{"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/learning-disentangled-representations-of-4","title":"Learning Disentangled Representations of Video with Missing Data","arxiv_id":"2006.13391","date":"2020-06-23","proceeding":null,"authors":["Armand Comas-Massagué","Chi Zhang","Zlatan Feric","Octavia Camps","Rose Yu"],"abstract":"Missing data poses significant challenges while learning representations of video sequences. We present Disentangled Imputed Video autoEncoder (DIVE), a deep generative model that imputes and predicts future video frames in the presence of missing data. Specifically, DIVE introduces a missingness latent variable, disentangles the hidden video representations into static and dynamic appearance, pose, and missingness factors for each object. DIVE imputes each object's trajectory where data is missing. On a moving MNIST dataset with various missing scenarios, DIVE outperforms the state of the art baselines by a substantial margin. We also present comparisons for real-world MOTSChallenge pedestrian dataset, which demonstrates the practical value of our method in a more realistic setting. Our code and data can be found at https://github.com/Rose-STL-Lab/DIVE.","url_abs":"https://arxiv.org/abs/2006.13391v2","url_pdf":"https://arxiv.org/pdf/2006.13391v2.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":"learning-disentangled-representations-of-4","repo_url":"https://github.com/Rose-STL-Lab/DIVE","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2006.13391","atlas_url":"https://app.syntology.ai/?focus=2006.13391","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.13391"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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":"deterministic:regex_extraction","url":"https://github.com/Rose-STL-Lab/DIVE","reach":null},{"provenance":"deterministic:regex_extraction","url":"https://github.com/jthsieh/DDPAE-video-prediction","reach":null}],"summary":{"ran":5,"unverified":6},"by_repo_kind":{"official":{"samples":7,"ran":4,"repositories":1},"found_in_text":{"samples":4,"ran":1,"repositories":1}},"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":0,"samples":[{"code_sha256_prefix":"65056688f9a348ae","entry":"AppearanceEncoder","repo":"Rose-STL-Lab/DIVE","repo_kind":"official","path":"models/DiveModel.py","file_url":"https://github.com/Rose-STL-Lab/DIVE/blob/HEAD/models/DiveModel.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"65056688f9a348ae"}},{"code_sha256_prefix":"c72a806093b6179a","entry":"BaseModel","repo":"Rose-STL-Lab/DIVE","repo_kind":"official","path":"models/DiveModel.py","file_url":"https://github.com/Rose-STL-Lab/DIVE/blob/HEAD/models/DiveModel.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c72a806093b6179a"}},{"code_sha256_prefix":"183ce4a6d6e9884e","entry":"ImageDecoder","repo":"Rose-STL-Lab/DIVE","repo_kind":"official","path":"models/DiveModel.py","file_url":"https://github.com/Rose-STL-Lab/DIVE/blob/HEAD/models/DiveModel.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"183ce4a6d6e9884e"}},{"code_sha256_prefix":"10f313642e413ed5","entry":"ImageEncoder","repo":"Rose-STL-Lab/DIVE","repo_kind":"official","path":"models/DiveModel.py","file_url":"https://github.com/Rose-STL-Lab/DIVE/blob/HEAD/models/DiveModel.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"10f313642e413ed5"}},{"code_sha256_prefix":"db946948e9cb7afc","entry":"SequenceEncoder","repo":"jthsieh/DDPAE-video-prediction","repo_kind":"found_in_text","path":"models/DDPAE.py","file_url":"https://github.com/jthsieh/DDPAE-video-prediction/blob/HEAD/models/DDPAE.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"db946948e9cb7afc"}},{"code_sha256_prefix":"50fa86d9ffb2c790","entry":"BaseModel","repo":"jthsieh/DDPAE-video-prediction","repo_kind":"found_in_text","path":"models/DDPAE.py","file_url":"https://github.com/jthsieh/DDPAE-video-prediction/blob/HEAD/models/DDPAE.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"50fa86d9ffb2c790"}},{"code_sha256_prefix":"dc0a8ab81a302f82","entry":"DDPAE","repo":"jthsieh/DDPAE-video-prediction","repo_kind":"found_in_text","path":"models/DDPAE.py","file_url":"https://github.com/jthsieh/DDPAE-video-prediction/blob/HEAD/models/DDPAE.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"dc0a8ab81a302f82"}},{"code_sha256_prefix":"5ec9e41854970f62","entry":"DiveModel","repo":"Rose-STL-Lab/DIVE","repo_kind":"official","path":"models/DiveModel.py","file_url":"https://github.com/Rose-STL-Lab/DIVE/blob/HEAD/models/DiveModel.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5ec9e41854970f62"}},{"code_sha256_prefix":"0654f8275a9e6fb2","entry":"PoseEncoder","repo":"Rose-STL-Lab/DIVE","repo_kind":"official","path":"models/DiveModel.py","file_url":"https://github.com/Rose-STL-Lab/DIVE/blob/HEAD/models/DiveModel.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0654f8275a9e6fb2"}},{"code_sha256_prefix":"07b1bf020bd68c41","entry":"PoseRNN","repo":"jthsieh/DDPAE-video-prediction","repo_kind":"found_in_text","path":"models/DDPAE.py","file_url":"https://github.com/jthsieh/DDPAE-video-prediction/blob/HEAD/models/DDPAE.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"07b1bf020bd68c41"}},{"code_sha256_prefix":"1da6f0594ca2dc30","entry":"init_weights","repo":"Rose-STL-Lab/DIVE","repo_kind":"official","path":"models/DiveModel.py","file_url":"https://github.com/Rose-STL-Lab/DIVE/blob/HEAD/models/DiveModel.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1da6f0594ca2dc30"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}