{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:SOWW6VS4JBOBMD3OVQT7CDR4ZH","short_pith_number":"pith:SOWW6VS4","schema_version":"1.0","canonical_sha256":"93ad6f565c485c160f6eac27f10e3cc9e9ae9edfaa37d840dce79c142b77c9de","source":{"kind":"arxiv","id":"2309.08020","version":1},"attestation_state":"computed","paper":{"title":"Temporal-aware Hierarchical Mask Classification for Video Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guolei Sun, Hao Tang, Luc Van Gool, Zhaochong An, Zongwei Wu","submitted_at":"2023-09-14T20:31:06Z","abstract_excerpt":"Modern approaches have proved the huge potential of addressing semantic segmentation as a mask classification task which is widely used in instance-level segmentation. This paradigm trains models by assigning part of object queries to ground truths via conventional one-to-one matching. However, we observe that the popular video semantic segmentation (VSS) dataset has limited categories per video, meaning less than 10% of queries could be matched to receive meaningful gradient updates during VSS training. This inefficiency limits the full expressive potential of all queries.Thus, we present a n"},"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":"2309.08020","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-14T20:31:06Z","cross_cats_sorted":[],"title_canon_sha256":"fd9d06cbbd4b224e09956fe732377065e78868da15bef3f5d1dc0fcc7de02461","abstract_canon_sha256":"819922aa317889c00557bb8d33aca9832b98787cc0f22d7a8c2cd009fedce28c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:51:00.877258Z","signature_b64":"EYXyQCgAte2iggVreJMyCoxCvpgUBuw8TGDDTNXvqlMTKX5Qg99KBzBRQd8Cge9YGkaF090lsTTso19PgSQjBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"93ad6f565c485c160f6eac27f10e3cc9e9ae9edfaa37d840dce79c142b77c9de","last_reissued_at":"2026-07-05T06:51:00.876850Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:51:00.876850Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Temporal-aware Hierarchical Mask Classification for Video Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guolei Sun, Hao Tang, Luc Van Gool, Zhaochong An, Zongwei Wu","submitted_at":"2023-09-14T20:31:06Z","abstract_excerpt":"Modern approaches have proved the huge potential of addressing semantic segmentation as a mask classification task which is widely used in instance-level segmentation. This paradigm trains models by assigning part of object queries to ground truths via conventional one-to-one matching. However, we observe that the popular video semantic segmentation (VSS) dataset has limited categories per video, meaning less than 10% of queries could be matched to receive meaningful gradient updates during VSS training. This inefficiency limits the full expressive potential of all queries.Thus, we present a n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.08020","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/2309.08020/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":"2309.08020","created_at":"2026-07-05T06:51:00.876914+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.08020v1","created_at":"2026-07-05T06:51:00.876914+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.08020","created_at":"2026-07-05T06:51:00.876914+00:00"},{"alias_kind":"pith_short_12","alias_value":"SOWW6VS4JBOB","created_at":"2026-07-05T06:51:00.876914+00:00"},{"alias_kind":"pith_short_16","alias_value":"SOWW6VS4JBOBMD3O","created_at":"2026-07-05T06:51:00.876914+00:00"},{"alias_kind":"pith_short_8","alias_value":"SOWW6VS4","created_at":"2026-07-05T06:51:00.876914+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.10950","citing_title":"Bootstrapping Video Semantic Segmentation Model via Distillation-assisted Test-Time Adaptation","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SOWW6VS4JBOBMD3OVQT7CDR4ZH","json":"https://pith.science/pith/SOWW6VS4JBOBMD3OVQT7CDR4ZH.json","graph_json":"https://pith.science/api/pith-number/SOWW6VS4JBOBMD3OVQT7CDR4ZH/graph.json","events_json":"https://pith.science/api/pith-number/SOWW6VS4JBOBMD3OVQT7CDR4ZH/events.json","paper":"https://pith.science/paper/SOWW6VS4"},"agent_actions":{"view_html":"https://pith.science/pith/SOWW6VS4JBOBMD3OVQT7CDR4ZH","download_json":"https://pith.science/pith/SOWW6VS4JBOBMD3OVQT7CDR4ZH.json","view_paper":"https://pith.science/paper/SOWW6VS4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.08020&json=true","fetch_graph":"https://pith.science/api/pith-number/SOWW6VS4JBOBMD3OVQT7CDR4ZH/graph.json","fetch_events":"https://pith.science/api/pith-number/SOWW6VS4JBOBMD3OVQT7CDR4ZH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SOWW6VS4JBOBMD3OVQT7CDR4ZH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SOWW6VS4JBOBMD3OVQT7CDR4ZH/action/storage_attestation","attest_author":"https://pith.science/pith/SOWW6VS4JBOBMD3OVQT7CDR4ZH/action/author_attestation","sign_citation":"https://pith.science/pith/SOWW6VS4JBOBMD3OVQT7CDR4ZH/action/citation_signature","submit_replication":"https://pith.science/pith/SOWW6VS4JBOBMD3OVQT7CDR4ZH/action/replication_record"}},"created_at":"2026-07-05T06:51:00.876914+00:00","updated_at":"2026-07-05T06:51:00.876914+00:00"}