{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:A3AGG4K2NX2FK7BNOOYNZF6EVS","short_pith_number":"pith:A3AGG4K2","schema_version":"1.0","canonical_sha256":"06c063715a6df4557c2d73b0dc97c4ac9c2e1f4b8f9ba6be313ab0a2a210c781","source":{"kind":"arxiv","id":"1908.05717","version":2},"attestation_state":"computed","paper":{"title":"Video Compression With Rate-Distortion Autoencoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"eess.IV","authors_text":"Amirhossein Habibian, Jakub M. Tomczak, Taco S. Cohen, Ties van Rozendaal","submitted_at":"2019-08-14T15:37:23Z","abstract_excerpt":"In this paper we present a a deep generative model for lossy video compression. We employ a model that consists of a 3D autoencoder with a discrete latent space and an autoregressive prior used for entropy coding. Both autoencoder and prior are trained jointly to minimize a rate-distortion loss, which is closely related to the ELBO used in variational autoencoders. Despite its simplicity, we find that our method outperforms the state-of-the-art learned video compression networks based on motion compensation or interpolation. We systematically evaluate various design choices, such as the use of"},"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":"1908.05717","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2019-08-14T15:37:23Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"83772d086ef3188858f8afa8ec484e893e96a2d6e799a44ca5d745caff325c1b","abstract_canon_sha256":"563f951258adb607aa0dcb59fbe183f20e07a93fe232fdabd4fdcb1281116d4d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:01:20.513861Z","signature_b64":"I88majC524x0JMCITLfw/thhVmdk52JxAlak5USKr0DoiYAlz0PJKSAnb9WsgDaS/+ryZDhPFoLUDqYlvN1rCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"06c063715a6df4557c2d73b0dc97c4ac9c2e1f4b8f9ba6be313ab0a2a210c781","last_reissued_at":"2026-07-05T01:01:20.513438Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:01:20.513438Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Video Compression With Rate-Distortion Autoencoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"eess.IV","authors_text":"Amirhossein Habibian, Jakub M. Tomczak, Taco S. Cohen, Ties van Rozendaal","submitted_at":"2019-08-14T15:37:23Z","abstract_excerpt":"In this paper we present a a deep generative model for lossy video compression. We employ a model that consists of a 3D autoencoder with a discrete latent space and an autoregressive prior used for entropy coding. Both autoencoder and prior are trained jointly to minimize a rate-distortion loss, which is closely related to the ELBO used in variational autoencoders. Despite its simplicity, we find that our method outperforms the state-of-the-art learned video compression networks based on motion compensation or interpolation. We systematically evaluate various design choices, such as the use of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.05717","kind":"arxiv","version":2},"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/1908.05717/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":"1908.05717","created_at":"2026-07-05T01:01:20.513496+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.05717v2","created_at":"2026-07-05T01:01:20.513496+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.05717","created_at":"2026-07-05T01:01:20.513496+00:00"},{"alias_kind":"pith_short_12","alias_value":"A3AGG4K2NX2F","created_at":"2026-07-05T01:01:20.513496+00:00"},{"alias_kind":"pith_short_16","alias_value":"A3AGG4K2NX2FK7BN","created_at":"2026-07-05T01:01:20.513496+00:00"},{"alias_kind":"pith_short_8","alias_value":"A3AGG4K2","created_at":"2026-07-05T01:01:20.513496+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/A3AGG4K2NX2FK7BNOOYNZF6EVS","json":"https://pith.science/pith/A3AGG4K2NX2FK7BNOOYNZF6EVS.json","graph_json":"https://pith.science/api/pith-number/A3AGG4K2NX2FK7BNOOYNZF6EVS/graph.json","events_json":"https://pith.science/api/pith-number/A3AGG4K2NX2FK7BNOOYNZF6EVS/events.json","paper":"https://pith.science/paper/A3AGG4K2"},"agent_actions":{"view_html":"https://pith.science/pith/A3AGG4K2NX2FK7BNOOYNZF6EVS","download_json":"https://pith.science/pith/A3AGG4K2NX2FK7BNOOYNZF6EVS.json","view_paper":"https://pith.science/paper/A3AGG4K2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.05717&json=true","fetch_graph":"https://pith.science/api/pith-number/A3AGG4K2NX2FK7BNOOYNZF6EVS/graph.json","fetch_events":"https://pith.science/api/pith-number/A3AGG4K2NX2FK7BNOOYNZF6EVS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A3AGG4K2NX2FK7BNOOYNZF6EVS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A3AGG4K2NX2FK7BNOOYNZF6EVS/action/storage_attestation","attest_author":"https://pith.science/pith/A3AGG4K2NX2FK7BNOOYNZF6EVS/action/author_attestation","sign_citation":"https://pith.science/pith/A3AGG4K2NX2FK7BNOOYNZF6EVS/action/citation_signature","submit_replication":"https://pith.science/pith/A3AGG4K2NX2FK7BNOOYNZF6EVS/action/replication_record"}},"created_at":"2026-07-05T01:01:20.513496+00:00","updated_at":"2026-07-05T01:01:20.513496+00:00"}