{"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/video-reenactment-as-inductive-bias-for","title":"Video Reenactment as Inductive Bias for Content-Motion Disentanglement","arxiv_id":"2102.00324","date":"2021-01-30","proceeding":null,"authors":["Juan F. Hernández Albarracín","Adín Ramírez Rivera"],"abstract":"Independent components within low-dimensional representations are essential inputs in several downstream tasks, and provide explanations over the observed data. Video-based disentangled factors of variation provide low-dimensional representations that can be identified and used to feed task-specific models. We introduce MTC-VAE, a self-supervised motion-transfer VAE model to disentangle motion and content from videos. Unlike previous work on video content-motion disentanglement, we adopt a chunk-wise modeling approach and take advantage of the motion information contained in spatiotemporal neighborhoods. Our model yields independent per-chunk representations that preserve temporal consistency. Hence, we reconstruct whole videos in a single forward-pass. We extend the ELBO's log-likelihood term and include a Blind Reenactment Loss as an inductive bias to leverage motion disentanglement, under the assumption that swapping motion features yields reenactment between two videos. We evaluate our model with recently-proposed disentanglement metrics and show that it outperforms a variety of methods for video motion-content disentanglement. Experiments on video reenactment show the effectiveness of our disentanglement in the input space where our model outperforms the baselines in reconstruction quality and motion alignment.","url_abs":"https://arxiv.org/abs/2102.00324v3","url_pdf":"https://arxiv.org/pdf/2102.00324v3.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":"video-reenactment-as-inductive-bias-for","repo_url":"https://gitlab.com/mipl/mtc-vae","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"disentanglement","task_name":"Disentanglement"},{"task_slug":"inductive-bias","task_name":"Inductive Bias"},{"task_slug":"motion-disentanglement","task_name":"Motion Disentanglement"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}