{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:LQGGDRJ34JGODO2LO57XDSLW7T","short_pith_number":"pith:LQGGDRJ3","schema_version":"1.0","canonical_sha256":"5c0c61c53be24ce1bb4b777f71c976fce9153eb1b960b70be0860d319f0f78f4","source":{"kind":"arxiv","id":"1604.06573","version":2},"attestation_state":"computed","paper":{"title":"Convolutional Two-Stream Network Fusion for Video Action Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrew Zisserman, Axel Pinz, Christoph Feichtenhofer","submitted_at":"2016-04-22T08:51:17Z","abstract_excerpt":"Recent applications of Convolutional Neural Networks (ConvNets) for human action recognition in videos have proposed different solutions for incorporating the appearance and motion information. We study a number of ways of fusing ConvNet towers both spatially and temporally in order to best take advantage of this spatio-temporal information. We make the following findings: (i) that rather than fusing at the softmax layer, a spatial and temporal network can be fused at a convolution layer without loss of performance, but with a substantial saving in parameters; (ii) that it is better to fuse su"},"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":"1604.06573","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-04-22T08:51:17Z","cross_cats_sorted":[],"title_canon_sha256":"9c0c3d8910eca07f585a3895bfcf46e45c259050079f23b5c00226b0d5aa48b1","abstract_canon_sha256":"d0909c58ccfcf9e88a8f4b34fe05598d202bd9f396dcc129548b814ef2783d22"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:03:59.141396Z","signature_b64":"6grpvoO/Z2/fWlWFOxvLEo4365edrTXjuh1IeJ6cuVgcx5WU7M8WMNr7yniRuPLoy18oJ77KaT5kZvZPuKbzBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5c0c61c53be24ce1bb4b777f71c976fce9153eb1b960b70be0860d319f0f78f4","last_reissued_at":"2026-05-18T01:03:59.140345Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:03:59.140345Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Convolutional Two-Stream Network Fusion for Video Action Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrew Zisserman, Axel Pinz, Christoph Feichtenhofer","submitted_at":"2016-04-22T08:51:17Z","abstract_excerpt":"Recent applications of Convolutional Neural Networks (ConvNets) for human action recognition in videos have proposed different solutions for incorporating the appearance and motion information. We study a number of ways of fusing ConvNet towers both spatially and temporally in order to best take advantage of this spatio-temporal information. We make the following findings: (i) that rather than fusing at the softmax layer, a spatial and temporal network can be fused at a convolution layer without loss of performance, but with a substantial saving in parameters; (ii) that it is better to fuse su"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1604.06573","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":"1604.06573","created_at":"2026-05-18T01:03:59.140622+00:00"},{"alias_kind":"arxiv_version","alias_value":"1604.06573v2","created_at":"2026-05-18T01:03:59.140622+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1604.06573","created_at":"2026-05-18T01:03:59.140622+00:00"},{"alias_kind":"pith_short_12","alias_value":"LQGGDRJ34JGO","created_at":"2026-05-18T12:30:29.479603+00:00"},{"alias_kind":"pith_short_16","alias_value":"LQGGDRJ34JGODO2L","created_at":"2026-05-18T12:30:29.479603+00:00"},{"alias_kind":"pith_short_8","alias_value":"LQGGDRJ3","created_at":"2026-05-18T12:30:29.479603+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/LQGGDRJ34JGODO2LO57XDSLW7T","json":"https://pith.science/pith/LQGGDRJ34JGODO2LO57XDSLW7T.json","graph_json":"https://pith.science/api/pith-number/LQGGDRJ34JGODO2LO57XDSLW7T/graph.json","events_json":"https://pith.science/api/pith-number/LQGGDRJ34JGODO2LO57XDSLW7T/events.json","paper":"https://pith.science/paper/LQGGDRJ3"},"agent_actions":{"view_html":"https://pith.science/pith/LQGGDRJ34JGODO2LO57XDSLW7T","download_json":"https://pith.science/pith/LQGGDRJ34JGODO2LO57XDSLW7T.json","view_paper":"https://pith.science/paper/LQGGDRJ3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1604.06573&json=true","fetch_graph":"https://pith.science/api/pith-number/LQGGDRJ34JGODO2LO57XDSLW7T/graph.json","fetch_events":"https://pith.science/api/pith-number/LQGGDRJ34JGODO2LO57XDSLW7T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LQGGDRJ34JGODO2LO57XDSLW7T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LQGGDRJ34JGODO2LO57XDSLW7T/action/storage_attestation","attest_author":"https://pith.science/pith/LQGGDRJ34JGODO2LO57XDSLW7T/action/author_attestation","sign_citation":"https://pith.science/pith/LQGGDRJ34JGODO2LO57XDSLW7T/action/citation_signature","submit_replication":"https://pith.science/pith/LQGGDRJ34JGODO2LO57XDSLW7T/action/replication_record"}},"created_at":"2026-05-18T01:03:59.140622+00:00","updated_at":"2026-05-18T01:03:59.140622+00:00"}