{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3HYT5FB2CTM4GYTDX6EPYIWIRC","short_pith_number":"pith:3HYT5FB2","schema_version":"1.0","canonical_sha256":"d9f13e943a14d9c36263bf88fc22c88880230dd3008e2c06fd0c6149813ed86b","source":{"kind":"arxiv","id":"2402.03241","version":1},"attestation_state":"computed","paper":{"title":"FROSTER: Frozen CLIP Is A Strong Teacher for Open-Vocabulary Action Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Hao Zhou, Kai Han, Kun Yao, Xiaohu Huang","submitted_at":"2024-02-05T17:56:41Z","abstract_excerpt":"In this paper, we introduce FROSTER, an effective framework for open-vocabulary action recognition. The CLIP model has achieved remarkable success in a range of image-based tasks, benefiting from its strong generalization capability stemming from pretaining on massive image-text pairs. However, applying CLIP directly to the open-vocabulary action recognition task is challenging due to the absence of temporal information in CLIP's pretraining. Further, fine-tuning CLIP on action recognition datasets may lead to overfitting and hinder its generalizability, resulting in unsatisfactory results whe"},"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":"2402.03241","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-05T17:56:41Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5aee2c1e3ff6714c0a537b6cfaebda552d360d6f47f82b6726a24b2b19f2de32","abstract_canon_sha256":"a1f9ba6530abd80881fe4e55ff49805a42d38149187ae69119dd21c6218ac48c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:41:32.787613Z","signature_b64":"TZFVdgDSy5vTqxVH3UsLUgnSnXAjrHLnuRXDtPRaqPtRJn3ZA35bFYk8j+w+HKBt3ubIE1YU2Cz/ZTuVwqUpAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d9f13e943a14d9c36263bf88fc22c88880230dd3008e2c06fd0c6149813ed86b","last_reissued_at":"2026-07-05T07:41:32.787088Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:41:32.787088Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FROSTER: Frozen CLIP Is A Strong Teacher for Open-Vocabulary Action Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Hao Zhou, Kai Han, Kun Yao, Xiaohu Huang","submitted_at":"2024-02-05T17:56:41Z","abstract_excerpt":"In this paper, we introduce FROSTER, an effective framework for open-vocabulary action recognition. The CLIP model has achieved remarkable success in a range of image-based tasks, benefiting from its strong generalization capability stemming from pretaining on massive image-text pairs. However, applying CLIP directly to the open-vocabulary action recognition task is challenging due to the absence of temporal information in CLIP's pretraining. Further, fine-tuning CLIP on action recognition datasets may lead to overfitting and hinder its generalizability, resulting in unsatisfactory results whe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.03241","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/2402.03241/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":"2402.03241","created_at":"2026-07-05T07:41:32.787168+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.03241v1","created_at":"2026-07-05T07:41:32.787168+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.03241","created_at":"2026-07-05T07:41:32.787168+00:00"},{"alias_kind":"pith_short_12","alias_value":"3HYT5FB2CTM4","created_at":"2026-07-05T07:41:32.787168+00:00"},{"alias_kind":"pith_short_16","alias_value":"3HYT5FB2CTM4GYTD","created_at":"2026-07-05T07:41:32.787168+00:00"},{"alias_kind":"pith_short_8","alias_value":"3HYT5FB2","created_at":"2026-07-05T07:41:32.787168+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.23288","citing_title":"Spatio-Temporal Similarity Volume Aggregation for Open-Vocabulary Action Recognition","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3HYT5FB2CTM4GYTDX6EPYIWIRC","json":"https://pith.science/pith/3HYT5FB2CTM4GYTDX6EPYIWIRC.json","graph_json":"https://pith.science/api/pith-number/3HYT5FB2CTM4GYTDX6EPYIWIRC/graph.json","events_json":"https://pith.science/api/pith-number/3HYT5FB2CTM4GYTDX6EPYIWIRC/events.json","paper":"https://pith.science/paper/3HYT5FB2"},"agent_actions":{"view_html":"https://pith.science/pith/3HYT5FB2CTM4GYTDX6EPYIWIRC","download_json":"https://pith.science/pith/3HYT5FB2CTM4GYTDX6EPYIWIRC.json","view_paper":"https://pith.science/paper/3HYT5FB2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.03241&json=true","fetch_graph":"https://pith.science/api/pith-number/3HYT5FB2CTM4GYTDX6EPYIWIRC/graph.json","fetch_events":"https://pith.science/api/pith-number/3HYT5FB2CTM4GYTDX6EPYIWIRC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3HYT5FB2CTM4GYTDX6EPYIWIRC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3HYT5FB2CTM4GYTDX6EPYIWIRC/action/storage_attestation","attest_author":"https://pith.science/pith/3HYT5FB2CTM4GYTDX6EPYIWIRC/action/author_attestation","sign_citation":"https://pith.science/pith/3HYT5FB2CTM4GYTDX6EPYIWIRC/action/citation_signature","submit_replication":"https://pith.science/pith/3HYT5FB2CTM4GYTDX6EPYIWIRC/action/replication_record"}},"created_at":"2026-07-05T07:41:32.787168+00:00","updated_at":"2026-07-05T07:41:32.787168+00:00"}