{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:AVM6D6NFJMFSEK4AHJMAQVWAR6","short_pith_number":"pith:AVM6D6NF","schema_version":"1.0","canonical_sha256":"0559e1f9a54b0b222b803a580856c08fb145d8c8f730d6b8f43aef099c42bd9f","source":{"kind":"arxiv","id":"2403.01560","version":2},"attestation_state":"computed","paper":{"title":"Rethinking CLIP-based Video Learners in Cross-Domain Open-Vocabulary Action Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Change Loy, Henghui Ding, Jiaming Zhou, Kun-Yu Lin, Wei-Shi Zheng, Yi-Xing Peng, Yu-Ming Tang, Zhilin Zhao","submitted_at":"2024-03-03T16:48:16Z","abstract_excerpt":"Building upon the impressive success of CLIP (Contrastive Language-Image Pretraining), recent pioneer works have proposed to adapt the powerful CLIP to video data, leading to efficient and effective video learners for open-vocabulary action recognition. Inspired by that humans perform actions in diverse environments, our work delves into an intriguing question: Can CLIP-based video learners effectively generalize to video domains they have not encountered during training? To answer this, we establish a CROSS-domain Open-Vocabulary Action recognition benchmark named XOV-Action, and conduct a co"},"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":"2403.01560","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-03T16:48:16Z","cross_cats_sorted":[],"title_canon_sha256":"533caeaa43e2d31b081ba909aa4c073046adc1ad59f081f68f8cec23d87e9153","abstract_canon_sha256":"cf6a875b1a9a73f6866fa093fd58cc4fa518c7882a274ccfa1b802389f2cc1f0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:22:38.212224Z","signature_b64":"sX4T3y/pY6J8ZwKOmcpck9LVwuYzEQuxz+kT6Nio3DStuYUyeTz+4xmsNYmF+j/LadwHkKZ6xTzgpFHgmf0lDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0559e1f9a54b0b222b803a580856c08fb145d8c8f730d6b8f43aef099c42bd9f","last_reissued_at":"2026-07-05T08:22:38.211648Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:22:38.211648Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rethinking CLIP-based Video Learners in Cross-Domain Open-Vocabulary Action Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Change Loy, Henghui Ding, Jiaming Zhou, Kun-Yu Lin, Wei-Shi Zheng, Yi-Xing Peng, Yu-Ming Tang, Zhilin Zhao","submitted_at":"2024-03-03T16:48:16Z","abstract_excerpt":"Building upon the impressive success of CLIP (Contrastive Language-Image Pretraining), recent pioneer works have proposed to adapt the powerful CLIP to video data, leading to efficient and effective video learners for open-vocabulary action recognition. Inspired by that humans perform actions in diverse environments, our work delves into an intriguing question: Can CLIP-based video learners effectively generalize to video domains they have not encountered during training? To answer this, we establish a CROSS-domain Open-Vocabulary Action recognition benchmark named XOV-Action, and conduct a co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.01560","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/2403.01560/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":"2403.01560","created_at":"2026-07-05T08:22:38.211704+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.01560v2","created_at":"2026-07-05T08:22:38.211704+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.01560","created_at":"2026-07-05T08:22:38.211704+00:00"},{"alias_kind":"pith_short_12","alias_value":"AVM6D6NFJMFS","created_at":"2026-07-05T08:22:38.211704+00:00"},{"alias_kind":"pith_short_16","alias_value":"AVM6D6NFJMFSEK4A","created_at":"2026-07-05T08:22:38.211704+00:00"},{"alias_kind":"pith_short_8","alias_value":"AVM6D6NF","created_at":"2026-07-05T08:22:38.211704+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/AVM6D6NFJMFSEK4AHJMAQVWAR6","json":"https://pith.science/pith/AVM6D6NFJMFSEK4AHJMAQVWAR6.json","graph_json":"https://pith.science/api/pith-number/AVM6D6NFJMFSEK4AHJMAQVWAR6/graph.json","events_json":"https://pith.science/api/pith-number/AVM6D6NFJMFSEK4AHJMAQVWAR6/events.json","paper":"https://pith.science/paper/AVM6D6NF"},"agent_actions":{"view_html":"https://pith.science/pith/AVM6D6NFJMFSEK4AHJMAQVWAR6","download_json":"https://pith.science/pith/AVM6D6NFJMFSEK4AHJMAQVWAR6.json","view_paper":"https://pith.science/paper/AVM6D6NF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.01560&json=true","fetch_graph":"https://pith.science/api/pith-number/AVM6D6NFJMFSEK4AHJMAQVWAR6/graph.json","fetch_events":"https://pith.science/api/pith-number/AVM6D6NFJMFSEK4AHJMAQVWAR6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AVM6D6NFJMFSEK4AHJMAQVWAR6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AVM6D6NFJMFSEK4AHJMAQVWAR6/action/storage_attestation","attest_author":"https://pith.science/pith/AVM6D6NFJMFSEK4AHJMAQVWAR6/action/author_attestation","sign_citation":"https://pith.science/pith/AVM6D6NFJMFSEK4AHJMAQVWAR6/action/citation_signature","submit_replication":"https://pith.science/pith/AVM6D6NFJMFSEK4AHJMAQVWAR6/action/replication_record"}},"created_at":"2026-07-05T08:22:38.211704+00:00","updated_at":"2026-07-05T08:22:38.211704+00:00"}