{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:YSD3KKKRGSFRILCRATSESSOFDE","short_pith_number":"pith:YSD3KKKR","schema_version":"1.0","canonical_sha256":"c487b52951348b142c5104e44949c519270f3cea049d634e018a77cc956b18ad","source":{"kind":"arxiv","id":"2104.03737","version":1},"attestation_state":"computed","paper":{"title":"Few-Shot Action Recognition with Compromised Metric via Optimal Transport","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"De-Chuan Zhan, Han-Jia Ye, Su Lu","submitted_at":"2021-04-08T12:42:05Z","abstract_excerpt":"Although vital to computer vision systems, few-shot action recognition is still not mature despite the wide research of few-shot image classification. Popular few-shot learning algorithms extract a transferable embedding from seen classes and reuse it on unseen classes by constructing a metric-based classifier. One main obstacle to applying these algorithms in action recognition is the complex structure of videos. Some existing solutions sample frames from a video and aggregate their embeddings to form a video-level representation, neglecting important temporal relations. Others perform an exp"},"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":"2104.03737","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-04-08T12:42:05Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"1cea37b6993c416e66fabd7044d5833f177a538e7d012e7656a86c3a38f16550","abstract_canon_sha256":"e075a4332f9d35b327ad456247808f2410a9161e918d0ea67f2ebc25f9f55f46"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:30:22.770847Z","signature_b64":"qf3RoAO8GqVcUYK0Yy+HdRj/qT3PYOu7qDvkkzXXzu3yIXcNkDkdNXtmclkbi04akcGw8EJtBgDz7i/jqQcmCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c487b52951348b142c5104e44949c519270f3cea049d634e018a77cc956b18ad","last_reissued_at":"2026-07-05T02:30:22.770361Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:30:22.770361Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Few-Shot Action Recognition with Compromised Metric via Optimal Transport","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"De-Chuan Zhan, Han-Jia Ye, Su Lu","submitted_at":"2021-04-08T12:42:05Z","abstract_excerpt":"Although vital to computer vision systems, few-shot action recognition is still not mature despite the wide research of few-shot image classification. Popular few-shot learning algorithms extract a transferable embedding from seen classes and reuse it on unseen classes by constructing a metric-based classifier. One main obstacle to applying these algorithms in action recognition is the complex structure of videos. Some existing solutions sample frames from a video and aggregate their embeddings to form a video-level representation, neglecting important temporal relations. Others perform an exp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.03737","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/2104.03737/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":"2104.03737","created_at":"2026-07-05T02:30:22.770419+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.03737v1","created_at":"2026-07-05T02:30:22.770419+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.03737","created_at":"2026-07-05T02:30:22.770419+00:00"},{"alias_kind":"pith_short_12","alias_value":"YSD3KKKRGSFR","created_at":"2026-07-05T02:30:22.770419+00:00"},{"alias_kind":"pith_short_16","alias_value":"YSD3KKKRGSFRILCR","created_at":"2026-07-05T02:30:22.770419+00:00"},{"alias_kind":"pith_short_8","alias_value":"YSD3KKKR","created_at":"2026-07-05T02:30:22.770419+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.06002","citing_title":"Task-Adapter++: Task-specific Adaptation with Order-aware Alignment for Few-shot Action Recognition","ref_index":45,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YSD3KKKRGSFRILCRATSESSOFDE","json":"https://pith.science/pith/YSD3KKKRGSFRILCRATSESSOFDE.json","graph_json":"https://pith.science/api/pith-number/YSD3KKKRGSFRILCRATSESSOFDE/graph.json","events_json":"https://pith.science/api/pith-number/YSD3KKKRGSFRILCRATSESSOFDE/events.json","paper":"https://pith.science/paper/YSD3KKKR"},"agent_actions":{"view_html":"https://pith.science/pith/YSD3KKKRGSFRILCRATSESSOFDE","download_json":"https://pith.science/pith/YSD3KKKRGSFRILCRATSESSOFDE.json","view_paper":"https://pith.science/paper/YSD3KKKR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.03737&json=true","fetch_graph":"https://pith.science/api/pith-number/YSD3KKKRGSFRILCRATSESSOFDE/graph.json","fetch_events":"https://pith.science/api/pith-number/YSD3KKKRGSFRILCRATSESSOFDE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YSD3KKKRGSFRILCRATSESSOFDE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YSD3KKKRGSFRILCRATSESSOFDE/action/storage_attestation","attest_author":"https://pith.science/pith/YSD3KKKRGSFRILCRATSESSOFDE/action/author_attestation","sign_citation":"https://pith.science/pith/YSD3KKKRGSFRILCRATSESSOFDE/action/citation_signature","submit_replication":"https://pith.science/pith/YSD3KKKRGSFRILCRATSESSOFDE/action/replication_record"}},"created_at":"2026-07-05T02:30:22.770419+00:00","updated_at":"2026-07-05T02:30:22.770419+00:00"}