{"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/a-variational-time-series-feature-extractor","title":"A Variational Time Series Feature Extractor for Action Prediction","arxiv_id":"1807.02350","date":"2018-07-06","proceeding":null,"authors":["Maxime Chaveroche","Adrien Malaisé","Francis Colas","François Charpillet","Serena Ivaldi"],"abstract":"We propose a Variational Time Series Feature Extractor (VTSFE), inspired by\nthe VAE-DMP model of Chen et al., to be used for action recognition and\nprediction. Our method is based on variational autoencoders. It improves\nVAE-DMP in that it has a better noise inference model, a simpler transition\nmodel constraining the acceleration in the trajectories of the latent space,\nand a tighter lower bound for the variational inference. We apply the method\nfor classification and prediction of whole-body movements on a dataset with 7\ntasks and 10 demonstrations per task, recorded with a wearable motion capture\nsuit. The comparison with VAE and VAE-DMP suggests the better performance of\nour method for feature extraction. An open-source software implementation of\neach method with TensorFlow is also provided. In addition, a more detailed\nversion of this work can be found in the indicated code repository. Although it\nwas meant to, the VTSFE hasn't been tested for action prediction, due to a lack\nof time in the context of Maxime Chaveroche's Master thesis at INRIA.","url_abs":"http://arxiv.org/abs/1807.02350v2","url_pdf":"http://arxiv.org/pdf/1807.02350v2.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":"a-variational-time-series-feature-extractor","repo_url":"https://github.com/inria-larsen/activity-recognition-prediction-wearable","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":"action-recognition","task_name":"Temporal Action Localization"},{"task_slug":"time-series-1","task_name":"Time Series"},{"task_slug":"time-series","task_name":"Time Series Analysis"},{"task_slug":"variational-inference","task_name":"Variational Inference"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}