{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:DZTSDMW345FDSC476OA3MBEQPN","short_pith_number":"pith:DZTSDMW3","schema_version":"1.0","canonical_sha256":"1e6721b2dbe74a390b9ff381b604907b475fbfbddacd4a684851ab2219679bb4","source":{"kind":"arxiv","id":"2303.03684","version":2},"attestation_state":"computed","paper":{"title":"MOSO: Decomposing MOtion, Scene and Object for Video Prediction","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jing Liu, Mingzhen Sun, Weining Wang, Xinxin Zhu","submitted_at":"2023-03-07T06:54:48Z","abstract_excerpt":"Motion, scene and object are three primary visual components of a video. In particular, objects represent the foreground, scenes represent the background, and motion traces their dynamics. Based on this insight, we propose a two-stage MOtion, Scene and Object decomposition framework (MOSO) for video prediction, consisting of MOSO-VQVAE and MOSO-Transformer. In the first stage, MOSO-VQVAE decomposes a previous video clip into the motion, scene and object components, and represents them as distinct groups of discrete tokens. Then, in the second stage, MOSO-Transformer predicts the object and sce"},"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":"2303.03684","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-07T06:54:48Z","cross_cats_sorted":[],"title_canon_sha256":"a1d908557709ef7e125d640c0ce99c3c22aa8362ea0f63680040d215e774710a","abstract_canon_sha256":"aa839f7e4ef64c3eeb83eefaf3ed3c22437af7070425c5915edafdab633842a6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:51:45.339129Z","signature_b64":"5AZ1SvoVjasKS6kWpXrkjXVSBjRIppbIsZpSppiMBoHTsSBFdtoJtnoXn2IR5mukpBf5MIGsnu0bSfZfTBDeCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1e6721b2dbe74a390b9ff381b604907b475fbfbddacd4a684851ab2219679bb4","last_reissued_at":"2026-07-05T05:51:45.338745Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:51:45.338745Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MOSO: Decomposing MOtion, Scene and Object for Video Prediction","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jing Liu, Mingzhen Sun, Weining Wang, Xinxin Zhu","submitted_at":"2023-03-07T06:54:48Z","abstract_excerpt":"Motion, scene and object are three primary visual components of a video. In particular, objects represent the foreground, scenes represent the background, and motion traces their dynamics. Based on this insight, we propose a two-stage MOtion, Scene and Object decomposition framework (MOSO) for video prediction, consisting of MOSO-VQVAE and MOSO-Transformer. In the first stage, MOSO-VQVAE decomposes a previous video clip into the motion, scene and object components, and represents them as distinct groups of discrete tokens. Then, in the second stage, MOSO-Transformer predicts the object and sce"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.03684","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/2303.03684/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":"2303.03684","created_at":"2026-07-05T05:51:45.338800+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.03684v2","created_at":"2026-07-05T05:51:45.338800+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.03684","created_at":"2026-07-05T05:51:45.338800+00:00"},{"alias_kind":"pith_short_12","alias_value":"DZTSDMW345FD","created_at":"2026-07-05T05:51:45.338800+00:00"},{"alias_kind":"pith_short_16","alias_value":"DZTSDMW345FDSC47","created_at":"2026-07-05T05:51:45.338800+00:00"},{"alias_kind":"pith_short_8","alias_value":"DZTSDMW3","created_at":"2026-07-05T05:51:45.338800+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.10562","citing_title":"On the Benefits of Instance Decomposition in Video Prediction Models","ref_index":47,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DZTSDMW345FDSC476OA3MBEQPN","json":"https://pith.science/pith/DZTSDMW345FDSC476OA3MBEQPN.json","graph_json":"https://pith.science/api/pith-number/DZTSDMW345FDSC476OA3MBEQPN/graph.json","events_json":"https://pith.science/api/pith-number/DZTSDMW345FDSC476OA3MBEQPN/events.json","paper":"https://pith.science/paper/DZTSDMW3"},"agent_actions":{"view_html":"https://pith.science/pith/DZTSDMW345FDSC476OA3MBEQPN","download_json":"https://pith.science/pith/DZTSDMW345FDSC476OA3MBEQPN.json","view_paper":"https://pith.science/paper/DZTSDMW3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.03684&json=true","fetch_graph":"https://pith.science/api/pith-number/DZTSDMW345FDSC476OA3MBEQPN/graph.json","fetch_events":"https://pith.science/api/pith-number/DZTSDMW345FDSC476OA3MBEQPN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DZTSDMW345FDSC476OA3MBEQPN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DZTSDMW345FDSC476OA3MBEQPN/action/storage_attestation","attest_author":"https://pith.science/pith/DZTSDMW345FDSC476OA3MBEQPN/action/author_attestation","sign_citation":"https://pith.science/pith/DZTSDMW345FDSC476OA3MBEQPN/action/citation_signature","submit_replication":"https://pith.science/pith/DZTSDMW345FDSC476OA3MBEQPN/action/replication_record"}},"created_at":"2026-07-05T05:51:45.338800+00:00","updated_at":"2026-07-05T05:51:45.338800+00:00"}