{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:WNFKLQRIKOSYRZJ4PPLU3UKY33","short_pith_number":"pith:WNFKLQRI","schema_version":"1.0","canonical_sha256":"b34aa5c22853a588e53c7bd74dd158def764407c33e6a7b4fe0fc129095dc1d7","source":{"kind":"arxiv","id":"2006.10704","version":1},"attestation_state":"computed","paper":{"title":"Latent Video Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Alexey Artemov, Denis Volkhonskiy, Denis Zorin, Evgeny Burnaev, Ruslan Rakhimov","submitted_at":"2020-06-18T17:38:38Z","abstract_excerpt":"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. "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2006.10704","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-06-18T17:38:38Z","cross_cats_sorted":["cs.LG","eess.IV"],"title_canon_sha256":"ffa72ab4082afddd247ce573154e11761296eedcf28b56ecea41687fdb116864","abstract_canon_sha256":"3fb9f9321da4b5f727620b204f849333c0f36ad00c352d0ae7c6faa88b50602e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:11:21.556162Z","signature_b64":"2hpzyZLJqRRcvLgVOBDiIaxHsZZlIXv0X8kTnRmt1eDAXqrWTFaQsdHTuJ3MHtNmlgRZPMq4Wn5/VrswTLKADg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b34aa5c22853a588e53c7bd74dd158def764407c33e6a7b4fe0fc129095dc1d7","last_reissued_at":"2026-07-05T01:11:21.555774Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:11:21.555774Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Latent Video Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Alexey Artemov, Denis Volkhonskiy, Denis Zorin, Evgeny Burnaev, Ruslan Rakhimov","submitted_at":"2020-06-18T17:38:38Z","abstract_excerpt":"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. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.10704","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2006.10704/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2006.10704","created_at":"2026-07-05T01:11:21.555821+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.10704v1","created_at":"2026-07-05T01:11:21.555821+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.10704","created_at":"2026-07-05T01:11:21.555821+00:00"},{"alias_kind":"pith_short_12","alias_value":"WNFKLQRIKOSY","created_at":"2026-07-05T01:11:21.555821+00:00"},{"alias_kind":"pith_short_16","alias_value":"WNFKLQRIKOSYRZJ4","created_at":"2026-07-05T01:11:21.555821+00:00"},{"alias_kind":"pith_short_8","alias_value":"WNFKLQRI","created_at":"2026-07-05T01:11:21.555821+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.09156","citing_title":"OmniGen-AR: AutoRegressive Any-to-Image Generation","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2210.02399","citing_title":"Phenaki: Variable Length Video Generation From Open Domain Textual Description","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2211.13221","citing_title":"Latent Video Diffusion Models for High-Fidelity Long Video Generation","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2104.10157","citing_title":"VideoGPT: Video Generation using VQ-VAE and Transformers","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2205.15868","citing_title":"CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WNFKLQRIKOSYRZJ4PPLU3UKY33","json":"https://pith.science/pith/WNFKLQRIKOSYRZJ4PPLU3UKY33.json","graph_json":"https://pith.science/api/pith-number/WNFKLQRIKOSYRZJ4PPLU3UKY33/graph.json","events_json":"https://pith.science/api/pith-number/WNFKLQRIKOSYRZJ4PPLU3UKY33/events.json","paper":"https://pith.science/paper/WNFKLQRI"},"agent_actions":{"view_html":"https://pith.science/pith/WNFKLQRIKOSYRZJ4PPLU3UKY33","download_json":"https://pith.science/pith/WNFKLQRIKOSYRZJ4PPLU3UKY33.json","view_paper":"https://pith.science/paper/WNFKLQRI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.10704&json=true","fetch_graph":"https://pith.science/api/pith-number/WNFKLQRIKOSYRZJ4PPLU3UKY33/graph.json","fetch_events":"https://pith.science/api/pith-number/WNFKLQRIKOSYRZJ4PPLU3UKY33/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WNFKLQRIKOSYRZJ4PPLU3UKY33/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WNFKLQRIKOSYRZJ4PPLU3UKY33/action/storage_attestation","attest_author":"https://pith.science/pith/WNFKLQRIKOSYRZJ4PPLU3UKY33/action/author_attestation","sign_citation":"https://pith.science/pith/WNFKLQRIKOSYRZJ4PPLU3UKY33/action/citation_signature","submit_replication":"https://pith.science/pith/WNFKLQRIKOSYRZJ4PPLU3UKY33/action/replication_record"}},"created_at":"2026-07-05T01:11:21.555821+00:00","updated_at":"2026-07-05T01:11:21.555821+00:00"}