{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:2DVOLJYGHLEABS4LVPO3IHADL7","short_pith_number":"pith:2DVOLJYG","schema_version":"1.0","canonical_sha256":"d0eae5a7063ac800cb8babddb41c035fe92d5e9599c2f9ba77db2d553fb816d6","source":{"kind":"arxiv","id":"1903.07912","version":1},"attestation_state":"computed","paper":{"title":"Improving Video Compression With Deep Visual-Attention Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexander Ploshkin, Dmitriy Vatolin, Mikhail Erofeev, Vitaliy Lyudvichenko","submitted_at":"2019-03-19T10:06:04Z","abstract_excerpt":"Recent advances in deep learning have markedly improved the quality of visual-attention modelling. In this work we apply these advances to video compression.\n  We propose a compression method that uses a saliency model to adaptively compress frame areas in accordance with their predicted saliency. We selected three state-of-the-art saliency models, adapted them for video compression and analyzed their results. The analysis includes objective evaluation of the models as well as objective and subjective evaluation of the compressed videos.\n  Our method, which is based on the x264 video codec, ca"},"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":"1903.07912","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2019-03-19T10:06:04Z","cross_cats_sorted":[],"title_canon_sha256":"0f77a7c83532a5783d5dbabd4b83f0c8a468092e9b51435994cafa61f195a939","abstract_canon_sha256":"a835378259b3da010100b1b79e086e8cdccd664fa7c5416dba799d04ea32a07d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:39.684372Z","signature_b64":"Bdye9oZeLvSAtJOSc1g7+z7nVGwUeOM+atb3vGGxAQvHUJTwOpNtts9A/J9a7bYMq9NHPrXzMbg+yesLIGbTCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d0eae5a7063ac800cb8babddb41c035fe92d5e9599c2f9ba77db2d553fb816d6","last_reissued_at":"2026-05-17T23:39:39.683896Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:39.683896Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Video Compression With Deep Visual-Attention Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexander Ploshkin, Dmitriy Vatolin, Mikhail Erofeev, Vitaliy Lyudvichenko","submitted_at":"2019-03-19T10:06:04Z","abstract_excerpt":"Recent advances in deep learning have markedly improved the quality of visual-attention modelling. In this work we apply these advances to video compression.\n  We propose a compression method that uses a saliency model to adaptively compress frame areas in accordance with their predicted saliency. We selected three state-of-the-art saliency models, adapted them for video compression and analyzed their results. The analysis includes objective evaluation of the models as well as objective and subjective evaluation of the compressed videos.\n  Our method, which is based on the x264 video codec, ca"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.07912","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":""},"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":"1903.07912","created_at":"2026-05-17T23:39:39.683963+00:00"},{"alias_kind":"arxiv_version","alias_value":"1903.07912v1","created_at":"2026-05-17T23:39:39.683963+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.07912","created_at":"2026-05-17T23:39:39.683963+00:00"},{"alias_kind":"pith_short_12","alias_value":"2DVOLJYGHLEA","created_at":"2026-05-18T12:33:07.085635+00:00"},{"alias_kind":"pith_short_16","alias_value":"2DVOLJYGHLEABS4L","created_at":"2026-05-18T12:33:07.085635+00:00"},{"alias_kind":"pith_short_8","alias_value":"2DVOLJYG","created_at":"2026-05-18T12:33:07.085635+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/2DVOLJYGHLEABS4LVPO3IHADL7","json":"https://pith.science/pith/2DVOLJYGHLEABS4LVPO3IHADL7.json","graph_json":"https://pith.science/api/pith-number/2DVOLJYGHLEABS4LVPO3IHADL7/graph.json","events_json":"https://pith.science/api/pith-number/2DVOLJYGHLEABS4LVPO3IHADL7/events.json","paper":"https://pith.science/paper/2DVOLJYG"},"agent_actions":{"view_html":"https://pith.science/pith/2DVOLJYGHLEABS4LVPO3IHADL7","download_json":"https://pith.science/pith/2DVOLJYGHLEABS4LVPO3IHADL7.json","view_paper":"https://pith.science/paper/2DVOLJYG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1903.07912&json=true","fetch_graph":"https://pith.science/api/pith-number/2DVOLJYGHLEABS4LVPO3IHADL7/graph.json","fetch_events":"https://pith.science/api/pith-number/2DVOLJYGHLEABS4LVPO3IHADL7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2DVOLJYGHLEABS4LVPO3IHADL7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2DVOLJYGHLEABS4LVPO3IHADL7/action/storage_attestation","attest_author":"https://pith.science/pith/2DVOLJYGHLEABS4LVPO3IHADL7/action/author_attestation","sign_citation":"https://pith.science/pith/2DVOLJYGHLEABS4LVPO3IHADL7/action/citation_signature","submit_replication":"https://pith.science/pith/2DVOLJYGHLEABS4LVPO3IHADL7/action/replication_record"}},"created_at":"2026-05-17T23:39:39.683963+00:00","updated_at":"2026-05-17T23:39:39.683963+00:00"}