{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T18:55:18Z","timestamp":1770749718939,"version":"3.50.0"},"publisher-location":"New York, NY, USA","reference-count":99,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,3,5]],"date-time":"2021-03-05T00:00:00Z","timestamp":1614902400000},"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":[[2021,3,5]]},"DOI":"10.1145\/3461353.3461388","type":"proceedings-article","created":{"date-parts":[[2021,9,6]],"date-time":"2021-09-06T17:21:15Z","timestamp":1630948875000},"page":"108-120","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["A Survey on Multimodal Deep Learning for Image Synthesis"],"prefix":"10.1145","author":[{"given":"Sanbi","family":"Luo","sequence":"first","affiliation":[{"name":"School of Cyber Security, University of Chinese Academy of Sciences, Beijing and Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2021,9,4]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1002\/widm.1345"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00379"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.471"},{"key":"e_1_3_2_1_4_1","volume-title":"Gwern Branwen, and Aaron Gokaslan.","author":"Anonymous","year":"2017"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3390462"},{"key":"e_1_3_2_1_6_1","volume-title":"Specifying Object Attributes and Relations in Interactive Scene Generation. In 2019 IEEE\/CVF International Conference on Computer Vision, ICCV 2019","author":"Ashual Oron","year":"2019"},{"key":"e_1_3_2_1_7_1","unstructured":"Samaneh Azadi Michael Tschannen Eric Tzeng Sylvain Gelly Trevor Darrell and Mario Lucic. 2019. Semantic Bottleneck Scene Generation. CoRR abs\/1911.11357(2019). arxiv:1911.11357http:\/\/arxiv.org\/abs\/1911.11357  Samaneh Azadi Michael Tschannen Eric Tzeng Sylvain Gelly Trevor Darrell and Mario Lucic. 2019. Semantic Bottleneck Scene Generation. CoRR abs\/1911.11357(2019). arxiv:1911.11357http:\/\/arxiv.org\/abs\/1911.11357"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01258-8_27"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2798607"},{"key":"e_1_3_2_1_10_1","unstructured":"brain development. [n.d.]. IXI Dataset. ([n.\u00a0d.]). http:\/\/brain-development.org\/ixi-dataset\/  brain development. [n.d.]. IXI Dataset. ([n.\u00a0d.]). http:\/\/brain-development.org\/ixi-dataset\/"},{"key":"e_1_3_2_1_11_1","volume-title":"COCO-Stuff: Thing and Stuff Classes in Context. In 2018 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2018","author":"Caesar Holger","year":"2018"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2017.2764326"},{"key":"e_1_3_2_1_13_1","volume-title":"Photographic Image Synthesis with Cascaded Refinement Networks. In IEEE International Conference on Computer Vision, ICCV 2017","author":"Chen Qifeng","year":"2017"},{"key":"e_1_3_2_1_14_1","volume-title":"The Cityscapes Dataset for Semantic Urban Scene Understanding. In 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016","author":"Cordts Marius","year":"2016"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"crossref","unstructured":"Nick Craswell. 2009. R-Precision. Springer US Boston MA 2453\u20132453. https:\/\/doi.org\/10.1007\/978-0-387-39940-9_486  Nick Craswell. 2009. R-Precision. Springer US Boston MA 2453\u20132453. https:\/\/doi.org\/10.1007\/978-0-387-39940-9_486","DOI":"10.1007\/978-0-387-39940-9_486"},{"key":"e_1_3_2_1_16_1","volume-title":"Visual Dialog. In 2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017","author":"Das Abhishek","year":"2017"},{"key":"e_1_3_2_1_17_1","volume-title":"Sheraz Ahmed, Marcus Liwicki, and Muhammad\u00a0Zeshan Afzal.","author":"Dash Ayushman","year":"2017"},{"key":"e_1_3_2_1_18_1","volume-title":"Semantic Image Manipulation Using Scene Graphs. In 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020","author":"Dhamo Helisa","year":"2020"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01040"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.5555\/3157382.3157459"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2017.2759265"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco_a_01273"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"e_1_3_2_1_24_1","unstructured":"Mehmet G\u00fcnel Erkut Erdem and Aykut Erdem. 2018. Language Guided Fashion Image Manipulation with Feature-wise Transformations. CoRR abs\/1808.04000(2018). arxiv:1808.04000http:\/\/arxiv.org\/abs\/1808.04000  Mehmet G\u00fcnel Erkut Erdem and Aykut Erdem. 2018. Language Guided Fashion Image Manipulation with Feature-wise Transformations. CoRR abs\/1808.04000(2018). arxiv:1808.04000http:\/\/arxiv.org\/abs\/1808.04000"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.277"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58574-7_13"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295408"},{"key":"e_1_3_2_1_28_1","volume-title":"7th International Conference on Learning Representations, ICLR 2019","author":"Hinz Tobias","year":"2019"},{"key":"e_1_3_2_1_29_1","unstructured":"Tobias Hinz Stefan Heinrich and Stefan Wermter. 2019. Semantic Object Accuracy for Generative Text-to-Image Synthesis. CoRR abs\/1910.13321(2019). arxiv:1910.13321http:\/\/arxiv.org\/abs\/1910.13321  Tobias Hinz Stefan Heinrich and Stefan Wermter. 2019. Semantic Object Accuracy for Generative Text-to-Image Synthesis. CoRR abs\/1910.13321(2019). arxiv:1910.13321http:\/\/arxiv.org\/abs\/1910.13321"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.5555\/3327144.3327195"},{"key":"e_1_3_2_1_31_1","volume-title":"Inferring Semantic Layout for Hierarchical Text-to-Image Synthesis. In 2018 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2018","author":"Hong Seunghoon","year":"2018"},{"key":"e_1_3_2_1_32_1","volume-title":"Image-to-Image Translation with Conditional Adversarial Networks. In 2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017","author":"Isola Phillip","year":"2017"},{"key":"e_1_3_2_1_33_1","unstructured":"Maor Ivgi Yaniv Benny Avichai Ben-David Jonathan Berant and Lior Wolf. 2020. Scene Graph to Image Generation with Contextualized Object Layout Refinement. CoRR abs\/2009.10939(2020). arxiv:2009.10939https:\/\/arxiv.org\/abs\/2009.10939  Maor Ivgi Yaniv Benny Avichai Ben-David Jonathan Berant and Lior Wolf. 2020. Scene Graph to Image Generation with Contextualized Object Layout Refinement. CoRR abs\/2009.10939(2020). arxiv:2009.10939https:\/\/arxiv.org\/abs\/2009.10939"},{"key":"e_1_3_2_1_34_1","volume-title":"Image Generation From Scene Graphs. In 2018 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2018","author":"Johnson Justin","year":"2018"},{"key":"e_1_3_2_1_35_1","volume-title":"CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning. In 2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017","author":"Johnson Justin","year":"2017"},{"key":"e_1_3_2_1_36_1","unstructured":"Levent Karacan Zeynep Akata Aykut Erdem and Erkut Erdem. 2016. Learning to Generate Images of Outdoor Scenes from Attributes and Semantic Layouts. CoRR abs\/1612.00215(2016). arxiv:1612.00215http:\/\/arxiv.org\/abs\/1612.00215  Levent Karacan Zeynep Akata Aykut Erdem and Erkut Erdem. 2016. Learning to Generate Images of Outdoor Scenes from Attributes and Semantic Layouts. CoRR abs\/1612.00215(2016). arxiv:1612.00215http:\/\/arxiv.org\/abs\/1612.00215"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00915"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1651"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.140"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.5555\/3454287.3454472"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.5555\/3454287.3454642"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cag.2019.03.009"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.3013418"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.425"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2016.07.009"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2120"},{"key":"e_1_3_2_1_49_1","volume-title":"4th International Conference on Learning Representations, ICLR 2016, San Juan, Puerto Rico, May 2-4, 2016, Conference Track Proceedings, Yoshua Bengio and Yann LeCun (Eds.). http:\/\/arxiv.org\/abs\/1511","author":"Mansimov Elman","year":"2016"},{"key":"e_1_3_2_1_50_1","volume-title":"Bilinear Representation for Language-based Image Editing Using Conditional Generative Adversarial Networks. In IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2019","author":"Mao Xiaofeng","year":"2019"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2014.2377694"},{"key":"e_1_3_2_1_52_1","volume-title":"ICLR 2019 Workshop","author":"Mittal Gaurav","year":"2019"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"e_1_3_2_1_54_1","volume-title":"Semantic Image Synthesis With Spatially-Adaptive Normalization. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2019","author":"Park Taesung","year":"2019"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_29"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.5555\/3454287.3454367"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00160"},{"key":"e_1_3_2_1_58_1","unstructured":"Aditya Ramesh Mikhail Pavlov Gabriel Goh and Scott GrayTadas. 2021. DALL\u00b7E: Creating Images from Text. (2021). https:\/\/openai.com\/blog\/dall-e\/  Aditya Ramesh Mikhail Pavlov Gabriel Goh and Scott GrayTadas. 2021. DALL\u00b7E: Creating Images from Text. (2021). https:\/\/openai.com\/blog\/dall-e\/"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.5555\/3157096.3157121"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.5555\/3045390.3045503"},{"key":"e_1_3_2_1_61_1","volume-title":"Network-to-Network Translation with Conditional Invertible Neural Networks. In Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020","author":"Rombach Robin","year":"2020"},{"key":"e_1_3_2_1_62_1","unstructured":"Negar Rostamzadeh Seyedarian Hosseini Thomas Boquet Wojciech Stokowiec Ying Zhang Christian Jauvin and Chris Pal. 2018. Fashion-Gen: The Generative Fashion Dataset and Challenge. CoRR abs\/1806.08317(2018). arxiv:1806.08317http:\/\/arxiv.org\/abs\/1806.08317  Negar Rostamzadeh Seyedarian Hosseini Thomas Boquet Wojciech Stokowiec Ying Zhang Christian Jauvin and Chris Pal. 2018. Fashion-Gen: The Generative Fashion Dataset and Challenge. CoRR abs\/1806.08317(2018). arxiv:1806.08317http:\/\/arxiv.org\/abs\/1806.08317"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.5555\/3157096.3157346"},{"key":"e_1_3_2_1_65_1","volume-title":"6th International Conference on Learning Representations, ICLR","author":"Sharma Shikhar","year":"2018"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"e_1_3_2_1_67_1","unstructured":"Wei Sun and Tianfu Wu. 2020. Learning Layout and Style Reconfigurable GANs for Controllable Image Synthesis. CoRR abs\/2003.11571(2020). arxiv:2003.11571https:\/\/arxiv.org\/abs\/2003.11571  Wei Sun and Tianfu Wu. 2020. Learning Layout and Style Reconfigurable GANs for Controllable Image Synthesis. CoRR abs\/2003.11571(2020). arxiv:2003.11571https:\/\/arxiv.org\/abs\/2003.11571"},{"key":"e_1_3_2_1_68_1","volume-title":"Rethinking the Inception Architecture for Computer Vision. In 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016","author":"Szegedy Christian","year":"2016"},{"key":"e_1_3_2_1_69_1","unstructured":"Ming Tao Hao Tang Songsong Wu Nicu Sebe Fei Wu and Xiao-Yuan Jing. 2020. DF-GAN: Deep Fusion Generative Adversarial Networks for Text-to-Image Synthesis. CoRR abs\/2008.05865(2020). arxiv:2008.05865https:\/\/arxiv.org\/abs\/2008.05865  Ming Tao Hao Tang Songsong Wu Nicu Sebe Fei Wu and Xiao-Yuan Jing. 2020. DF-GAN: Deep Fusion Generative Adversarial Networks for Text-to-Image Synthesis. CoRR abs\/2008.05865(2020). arxiv:2008.05865https:\/\/arxiv.org\/abs\/2008.05865"},{"key":"e_1_3_2_1_70_1","volume-title":"Multimodal Image-to-Image Translation for Generation of Gastritis Images. In IEEE International Conference on Image Processing, ICIP 2020","author":"Togo Ren","year":"2020"},{"key":"e_1_3_2_1_71_1","unstructured":"Subarna Tripathi Anahita Bhiwandiwalla Alexei Bastidas and Hanlin Tang. 2019. Using Scene Graph Context to Improve Image Generation. CoRR abs\/1901.03762(2019). arxiv:1901.03762http:\/\/arxiv.org\/abs\/1901.03762  Subarna Tripathi Anahita Bhiwandiwalla Alexei Bastidas and Hanlin Tang. 2019. Using Scene Graph Context to Improve Image Generation. CoRR abs\/1901.03762(2019). arxiv:1901.03762http:\/\/arxiv.org\/abs\/1901.03762"},{"key":"e_1_3_2_1_72_1","volume-title":"Compact Scene Graphs for Layout Composition and Patch Retrieval. In IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2019","author":"Tripathi Subarna","year":"2019"},{"key":"e_1_3_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14047"},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018901"},{"key":"e_1_3_2_1_75_1","volume-title":"GCPR 2013, Saarbr\u00fccken, Germany, September 3-6, 2013. Proceedings(Lecture Notes in Computer Science), Joachim Weickert, Matthias Hein, and Bernt Schiele (Eds.), Vol.\u00a08142","author":"Tylecek Radim","year":"2013"},{"key":"e_1_3_2_1_76_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2982224"},{"key":"e_1_3_2_1_77_1","volume-title":"Example-Guided Style-Consistent Image Synthesis From Semantic Labeling. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2019","author":"Wang Miao","year":"2019"},{"key":"e_1_3_2_1_78_1","volume-title":"High-Resolution Image Synthesis and Semantic Manipulation With Conditional GANs. In 2018 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2018","author":"Wang Ting-Chun","year":"2018"},{"key":"e_1_3_2_1_79_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"e_1_3_2_1_80_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACSSC.2003.1292216"},{"key":"e_1_3_2_1_81_1","unstructured":"Peter Welinder Steve Branson Takeshi Mita Catherine Wah Florian Schroff Serge Belongie and Pietro Perona. 2010. Caltech-UCSD birds 200. (2010).  Peter Welinder Steve Branson Takeshi Mita Catherine Wah Florian Schroff Serge Belongie and Pietro Perona. 2010. Caltech-UCSD birds 200. (2010)."},{"key":"e_1_3_2_1_82_1","unstructured":"Weihao Xia Yujiu Yang Jing-Hao Xue and Baoyuan Wu. 2020. TediGAN: Text-Guided Diverse Image Generation and Manipulation. CoRR abs\/2012.03308(2020). arxiv:2012.03308https:\/\/arxiv.org\/abs\/2012.03308  Weihao Xia Yujiu Yang Jing-Hao Xue and Baoyuan Wu. 2020. TediGAN: Text-Guided Diverse Image Generation and Manipulation. CoRR abs\/2012.03308(2020). arxiv:2012.03308https:\/\/arxiv.org\/abs\/2012.03308"},{"key":"e_1_3_2_1_83_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2857768"},{"key":"e_1_3_2_1_84_1","volume-title":"Transfer-Gan: Multimodal Ct Image Super-Resolution Via Transfer Generative Adversarial Networks. In 17th IEEE International Symposium on Biomedical Imaging, ISBI 2020","author":"Xiao Yao","year":"2020"},{"key":"e_1_3_2_1_85_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00143"},{"key":"e_1_3_2_1_86_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00271"},{"key":"e_1_3_2_1_87_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.2987728"},{"key":"e_1_3_2_1_88_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.629"},{"key":"e_1_3_2_1_89_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2856256"},{"key":"e_1_3_2_1_90_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_40"},{"key":"e_1_3_2_1_91_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"e_1_3_2_1_92_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00649"},{"key":"e_1_3_2_1_93_1","volume-title":"Image Generation From Layout. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2019","author":"Zhao Bo","year":"2019"},{"key":"e_1_3_2_1_94_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"e_1_3_2_1_95_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2020.2975344"},{"key":"e_1_3_2_1_96_1","volume-title":"Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks. In IEEE International Conference on Computer Vision, ICCV 2017","author":"Zhu Jun-Yan","year":"2017"},{"key":"e_1_3_2_1_97_1","volume-title":"DM-GAN: Dynamic Memory Generative Adversarial Networks for Text-To-Image Synthesis. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2019","author":"Zhu Minfeng","year":"2019"},{"key":"e_1_3_2_1_98_1","volume-title":"Be Your Own Prada: Fashion Synthesis with Structural Coherence. In IEEE International Conference on Computer Vision, ICCV 2017","author":"Zhu Shizhan","year":"2017"},{"key":"e_1_3_2_1_99_1","volume-title":"Semantically Multi-Modal Image Synthesis. In 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020","author":"Zhu Zhen","year":"2020"}],"event":{"name":"ICIAI 2021: 2021 the 5th International Conference on Innovation in Artificial Intelligence","location":"Xia men China","acronym":"ICIAI 2021"},"container-title":["2021 the 5th International Conference on Innovation in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3461353.3461388","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3461353.3461388","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T21:28:35Z","timestamp":1750195715000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3461353.3461388"}},"subtitle":["Applications, methods, datasets, evaluation metrics, and results comparison"],"short-title":[],"issued":{"date-parts":[[2021,3,5]]},"references-count":99,"alternative-id":["10.1145\/3461353.3461388","10.1145\/3461353"],"URL":"https:\/\/doi.org\/10.1145\/3461353.3461388","relation":{},"subject":[],"published":{"date-parts":[[2021,3,5]]},"assertion":[{"value":"2021-09-04","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}