{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T05:05:15Z","timestamp":1750309515760,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":26,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100001691","name":"Japan Society for the Promotion of Science","doi-asserted-by":"publisher","award":["22H03612"],"award-info":[{"award-number":["22H03612"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100001691","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3681202","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:41Z","timestamp":1729925981000},"page":"7307-7315","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Investigating Conceptual Blending of a Diffusion Model for Improving Nonword-to-Image Generation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2453-4560","authenticated-orcid":false,"given":"Chihaya","family":"Matsuhira","sequence":"first","affiliation":[{"name":"Nagoya University, Nagoya, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9193-5973","authenticated-orcid":false,"given":"Marc A.","family":"Kastner","sequence":"additional","affiliation":[{"name":"Hiroshima City University, Hiroshima, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3041-4330","authenticated-orcid":false,"given":"Takahiro","family":"Komamizu","sequence":"additional","affiliation":[{"name":"Nagoya University, Naogya, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6290-9680","authenticated-orcid":false,"given":"Takatsugu","family":"Hirayama","sequence":"additional","affiliation":[{"name":"University of Human Environments, Okazaki, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3942-9296","authenticated-orcid":false,"given":"Ichiro","family":"Ide","sequence":"additional","affiliation":[{"name":"Nagoya University, Nagoya, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Improving image generation with better captions. https:\/\/cdn.openai.com\/papers\/dall-e-3.pdf (Accessed","author":"Betker James","year":"2024","unstructured":"James Betker, Gabriel Goh, Li Jing, Tim Brooks, Jianfeng Wang, Linjie Li, Long Ouyang, Juntang Zhuang, Joyce Lee, Yufei Guo, Wesam Manassra, Prafulla Dhariwal, Casey Chu, Yunxin Jiao, and Aditya Ramesh. 2023. Improving image generation with better captions. https:\/\/cdn.openai.com\/papers\/dall-e-3.pdf (Accessed August 7, 2024), OpenAI."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1080\/14640748108400805"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0364-0213(99)80038-X"},{"key":"e_1_3_2_1_4_1","volume-title":"Adv. Neural Inf. Process. Syst.","volume":"27","author":"Goodfellow Ian J.","year":"2014","unstructured":"Ian J. Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. 2014. Generative adversarial nets. Adv. Neural Inf. Process. Syst., Vol. 27 (12 2014), 9 pages."},{"key":"e_1_3_2_1_5_1","first-page":"6626","article-title":"GANs trained by a two time-scale update rule converge to a local Nash equilibrium","volume":"30","author":"Heusel Martin","year":"2017","unstructured":"Martin Heusel, Hubert Ramsauer, Thomas Unterthiner, Bernhard Nessler, and Sepp Hochreiter. 2017. GANs trained by a two time-scale update rule converge to a local Nash equilibrium. Adv. Neural Inf. Process. Syst., Vol. 30 (2017), 6626--6637.","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511751806"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1312.6114"},{"key":"e_1_3_2_1_8_1","unstructured":"Wolfgang K\u00f6hler. 1929. Gestalt Psychology. H. Liveright New York NY USA."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3607541.3616818"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.2303.03144"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3378095"},{"key":"e_1_3_2_1_12_1","volume-title":"Proc. 7th Image Schema Day","author":"Melzi Simone","year":"2023","unstructured":"Simone Melzi, Rafael Pe\u00f1aloza, and Alessandro Raganato. 2023. Does Stable Diffusion dream of electric sheep?. In Proc. 7th Image Schema Day (Rhodes, Greece) (CEUR Workshop Proceedings 3511). 11 pages."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/219717.219748"},{"key":"e_1_3_2_1_14_1","volume-title":"Proc. 39th Int. Conf. Mach. Learn., Proc. Mach. Learn. Res.","volume":"162","author":"Nichol Alex","year":"2022","unstructured":"Alex Nichol, Prafulla Dhariwal, Aditya Ramesh, Pranav Shyam, Pamela Mishkin, Bob McGrew, Ilya Sutskever, and Mark Chen. 2022. GLIDE: Towards photorealistic image generation and editing with text-guided diffusion models. In Proc. 39th Int. Conf. Mach. Learn., Proc. Mach. Learn. Res. (Baltimore, MD, USA), Vol. 162. 16784--16804."},{"key":"e_1_3_2_1_15_1","volume-title":"Proc. 38th Int. Conf. Mach. Learn., Proc. Mach. Learn. Res. (Online)","volume":"139","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, Gretchen Krueger, and Ilya Sutskever. 2021. Learning transferable visual models from natural language supervision. In Proc. 38th Int. Conf. Mach. Learn., Proc. Mach. Learn. Res. (Online), Vol. 139. 8748--8763."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2204.06125"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1207\/S15327868MS1901_2"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.2205.11487"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1037\/h0070931"},{"key":"e_1_3_2_1_22_1","first-page":"25278","article-title":"LAION-5B: An open large-scale dataset for training next generation image-text models","volume":"35","author":"Schuhmann Christoph","year":"2022","unstructured":"Christoph Schuhmann, Romain Beaumont, Richard Vencu, Cade W. Gordon, Ross Wightman, Mehdi Cherti, Theo Coombes, Aarush Katta, Clayton Mullis, Mitchell Wortsman, Patrick Schramowski, Srivatsa R. Kundurthy, Katherine Crowson, Ludwig Schmidt, Robert Kaczmarczyk, and Jenia Jitsev. 2022. LAION-5B: An open large-scale dataset for training next generation image-text models. Adv. Neural Inf. Process. Syst., Vol. 35 (2022), 25278--25294.","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"e_1_3_2_1_23_1","volume-title":"Proc. 32nd Int. Conf. Mach. Learn., Proc. Mach. Learn. Res. (Lille","volume":"37","author":"Sohl-Dickstein Jascha","year":"2015","unstructured":"Jascha Sohl-Dickstein, Eric Weiss, Niru Maheswaranathan, and Surya Ganguli. 2015. Deep unsupervised learning using nonequilibrium thermodynamics. In Proc. 32nd Int. Conf. Mach. Learn., Proc. Mach. Learn. Res. (Lille, Nord, France), Vol. 37. 2256--2265."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","unstructured":"Robyn Speer Joshua Chin Andrew Lin Sara Jewett and Lance Nathan. 2018. LuminosoInsight\/wordfreq: v2.2. https:\/\/doi.org\/10.5281\/zenodo.1443582","DOI":"10.5281\/zenodo.1443582"},{"key":"e_1_3_2_1_25_1","volume-title":"https:\/\/github.com\/CompVis\/stable-diffusion\/ (Accessed","author":"Computer Vision and Learning Research Group at Ludwig Maximilian University of Munich. 2022. Stable Diffusion.","year":"2024","unstructured":"Computer Vision and Learning Research Group at Ludwig Maximilian University of Munich. 2022. Stable Diffusion. https:\/\/github.com\/CompVis\/stable-diffusion\/ (Accessed August 7, 2024)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747669"}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Melbourne VIC Australia","acronym":"MM '24"},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681202","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681202","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:18:02Z","timestamp":1750295882000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681202"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":26,"alternative-id":["10.1145\/3664647.3681202","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681202","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}