{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:U2DGPAR3ZA45YSLLPB2UQF7XL3","short_pith_number":"pith:U2DGPAR3","schema_version":"1.0","canonical_sha256":"a68667823bc839dc496b78754817f75ece9018620a41491833becb5e06ba31fe","source":{"kind":"arxiv","id":"2504.05956","version":1},"attestation_state":"computed","paper":{"title":"Temporal Alignment-Free Video Matching for Few-shot Action Recognition","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Hyun Seok Seong, Jae-Pil Heo, SuBeen Lee, WonJun Moon","submitted_at":"2025-04-08T12:11:11Z","abstract_excerpt":"Few-Shot Action Recognition (FSAR) aims to train a model with only a few labeled video instances. A key challenge in FSAR is handling divergent narrative trajectories for precise video matching. While the frame- and tuple-level alignment approaches have been promising, their methods heavily rely on pre-defined and length-dependent alignment units (e.g., frames or tuples), which limits flexibility for actions of varying lengths and speeds. In this work, we introduce a novel TEmporal Alignment-free Matching (TEAM) approach, which eliminates the need for temporal units in action representation an"},"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":"2504.05956","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-08T12:11:11Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"82387d72ac81db2fa75161d9973b8f7601942097012e680d6b4b2c10992ee0d9","abstract_canon_sha256":"4d5eb7d132b77fc2a0c98e2e3912feb78a5fd1691f35d2b4462c127c0e4c47cf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:46:12.508196Z","signature_b64":"5Eu+GWSt+1rqE2tt2kJDwS7OrbMigIWP2NXztowdj6R+NZxqrPYHMupOdNOjunloMar6tXYXXDoU4/I3oEHWCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a68667823bc839dc496b78754817f75ece9018620a41491833becb5e06ba31fe","last_reissued_at":"2026-07-05T10:46:12.507639Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:46:12.507639Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Temporal Alignment-Free Video Matching for Few-shot Action Recognition","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Hyun Seok Seong, Jae-Pil Heo, SuBeen Lee, WonJun Moon","submitted_at":"2025-04-08T12:11:11Z","abstract_excerpt":"Few-Shot Action Recognition (FSAR) aims to train a model with only a few labeled video instances. A key challenge in FSAR is handling divergent narrative trajectories for precise video matching. While the frame- and tuple-level alignment approaches have been promising, their methods heavily rely on pre-defined and length-dependent alignment units (e.g., frames or tuples), which limits flexibility for actions of varying lengths and speeds. In this work, we introduce a novel TEmporal Alignment-free Matching (TEAM) approach, which eliminates the need for temporal units in action representation an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.05956","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/2504.05956/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":"2504.05956","created_at":"2026-07-05T10:46:12.507709+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.05956v1","created_at":"2026-07-05T10:46:12.507709+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.05956","created_at":"2026-07-05T10:46:12.507709+00:00"},{"alias_kind":"pith_short_12","alias_value":"U2DGPAR3ZA45","created_at":"2026-07-05T10:46:12.507709+00:00"},{"alias_kind":"pith_short_16","alias_value":"U2DGPAR3ZA45YSLL","created_at":"2026-07-05T10:46:12.507709+00:00"},{"alias_kind":"pith_short_8","alias_value":"U2DGPAR3","created_at":"2026-07-05T10:46:12.507709+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.13202","citing_title":"STAR: Semantic-Temporal Adaptive Representation Learning for Few-Shot Action Recognition","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U2DGPAR3ZA45YSLLPB2UQF7XL3","json":"https://pith.science/pith/U2DGPAR3ZA45YSLLPB2UQF7XL3.json","graph_json":"https://pith.science/api/pith-number/U2DGPAR3ZA45YSLLPB2UQF7XL3/graph.json","events_json":"https://pith.science/api/pith-number/U2DGPAR3ZA45YSLLPB2UQF7XL3/events.json","paper":"https://pith.science/paper/U2DGPAR3"},"agent_actions":{"view_html":"https://pith.science/pith/U2DGPAR3ZA45YSLLPB2UQF7XL3","download_json":"https://pith.science/pith/U2DGPAR3ZA45YSLLPB2UQF7XL3.json","view_paper":"https://pith.science/paper/U2DGPAR3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.05956&json=true","fetch_graph":"https://pith.science/api/pith-number/U2DGPAR3ZA45YSLLPB2UQF7XL3/graph.json","fetch_events":"https://pith.science/api/pith-number/U2DGPAR3ZA45YSLLPB2UQF7XL3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U2DGPAR3ZA45YSLLPB2UQF7XL3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U2DGPAR3ZA45YSLLPB2UQF7XL3/action/storage_attestation","attest_author":"https://pith.science/pith/U2DGPAR3ZA45YSLLPB2UQF7XL3/action/author_attestation","sign_citation":"https://pith.science/pith/U2DGPAR3ZA45YSLLPB2UQF7XL3/action/citation_signature","submit_replication":"https://pith.science/pith/U2DGPAR3ZA45YSLLPB2UQF7XL3/action/replication_record"}},"created_at":"2026-07-05T10:46:12.507709+00:00","updated_at":"2026-07-05T10:46:12.507709+00:00"}