{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:EWVZEBHVRS5HC2AS6R757VEFMJ","short_pith_number":"pith:EWVZEBHV","schema_version":"1.0","canonical_sha256":"25ab9204f58cba716812f47fdfd485625caeb74da5c6e98ff34ed695327c052a","source":{"kind":"arxiv","id":"2309.03869","version":1},"attestation_state":"computed","paper":{"title":"Text-to-feature diffusion for audio-visual few-shot learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"A. Sophia Koepke, Otniel-Bogdan Mercea, Thomas Hummel, Zeynep Akata","submitted_at":"2023-09-07T17:30:36Z","abstract_excerpt":"Training deep learning models for video classification from audio-visual data commonly requires immense amounts of labeled training data collected via a costly process. A challenging and underexplored, yet much cheaper, setup is few-shot learning from video data. In particular, the inherently multi-modal nature of video data with sound and visual information has not been leveraged extensively for the few-shot video classification task. Therefore, we introduce a unified audio-visual few-shot video classification benchmark on three datasets, i.e. the VGGSound-FSL, UCF-FSL, ActivityNet-FSL datase"},"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":"2309.03869","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-07T17:30:36Z","cross_cats_sorted":[],"title_canon_sha256":"979725c556ab68ab6793d3b58b49fe21b96150acef9281307ca1051403dfbb16","abstract_canon_sha256":"fe31dc17904758fba22d1ee7553f45f24e079b09531eb4b71a79d48b2f8ec762"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:48:42.948583Z","signature_b64":"e51xiPIGfZq49YT5kqV9dz/oaMvvANxh7IKKEMVjtrwnWDD8N5GFRDvPvY6UT59VDfwDzLmuMOuQOrhfy62yDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"25ab9204f58cba716812f47fdfd485625caeb74da5c6e98ff34ed695327c052a","last_reissued_at":"2026-07-05T06:48:42.948155Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:48:42.948155Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Text-to-feature diffusion for audio-visual few-shot learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"A. Sophia Koepke, Otniel-Bogdan Mercea, Thomas Hummel, Zeynep Akata","submitted_at":"2023-09-07T17:30:36Z","abstract_excerpt":"Training deep learning models for video classification from audio-visual data commonly requires immense amounts of labeled training data collected via a costly process. A challenging and underexplored, yet much cheaper, setup is few-shot learning from video data. In particular, the inherently multi-modal nature of video data with sound and visual information has not been leveraged extensively for the few-shot video classification task. Therefore, we introduce a unified audio-visual few-shot video classification benchmark on three datasets, i.e. the VGGSound-FSL, UCF-FSL, ActivityNet-FSL datase"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.03869","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/2309.03869/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":"2309.03869","created_at":"2026-07-05T06:48:42.948211+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.03869v1","created_at":"2026-07-05T06:48:42.948211+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.03869","created_at":"2026-07-05T06:48:42.948211+00:00"},{"alias_kind":"pith_short_12","alias_value":"EWVZEBHVRS5H","created_at":"2026-07-05T06:48:42.948211+00:00"},{"alias_kind":"pith_short_16","alias_value":"EWVZEBHVRS5HC2AS","created_at":"2026-07-05T06:48:42.948211+00:00"},{"alias_kind":"pith_short_8","alias_value":"EWVZEBHV","created_at":"2026-07-05T06:48:42.948211+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/EWVZEBHVRS5HC2AS6R757VEFMJ","json":"https://pith.science/pith/EWVZEBHVRS5HC2AS6R757VEFMJ.json","graph_json":"https://pith.science/api/pith-number/EWVZEBHVRS5HC2AS6R757VEFMJ/graph.json","events_json":"https://pith.science/api/pith-number/EWVZEBHVRS5HC2AS6R757VEFMJ/events.json","paper":"https://pith.science/paper/EWVZEBHV"},"agent_actions":{"view_html":"https://pith.science/pith/EWVZEBHVRS5HC2AS6R757VEFMJ","download_json":"https://pith.science/pith/EWVZEBHVRS5HC2AS6R757VEFMJ.json","view_paper":"https://pith.science/paper/EWVZEBHV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.03869&json=true","fetch_graph":"https://pith.science/api/pith-number/EWVZEBHVRS5HC2AS6R757VEFMJ/graph.json","fetch_events":"https://pith.science/api/pith-number/EWVZEBHVRS5HC2AS6R757VEFMJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EWVZEBHVRS5HC2AS6R757VEFMJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EWVZEBHVRS5HC2AS6R757VEFMJ/action/storage_attestation","attest_author":"https://pith.science/pith/EWVZEBHVRS5HC2AS6R757VEFMJ/action/author_attestation","sign_citation":"https://pith.science/pith/EWVZEBHVRS5HC2AS6R757VEFMJ/action/citation_signature","submit_replication":"https://pith.science/pith/EWVZEBHVRS5HC2AS6R757VEFMJ/action/replication_record"}},"created_at":"2026-07-05T06:48:42.948211+00:00","updated_at":"2026-07-05T06:48:42.948211+00:00"}