{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T13:46:06Z","timestamp":1765547166354,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":20,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,1,4]],"date-time":"2024-01-04T00:00:00Z","timestamp":1704326400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,1,4]]},"DOI":"10.1145\/3632410.3632467","type":"proceedings-article","created":{"date-parts":[[2024,1,3]],"date-time":"2024-01-03T18:15:16Z","timestamp":1704305716000},"page":"422-429","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["GIMNet: Assembly Plan Generation from Graphical Instruction Manual"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8201-5959","authenticated-orcid":false,"given":"Abhinav","family":"Upadhyay","sequence":"first","affiliation":[{"name":"Accenture Labs, Bangalore, India"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8217-8707","authenticated-orcid":false,"given":"Alpana","family":"Dubey","sequence":"additional","affiliation":[{"name":"Accenture Labs, Bangalore, India"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5490-9928","authenticated-orcid":false,"given":"Suma Mani","family":"Kuriakose","sequence":"additional","affiliation":[{"name":"Accenture Labs, Bangalore, India"}]}],"member":"320","published-online":{"date-parts":[[2024,1,4]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"e_1_3_2_1_2_1","volume-title":"An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929","author":"Dosovitskiy Alexey","year":"2020","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794114"},{"key":"e_1_3_2_1_4_1","unstructured":"IKEA. 2023. Lack Side Table. http:\/\/surl.li\/jersp [Accessed: 15 Jul 2023]."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3064149"},{"key":"e_1_3_2_1_6_1","volume-title":"Combinatorial 3D shape generation via sequential assembly. arXiv preprint arXiv:2004.07414","author":"Kim Jungtaek","year":"2020","unstructured":"Jungtaek Kim, Hyunsoo Chung, Jinhwi Lee, Minsu Cho, and Jaesik Park. 2020. Combinatorial 3D shape generation via sequential assembly. arXiv preprint arXiv:2004.07414 (2020)."},{"key":"e_1_3_2_1_7_1","volume-title":"Segment anything. arXiv preprint arXiv:2304.02643","author":"Kirillov Alexander","year":"2023","unstructured":"Alexander Kirillov, Eric Mintun, Nikhila Ravi, Hanzi Mao, Chloe Rolland, Laura Gustafson, Tete Xiao, Spencer Whitehead, Alexander\u00a0C Berg, Wan-Yen Lo, 2023. Segment anything. arXiv preprint arXiv:2304.02643 (2023)."},{"key":"e_1_3_2_1_8_1","volume-title":"d.]. Object Detection for Understanding Assembly Instruction Using Context-aware Data Augmentation and Cascade Mask R-CNN. arXiv","author":"Lee J","year":"2021","unstructured":"J Lee, S Lee, S Back, S Shin, and K Lee. [n. d.]. Object Detection for Understanding Assembly Instruction Using Context-aware Data Augmentation and Cascade Mask R-CNN. arXiv 2021. arXiv preprint arXiv:2101.02509 ([n. d.])."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11370-022-00427-5"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759413"},{"key":"e_1_3_2_1_12_1","volume-title":"https:\/\/pymupdf.readthedocs.io\/en\/latest\/ [Accessed","author":"PDF.","year":"2023","unstructured":"PyMuPDF. 2023. PyMuPDF. https:\/\/pymupdf.readthedocs.io\/en\/latest\/ [Accessed: 08 Oct, 2023]."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636041"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/2980179.2982416"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CoASE.2015.7294142"},{"key":"e_1_3_2_1_16_1","unstructured":"Abhinav Upadhyay Priyanshu\u00a0Abhijit Barua Alpana Dubey Shubhashis Sengupta Suma\u00a0Mani Kuriakose and Piyush Goenka. [n. d.]. P3DAttnNet: Automated Assembly Plan Generation from Video Demonstration. ([n. d.])."},{"key":"e_1_3_2_1_17_1","first-page":"28428","article-title":"Ikea-manual: Seeing shape assembly step by step","volume":"35","author":"Wang Ruocheng","year":"2022","unstructured":"Ruocheng Wang, Yunzhi Zhang, Jiayuan Mao, Ran Zhang, Chin-Yi Cheng, and Jiajun Wu. 2022. Ikea-manual: Seeing shape assembly step by step. Advances in Neural Information Processing Systems 35 (2022), 28428\u201328440.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_18_1","volume-title":"Roboassembly: Learning generalizable furniture assembly policy in a novel multi-robot contact-rich simulation environment. arXiv preprint arXiv:2112.10143","author":"Yu Mingxin","year":"2021","unstructured":"Mingxin Yu, Lin Shao, Zhehuan Chen, Tianhao Wu, Qingnan Fan, Kaichun Mo, and Hao Dong. 2021. Roboassembly: Learning generalizable furniture assembly policy in a novel multi-robot contact-rich simulation environment. arXiv preprint arXiv:2112.10143 (2021)."},{"key":"e_1_3_2_1_19_1","first-page":"6315","article-title":"Generative 3d part assembly via dynamic graph learning","volume":"33","author":"Zhan Guanqi","year":"2020","unstructured":"Guanqi Zhan, Qingnan Fan, Kaichun Mo, Lin Shao, Baoquan Chen, Leonidas\u00a0J Guibas, Hao Dong, 2020. Generative 3d part assembly via dynamic graph learning. Advances in Neural Information Processing Systems 33 (2020), 6315\u20136326.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"}],"event":{"name":"CODS-COMAD 2024: 7th Joint International Conference on Data Science & Management of Data (11th ACM IKDD CODS and 29th COMAD)","acronym":"CODS-COMAD 2024","location":"Bangalore India"},"container-title":["Proceedings of the 7th Joint International Conference on Data Science & Management of Data (11th ACM IKDD CODS and 29th COMAD)"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3632410.3632467","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3632410.3632467","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T13:38:01Z","timestamp":1755869881000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3632410.3632467"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,4]]},"references-count":20,"alternative-id":["10.1145\/3632410.3632467","10.1145\/3632410"],"URL":"https:\/\/doi.org\/10.1145\/3632410.3632467","relation":{},"subject":[],"published":{"date-parts":[[2024,1,4]]},"assertion":[{"value":"2024-01-04","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}