{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:YGG3NHMDTZ2EGPALZXSFFPZH4Y","short_pith_number":"pith:YGG3NHMD","schema_version":"1.0","canonical_sha256":"c18db69d839e74433c0bcde452bf27e61572821a34b127b26c59e1cea5684ecb","source":{"kind":"arxiv","id":"2310.10125","version":1},"attestation_state":"computed","paper":{"title":"Few-shot Action Recognition with Captioning Foundation Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changxin Gao, Deli Zhao, Hangjie Yuan, Nong Sang, Shiwei Zhang, Xiang Wang, Yingya Zhang","submitted_at":"2023-10-16T07:08:39Z","abstract_excerpt":"Transferring vision-language knowledge from pretrained multimodal foundation models to various downstream tasks is a promising direction. However, most current few-shot action recognition methods are still limited to a single visual modality input due to the high cost of annotating additional textual descriptions. In this paper, we develop an effective plug-and-play framework called CapFSAR to exploit the knowledge of multimodal models without manually annotating text. To be specific, we first utilize a captioning foundation model (i.e., BLIP) to extract visual features and automatically gener"},"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":"2310.10125","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-16T07:08:39Z","cross_cats_sorted":[],"title_canon_sha256":"0888f55f5a5bee897fbd7f901b9b5b8709876be838c3f8a2c34c26b8fede9cf6","abstract_canon_sha256":"7a4816e28b14c6075fbd0ac5af74d9e96f3da19fa414e9522320b27452e6f9e9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:01:15.591804Z","signature_b64":"p5DDtpuhnpXryrD0Hn6XC3quNYU6YTKme+RI8MS1eYUPP/OH/wimY8U2BSGnOeoe0CYO8UeOfXIkWJ0t270VBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c18db69d839e74433c0bcde452bf27e61572821a34b127b26c59e1cea5684ecb","last_reissued_at":"2026-07-05T07:01:15.591253Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:01:15.591253Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Few-shot Action Recognition with Captioning Foundation Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changxin Gao, Deli Zhao, Hangjie Yuan, Nong Sang, Shiwei Zhang, Xiang Wang, Yingya Zhang","submitted_at":"2023-10-16T07:08:39Z","abstract_excerpt":"Transferring vision-language knowledge from pretrained multimodal foundation models to various downstream tasks is a promising direction. However, most current few-shot action recognition methods are still limited to a single visual modality input due to the high cost of annotating additional textual descriptions. In this paper, we develop an effective plug-and-play framework called CapFSAR to exploit the knowledge of multimodal models without manually annotating text. To be specific, we first utilize a captioning foundation model (i.e., BLIP) to extract visual features and automatically gener"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.10125","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/2310.10125/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":"2310.10125","created_at":"2026-07-05T07:01:15.591309+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.10125v1","created_at":"2026-07-05T07:01:15.591309+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.10125","created_at":"2026-07-05T07:01:15.591309+00:00"},{"alias_kind":"pith_short_12","alias_value":"YGG3NHMDTZ2E","created_at":"2026-07-05T07:01:15.591309+00:00"},{"alias_kind":"pith_short_16","alias_value":"YGG3NHMDTZ2EGPAL","created_at":"2026-07-05T07:01:15.591309+00:00"},{"alias_kind":"pith_short_8","alias_value":"YGG3NHMD","created_at":"2026-07-05T07:01:15.591309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.16287","citing_title":"Beyond Label Semantics: Language-Guided Action Anatomy for Few-shot Action Recognition","ref_index":44,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YGG3NHMDTZ2EGPALZXSFFPZH4Y","json":"https://pith.science/pith/YGG3NHMDTZ2EGPALZXSFFPZH4Y.json","graph_json":"https://pith.science/api/pith-number/YGG3NHMDTZ2EGPALZXSFFPZH4Y/graph.json","events_json":"https://pith.science/api/pith-number/YGG3NHMDTZ2EGPALZXSFFPZH4Y/events.json","paper":"https://pith.science/paper/YGG3NHMD"},"agent_actions":{"view_html":"https://pith.science/pith/YGG3NHMDTZ2EGPALZXSFFPZH4Y","download_json":"https://pith.science/pith/YGG3NHMDTZ2EGPALZXSFFPZH4Y.json","view_paper":"https://pith.science/paper/YGG3NHMD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.10125&json=true","fetch_graph":"https://pith.science/api/pith-number/YGG3NHMDTZ2EGPALZXSFFPZH4Y/graph.json","fetch_events":"https://pith.science/api/pith-number/YGG3NHMDTZ2EGPALZXSFFPZH4Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YGG3NHMDTZ2EGPALZXSFFPZH4Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YGG3NHMDTZ2EGPALZXSFFPZH4Y/action/storage_attestation","attest_author":"https://pith.science/pith/YGG3NHMDTZ2EGPALZXSFFPZH4Y/action/author_attestation","sign_citation":"https://pith.science/pith/YGG3NHMDTZ2EGPALZXSFFPZH4Y/action/citation_signature","submit_replication":"https://pith.science/pith/YGG3NHMDTZ2EGPALZXSFFPZH4Y/action/replication_record"}},"created_at":"2026-07-05T07:01:15.591309+00:00","updated_at":"2026-07-05T07:01:15.591309+00:00"}