{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7E6RC7YC5XCVVR3MRFGPM3ROYH","short_pith_number":"pith:7E6RC7YC","schema_version":"1.0","canonical_sha256":"f93d117f02edc55ac76c894cf66e2ec1e84e50abdb7a6799088dcf4913bb8f94","source":{"kind":"arxiv","id":"2404.09842","version":1},"attestation_state":"computed","paper":{"title":"STMixer: A One-Stage Sparse Action Detector","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gangshan Wu, Limin Wang, Mengqi Cao, Tao Wu, Ziteng Gao","submitted_at":"2024-04-15T14:52:02Z","abstract_excerpt":"Traditional video action detectors typically adopt the two-stage pipeline, where a person detector is first employed to generate actor boxes and then 3D RoIAlign is used to extract actor-specific features for classification. This detection paradigm requires multi-stage training and inference, and the feature sampling is constrained inside the box, failing to effectively leverage richer context information outside. Recently, a few query-based action detectors have been proposed to predict action instances in an end-to-end manner. However, they still lack adaptability in feature sampling and dec"},"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":"2404.09842","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-15T14:52:02Z","cross_cats_sorted":[],"title_canon_sha256":"3e75751a9521585c852b5e1b6597b6f2e7ab718cfe55332211ed09b9ee7aad8d","abstract_canon_sha256":"198a363aa0df5f326b64ad7bb40b3700fce2ec02cdf1d5cef7f94480070032a3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:08:12.359670Z","signature_b64":"S4DVFVu0Ig0ns4UonyJCI6J9DxgcAP8QUzR81QflKmV7kDQSN74VspmaFcmOUqbF+QokTk1GGDo4T16eEwWYCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f93d117f02edc55ac76c894cf66e2ec1e84e50abdb7a6799088dcf4913bb8f94","last_reissued_at":"2026-07-05T08:08:12.359294Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:08:12.359294Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"STMixer: A One-Stage Sparse Action Detector","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gangshan Wu, Limin Wang, Mengqi Cao, Tao Wu, Ziteng Gao","submitted_at":"2024-04-15T14:52:02Z","abstract_excerpt":"Traditional video action detectors typically adopt the two-stage pipeline, where a person detector is first employed to generate actor boxes and then 3D RoIAlign is used to extract actor-specific features for classification. This detection paradigm requires multi-stage training and inference, and the feature sampling is constrained inside the box, failing to effectively leverage richer context information outside. Recently, a few query-based action detectors have been proposed to predict action instances in an end-to-end manner. However, they still lack adaptability in feature sampling and dec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.09842","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/2404.09842/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":"2404.09842","created_at":"2026-07-05T08:08:12.359359+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.09842v1","created_at":"2026-07-05T08:08:12.359359+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.09842","created_at":"2026-07-05T08:08:12.359359+00:00"},{"alias_kind":"pith_short_12","alias_value":"7E6RC7YC5XCV","created_at":"2026-07-05T08:08:12.359359+00:00"},{"alias_kind":"pith_short_16","alias_value":"7E6RC7YC5XCVVR3M","created_at":"2026-07-05T08:08:12.359359+00:00"},{"alias_kind":"pith_short_8","alias_value":"7E6RC7YC","created_at":"2026-07-05T08:08:12.359359+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/7E6RC7YC5XCVVR3MRFGPM3ROYH","json":"https://pith.science/pith/7E6RC7YC5XCVVR3MRFGPM3ROYH.json","graph_json":"https://pith.science/api/pith-number/7E6RC7YC5XCVVR3MRFGPM3ROYH/graph.json","events_json":"https://pith.science/api/pith-number/7E6RC7YC5XCVVR3MRFGPM3ROYH/events.json","paper":"https://pith.science/paper/7E6RC7YC"},"agent_actions":{"view_html":"https://pith.science/pith/7E6RC7YC5XCVVR3MRFGPM3ROYH","download_json":"https://pith.science/pith/7E6RC7YC5XCVVR3MRFGPM3ROYH.json","view_paper":"https://pith.science/paper/7E6RC7YC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.09842&json=true","fetch_graph":"https://pith.science/api/pith-number/7E6RC7YC5XCVVR3MRFGPM3ROYH/graph.json","fetch_events":"https://pith.science/api/pith-number/7E6RC7YC5XCVVR3MRFGPM3ROYH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7E6RC7YC5XCVVR3MRFGPM3ROYH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7E6RC7YC5XCVVR3MRFGPM3ROYH/action/storage_attestation","attest_author":"https://pith.science/pith/7E6RC7YC5XCVVR3MRFGPM3ROYH/action/author_attestation","sign_citation":"https://pith.science/pith/7E6RC7YC5XCVVR3MRFGPM3ROYH/action/citation_signature","submit_replication":"https://pith.science/pith/7E6RC7YC5XCVVR3MRFGPM3ROYH/action/replication_record"}},"created_at":"2026-07-05T08:08:12.359359+00:00","updated_at":"2026-07-05T08:08:12.359359+00:00"}