{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T22:18:05Z","timestamp":1757542685511,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":27,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,2,2]],"date-time":"2024-02-02T00:00:00Z","timestamp":1706832000000},"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":[[2024,2,2]]},"DOI":"10.1145\/3651671.3651711","type":"proceedings-article","created":{"date-parts":[[2024,6,7]],"date-time":"2024-06-07T18:55:50Z","timestamp":1717786550000},"page":"677-683","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Integrated Artificial Intelligence for Making Digital Human II"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-6163-6340","authenticated-orcid":false,"given":"Yoshiyuki","family":"Usami","sequence":"first","affiliation":[{"name":"Department of Applied Physics, Kanagawa University, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-0887-4042","authenticated-orcid":false,"given":"Shota","family":"Moro","sequence":"additional","affiliation":[{"name":"Coordinated Engineering Program, Kanagawa University, Japan"}]}],"member":"320","published-online":{"date-parts":[[2024,6,7]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"[1] Amelia\u00a0Conversational AI. 2022. http\/\/amelia.ai\/conversationao-ai."},{"key":"e_1_3_2_1_2_1","unstructured":"[2] Stability AI. 2023. https:\/\/huggingface.co\/stabilityai\/stable-diffusion-xl-base-1.0."},{"key":"e_1_3_2_1_3_1","unstructured":"[3] D. Alan. 2021. Leta GPT-3 AI - Episode 0 - World Gifted Conf 2021 - The New Irrelevance of Intelligence https:\/\/www.youtube. com\/watch?v=zj-WZj7Vd-Q."},{"key":"e_1_3_2_1_4_1","unstructured":"[4] AUTOMATIC1111. 2022. https:\/\/github.com\/AUTOMATIC1111\/stable-diffusion-webui."},{"key":"e_1_3_2_1_5_1","unstructured":"[5] Hugging\u00a0Face\/openai community\/gpt2 medium. 2019. https:\/\/huggingface.co\/openai-community\/gpt2-medium."},{"key":"e_1_3_2_1_6_1","unstructured":"[6] UNEEQ:\u00a0Revolutionize customer experiences with scalable\u00a0human connections. 2020. https:\/\/www.digitalhumans.com."},{"key":"e_1_3_2_1_7_1","unstructured":"[7] diff_usion. 2022. A correction of resourcxes and papers on Diffusion Models. https:\/\/github.com\/diff-usion\/Awesome-Diffusion-Models."},{"key":"e_1_3_2_1_8_1","unstructured":"[8] NEON is\u00a0a computationally created virtual being\u00a0that looks and behaves\u00a0like us. 2019. http\/\/neonlive.aio-ai."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"e_1_3_2_1_10_1","volume-title":"The Illustrated Image Captioning using transformers. ankur3107.github.io","author":"Kumar Ankur","year":"2022","unstructured":"Ankur Kumar. 2022. The Illustrated Image Captioning using transformers. ankur3107.github.io (2022). https:\/\/ankur3107.github.io\/blogs\/the- illustrated-image- captioning."},{"key":"e_1_3_2_1_11_1","unstructured":"[11] MicroSoft. 2016. Microsoft Research Paraphrase Corpus: https:\/\/gluebenchmark.com."},{"key":"e_1_3_2_1_12_1","unstructured":"[12] Amrrs Nulldata. 2021. https:\/\/www.kaggle.com\/code\/nulldata\/fine-tuning-gpt-2-to-generate-netlfix-descriptions."},{"key":"e_1_3_2_1_13_1","unstructured":"[13] OpenAI. 2020. https:\/\/huggingface.co\/transformers\/v3.0.2\/index.html."},{"key":"e_1_3_2_1_14_1","unstructured":"[14] OpenAI. 2023. https:\/\/huggingface.co\/docs\/transformers\/v4.38.2\/en."},{"key":"e_1_3_2_1_15_1","unstructured":"[15] OpenAI. 2023. https:\/\/platform.openai.com\/docs\/guides\/fine-tuning."},{"key":"e_1_3_2_1_16_1","unstructured":"[16] OpenAI. 2023. https:\/\/openai.com\/research\/gpt-4."},{"key":"e_1_3_2_1_17_1","unstructured":"[17] Marc Puig. 2023. https:\/\/github.com\/mpuig\/gpt2-fine-tuning."},{"key":"e_1_3_2_1_18_1","volume-title":"Language models are unsupervised multitask learners. OpenAI blog 1, 8","author":"Radford Alec","year":"2019","unstructured":"Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, Ilya Sutskever, 2019. Language models are unsupervised multitask learners. OpenAI blog 1, 8 (2019), 9."},{"key":"e_1_3_2_1_19_1","unstructured":"Romal Thoppilan 2022. LaMDA: Language Models for Dialog Applications. arxiv:2201.08239\u00a0[cs.CL]"},{"key":"e_1_3_2_1_20_1","unstructured":"Tensorflow tutorials\u00a0in tensorflow.org. 2020. Image captioning with visual attention."},{"key":"e_1_3_2_1_21_1","unstructured":"[21] Yoshiyuki Usami. 2022. http\/\/github\/usami0jp\/ai."},{"key":"e_1_3_2_1_22_1","unstructured":"Yoshiyuki Usami. 2022. Making Integrated AI Having Abilities of Hearing Looking and Answering. Amazon.com."},{"key":"e_1_3_2_1_23_1","volume-title":"Show and Tell: A Neural Image Caption Generator. CoRR abs\/1411.4555","author":"Vinyals Oriol","year":"2014","unstructured":"Oriol Vinyals, Alexander Toshev, Samy Bengio, and Dumitru Erhan. 2014. Show and Tell: A Neural Image Caption Generator. CoRR abs\/1411.4555 (2014). arXiv:1411.4555.http:\/\/arxiv.org\/abs\/1411.4555"},{"key":"e_1_3_2_1_24_1","first-page":"11","article-title":"Loss of recent memory after bilateral hippocampal lesions","author":"William Scoville","year":"1957","unstructured":"Scoville William, B. and Brenda Milner.1957. Loss of recent memory after bilateral hippocampal lesions. Journal of Neurology., 11\u201321.","journal-title":"Journal of Neurology."},{"key":"e_1_3_2_1_25_1","volume-title":"YOLOv8.1","author":"Ultralytics","year":"2024","unstructured":"[25] Ultralytics: YOLOv8.1. 2024. https:\/\/docs.ultralytics.com\/."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3587716.3587760"},{"key":"e_1_3_2_1_27_1","volume-title":"MakeItTalk: Speaker-Aware Talking Head Animation. CoRR abs\/2004.12992","author":"Zhou Yang","year":"2020","unstructured":"Yang Zhou, Dingzeyu Li, Xintong Han, Evangelos Kalogerakis, Eli Shechtman, and Jose Echevarria. 2020. MakeItTalk: Speaker-Aware Talking Head Animation. CoRR abs\/2004.12992 (2020). arXiv:2004.12992.https:\/\/arxiv.org\/abs\/2004.12992."}],"event":{"name":"ICMLC 2024: 2024 16th International Conference on Machine Learning and Computing","acronym":"ICMLC 2024","location":"Shenzhen China"},"container-title":["Proceedings of the 2024 16th International Conference on Machine Learning and Computing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3651671.3651711","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3651671.3651711","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T11:20:56Z","timestamp":1755861656000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3651671.3651711"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2,2]]},"references-count":27,"alternative-id":["10.1145\/3651671.3651711","10.1145\/3651671"],"URL":"https:\/\/doi.org\/10.1145\/3651671.3651711","relation":{},"subject":[],"published":{"date-parts":[[2024,2,2]]},"assertion":[{"value":"2024-06-07","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}