{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:Q36APAI3JTCD6WIE25K37VFLHL","short_pith_number":"pith:Q36APAI3","schema_version":"1.0","canonical_sha256":"86fc07811b4cc43f5904d755bfd4ab3add34fd5a17c38e79106d84613febdefb","source":{"kind":"arxiv","id":"2511.13039","version":2},"attestation_state":"computed","paper":{"title":"MGCA-Net: Multi-Grained Category-Aware Network for Open-Vocabulary Temporal Action Localization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Richang Hong, Zhenying Fang","submitted_at":"2025-11-17T06:40:02Z","abstract_excerpt":"Open-Vocabulary Temporal Action Localization (OV-TAL) aims to recognize and localize instances of any desired action categories in videos without explicitly curating training data for all categories. Existing methods mostly recognize action categories at a single granularity, which degrades the recognition accuracy of both base and novel action categories. To address these issues, we propose a Multi-Grained Category-Aware Network (MGCA-Net) comprising a localizer, an action presence predictor, a conventional classifier, and a coarse-to-fine classifier. Specifically, the localizer localizes cat"},"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":"2511.13039","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-11-17T06:40:02Z","cross_cats_sorted":[],"title_canon_sha256":"18b09e18bd9146cb1128028f03f1c16dbb155f980ab932d6538884a8868aed1a","abstract_canon_sha256":"1bcc21d5dc6840b07f8a5f89868de852ab38d5db1ceda8c460c463c020c8af96"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T01:16:00.871206Z","signature_b64":"OzM2SR7lEc0cTKQzN4+XdqIIrs1XiWJUf7gSroZU0BRfdxAVWwPz00HghMzAw+pKdQ5DGa3tJlsTa6l4A9N1AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"86fc07811b4cc43f5904d755bfd4ab3add34fd5a17c38e79106d84613febdefb","last_reissued_at":"2026-07-07T01:16:00.870171Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T01:16:00.870171Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MGCA-Net: Multi-Grained Category-Aware Network for Open-Vocabulary Temporal Action Localization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Richang Hong, Zhenying Fang","submitted_at":"2025-11-17T06:40:02Z","abstract_excerpt":"Open-Vocabulary Temporal Action Localization (OV-TAL) aims to recognize and localize instances of any desired action categories in videos without explicitly curating training data for all categories. Existing methods mostly recognize action categories at a single granularity, which degrades the recognition accuracy of both base and novel action categories. To address these issues, we propose a Multi-Grained Category-Aware Network (MGCA-Net) comprising a localizer, an action presence predictor, a conventional classifier, and a coarse-to-fine classifier. Specifically, the localizer localizes cat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.13039","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/2511.13039/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":"2511.13039","created_at":"2026-07-07T01:16:00.870325+00:00"},{"alias_kind":"arxiv_version","alias_value":"2511.13039v2","created_at":"2026-07-07T01:16:00.870325+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.13039","created_at":"2026-07-07T01:16:00.870325+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q36APAI3JTCD","created_at":"2026-07-07T01:16:00.870325+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q36APAI3JTCD6WIE","created_at":"2026-07-07T01:16:00.870325+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q36APAI3","created_at":"2026-07-07T01:16:00.870325+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/Q36APAI3JTCD6WIE25K37VFLHL","json":"https://pith.science/pith/Q36APAI3JTCD6WIE25K37VFLHL.json","graph_json":"https://pith.science/api/pith-number/Q36APAI3JTCD6WIE25K37VFLHL/graph.json","events_json":"https://pith.science/api/pith-number/Q36APAI3JTCD6WIE25K37VFLHL/events.json","paper":"https://pith.science/paper/Q36APAI3"},"agent_actions":{"view_html":"https://pith.science/pith/Q36APAI3JTCD6WIE25K37VFLHL","download_json":"https://pith.science/pith/Q36APAI3JTCD6WIE25K37VFLHL.json","view_paper":"https://pith.science/paper/Q36APAI3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2511.13039&json=true","fetch_graph":"https://pith.science/api/pith-number/Q36APAI3JTCD6WIE25K37VFLHL/graph.json","fetch_events":"https://pith.science/api/pith-number/Q36APAI3JTCD6WIE25K37VFLHL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q36APAI3JTCD6WIE25K37VFLHL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q36APAI3JTCD6WIE25K37VFLHL/action/storage_attestation","attest_author":"https://pith.science/pith/Q36APAI3JTCD6WIE25K37VFLHL/action/author_attestation","sign_citation":"https://pith.science/pith/Q36APAI3JTCD6WIE25K37VFLHL/action/citation_signature","submit_replication":"https://pith.science/pith/Q36APAI3JTCD6WIE25K37VFLHL/action/replication_record"}},"created_at":"2026-07-07T01:16:00.870325+00:00","updated_at":"2026-07-07T01:16:00.870325+00:00"}