"crossref","unstructured":"Liu C. J. Wu P. Kohli and Y. Furukawa. 2017. \u201cRaster-to-vector: Revisiting floorplan transformation.\u201d In Proc. IEEE Int. Conf. on Computer Vision 2195\u20132203. New York: IEEE.","DOI":"10.1109\/ICCV.2017.241"},{"key":"e_1_3_4_28_1","doi-asserted-by":"crossref","unstructured":"Liu W. D. Anguelov D. Erhan C. Szegedy S. Reed C.-Y. Fu and A. C. Berg. 2016. \u201cSSD: Single shot multibox detector.\u201d In Proc. Computer Vision\u2013ECCV 2016: 14th European Conf. 21\u201337. Cham Switzerland: Springer.","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"e_1_3_4_29_1","unstructured":"Liu W. T. Yang Y. Wang Q. Yu and L. Zhang. 2024. \u201cSymbol as points: Panoptic symbol spotting via point-based representation.\u201d Preprint submitted January 19 2024. https:\/\/arxiv.org\/abs\/2401.10556."},{"key":"e_1_3_4_30_1","doi-asserted-by":"crossref","unstructured":"Liu Z. H. Mao C.-Y. Wu C. Feichtenhofer T. Darrell and S. Xie. 2022. \u201cA convnet for the 2020s.\u201d In Proc. IEEE\/CVF Conf. on Computer Vision and Pattern Recognition 11976\u201311986. New York: IEEE.","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"e_1_3_4_31_1","doi-asserted-by":"crossref","first-page":"150","DOI":"10.1007\/s001380050068","article-title":"A system to understand hand-drawn floor plans using subgraph isomorphism and Hough transform","volume":"10","author":"Llad\u00f3s J.","year":"1997","unstructured":"Llad\u00f3s, J., J. L\u00f3pez-Krahe, and E. Mart\u00ed. 1997. \u201cA system to understand hand-drawn floor plans using subgraph isomorphism and Hough transform.\u201d Mach. Vision Appl. 10 (Aug): 150\u2013158. https:\/\/doi.org\/10.1007\/s001380050068.","journal-title":"Mach. Vision Appl."},{"key":"e_1_3_4_32_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2021.03.032"},{"key":"e_1_3_4_33_1","unstructured":"Or S.-H. K.-H. Wong Y.-K. Yu and M. M.-Y. Chang. 2005. \u201cHighly automatic approach to architectural floorplan image understanding & model generation.\u201d In Proc. of Vision Modeling and Visualization 2005 25\u201332. New York: Association for Computing Machinery."},{"key":"e_1_3_4_34_1","unstructured":"Paschalidou D. A. Kar M. Shugrina K. Kreis A. Geiger and S. Fidler. 2021. \u201cATISS: Autoregressive transformers for indoor scene synthesis.\u201d In Vol.\u00a034 of Proc. Advances in Neural Information Processing Systems 12013\u201312026. Red Hook NY: Curran Associates."},{"key":"e_1_3_4_35_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.autcon.2022.104348"},{"key":"e_1_3_4_36_1","doi-asserted-by":"crossref","unstructured":"Plocharski A. J. Swidzinski J. Porter-Sobieraj and P. Musialski. 2024. \u201cFa\u00e7AID: A transformer model for neuro-symbolic facade reconstruction.\u201d In Proc. SIGGRAPH Asia 2024 Conf. Papers 1\u201311. New York: Association for Computing Machinery.","DOI":"10.1145\/3680528.3687657"},{"key":"e_1_3_4_37_1","unstructured":"Radford A. et\u00a0al. 2021. \u201cLearning transferable visual models from natural language supervision.\u201d Preprint submitted February 26 2021. https:\/\/arxiv.org\/abs\/2103.00020."},{"key":"e_1_3_4_38_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0146-664X(72)80017-0"},{"key":"e_1_3_4_39_1","doi-asserted-by":"crossref","unstructured":"Rendek J. G. Masini P. Dosch and K. Tombre. 2004. \u201cThe search for genericity in graphics recognition applications: Design issues of the QGAR software system.\u201d In Proc. Document Analysis Systems VI: 6th Int. Workshop DAS 2004 366\u2013377. Berlin: Springer.","DOI":"10.1007\/978-3-540-28640-0_35"},{"key":"e_1_3_4_40_1","doi-asserted-by":"crossref","unstructured":"Ryall K. S. Shieber J. Marks and M. Mazer. 1995. \u201cSemi-automatic delineation of regions in floor plans.\u201d In Vol.\u00a02 of Proc. 3rd Int. Conf. on Document Analysis and Recognition 964\u2013969. New York: IEEE.","DOI":"10.1109\/ICDAR.1995.602062"},{"key":"e_1_3_4_41_1","doi-asserted-by":"publisher","DOI":"10.1049\/iet-cvi.2017.0581"},{"key":"e_1_3_4_42_1","doi-asserted-by":"crossref","unstructured":"Sharma D. C. Chattopadhyay and G. Harit. 2016. \u201cA unified framework for semantic matching of architectural floorplans.\u201d In Proc. 2016 23rd Int. Conf. on Pattern Recognition (ICPR) 2422\u20132427. New York: IEEE.","DOI":"10.1109\/ICPR.2016.7899999"},{"key":"e_1_3_4_43_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cad.2017.10.005"},{"key":"e_1_3_4_44_1","doi-asserted-by":"crossref","unstructured":"Sun K. B. Xiao D. Liu and J. Wang. 2019. \u201cDeep high-resolution representation learning for human pose estimation.\u201d In Proc. IEEE\/CVF Conf. on Computer Vision and Pattern Recognition 5693\u20135703. New York: IEEE.","DOI":"10.1109\/CVPR.2019.00584"},{"key":"e_1_3_4_45_1","doi-asserted-by":"crossref","unstructured":"Surikov I. Y. M. A. Nakhatovich S. Y. Belyaev and D. A. Savchuk. 2020. \u201cFloor plan recognition and vectorization using combination UNet Faster-RCNN statistical component analysis and Ramer-Douglas-Peucker.\u201d In Proc. Int. Conf. on Computing Science Communication and Security 16\u201328. Singapore: Springer.","DOI":"10.1007\/978-981-15-6648-6_2"},{"key":"e_1_3_4_46_1","unstructured":"Vaswani A. 2017. \u201cAttention is all you need.\u201d Preprint submitted June 12 2017. https:\/\/arxiv.org\/abs\/1706.03762."},{"key":"e_1_3_4_47_1","doi-asserted-by":"crossref","unstructured":"Woo S. S. Debnath R. Hu X. Chen Z. Liu I. S. Kweon and S. Xie. 2023. \u201cConvnext v2: Co-designing and scaling convnets with masked autoencoders.\u201d In Proc. IEEE\/CVF Conf. on Computer Vision and Pattern Recognition 16133\u201316142. New York: IEEE.","DOI":"10.1109\/CVPR52729.2023.01548"},{"key":"e_1_3_4_48_1","unstructured":"Xu J. C. Wang Z. Zhao W. Liu Y. Ma and S. Gao. 2024. \u201cCAD-MLLM: Unifying multimodality-conditioned cad generation with MLLM.\u201d Preprint submitted November 7 2024. https:\/\/arxiv.org\/abs\/2411.04954."},{"key":"e_1_3_4_49_1","doi-asserted-by":"crossref","unstructured":"Yamasaki T. J. Zhang and Y. Takada. 2018. \u201cApartment structure estimation using fully convolutional networks and graph model.\u201d In Proc. 2018 ACM Workshop on Multimedia for Real Estate Tech 1\u20136. New York: Association for Computing Machinery.","DOI":"10.1145\/3210499.3210528"},{"key":"e_1_3_4_50_1","doi-asserted-by":"crossref","unstructured":"Yang J. H. Jang J. Kim and J. Kim. 2018. \u201cSemantic segmentation in architectural floor plans for detecting walls and doors.\u201d In Proc. 2018 11th Int. Congress on Image and Signal Processing BioMedical Engineering and Informatics (CISP-BMEI) 1\u20139. New York: IEEE.","DOI":"10.1109\/CISP-BMEI.2018.8633243"},{"key":"e_1_3_4_51_1","unstructured":"Yuan Y. S. Sun Q. Liu and J. Bian. n.d. \u201cCAD-editor: Text-based CAD editing through adapting large language models with synthetic data.\u201d Accessed February 5 2025. https:\/\/openreview.net\/forum?id=Jrb9yXZJKG."},{"key":"e_1_3_4_52_1","doi-asserted-by":"crossref","unstructured":"Zhao H. L. Jiang J. Jia P. H. Torr and V. Koltun. 2021. \u201cPoint transformer.\u201d In Proc. IEEE\/CVF Int. Conf. on Computer Vision 16259\u201316268. New York: IEEE.","DOI":"10.1109\/ICCV48922.2021.01595"},{"key":"e_1_3_4_53_1","unstructured":"Zhou X. D. Wang and P. Kr\u00e4henb\u00fchl. 2019. \u201cObjects as points.\u201d Preprint submitted April 16 2019. https:\/\/arxiv.org\/abs\/1904.07850."}],"container-title":["Journal of Computing in Civil Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/ascelibrary.org\/doi\/pdf\/10.1061\/JCCEE5.CPENG-6500","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,13]],"date-time":"2025-08-13T11:47:39Z","timestamp":1755085659000},"score":1,"resource":{"primary":{"URL":"https:\/\/ascelibrary.org\/doi\/10.1061\/JCCEE5.CPENG-6500"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11]]},"references-count":52,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2025,11]]}},"alternative-id":["10.1061\/JCCEE5.CPENG-6500"],"URL":"https:\/\/doi.org\/10.1061\/jccee5.cpeng-6500","relation":{},"ISSN":["0887-3801","1943-5487"],"issn-type":[{"value":"0887-3801","type":"print"},{"value":"1943-5487","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11]]},"assertion":[{"value":"2024-09-28","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-04-15","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-08-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"04025095"}}