{"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/disentangled-sequential-autoencoder","title":"Disentangled Sequential Autoencoder","arxiv_id":"1803.02991","date":"2018-03-08","proceeding":"ICML 2018 7","authors":["Yingzhen Li","Stephan Mandt"],"abstract":"We present a VAE architecture for encoding and generating high dimensional\nsequential data, such as video or audio. Our deep generative model learns a\nlatent representation of the data which is split into a static and dynamic\npart, allowing us to approximately disentangle latent time-dependent features\n(dynamics) from features which are preserved over time (content). This\narchitecture gives us partial control over generating content and dynamics by\nconditioning on either one of these sets of features. In our experiments on\nartificially generated cartoon video clips and voice recordings, we show that\nwe can convert the content of a given sequence into another one by such content\nswapping. For audio, this allows us to convert a male speaker into a female\nspeaker and vice versa, while for video we can separately manipulate shapes and\ndynamics. Furthermore, we give empirical evidence for the hypothesis that\nstochastic RNNs as latent state models are more efficient at compressing and\ngenerating long sequences than deterministic ones, which may be relevant for\napplications in video compression.","url_abs":"http://arxiv.org/abs/1803.02991v2","url_pdf":"http://arxiv.org/pdf/1803.02991v2.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":"disentangled-sequential-autoencoder","repo_url":"https://github.com/YingzhenLi/Sprites","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"disentangled-sequential-autoencoder","repo_url":"https://github.com/mazzzystar/Disentangled-Sequential-Autoencoder","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"disentangled-sequential-autoencoder","repo_url":"https://github.com/yatindandi/Disentangled-Sequential-Autoencoder","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"video-compression","task_name":"Video Compression"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1803.02991","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.02991"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/YingzhenLi/Sprites","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mazzzystar/Disentangled-Sequential-Autoencoder","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yatindandi/Disentangled-Sequential-Autoencoder","reach":null}],"summary":{"ran_honours":2},"by_repo_kind":{"listed":{"samples":2,"ran":2,"repositories":2}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":2,"samples":[{"code_sha256_prefix":"4360bbfc62d0fcb0","entry":"loss_fn","repo":"mazzzystar/Disentangled-Sequential-Autoencoder","repo_kind":"listed","path":"disVAE.py","file_url":"https://github.com/mazzzystar/Disentangled-Sequential-Autoencoder/blob/HEAD/disVAE.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4360bbfc62d0fcb0"}},{"code_sha256_prefix":"26aff04580832904","entry":"loss_fn","repo":"yatindandi/Disentangled-Sequential-Autoencoder","repo_kind":"listed","path":"trainer.py","file_url":"https://github.com/yatindandi/Disentangled-Sequential-Autoencoder/blob/HEAD/trainer.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"26aff04580832904"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}