{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:7OSI2UP5GWYSOTHCD5MJ2BOINL","short_pith_number":"pith:7OSI2UP5","schema_version":"1.0","canonical_sha256":"fba48d51fd35b1274ce21f589d05c86ad2e4c0751ded9e92e4169cf96b5af7ec","source":{"kind":"arxiv","id":"1703.10667","version":1},"attestation_state":"computed","paper":{"title":"TS-LSTM and Temporal-Inception: Exploiting Spatiotemporal Dynamics for Activity Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chih-Yao Ma, Ghassan AlRegib, Min-Hung Chen, Zsolt Kira","submitted_at":"2017-03-30T20:45:00Z","abstract_excerpt":"Recent two-stream deep Convolutional Neural Networks (ConvNets) have made significant progress in recognizing human actions in videos. Despite their success, methods extending the basic two-stream ConvNet have not systematically explored possible network architectures to further exploit spatiotemporal dynamics within video sequences. Further, such networks often use different baseline two-stream networks. Therefore, the differences and the distinguishing factors between various methods using Recurrent Neural Networks (RNN) or convolutional networks on temporally-constructed feature vectors (Te"},"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":"1703.10667","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-03-30T20:45:00Z","cross_cats_sorted":[],"title_canon_sha256":"18d687722cbe4594360f225b1669a38a384b51f5bb4b2746b890eba7d1ebd133","abstract_canon_sha256":"d81d147e14dce71eb1d5846feb115b23a1c482c139a4b31250f7739af41acc23"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:47:33.024931Z","signature_b64":"YHxl0n66gETCHCRX5F2uPCuUW9gx6m0W0Hc0rOibHX4CKytMJ+Z7AbswBfkNXvBHrtbJhv6msLvJDvcWcqbyAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fba48d51fd35b1274ce21f589d05c86ad2e4c0751ded9e92e4169cf96b5af7ec","last_reissued_at":"2026-05-18T00:47:33.024367Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:47:33.024367Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TS-LSTM and Temporal-Inception: Exploiting Spatiotemporal Dynamics for Activity Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chih-Yao Ma, Ghassan AlRegib, Min-Hung Chen, Zsolt Kira","submitted_at":"2017-03-30T20:45:00Z","abstract_excerpt":"Recent two-stream deep Convolutional Neural Networks (ConvNets) have made significant progress in recognizing human actions in videos. Despite their success, methods extending the basic two-stream ConvNet have not systematically explored possible network architectures to further exploit spatiotemporal dynamics within video sequences. Further, such networks often use different baseline two-stream networks. Therefore, the differences and the distinguishing factors between various methods using Recurrent Neural Networks (RNN) or convolutional networks on temporally-constructed feature vectors (Te"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.10667","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":""},"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":"1703.10667","created_at":"2026-05-18T00:47:33.024448+00:00"},{"alias_kind":"arxiv_version","alias_value":"1703.10667v1","created_at":"2026-05-18T00:47:33.024448+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.10667","created_at":"2026-05-18T00:47:33.024448+00:00"},{"alias_kind":"pith_short_12","alias_value":"7OSI2UP5GWYS","created_at":"2026-05-18T12:31:05.417338+00:00"},{"alias_kind":"pith_short_16","alias_value":"7OSI2UP5GWYSOTHC","created_at":"2026-05-18T12:31:05.417338+00:00"},{"alias_kind":"pith_short_8","alias_value":"7OSI2UP5","created_at":"2026-05-18T12:31:05.417338+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/7OSI2UP5GWYSOTHCD5MJ2BOINL","json":"https://pith.science/pith/7OSI2UP5GWYSOTHCD5MJ2BOINL.json","graph_json":"https://pith.science/api/pith-number/7OSI2UP5GWYSOTHCD5MJ2BOINL/graph.json","events_json":"https://pith.science/api/pith-number/7OSI2UP5GWYSOTHCD5MJ2BOINL/events.json","paper":"https://pith.science/paper/7OSI2UP5"},"agent_actions":{"view_html":"https://pith.science/pith/7OSI2UP5GWYSOTHCD5MJ2BOINL","download_json":"https://pith.science/pith/7OSI2UP5GWYSOTHCD5MJ2BOINL.json","view_paper":"https://pith.science/paper/7OSI2UP5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1703.10667&json=true","fetch_graph":"https://pith.science/api/pith-number/7OSI2UP5GWYSOTHCD5MJ2BOINL/graph.json","fetch_events":"https://pith.science/api/pith-number/7OSI2UP5GWYSOTHCD5MJ2BOINL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7OSI2UP5GWYSOTHCD5MJ2BOINL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7OSI2UP5GWYSOTHCD5MJ2BOINL/action/storage_attestation","attest_author":"https://pith.science/pith/7OSI2UP5GWYSOTHCD5MJ2BOINL/action/author_attestation","sign_citation":"https://pith.science/pith/7OSI2UP5GWYSOTHCD5MJ2BOINL/action/citation_signature","submit_replication":"https://pith.science/pith/7OSI2UP5GWYSOTHCD5MJ2BOINL/action/replication_record"}},"created_at":"2026-05-18T00:47:33.024448+00:00","updated_at":"2026-05-18T00:47:33.024448+00:00"}