{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VP3BOYNOR2GAYTXJPKC7KOMO6S","short_pith_number":"pith:VP3BOYNO","schema_version":"1.0","canonical_sha256":"abf61761ae8e8c0c4ee97a85f5398ef49cc4d5e31c487c1e3a374259d4ef7a56","source":{"kind":"arxiv","id":"2410.02152","version":1},"attestation_state":"computed","paper":{"title":"An Evaluation of Large Pre-Trained Models for Gesture Recognition using Synthetic Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Arun Reddy, Celso M. de Melo, Corban Rivera, Ketul Shah, Rama Chellappa, William Paul","submitted_at":"2024-10-03T02:31:14Z","abstract_excerpt":"In this work, we explore the possibility of using synthetically generated data for video-based gesture recognition with large pre-trained models. We consider whether these models have sufficiently robust and expressive representation spaces to enable \"training-free\" classification. Specifically, we utilize various state-of-the-art video encoders to extract features for use in k-nearest neighbors classification, where the training data points are derived from synthetic videos only. We compare these results with another training-free approach -- zero-shot classification using text descriptions o"},"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":"2410.02152","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-03T02:31:14Z","cross_cats_sorted":[],"title_canon_sha256":"8de7960e47884625013bc464e88fc2bdab36d569c6d41e387ec3ff9f7550b77b","abstract_canon_sha256":"612aa85f37417338731203e0dd191b45cce95e47a8c61c3fa57ae35be9da8b03"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:15:16.972889Z","signature_b64":"Q2Q31yIzpvaJVgOwRIe2lSWkXQ+MuWOmr+MZAD6ZnRwDepvoalaFwpOSuG3BA1I+MCZgXtCgmB1ohh+3gVHvCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"abf61761ae8e8c0c4ee97a85f5398ef49cc4d5e31c487c1e3a374259d4ef7a56","last_reissued_at":"2026-07-05T09:15:16.972368Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:15:16.972368Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Evaluation of Large Pre-Trained Models for Gesture Recognition using Synthetic Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Arun Reddy, Celso M. de Melo, Corban Rivera, Ketul Shah, Rama Chellappa, William Paul","submitted_at":"2024-10-03T02:31:14Z","abstract_excerpt":"In this work, we explore the possibility of using synthetically generated data for video-based gesture recognition with large pre-trained models. We consider whether these models have sufficiently robust and expressive representation spaces to enable \"training-free\" classification. Specifically, we utilize various state-of-the-art video encoders to extract features for use in k-nearest neighbors classification, where the training data points are derived from synthetic videos only. We compare these results with another training-free approach -- zero-shot classification using text descriptions o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.02152","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/2410.02152/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":"2410.02152","created_at":"2026-07-05T09:15:16.972426+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.02152v1","created_at":"2026-07-05T09:15:16.972426+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.02152","created_at":"2026-07-05T09:15:16.972426+00:00"},{"alias_kind":"pith_short_12","alias_value":"VP3BOYNOR2GA","created_at":"2026-07-05T09:15:16.972426+00:00"},{"alias_kind":"pith_short_16","alias_value":"VP3BOYNOR2GAYTXJ","created_at":"2026-07-05T09:15:16.972426+00:00"},{"alias_kind":"pith_short_8","alias_value":"VP3BOYNO","created_at":"2026-07-05T09:15:16.972426+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VP3BOYNOR2GAYTXJPKC7KOMO6S","json":"https://pith.science/pith/VP3BOYNOR2GAYTXJPKC7KOMO6S.json","graph_json":"https://pith.science/api/pith-number/VP3BOYNOR2GAYTXJPKC7KOMO6S/graph.json","events_json":"https://pith.science/api/pith-number/VP3BOYNOR2GAYTXJPKC7KOMO6S/events.json","paper":"https://pith.science/paper/VP3BOYNO"},"agent_actions":{"view_html":"https://pith.science/pith/VP3BOYNOR2GAYTXJPKC7KOMO6S","download_json":"https://pith.science/pith/VP3BOYNOR2GAYTXJPKC7KOMO6S.json","view_paper":"https://pith.science/paper/VP3BOYNO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.02152&json=true","fetch_graph":"https://pith.science/api/pith-number/VP3BOYNOR2GAYTXJPKC7KOMO6S/graph.json","fetch_events":"https://pith.science/api/pith-number/VP3BOYNOR2GAYTXJPKC7KOMO6S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VP3BOYNOR2GAYTXJPKC7KOMO6S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VP3BOYNOR2GAYTXJPKC7KOMO6S/action/storage_attestation","attest_author":"https://pith.science/pith/VP3BOYNOR2GAYTXJPKC7KOMO6S/action/author_attestation","sign_citation":"https://pith.science/pith/VP3BOYNOR2GAYTXJPKC7KOMO6S/action/citation_signature","submit_replication":"https://pith.science/pith/VP3BOYNOR2GAYTXJPKC7KOMO6S/action/replication_record"}},"created_at":"2026-07-05T09:15:16.972426+00:00","updated_at":"2026-07-05T09:15:16.972426+00:00"}