{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:JSO77J2WYVYNB4FJHO6U3CTPJL","short_pith_number":"pith:JSO77J2W","schema_version":"1.0","canonical_sha256":"4c9dffa756c570d0f0a93bbd4d8a6f4af600187330b4fcf66d55ce8eed399f4a","source":{"kind":"arxiv","id":"2312.09525","version":1},"attestation_state":"computed","paper":{"title":"Hierarchical Graph Pattern Understanding for Zero-Shot VOS","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fumin Shen, Gensheng Pei, Heng-Tao Shen, Tao Chen, Xian-Sheng Hua, Yazhou Yao","submitted_at":"2023-12-15T04:13:21Z","abstract_excerpt":"The optical flow guidance strategy is ideal for obtaining motion information of objects in the video. It is widely utilized in video segmentation tasks. However, existing optical flow-based methods have a significant dependency on optical flow, which results in poor performance when the optical flow estimation fails for a particular scene. The temporal consistency provided by the optical flow could be effectively supplemented by modeling in a structural form. This paper proposes a new hierarchical graph neural network (GNN) architecture, dubbed hierarchical graph pattern understanding (HGPU), "},"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":"2312.09525","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-15T04:13:21Z","cross_cats_sorted":[],"title_canon_sha256":"68721e054a59b3d6c17218d7813e9b5cee35ad37725204ff66488d77ab6a111e","abstract_canon_sha256":"36b596414df578b7fe9e428f7bb57fa331b8e1eb5551e2f16bc79f0cd23bf128"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:24:26.365232Z","signature_b64":"u+ntfLYhWlD0UwYOQoG30cL+uwQHMA4iku3P42395qC0vSTtRtewlWAfk9PRzIJSIkOZcWQkAFalvADWEkgPDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4c9dffa756c570d0f0a93bbd4d8a6f4af600187330b4fcf66d55ce8eed399f4a","last_reissued_at":"2026-07-05T07:24:26.364786Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:24:26.364786Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hierarchical Graph Pattern Understanding for Zero-Shot VOS","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fumin Shen, Gensheng Pei, Heng-Tao Shen, Tao Chen, Xian-Sheng Hua, Yazhou Yao","submitted_at":"2023-12-15T04:13:21Z","abstract_excerpt":"The optical flow guidance strategy is ideal for obtaining motion information of objects in the video. It is widely utilized in video segmentation tasks. However, existing optical flow-based methods have a significant dependency on optical flow, which results in poor performance when the optical flow estimation fails for a particular scene. The temporal consistency provided by the optical flow could be effectively supplemented by modeling in a structural form. This paper proposes a new hierarchical graph neural network (GNN) architecture, dubbed hierarchical graph pattern understanding (HGPU), "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.09525","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/2312.09525/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":"2312.09525","created_at":"2026-07-05T07:24:26.364838+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.09525v1","created_at":"2026-07-05T07:24:26.364838+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.09525","created_at":"2026-07-05T07:24:26.364838+00:00"},{"alias_kind":"pith_short_12","alias_value":"JSO77J2WYVYN","created_at":"2026-07-05T07:24:26.364838+00:00"},{"alias_kind":"pith_short_16","alias_value":"JSO77J2WYVYNB4FJ","created_at":"2026-07-05T07:24:26.364838+00:00"},{"alias_kind":"pith_short_8","alias_value":"JSO77J2W","created_at":"2026-07-05T07:24:26.364838+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.22465","citing_title":"Shallow Features Matter: Hierarchical Memory with Heterogeneous Interaction for Unsupervised Video Object Segmentation","ref_index":41,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JSO77J2WYVYNB4FJHO6U3CTPJL","json":"https://pith.science/pith/JSO77J2WYVYNB4FJHO6U3CTPJL.json","graph_json":"https://pith.science/api/pith-number/JSO77J2WYVYNB4FJHO6U3CTPJL/graph.json","events_json":"https://pith.science/api/pith-number/JSO77J2WYVYNB4FJHO6U3CTPJL/events.json","paper":"https://pith.science/paper/JSO77J2W"},"agent_actions":{"view_html":"https://pith.science/pith/JSO77J2WYVYNB4FJHO6U3CTPJL","download_json":"https://pith.science/pith/JSO77J2WYVYNB4FJHO6U3CTPJL.json","view_paper":"https://pith.science/paper/JSO77J2W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.09525&json=true","fetch_graph":"https://pith.science/api/pith-number/JSO77J2WYVYNB4FJHO6U3CTPJL/graph.json","fetch_events":"https://pith.science/api/pith-number/JSO77J2WYVYNB4FJHO6U3CTPJL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JSO77J2WYVYNB4FJHO6U3CTPJL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JSO77J2WYVYNB4FJHO6U3CTPJL/action/storage_attestation","attest_author":"https://pith.science/pith/JSO77J2WYVYNB4FJHO6U3CTPJL/action/author_attestation","sign_citation":"https://pith.science/pith/JSO77J2WYVYNB4FJHO6U3CTPJL/action/citation_signature","submit_replication":"https://pith.science/pith/JSO77J2WYVYNB4FJHO6U3CTPJL/action/replication_record"}},"created_at":"2026-07-05T07:24:26.364838+00:00","updated_at":"2026-07-05T07:24:26.364838+00:00"}