{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:F77KPFXERTMVSN4DSDY52YVMOL","short_pith_number":"pith:F77KPFXE","schema_version":"1.0","canonical_sha256":"2ffea796e48cd959378390f1dd62ac72f7eb3e7402428eb13cfafa4a669ff35e","source":{"kind":"arxiv","id":"1908.02486","version":2},"attestation_state":"computed","paper":{"title":"STM: SpatioTemporal and Motion Encoding for Action Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Boyuan Jiang, Junjie Yan, Mengmeng Wang, Weihao Gan, Wei Wu","submitted_at":"2019-08-07T08:28:38Z","abstract_excerpt":"Spatiotemporal and motion features are two complementary and crucial information for video action recognition. Recent state-of-the-art methods adopt a 3D CNN stream to learn spatiotemporal features and another flow stream to learn motion features. In this work, we aim to efficiently encode these two features in a unified 2D framework. To this end, we first propose an STM block, which contains a Channel-wise SpatioTemporal Module (CSTM) to present the spatiotemporal features and a Channel-wise Motion Module (CMM) to efficiently encode motion features. We then replace original residual blocks in"},"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":"1908.02486","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-07T08:28:38Z","cross_cats_sorted":[],"title_canon_sha256":"807fc9f1363f9bb206911896162dda9ed0ff79d9ce07d73f0e02cfa6b040e776","abstract_canon_sha256":"58b87ec5028e236241207e52425dd2231738ecc7e04dbf05f39bb545209c960e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:57:51.552255Z","signature_b64":"s/0S0lGJ/KKa+EJO5UjBpXepVG6h2YD+tx+LSjjv5reQnNKunyjy/JOnIULVYGid4BZRWpU2b99Fgz7kpoBECw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2ffea796e48cd959378390f1dd62ac72f7eb3e7402428eb13cfafa4a669ff35e","last_reissued_at":"2026-07-04T23:57:51.551777Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:57:51.551777Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"STM: SpatioTemporal and Motion Encoding for Action Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Boyuan Jiang, Junjie Yan, Mengmeng Wang, Weihao Gan, Wei Wu","submitted_at":"2019-08-07T08:28:38Z","abstract_excerpt":"Spatiotemporal and motion features are two complementary and crucial information for video action recognition. Recent state-of-the-art methods adopt a 3D CNN stream to learn spatiotemporal features and another flow stream to learn motion features. In this work, we aim to efficiently encode these two features in a unified 2D framework. To this end, we first propose an STM block, which contains a Channel-wise SpatioTemporal Module (CSTM) to present the spatiotemporal features and a Channel-wise Motion Module (CMM) to efficiently encode motion features. We then replace original residual blocks in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.02486","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/1908.02486/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":"1908.02486","created_at":"2026-07-04T23:57:51.551842+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.02486v2","created_at":"2026-07-04T23:57:51.551842+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.02486","created_at":"2026-07-04T23:57:51.551842+00:00"},{"alias_kind":"pith_short_12","alias_value":"F77KPFXERTMV","created_at":"2026-07-04T23:57:51.551842+00:00"},{"alias_kind":"pith_short_16","alias_value":"F77KPFXERTMVSN4D","created_at":"2026-07-04T23:57:51.551842+00:00"},{"alias_kind":"pith_short_8","alias_value":"F77KPFXE","created_at":"2026-07-04T23:57:51.551842+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/F77KPFXERTMVSN4DSDY52YVMOL","json":"https://pith.science/pith/F77KPFXERTMVSN4DSDY52YVMOL.json","graph_json":"https://pith.science/api/pith-number/F77KPFXERTMVSN4DSDY52YVMOL/graph.json","events_json":"https://pith.science/api/pith-number/F77KPFXERTMVSN4DSDY52YVMOL/events.json","paper":"https://pith.science/paper/F77KPFXE"},"agent_actions":{"view_html":"https://pith.science/pith/F77KPFXERTMVSN4DSDY52YVMOL","download_json":"https://pith.science/pith/F77KPFXERTMVSN4DSDY52YVMOL.json","view_paper":"https://pith.science/paper/F77KPFXE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.02486&json=true","fetch_graph":"https://pith.science/api/pith-number/F77KPFXERTMVSN4DSDY52YVMOL/graph.json","fetch_events":"https://pith.science/api/pith-number/F77KPFXERTMVSN4DSDY52YVMOL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F77KPFXERTMVSN4DSDY52YVMOL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F77KPFXERTMVSN4DSDY52YVMOL/action/storage_attestation","attest_author":"https://pith.science/pith/F77KPFXERTMVSN4DSDY52YVMOL/action/author_attestation","sign_citation":"https://pith.science/pith/F77KPFXERTMVSN4DSDY52YVMOL/action/citation_signature","submit_replication":"https://pith.science/pith/F77KPFXERTMVSN4DSDY52YVMOL/action/replication_record"}},"created_at":"2026-07-04T23:57:51.551842+00:00","updated_at":"2026-07-04T23:57:51.551842+00:00"}