{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CJDRQ3HCRMFCQLEFGKACK4MTOR","short_pith_number":"pith:CJDRQ3HC","schema_version":"1.0","canonical_sha256":"1247186ce28b0a282c853280257193744e4adcca42bb5a0e41b81f50728a57c9","source":{"kind":"arxiv","id":"2404.12389","version":2},"attestation_state":"computed","paper":{"title":"Moving Object Segmentation: All You Need Is SAM (and Flow)","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrew Zisserman, Charig Yang, Junyu Xie, Weidi Xie","submitted_at":"2024-04-18T17:59:53Z","abstract_excerpt":"The objective of this paper is motion segmentation -- discovering and segmenting the moving objects in a video. This is a much studied area with numerous careful, and sometimes complex, approaches and training schemes including: self-supervised learning, learning from synthetic datasets, object-centric representations, amodal representations, and many more. Our interest in this paper is to determine if the Segment Anything model (SAM) can contribute to this task. We investigate two models for combining SAM with optical flow that harness the segmentation power of SAM with the ability of flow to"},"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":"2404.12389","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-18T17:59:53Z","cross_cats_sorted":[],"title_canon_sha256":"8c18ac738a93e465812f558cc115d0b5bec47e0c507787e55adfeda6b1451d21","abstract_canon_sha256":"b607f483ac51e674d499c3f11fd96b155ff307ff573b6cb96df56be50bbb08b0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:38:49.008258Z","signature_b64":"qRuGjeP4p6F9fnHt/Bf0Q8+yYNy8d7UQwgjR1sPtJ2chnLs5ff6MmqZS2PATlEudob3VpEPMLvkWhE9L8PTmBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1247186ce28b0a282c853280257193744e4adcca42bb5a0e41b81f50728a57c9","last_reissued_at":"2026-07-05T09:38:49.007769Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:38:49.007769Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Moving Object Segmentation: All You Need Is SAM (and Flow)","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrew Zisserman, Charig Yang, Junyu Xie, Weidi Xie","submitted_at":"2024-04-18T17:59:53Z","abstract_excerpt":"The objective of this paper is motion segmentation -- discovering and segmenting the moving objects in a video. This is a much studied area with numerous careful, and sometimes complex, approaches and training schemes including: self-supervised learning, learning from synthetic datasets, object-centric representations, amodal representations, and many more. Our interest in this paper is to determine if the Segment Anything model (SAM) can contribute to this task. We investigate two models for combining SAM with optical flow that harness the segmentation power of SAM with the ability of flow to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.12389","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/2404.12389/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":"2404.12389","created_at":"2026-07-05T09:38:49.007831+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.12389v2","created_at":"2026-07-05T09:38:49.007831+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.12389","created_at":"2026-07-05T09:38:49.007831+00:00"},{"alias_kind":"pith_short_12","alias_value":"CJDRQ3HCRMFC","created_at":"2026-07-05T09:38:49.007831+00:00"},{"alias_kind":"pith_short_16","alias_value":"CJDRQ3HCRMFCQLEF","created_at":"2026-07-05T09:38:49.007831+00:00"},{"alias_kind":"pith_short_8","alias_value":"CJDRQ3HC","created_at":"2026-07-05T09:38:49.007831+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.00659","citing_title":"LoD-Loc v2: Aerial Visual Localization over Low Level-of-Detail City Models using Explicit Silhouette Alignment","ref_index":89,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CJDRQ3HCRMFCQLEFGKACK4MTOR","json":"https://pith.science/pith/CJDRQ3HCRMFCQLEFGKACK4MTOR.json","graph_json":"https://pith.science/api/pith-number/CJDRQ3HCRMFCQLEFGKACK4MTOR/graph.json","events_json":"https://pith.science/api/pith-number/CJDRQ3HCRMFCQLEFGKACK4MTOR/events.json","paper":"https://pith.science/paper/CJDRQ3HC"},"agent_actions":{"view_html":"https://pith.science/pith/CJDRQ3HCRMFCQLEFGKACK4MTOR","download_json":"https://pith.science/pith/CJDRQ3HCRMFCQLEFGKACK4MTOR.json","view_paper":"https://pith.science/paper/CJDRQ3HC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.12389&json=true","fetch_graph":"https://pith.science/api/pith-number/CJDRQ3HCRMFCQLEFGKACK4MTOR/graph.json","fetch_events":"https://pith.science/api/pith-number/CJDRQ3HCRMFCQLEFGKACK4MTOR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CJDRQ3HCRMFCQLEFGKACK4MTOR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CJDRQ3HCRMFCQLEFGKACK4MTOR/action/storage_attestation","attest_author":"https://pith.science/pith/CJDRQ3HCRMFCQLEFGKACK4MTOR/action/author_attestation","sign_citation":"https://pith.science/pith/CJDRQ3HCRMFCQLEFGKACK4MTOR/action/citation_signature","submit_replication":"https://pith.science/pith/CJDRQ3HCRMFCQLEFGKACK4MTOR/action/replication_record"}},"created_at":"2026-07-05T09:38:49.007831+00:00","updated_at":"2026-07-05T09:38:49.007831+00:00"}