{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OOUWVM2C2CXJYSJP6G4MEM5PPQ","short_pith_number":"pith:OOUWVM2C","schema_version":"1.0","canonical_sha256":"73a96ab342d0ae9c492ff1b8c233af7c2fb21d18411aae1c1c9cb82440c7b774","source":{"kind":"arxiv","id":"2501.13795","version":1},"attestation_state":"computed","paper":{"title":"Training-Free Zero-Shot Temporal Action Detection with Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chaolei Han, Hongsong Wang, Jidong Kuang, Jie Gui, Lei Zhang","submitted_at":"2025-01-23T16:13:58Z","abstract_excerpt":"Existing zero-shot temporal action detection (ZSTAD) methods predominantly use fully supervised or unsupervised strategies to recognize unseen activities. However, these training-based methods are prone to domain shifts and require high computational costs, which hinder their practical applicability in real-world scenarios. In this paper, unlike previous works, we propose a training-Free Zero-shot temporal Action Detection (FreeZAD) method, leveraging existing vision-language (ViL) models to directly classify and localize unseen activities within untrimmed videos without any additional fine-tu"},"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":"2501.13795","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-23T16:13:58Z","cross_cats_sorted":[],"title_canon_sha256":"9f151fc92fe09e647d89cd861eba5ca227da838e381b988481388629b05ba54b","abstract_canon_sha256":"4fea2de4a2849dd1984c225a6212f7be0087d2f927fdc8f131000693e6acbcab"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:04:07.497455Z","signature_b64":"oIR+MSRXisB34Tc9DeFcQ6eZMV2LdVuWIuDf3Yi8pFGYEk0ga09BY4QLlYGIsoOyF6l978OdHWYLyoHICNrNCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"73a96ab342d0ae9c492ff1b8c233af7c2fb21d18411aae1c1c9cb82440c7b774","last_reissued_at":"2026-05-20T00:04:07.496663Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:04:07.496663Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Training-Free Zero-Shot Temporal Action Detection with Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chaolei Han, Hongsong Wang, Jidong Kuang, Jie Gui, Lei Zhang","submitted_at":"2025-01-23T16:13:58Z","abstract_excerpt":"Existing zero-shot temporal action detection (ZSTAD) methods predominantly use fully supervised or unsupervised strategies to recognize unseen activities. However, these training-based methods are prone to domain shifts and require high computational costs, which hinder their practical applicability in real-world scenarios. In this paper, unlike previous works, we propose a training-Free Zero-shot temporal Action Detection (FreeZAD) method, leveraging existing vision-language (ViL) models to directly classify and localize unseen activities within untrimmed videos without any additional fine-tu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.13795","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/2501.13795/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":"2501.13795","created_at":"2026-05-20T00:04:07.496786+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.13795v1","created_at":"2026-05-20T00:04:07.496786+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.13795","created_at":"2026-05-20T00:04:07.496786+00:00"},{"alias_kind":"pith_short_12","alias_value":"OOUWVM2C2CXJ","created_at":"2026-05-20T00:04:07.496786+00:00"},{"alias_kind":"pith_short_16","alias_value":"OOUWVM2C2CXJYSJP","created_at":"2026-05-20T00:04:07.496786+00:00"},{"alias_kind":"pith_short_8","alias_value":"OOUWVM2C","created_at":"2026-05-20T00:04:07.496786+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.00496","citing_title":"High-Speed Vision Improves Zero-Shot Semantic Understanding of Human Actions","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OOUWVM2C2CXJYSJP6G4MEM5PPQ","json":"https://pith.science/pith/OOUWVM2C2CXJYSJP6G4MEM5PPQ.json","graph_json":"https://pith.science/api/pith-number/OOUWVM2C2CXJYSJP6G4MEM5PPQ/graph.json","events_json":"https://pith.science/api/pith-number/OOUWVM2C2CXJYSJP6G4MEM5PPQ/events.json","paper":"https://pith.science/paper/OOUWVM2C"},"agent_actions":{"view_html":"https://pith.science/pith/OOUWVM2C2CXJYSJP6G4MEM5PPQ","download_json":"https://pith.science/pith/OOUWVM2C2CXJYSJP6G4MEM5PPQ.json","view_paper":"https://pith.science/paper/OOUWVM2C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.13795&json=true","fetch_graph":"https://pith.science/api/pith-number/OOUWVM2C2CXJYSJP6G4MEM5PPQ/graph.json","fetch_events":"https://pith.science/api/pith-number/OOUWVM2C2CXJYSJP6G4MEM5PPQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OOUWVM2C2CXJYSJP6G4MEM5PPQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OOUWVM2C2CXJYSJP6G4MEM5PPQ/action/storage_attestation","attest_author":"https://pith.science/pith/OOUWVM2C2CXJYSJP6G4MEM5PPQ/action/author_attestation","sign_citation":"https://pith.science/pith/OOUWVM2C2CXJYSJP6G4MEM5PPQ/action/citation_signature","submit_replication":"https://pith.science/pith/OOUWVM2C2CXJYSJP6G4MEM5PPQ/action/replication_record"}},"created_at":"2026-05-20T00:04:07.496786+00:00","updated_at":"2026-05-20T00:04:07.496786+00:00"}