{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:ECXIKAU3MPTKEPGB5ETCOCDAFL","short_pith_number":"pith:ECXIKAU3","schema_version":"1.0","canonical_sha256":"20ae85029b63e6a23cc1e9262708602aeef585966fa7019f55acc84713864016","source":{"kind":"arxiv","id":"2202.07925","version":2},"attestation_state":"computed","paper":{"title":"ActionFormer: Localizing Moments of Actions with Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenlin Zhang, Jianxin Wu, Yin Li","submitted_at":"2022-02-16T08:34:11Z","abstract_excerpt":"Self-attention based Transformer models have demonstrated impressive results for image classification and object detection, and more recently for video understanding. Inspired by this success, we investigate the application of Transformer networks for temporal action localization in videos. To this end, we present ActionFormer -- a simple yet powerful model to identify actions in time and recognize their categories in a single shot, without using action proposals or relying on pre-defined anchor windows. ActionFormer combines a multiscale feature representation with local self-attention, and u"},"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":"2202.07925","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-02-16T08:34:11Z","cross_cats_sorted":[],"title_canon_sha256":"f1a8747fe02ee69df49154a279539e5d1330c7a17729ebd638d2d2ec2d42eabb","abstract_canon_sha256":"de1c514bfd145152af84feef2a9dc0012857e0f0f958671dcbff01c282aba818"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:51:55.135608Z","signature_b64":"hcM/odsx8X/gZ1V2HbYrD5SF9+Zblz3VtosiM+0dLPtRn1F076pWTq/QZEkhe+4TMN3a7US1s4IvVls90BeiDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"20ae85029b63e6a23cc1e9262708602aeef585966fa7019f55acc84713864016","last_reissued_at":"2026-07-05T04:51:55.135163Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:51:55.135163Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ActionFormer: Localizing Moments of Actions with Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenlin Zhang, Jianxin Wu, Yin Li","submitted_at":"2022-02-16T08:34:11Z","abstract_excerpt":"Self-attention based Transformer models have demonstrated impressive results for image classification and object detection, and more recently for video understanding. Inspired by this success, we investigate the application of Transformer networks for temporal action localization in videos. To this end, we present ActionFormer -- a simple yet powerful model to identify actions in time and recognize their categories in a single shot, without using action proposals or relying on pre-defined anchor windows. ActionFormer combines a multiscale feature representation with local self-attention, and u"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.07925","kind":"arxiv","version":2},"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/2202.07925/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":"2202.07925","created_at":"2026-07-05T04:51:55.135228+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.07925v2","created_at":"2026-07-05T04:51:55.135228+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.07925","created_at":"2026-07-05T04:51:55.135228+00:00"},{"alias_kind":"pith_short_12","alias_value":"ECXIKAU3MPTK","created_at":"2026-07-05T04:51:55.135228+00:00"},{"alias_kind":"pith_short_16","alias_value":"ECXIKAU3MPTKEPGB","created_at":"2026-07-05T04:51:55.135228+00:00"},{"alias_kind":"pith_short_8","alias_value":"ECXIKAU3","created_at":"2026-07-05T04:51:55.135228+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.00667","citing_title":"Scene Detection Policies and Keyframe Extraction Strategies for Large-Scale Video Analysis","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ECXIKAU3MPTKEPGB5ETCOCDAFL","json":"https://pith.science/pith/ECXIKAU3MPTKEPGB5ETCOCDAFL.json","graph_json":"https://pith.science/api/pith-number/ECXIKAU3MPTKEPGB5ETCOCDAFL/graph.json","events_json":"https://pith.science/api/pith-number/ECXIKAU3MPTKEPGB5ETCOCDAFL/events.json","paper":"https://pith.science/paper/ECXIKAU3"},"agent_actions":{"view_html":"https://pith.science/pith/ECXIKAU3MPTKEPGB5ETCOCDAFL","download_json":"https://pith.science/pith/ECXIKAU3MPTKEPGB5ETCOCDAFL.json","view_paper":"https://pith.science/paper/ECXIKAU3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.07925&json=true","fetch_graph":"https://pith.science/api/pith-number/ECXIKAU3MPTKEPGB5ETCOCDAFL/graph.json","fetch_events":"https://pith.science/api/pith-number/ECXIKAU3MPTKEPGB5ETCOCDAFL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ECXIKAU3MPTKEPGB5ETCOCDAFL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ECXIKAU3MPTKEPGB5ETCOCDAFL/action/storage_attestation","attest_author":"https://pith.science/pith/ECXIKAU3MPTKEPGB5ETCOCDAFL/action/author_attestation","sign_citation":"https://pith.science/pith/ECXIKAU3MPTKEPGB5ETCOCDAFL/action/citation_signature","submit_replication":"https://pith.science/pith/ECXIKAU3MPTKEPGB5ETCOCDAFL/action/replication_record"}},"created_at":"2026-07-05T04:51:55.135228+00:00","updated_at":"2026-07-05T04:51:55.135228+00:00"}