{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:QTXLYLFLWYOJC66IQ6MSIYQEVY","short_pith_number":"pith:QTXLYLFL","schema_version":"1.0","canonical_sha256":"84eebc2cabb61c917bc88799246204ae3a7560f2c2f29aba2000ea25d8596a62","source":{"kind":"arxiv","id":"2101.08085","version":4},"attestation_state":"computed","paper":{"title":"Few-shot Action Recognition with Prototype-centered Attentive Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Antoine Toisoul, Brais Martinez, Juan-Manuel Perez-Rua, Li Zhang, Tao Xiang, Xiatian Zhu","submitted_at":"2021-01-20T11:48:12Z","abstract_excerpt":"Few-shot action recognition aims to recognize action classes with few training samples. Most existing methods adopt a meta-learning approach with episodic training. In each episode, the few samples in a meta-training task are split into support and query sets. The former is used to build a classifier, which is then evaluated on the latter using a query-centered loss for model updating. There are however two major limitations: lack of data efficiency due to the query-centered only loss design and inability to deal with the support set outlying samples and inter-class distribution overlapping pr"},"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":"2101.08085","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-01-20T11:48:12Z","cross_cats_sorted":[],"title_canon_sha256":"4fefdb89fbc03a3639a148fae722f7bf98a4adf23938497910a73cec1bd75677","abstract_canon_sha256":"512d7efdf1aae673f4db0eeb0ff9b05820413f765ed1e6c6e14c025fb9d0fac2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:25:12.017852Z","signature_b64":"Gbx1nk8O9k3vyyAtAvkP0udKAnktzRn2eUz1Vd8bJS5DGXYjX/fneu3zlmxvgAttxPVJD+l5pE7XoGcCTuECCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"84eebc2cabb61c917bc88799246204ae3a7560f2c2f29aba2000ea25d8596a62","last_reissued_at":"2026-07-05T03:25:12.017445Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:25:12.017445Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Few-shot Action Recognition with Prototype-centered Attentive Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Antoine Toisoul, Brais Martinez, Juan-Manuel Perez-Rua, Li Zhang, Tao Xiang, Xiatian Zhu","submitted_at":"2021-01-20T11:48:12Z","abstract_excerpt":"Few-shot action recognition aims to recognize action classes with few training samples. Most existing methods adopt a meta-learning approach with episodic training. In each episode, the few samples in a meta-training task are split into support and query sets. The former is used to build a classifier, which is then evaluated on the latter using a query-centered loss for model updating. There are however two major limitations: lack of data efficiency due to the query-centered only loss design and inability to deal with the support set outlying samples and inter-class distribution overlapping pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.08085","kind":"arxiv","version":4},"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/2101.08085/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":"2101.08085","created_at":"2026-07-05T03:25:12.017505+00:00"},{"alias_kind":"arxiv_version","alias_value":"2101.08085v4","created_at":"2026-07-05T03:25:12.017505+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.08085","created_at":"2026-07-05T03:25:12.017505+00:00"},{"alias_kind":"pith_short_12","alias_value":"QTXLYLFLWYOJ","created_at":"2026-07-05T03:25:12.017505+00:00"},{"alias_kind":"pith_short_16","alias_value":"QTXLYLFLWYOJC66I","created_at":"2026-07-05T03:25:12.017505+00:00"},{"alias_kind":"pith_short_8","alias_value":"QTXLYLFL","created_at":"2026-07-05T03:25:12.017505+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.14719","citing_title":"Prototypical Calibrating Ambiguous Samples for Micro-Action Recognition","ref_index":44,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QTXLYLFLWYOJC66IQ6MSIYQEVY","json":"https://pith.science/pith/QTXLYLFLWYOJC66IQ6MSIYQEVY.json","graph_json":"https://pith.science/api/pith-number/QTXLYLFLWYOJC66IQ6MSIYQEVY/graph.json","events_json":"https://pith.science/api/pith-number/QTXLYLFLWYOJC66IQ6MSIYQEVY/events.json","paper":"https://pith.science/paper/QTXLYLFL"},"agent_actions":{"view_html":"https://pith.science/pith/QTXLYLFLWYOJC66IQ6MSIYQEVY","download_json":"https://pith.science/pith/QTXLYLFLWYOJC66IQ6MSIYQEVY.json","view_paper":"https://pith.science/paper/QTXLYLFL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2101.08085&json=true","fetch_graph":"https://pith.science/api/pith-number/QTXLYLFLWYOJC66IQ6MSIYQEVY/graph.json","fetch_events":"https://pith.science/api/pith-number/QTXLYLFLWYOJC66IQ6MSIYQEVY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QTXLYLFLWYOJC66IQ6MSIYQEVY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QTXLYLFLWYOJC66IQ6MSIYQEVY/action/storage_attestation","attest_author":"https://pith.science/pith/QTXLYLFLWYOJC66IQ6MSIYQEVY/action/author_attestation","sign_citation":"https://pith.science/pith/QTXLYLFLWYOJC66IQ6MSIYQEVY/action/citation_signature","submit_replication":"https://pith.science/pith/QTXLYLFLWYOJC66IQ6MSIYQEVY/action/replication_record"}},"created_at":"2026-07-05T03:25:12.017505+00:00","updated_at":"2026-07-05T03:25:12.017505+00:00"}