{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:I6W2VTUDCRPCL7RQEUTEARIPEZ","short_pith_number":"pith:I6W2VTUD","schema_version":"1.0","canonical_sha256":"47adaace83145e25fe30252640450f26490e6e60056a57bb11dcf4ee1a06b327","source":{"kind":"arxiv","id":"2105.04823","version":1},"attestation_state":"computed","paper":{"title":"Learning Implicit Temporal Alignment for Few-shot Video Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Jiale Zhou, Songyang Zhang, Xuming He","submitted_at":"2021-05-11T07:18:57Z","abstract_excerpt":"Few-shot video classification aims to learn new video categories with only a few labeled examples, alleviating the burden of costly annotation in real-world applications. However, it is particularly challenging to learn a class-invariant spatial-temporal representation in such a setting. To address this, we propose a novel matching-based few-shot learning strategy for video sequences in this work. Our main idea is to introduce an implicit temporal alignment for a video pair, capable of estimating the similarity between them in an accurate and robust manner. Moreover, we design an effective con"},"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":"2105.04823","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-05-11T07:18:57Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"14887b0ba60431df00081cefcc9d6ffca4760761e51463bf797dba2092da4e41","abstract_canon_sha256":"7876fecaa97fd3bc716f942c68ef6fea26b74220b26a66ac64caa46c484d0511"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:39:24.632807Z","signature_b64":"4ADHoGBevgVBwYgnmfkwFN4CrpPbTUYCWIvslIf+gtijt0w3QhyV70bFp5fhYlzReK3XAb4cfsyxTshsVEO3Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"47adaace83145e25fe30252640450f26490e6e60056a57bb11dcf4ee1a06b327","last_reissued_at":"2026-07-05T02:39:24.632275Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:39:24.632275Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Implicit Temporal Alignment for Few-shot Video Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Jiale Zhou, Songyang Zhang, Xuming He","submitted_at":"2021-05-11T07:18:57Z","abstract_excerpt":"Few-shot video classification aims to learn new video categories with only a few labeled examples, alleviating the burden of costly annotation in real-world applications. However, it is particularly challenging to learn a class-invariant spatial-temporal representation in such a setting. To address this, we propose a novel matching-based few-shot learning strategy for video sequences in this work. Our main idea is to introduce an implicit temporal alignment for a video pair, capable of estimating the similarity between them in an accurate and robust manner. Moreover, we design an effective con"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.04823","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/2105.04823/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":"2105.04823","created_at":"2026-07-05T02:39:24.632337+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.04823v1","created_at":"2026-07-05T02:39:24.632337+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.04823","created_at":"2026-07-05T02:39:24.632337+00:00"},{"alias_kind":"pith_short_12","alias_value":"I6W2VTUDCRPC","created_at":"2026-07-05T02:39:24.632337+00:00"},{"alias_kind":"pith_short_16","alias_value":"I6W2VTUDCRPCL7RQ","created_at":"2026-07-05T02:39:24.632337+00:00"},{"alias_kind":"pith_short_8","alias_value":"I6W2VTUD","created_at":"2026-07-05T02:39:24.632337+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":52,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/I6W2VTUDCRPCL7RQEUTEARIPEZ","json":"https://pith.science/pith/I6W2VTUDCRPCL7RQEUTEARIPEZ.json","graph_json":"https://pith.science/api/pith-number/I6W2VTUDCRPCL7RQEUTEARIPEZ/graph.json","events_json":"https://pith.science/api/pith-number/I6W2VTUDCRPCL7RQEUTEARIPEZ/events.json","paper":"https://pith.science/paper/I6W2VTUD"},"agent_actions":{"view_html":"https://pith.science/pith/I6W2VTUDCRPCL7RQEUTEARIPEZ","download_json":"https://pith.science/pith/I6W2VTUDCRPCL7RQEUTEARIPEZ.json","view_paper":"https://pith.science/paper/I6W2VTUD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.04823&json=true","fetch_graph":"https://pith.science/api/pith-number/I6W2VTUDCRPCL7RQEUTEARIPEZ/graph.json","fetch_events":"https://pith.science/api/pith-number/I6W2VTUDCRPCL7RQEUTEARIPEZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I6W2VTUDCRPCL7RQEUTEARIPEZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I6W2VTUDCRPCL7RQEUTEARIPEZ/action/storage_attestation","attest_author":"https://pith.science/pith/I6W2VTUDCRPCL7RQEUTEARIPEZ/action/author_attestation","sign_citation":"https://pith.science/pith/I6W2VTUDCRPCL7RQEUTEARIPEZ/action/citation_signature","submit_replication":"https://pith.science/pith/I6W2VTUDCRPCL7RQEUTEARIPEZ/action/replication_record"}},"created_at":"2026-07-05T02:39:24.632337+00:00","updated_at":"2026-07-05T02:39:24.632337+00:00"}