{"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/latent-video-transformer","title":"Latent Video Transformer","arxiv_id":"2006.10704","date":"2020-06-18","proceeding":null,"authors":["Ruslan Rakhimov","Denis Volkhonskiy","Alexey Artemov","Denis Zorin","Evgeny Burnaev"],"abstract":"The video generation task can be formulated as a prediction of future video frames given some past frames. Recent generative models for videos face the problem of high computational requirements. Some models require up to 512 Tensor Processing Units for parallel training. In this work, we address this problem via modeling the dynamics in a latent space. After the transformation of frames into the latent space, our model predicts latent representation for the next frames in an autoregressive manner. We demonstrate the performance of our approach on BAIR Robot Pushing and Kinetics-600 datasets. The approach tends to reduce requirements to 8 Graphical Processing Units for training the models while maintaining comparable generation quality.","url_abs":"https://arxiv.org/abs/2006.10704v1","url_pdf":"https://arxiv.org/pdf/2006.10704v1.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":"latent-video-transformer","repo_url":"https://github.com/rakhimovv/lvt","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"video-generation","task_name":"Video Generation"},{"task_slug":"video-prediction","task_name":"Video Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/video-generation-on-bair-robot-pushing","task":"Video Generation","dataset":"BAIR Robot Pushing","model":"LVT","rank_in_archive_order":14,"of":31,"metrics":{"Cond":"1","FVD score":"125.76±2.90","Pred":"15","Train":"15"},"uses_additional_data":false},{"leaderboard":"/sota/video-generation-on-bair-robot-pushing","task":"Video Generation","dataset":"BAIR Robot Pushing","model":"Baseline (from LVT)","rank_in_archive_order":28,"of":31,"metrics":{"Cond":"1","FVD score":"320.9","Pred":"15","Train":"15"},"uses_additional_data":false},{"leaderboard":"/sota/video-prediction-on-kinetics-600-12-frames","task":"Video Prediction","dataset":"Kinetics-600 12 frames, 64x64","model":"LVT","rank_in_archive_order":16,"of":16,"metrics":{"Cond":"5","FVD":"224.73","Pred":"11"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2006.10704","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.10704"}},"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/rakhimovv/lvt","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_fixture":1,"unverified":4},"by_repo_kind":{"official":{"samples":5,"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":"6cbf46794989b731","entry":"cat","repo":"rakhimovv/lvt","repo_kind":"official","path":"vidgen/layers/wrappers.py","file_url":"https://github.com/rakhimovv/lvt/blob/HEAD/vidgen/layers/wrappers.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6cbf46794989b731"}},{"code_sha256_prefix":"a89e04e4f41aac23","entry":"all_gather","repo":"rakhimovv/lvt","repo_kind":"official","path":"vidgen/layers/all_gather.py","file_url":"https://github.com/rakhimovv/lvt/blob/HEAD/vidgen/layers/all_gather.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a89e04e4f41aac23"}},{"code_sha256_prefix":"cfb81a25ee5235c6","entry":"get_out_channel","repo":"rakhimovv/lvt","repo_kind":"official","path":"vidgen/layers/wrappers.py","file_url":"https://github.com/rakhimovv/lvt/blob/HEAD/vidgen/layers/wrappers.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"cfb81a25ee5235c6"}},{"code_sha256_prefix":"e50af06007f00579","entry":"norm_layer","repo":"rakhimovv/lvt","repo_kind":"official","path":"vidgen/layers/wrappers.py","file_url":"https://github.com/rakhimovv/lvt/blob/HEAD/vidgen/layers/wrappers.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e50af06007f00579"}},{"code_sha256_prefix":"8261b186b6cd4b15","entry":"reduce_scatter","repo":"rakhimovv/lvt","repo_kind":"official","path":"vidgen/layers/all_gather.py","file_url":"https://github.com/rakhimovv/lvt/blob/HEAD/vidgen/layers/all_gather.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8261b186b6cd4b15"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}