{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/human-action-generation-with-generative","title":"Human Action Generation with Generative Adversarial Networks","arxiv_id":"1805.10416","date":"2018-05-26","proceeding":null,"authors":["Mohammad Ahangar Kiasari","Dennis Singh Moirangthem","Minho Lee"],"abstract":"Inspired by the recent advances in generative models, we introduce a human\naction generation model in order to generate a consecutive sequence of human\nmotions to formulate novel actions. We propose a framework of an autoencoder\nand a generative adversarial network (GAN) to produce multiple and consecutive\nhuman actions conditioned on the initial state and the given class label. The\nproposed model is trained in an end-to-end fashion, where the autoencoder is\njointly trained with the GAN. The model is trained on the NTU RGB+D dataset and\nwe show that the proposed model can generate different styles of actions.\nMoreover, the model can successfully generate a sequence of novel actions given\ndifferent action labels as conditions. The conventional human action prediction\nand generation models lack those features, which are essential for practical\napplications.","url_abs":"http://arxiv.org/abs/1805.10416v1","url_pdf":"http://arxiv.org/pdf/1805.10416v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"human-action-generation-with-generative","repo_url":"https://github.com/xingchenzhao/Generating-Human-Skeletons-with-Mutual-Actions-WGAN-Pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"human-action-generation-with-generative","repo_url":"https://github.com/xingchenzhao/deep-learning-team-project","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"action-generation","task_name":"Action Generation"},{"task_slug":null,"task_name":"Generative Adversarial Network"},{"task_slug":"human-action-generation","task_name":"Human action generation"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}