{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:66C37R7IFUZJ7S5A56DKILSS3K","short_pith_number":"pith:66C37R7I","schema_version":"1.0","canonical_sha256":"f785bfc7e82d329fcba0ef86a42e52da86f4458b48b3f6342384803c5ed9cd4a","source":{"kind":"arxiv","id":"1704.00389","version":4},"attestation_state":"computed","paper":{"title":"Hidden Two-Stream Convolutional Networks for Action Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Alexander G. Hauptmann, Shawn Newsam, Yi Zhu, Zhenzhong Lan","submitted_at":"2017-04-02T23:39:51Z","abstract_excerpt":"Analyzing videos of human actions involves understanding the temporal relationships among video frames. State-of-the-art action recognition approaches rely on traditional optical flow estimation methods to pre-compute motion information for CNNs. Such a two-stage approach is computationally expensive, storage demanding, and not end-to-end trainable. In this paper, we present a novel CNN architecture that implicitly captures motion information between adjacent frames. We name our approach hidden two-stream CNNs because it only takes raw video frames as input and directly predicts action classes"},"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":"1704.00389","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-04-02T23:39:51Z","cross_cats_sorted":["cs.LG","cs.MM"],"title_canon_sha256":"aba2226212b2efb5fca61a931a5451e85fcc32df2317951af96b0e8db9fb26ac","abstract_canon_sha256":"67f3cc8764136077ba29868a9964e8ca6ba5f79117de4fd03e48757ca24fe900"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:02:02.239009Z","signature_b64":"8/0RVBvnrzfzda3r5pNgDGfH6K2xRUrskHlJJqlxy0dgp1Ri+rt3leKXnamoAJomcWIkACkHeZ1pGn0EW8P1Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f785bfc7e82d329fcba0ef86a42e52da86f4458b48b3f6342384803c5ed9cd4a","last_reissued_at":"2026-05-18T00:02:02.238565Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:02:02.238565Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hidden Two-Stream Convolutional Networks for Action Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Alexander G. Hauptmann, Shawn Newsam, Yi Zhu, Zhenzhong Lan","submitted_at":"2017-04-02T23:39:51Z","abstract_excerpt":"Analyzing videos of human actions involves understanding the temporal relationships among video frames. State-of-the-art action recognition approaches rely on traditional optical flow estimation methods to pre-compute motion information for CNNs. Such a two-stage approach is computationally expensive, storage demanding, and not end-to-end trainable. In this paper, we present a novel CNN architecture that implicitly captures motion information between adjacent frames. We name our approach hidden two-stream CNNs because it only takes raw video frames as input and directly predicts action classes"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.00389","kind":"arxiv","version":4},"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":"1704.00389","created_at":"2026-05-18T00:02:02.238644+00:00"},{"alias_kind":"arxiv_version","alias_value":"1704.00389v4","created_at":"2026-05-18T00:02:02.238644+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.00389","created_at":"2026-05-18T00:02:02.238644+00:00"},{"alias_kind":"pith_short_12","alias_value":"66C37R7IFUZJ","created_at":"2026-05-18T12:31:03.183658+00:00"},{"alias_kind":"pith_short_16","alias_value":"66C37R7IFUZJ7S5A","created_at":"2026-05-18T12:31:03.183658+00:00"},{"alias_kind":"pith_short_8","alias_value":"66C37R7I","created_at":"2026-05-18T12:31:03.183658+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.11628","citing_title":"Unsupervised Learning for Optical Flow Estimation Using Pyramid Convolution LSTM","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/66C37R7IFUZJ7S5A56DKILSS3K","json":"https://pith.science/pith/66C37R7IFUZJ7S5A56DKILSS3K.json","graph_json":"https://pith.science/api/pith-number/66C37R7IFUZJ7S5A56DKILSS3K/graph.json","events_json":"https://pith.science/api/pith-number/66C37R7IFUZJ7S5A56DKILSS3K/events.json","paper":"https://pith.science/paper/66C37R7I"},"agent_actions":{"view_html":"https://pith.science/pith/66C37R7IFUZJ7S5A56DKILSS3K","download_json":"https://pith.science/pith/66C37R7IFUZJ7S5A56DKILSS3K.json","view_paper":"https://pith.science/paper/66C37R7I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1704.00389&json=true","fetch_graph":"https://pith.science/api/pith-number/66C37R7IFUZJ7S5A56DKILSS3K/graph.json","fetch_events":"https://pith.science/api/pith-number/66C37R7IFUZJ7S5A56DKILSS3K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/66C37R7IFUZJ7S5A56DKILSS3K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/66C37R7IFUZJ7S5A56DKILSS3K/action/storage_attestation","attest_author":"https://pith.science/pith/66C37R7IFUZJ7S5A56DKILSS3K/action/author_attestation","sign_citation":"https://pith.science/pith/66C37R7IFUZJ7S5A56DKILSS3K/action/citation_signature","submit_replication":"https://pith.science/pith/66C37R7IFUZJ7S5A56DKILSS3K/action/replication_record"}},"created_at":"2026-05-18T00:02:02.238644+00:00","updated_at":"2026-05-18T00:02:02.238644+00:00"}