{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:JPSH2AZ4WE3UBE37BLSUBNBOLM","short_pith_number":"pith:JPSH2AZ4","schema_version":"1.0","canonical_sha256":"4be47d033cb13740937f0ae540b42e5b2a32e6a36ef68c3627a7a81ec072ba77","source":{"kind":"arxiv","id":"1703.10106","version":2},"attestation_state":"computed","paper":{"title":"Pose-conditioned Spatio-Temporal Attention for Human Action Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Christian Wolf, Fabien Baradel, Julien Mille","submitted_at":"2017-03-29T15:48:30Z","abstract_excerpt":"We address human action recognition from multi-modal video data involving articulated pose and RGB frames and propose a two-stream approach. The pose stream is processed with a convolutional model taking as input a 3D tensor holding data from a sub-sequence. A specific joint ordering, which respects the topology of the human body, ensures that different convolutional layers correspond to meaningful levels of abstraction. The raw RGB stream is handled by a spatio-temporal soft-attention mechanism conditioned on features from the pose network. An LSTM network receives input from a set of image l"},"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":"1703.10106","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-03-29T15:48:30Z","cross_cats_sorted":[],"title_canon_sha256":"d1fe6f1c69e3fdba3aedb242fff60987a37350f15955ce480a2dcb250008e679","abstract_canon_sha256":"8500221ec92998c769350dbfdfb127e1f98ceeea4dcecd9065f27b2ed3188091"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:38:35.832245Z","signature_b64":"fCPXBoy9TMRaGwdvuj/jYTrb250dMw5/wWS/fObrFHJ4CcQk5gcemW0f/iN55kdEg3eWcNCkxxi2ntUZMG0uAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4be47d033cb13740937f0ae540b42e5b2a32e6a36ef68c3627a7a81ec072ba77","last_reissued_at":"2026-05-18T00:38:35.831803Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:38:35.831803Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pose-conditioned Spatio-Temporal Attention for Human Action Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Christian Wolf, Fabien Baradel, Julien Mille","submitted_at":"2017-03-29T15:48:30Z","abstract_excerpt":"We address human action recognition from multi-modal video data involving articulated pose and RGB frames and propose a two-stream approach. The pose stream is processed with a convolutional model taking as input a 3D tensor holding data from a sub-sequence. A specific joint ordering, which respects the topology of the human body, ensures that different convolutional layers correspond to meaningful levels of abstraction. The raw RGB stream is handled by a spatio-temporal soft-attention mechanism conditioned on features from the pose network. An LSTM network receives input from a set of image l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.10106","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":""},"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":"1703.10106","created_at":"2026-05-18T00:38:35.831859+00:00"},{"alias_kind":"arxiv_version","alias_value":"1703.10106v2","created_at":"2026-05-18T00:38:35.831859+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.10106","created_at":"2026-05-18T00:38:35.831859+00:00"},{"alias_kind":"pith_short_12","alias_value":"JPSH2AZ4WE3U","created_at":"2026-05-18T12:31:24.725408+00:00"},{"alias_kind":"pith_short_16","alias_value":"JPSH2AZ4WE3UBE37","created_at":"2026-05-18T12:31:24.725408+00:00"},{"alias_kind":"pith_short_8","alias_value":"JPSH2AZ4","created_at":"2026-05-18T12:31:24.725408+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/JPSH2AZ4WE3UBE37BLSUBNBOLM","json":"https://pith.science/pith/JPSH2AZ4WE3UBE37BLSUBNBOLM.json","graph_json":"https://pith.science/api/pith-number/JPSH2AZ4WE3UBE37BLSUBNBOLM/graph.json","events_json":"https://pith.science/api/pith-number/JPSH2AZ4WE3UBE37BLSUBNBOLM/events.json","paper":"https://pith.science/paper/JPSH2AZ4"},"agent_actions":{"view_html":"https://pith.science/pith/JPSH2AZ4WE3UBE37BLSUBNBOLM","download_json":"https://pith.science/pith/JPSH2AZ4WE3UBE37BLSUBNBOLM.json","view_paper":"https://pith.science/paper/JPSH2AZ4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1703.10106&json=true","fetch_graph":"https://pith.science/api/pith-number/JPSH2AZ4WE3UBE37BLSUBNBOLM/graph.json","fetch_events":"https://pith.science/api/pith-number/JPSH2AZ4WE3UBE37BLSUBNBOLM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JPSH2AZ4WE3UBE37BLSUBNBOLM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JPSH2AZ4WE3UBE37BLSUBNBOLM/action/storage_attestation","attest_author":"https://pith.science/pith/JPSH2AZ4WE3UBE37BLSUBNBOLM/action/author_attestation","sign_citation":"https://pith.science/pith/JPSH2AZ4WE3UBE37BLSUBNBOLM/action/citation_signature","submit_replication":"https://pith.science/pith/JPSH2AZ4WE3UBE37BLSUBNBOLM/action/replication_record"}},"created_at":"2026-05-18T00:38:35.831859+00:00","updated_at":"2026-05-18T00:38:35.831859+00:00"}