{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:EC6P73RUA3BSPFRUBX64G34NYN","short_pith_number":"pith:EC6P73RU","schema_version":"1.0","canonical_sha256":"20bcffee3406c32796340dfdc36f8dc37d925b4570b4e1c84b49c323ee066c44","source":{"kind":"arxiv","id":"2212.05638","version":3},"attestation_state":"computed","paper":{"title":"Cross-Modal Learning with 3D Deformable Attention for Action Recognition","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Byoung Chul Ko, Dasom Ahn, Sangwon Kim","submitted_at":"2022-12-12T00:31:08Z","abstract_excerpt":"An important challenge in vision-based action recognition is the embedding of spatiotemporal features with two or more heterogeneous modalities into a single feature. In this study, we propose a new 3D deformable transformer for action recognition with adaptive spatiotemporal receptive fields and a cross-modal learning scheme. The 3D deformable transformer consists of three attention modules: 3D deformability, local joint stride, and temporal stride attention. The two cross-modal tokens are input into the 3D deformable attention module to create a cross-attention token with a reflected spatiot"},"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":"2212.05638","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-12-12T00:31:08Z","cross_cats_sorted":[],"title_canon_sha256":"a5a131adf1276606b06eff6ada937cff6d73f37cfbf79915ef81a2cb7a2afea1","abstract_canon_sha256":"2cff3ab0245fb80169658d89519c0056b19802462882bf3ecbef734a68a03172"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:42:03.213077Z","signature_b64":"M0LlnyNJyW2oL1pmJak7/koN2jKY4ramjMXL/rx2ljNURv7HfMHWmKUngWEEFz6xVGogXpGc+F/4NTBZKtLPBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"20bcffee3406c32796340dfdc36f8dc37d925b4570b4e1c84b49c323ee066c44","last_reissued_at":"2026-07-05T06:42:03.212646Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:42:03.212646Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cross-Modal Learning with 3D Deformable Attention for Action Recognition","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Byoung Chul Ko, Dasom Ahn, Sangwon Kim","submitted_at":"2022-12-12T00:31:08Z","abstract_excerpt":"An important challenge in vision-based action recognition is the embedding of spatiotemporal features with two or more heterogeneous modalities into a single feature. In this study, we propose a new 3D deformable transformer for action recognition with adaptive spatiotemporal receptive fields and a cross-modal learning scheme. The 3D deformable transformer consists of three attention modules: 3D deformability, local joint stride, and temporal stride attention. The two cross-modal tokens are input into the 3D deformable attention module to create a cross-attention token with a reflected spatiot"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.05638","kind":"arxiv","version":3},"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/2212.05638/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":"2212.05638","created_at":"2026-07-05T06:42:03.212701+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.05638v3","created_at":"2026-07-05T06:42:03.212701+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.05638","created_at":"2026-07-05T06:42:03.212701+00:00"},{"alias_kind":"pith_short_12","alias_value":"EC6P73RUA3BS","created_at":"2026-07-05T06:42:03.212701+00:00"},{"alias_kind":"pith_short_16","alias_value":"EC6P73RUA3BSPFRU","created_at":"2026-07-05T06:42:03.212701+00:00"},{"alias_kind":"pith_short_8","alias_value":"EC6P73RU","created_at":"2026-07-05T06:42:03.212701+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.00692","citing_title":"CascadeFormer: A Family of Two-stage Cascading Transformers for Skeleton-based Human Action Recognition","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EC6P73RUA3BSPFRUBX64G34NYN","json":"https://pith.science/pith/EC6P73RUA3BSPFRUBX64G34NYN.json","graph_json":"https://pith.science/api/pith-number/EC6P73RUA3BSPFRUBX64G34NYN/graph.json","events_json":"https://pith.science/api/pith-number/EC6P73RUA3BSPFRUBX64G34NYN/events.json","paper":"https://pith.science/paper/EC6P73RU"},"agent_actions":{"view_html":"https://pith.science/pith/EC6P73RUA3BSPFRUBX64G34NYN","download_json":"https://pith.science/pith/EC6P73RUA3BSPFRUBX64G34NYN.json","view_paper":"https://pith.science/paper/EC6P73RU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.05638&json=true","fetch_graph":"https://pith.science/api/pith-number/EC6P73RUA3BSPFRUBX64G34NYN/graph.json","fetch_events":"https://pith.science/api/pith-number/EC6P73RUA3BSPFRUBX64G34NYN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EC6P73RUA3BSPFRUBX64G34NYN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EC6P73RUA3BSPFRUBX64G34NYN/action/storage_attestation","attest_author":"https://pith.science/pith/EC6P73RUA3BSPFRUBX64G34NYN/action/author_attestation","sign_citation":"https://pith.science/pith/EC6P73RUA3BSPFRUBX64G34NYN/action/citation_signature","submit_replication":"https://pith.science/pith/EC6P73RUA3BSPFRUBX64G34NYN/action/replication_record"}},"created_at":"2026-07-05T06:42:03.212701+00:00","updated_at":"2026-07-05T06:42:03.212701+00:00"}