{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:AZJ5OQJTOSPZUZGKEIXTGLH4I5","short_pith_number":"pith:AZJ5OQJT","schema_version":"1.0","canonical_sha256":"0653d74133749f9a64ca222f332cfc47589a53694e0d43120a7d6df93eaa95b8","source":{"kind":"arxiv","id":"1509.06086","version":2},"attestation_state":"computed","paper":{"title":"Fusing Multi-Stream Deep Networks for Video Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Hao Ye, Jun Wang, Xiangyang Xue, Xi Wang, Yu-Gang Jiang, Zuxuan Wu","submitted_at":"2015-09-21T00:38:54Z","abstract_excerpt":"This paper studies deep network architectures to address the problem of video classification. A multi-stream framework is proposed to fully utilize the rich multimodal information in videos. Specifically, we first train three Convolutional Neural Networks to model spatial, short-term motion and audio clues respectively. Long Short Term Memory networks are then adopted to explore long-term temporal dynamics. With the outputs of the individual streams, we propose a simple and effective fusion method to generate the final predictions, where the optimal fusion weights are learned adaptively for ea"},"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":"1509.06086","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-09-21T00:38:54Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"5a28e120b9c8ffa4e3f442bfeb2d4248a614c3a0fb6ca4e11a6108fe93d6e074","abstract_canon_sha256":"b5cb99f59718107d272e3dcc7cdaa46183d4204bdef1f38e7837c46a63b57ada"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:27:16.005445Z","signature_b64":"qPKBxwwdLKwlPRW+GaKRpTFy6N0Vps/HlM2XPVUqdcAkQ1ohpuCawl9d/xlYd8WRdZ7CH+tdrQOHLFds4NjMDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0653d74133749f9a64ca222f332cfc47589a53694e0d43120a7d6df93eaa95b8","last_reissued_at":"2026-05-18T01:27:16.004721Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:27:16.004721Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fusing Multi-Stream Deep Networks for Video Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Hao Ye, Jun Wang, Xiangyang Xue, Xi Wang, Yu-Gang Jiang, Zuxuan Wu","submitted_at":"2015-09-21T00:38:54Z","abstract_excerpt":"This paper studies deep network architectures to address the problem of video classification. A multi-stream framework is proposed to fully utilize the rich multimodal information in videos. Specifically, we first train three Convolutional Neural Networks to model spatial, short-term motion and audio clues respectively. Long Short Term Memory networks are then adopted to explore long-term temporal dynamics. With the outputs of the individual streams, we propose a simple and effective fusion method to generate the final predictions, where the optimal fusion weights are learned adaptively for ea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1509.06086","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":"1509.06086","created_at":"2026-05-18T01:27:16.004833+00:00"},{"alias_kind":"arxiv_version","alias_value":"1509.06086v2","created_at":"2026-05-18T01:27:16.004833+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1509.06086","created_at":"2026-05-18T01:27:16.004833+00:00"},{"alias_kind":"pith_short_12","alias_value":"AZJ5OQJTOSPZ","created_at":"2026-05-18T12:29:14.074870+00:00"},{"alias_kind":"pith_short_16","alias_value":"AZJ5OQJTOSPZUZGK","created_at":"2026-05-18T12:29:14.074870+00:00"},{"alias_kind":"pith_short_8","alias_value":"AZJ5OQJT","created_at":"2026-05-18T12:29:14.074870+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.09282","citing_title":"MsEdF: A Multi-stream Encoder-decoder Framework for Remote Sensing Image Captioning","ref_index":24,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AZJ5OQJTOSPZUZGKEIXTGLH4I5","json":"https://pith.science/pith/AZJ5OQJTOSPZUZGKEIXTGLH4I5.json","graph_json":"https://pith.science/api/pith-number/AZJ5OQJTOSPZUZGKEIXTGLH4I5/graph.json","events_json":"https://pith.science/api/pith-number/AZJ5OQJTOSPZUZGKEIXTGLH4I5/events.json","paper":"https://pith.science/paper/AZJ5OQJT"},"agent_actions":{"view_html":"https://pith.science/pith/AZJ5OQJTOSPZUZGKEIXTGLH4I5","download_json":"https://pith.science/pith/AZJ5OQJTOSPZUZGKEIXTGLH4I5.json","view_paper":"https://pith.science/paper/AZJ5OQJT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1509.06086&json=true","fetch_graph":"https://pith.science/api/pith-number/AZJ5OQJTOSPZUZGKEIXTGLH4I5/graph.json","fetch_events":"https://pith.science/api/pith-number/AZJ5OQJTOSPZUZGKEIXTGLH4I5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AZJ5OQJTOSPZUZGKEIXTGLH4I5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AZJ5OQJTOSPZUZGKEIXTGLH4I5/action/storage_attestation","attest_author":"https://pith.science/pith/AZJ5OQJTOSPZUZGKEIXTGLH4I5/action/author_attestation","sign_citation":"https://pith.science/pith/AZJ5OQJTOSPZUZGKEIXTGLH4I5/action/citation_signature","submit_replication":"https://pith.science/pith/AZJ5OQJTOSPZUZGKEIXTGLH4I5/action/replication_record"}},"created_at":"2026-05-18T01:27:16.004833+00:00","updated_at":"2026-05-18T01:27:16.004833+00:00"}