{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XCYOLCKPFHBBKW64SDH7Q7QSOU","short_pith_number":"pith:XCYOLCKP","schema_version":"1.0","canonical_sha256":"b8b0e5894f29c2155bdc90cff87e127504d64a30339af3600851f79ad0bca473","source":{"kind":"arxiv","id":"2405.02077","version":4},"attestation_state":"computed","paper":{"title":"MVP-Shot: Multi-Velocity Progressive-Alignment Framework for Few-Shot Action Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guo-Sen Xie, Hailiang Gao, Hongyu Qu, Peng Huang, Rui Yan, Xiangbo Shu","submitted_at":"2024-05-03T13:10:16Z","abstract_excerpt":"Recent few-shot action recognition (FSAR) methods typically perform semantic matching on learned discriminative features to achieve promising performance. However, most FSAR methods focus on single-scale (e.g., frame-level, segment-level, etc) feature alignment, which ignores that human actions with the same semantic may appear at different velocities. To this end, we develop a novel Multi-Velocity Progressive-alignment (MVP-Shot) framework to progressively learn and align semantic-related action features at multi-velocity levels. Concretely, a Multi-Velocity Feature Alignment (MVFA) module is"},"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":"2405.02077","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-03T13:10:16Z","cross_cats_sorted":[],"title_canon_sha256":"d9f4f5d50ed83902c5a4fa76cd6b9dcbd5cf55fb30c4ba132792607536b1ed5a","abstract_canon_sha256":"3568f0a5a38225493ea0d46c9927e52037ccd6f5fd6b2952b93ba0ee5ff3fcca"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:24:21.621938Z","signature_b64":"USzjNzKohtH0oVi9+K4uuqg1IzE7MjeWG2qVSiKYPJAReP9XgOgA7t8r+tZJlaHHop6sFkwmHSkyyPHeAr1CBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b8b0e5894f29c2155bdc90cff87e127504d64a30339af3600851f79ad0bca473","last_reissued_at":"2026-07-05T10:24:21.621131Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:24:21.621131Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MVP-Shot: Multi-Velocity Progressive-Alignment Framework for Few-Shot Action Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guo-Sen Xie, Hailiang Gao, Hongyu Qu, Peng Huang, Rui Yan, Xiangbo Shu","submitted_at":"2024-05-03T13:10:16Z","abstract_excerpt":"Recent few-shot action recognition (FSAR) methods typically perform semantic matching on learned discriminative features to achieve promising performance. However, most FSAR methods focus on single-scale (e.g., frame-level, segment-level, etc) feature alignment, which ignores that human actions with the same semantic may appear at different velocities. To this end, we develop a novel Multi-Velocity Progressive-alignment (MVP-Shot) framework to progressively learn and align semantic-related action features at multi-velocity levels. Concretely, a Multi-Velocity Feature Alignment (MVFA) module is"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.02077","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/2405.02077/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":"2405.02077","created_at":"2026-07-05T10:24:21.621231+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.02077v4","created_at":"2026-07-05T10:24:21.621231+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.02077","created_at":"2026-07-05T10:24:21.621231+00:00"},{"alias_kind":"pith_short_12","alias_value":"XCYOLCKPFHBB","created_at":"2026-07-05T10:24:21.621231+00:00"},{"alias_kind":"pith_short_16","alias_value":"XCYOLCKPFHBBKW64","created_at":"2026-07-05T10:24:21.621231+00:00"},{"alias_kind":"pith_short_8","alias_value":"XCYOLCKP","created_at":"2026-07-05T10:24:21.621231+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":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XCYOLCKPFHBBKW64SDH7Q7QSOU","json":"https://pith.science/pith/XCYOLCKPFHBBKW64SDH7Q7QSOU.json","graph_json":"https://pith.science/api/pith-number/XCYOLCKPFHBBKW64SDH7Q7QSOU/graph.json","events_json":"https://pith.science/api/pith-number/XCYOLCKPFHBBKW64SDH7Q7QSOU/events.json","paper":"https://pith.science/paper/XCYOLCKP"},"agent_actions":{"view_html":"https://pith.science/pith/XCYOLCKPFHBBKW64SDH7Q7QSOU","download_json":"https://pith.science/pith/XCYOLCKPFHBBKW64SDH7Q7QSOU.json","view_paper":"https://pith.science/paper/XCYOLCKP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.02077&json=true","fetch_graph":"https://pith.science/api/pith-number/XCYOLCKPFHBBKW64SDH7Q7QSOU/graph.json","fetch_events":"https://pith.science/api/pith-number/XCYOLCKPFHBBKW64SDH7Q7QSOU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XCYOLCKPFHBBKW64SDH7Q7QSOU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XCYOLCKPFHBBKW64SDH7Q7QSOU/action/storage_attestation","attest_author":"https://pith.science/pith/XCYOLCKPFHBBKW64SDH7Q7QSOU/action/author_attestation","sign_citation":"https://pith.science/pith/XCYOLCKPFHBBKW64SDH7Q7QSOU/action/citation_signature","submit_replication":"https://pith.science/pith/XCYOLCKPFHBBKW64SDH7Q7QSOU/action/replication_record"}},"created_at":"2026-07-05T10:24:21.621231+00:00","updated_at":"2026-07-05T10:24:21.621231+00:00"}