{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:QJ6H3RJYVFORMU7Z425XGNNFWM","short_pith_number":"pith:QJ6H3RJY","schema_version":"1.0","canonical_sha256":"827c7dc538a95d1653f9e6bb7335a5b331c7d7aa92c9ae22459a1a2970c7268e","source":{"kind":"arxiv","id":"1504.01561","version":1},"attestation_state":"computed","paper":{"title":"Modeling Spatial-Temporal Clues in a Hybrid Deep Learning Framework 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, Xiangyang Xue, Xi Wang, Yu-Gang Jiang, Zuxuan Wu","submitted_at":"2015-04-07T11:53:46Z","abstract_excerpt":"Classifying videos according to content semantics is an important problem with a wide range of applications. In this paper, we propose a hybrid deep learning framework for video classification, which is able to model static spatial information, short-term motion, as well as long-term temporal clues in the videos. Specifically, the spatial and the short-term motion features are extracted separately by two Convolutional Neural Networks (CNN). These two types of CNN-based features are then combined in a regularized feature fusion network for classification, which is able to learn and utilize feat"},"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":"1504.01561","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-04-07T11:53:46Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"878af094a73a0963d22abb1d03c063ebf9b846bc57ec59ceed498f2b0c681793","abstract_canon_sha256":"cfc3ff4135ea74739356349c43ccb33ff7ca4ba45501f89ab1a779e13a51a4df"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:19:26.792022Z","signature_b64":"JCjK7YF0YtUBstPXeSkw/exNYjFMK1XvN5goo4g8hh5tGgemZU8iwxhs1+R5n9TEPARwDYxE8bul8jawIJ7rDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"827c7dc538a95d1653f9e6bb7335a5b331c7d7aa92c9ae22459a1a2970c7268e","last_reissued_at":"2026-05-18T02:19:26.791398Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:19:26.791398Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Modeling Spatial-Temporal Clues in a Hybrid Deep Learning Framework 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, Xiangyang Xue, Xi Wang, Yu-Gang Jiang, Zuxuan Wu","submitted_at":"2015-04-07T11:53:46Z","abstract_excerpt":"Classifying videos according to content semantics is an important problem with a wide range of applications. In this paper, we propose a hybrid deep learning framework for video classification, which is able to model static spatial information, short-term motion, as well as long-term temporal clues in the videos. Specifically, the spatial and the short-term motion features are extracted separately by two Convolutional Neural Networks (CNN). These two types of CNN-based features are then combined in a regularized feature fusion network for classification, which is able to learn and utilize feat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1504.01561","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":"1504.01561","created_at":"2026-05-18T02:19:26.791501+00:00"},{"alias_kind":"arxiv_version","alias_value":"1504.01561v1","created_at":"2026-05-18T02:19:26.791501+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1504.01561","created_at":"2026-05-18T02:19:26.791501+00:00"},{"alias_kind":"pith_short_12","alias_value":"QJ6H3RJYVFOR","created_at":"2026-05-18T12:29:37.295048+00:00"},{"alias_kind":"pith_short_16","alias_value":"QJ6H3RJYVFORMU7Z","created_at":"2026-05-18T12:29:37.295048+00:00"},{"alias_kind":"pith_short_8","alias_value":"QJ6H3RJY","created_at":"2026-05-18T12:29:37.295048+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/QJ6H3RJYVFORMU7Z425XGNNFWM","json":"https://pith.science/pith/QJ6H3RJYVFORMU7Z425XGNNFWM.json","graph_json":"https://pith.science/api/pith-number/QJ6H3RJYVFORMU7Z425XGNNFWM/graph.json","events_json":"https://pith.science/api/pith-number/QJ6H3RJYVFORMU7Z425XGNNFWM/events.json","paper":"https://pith.science/paper/QJ6H3RJY"},"agent_actions":{"view_html":"https://pith.science/pith/QJ6H3RJYVFORMU7Z425XGNNFWM","download_json":"https://pith.science/pith/QJ6H3RJYVFORMU7Z425XGNNFWM.json","view_paper":"https://pith.science/paper/QJ6H3RJY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1504.01561&json=true","fetch_graph":"https://pith.science/api/pith-number/QJ6H3RJYVFORMU7Z425XGNNFWM/graph.json","fetch_events":"https://pith.science/api/pith-number/QJ6H3RJYVFORMU7Z425XGNNFWM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QJ6H3RJYVFORMU7Z425XGNNFWM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QJ6H3RJYVFORMU7Z425XGNNFWM/action/storage_attestation","attest_author":"https://pith.science/pith/QJ6H3RJYVFORMU7Z425XGNNFWM/action/author_attestation","sign_citation":"https://pith.science/pith/QJ6H3RJYVFORMU7Z425XGNNFWM/action/citation_signature","submit_replication":"https://pith.science/pith/QJ6H3RJYVFORMU7Z425XGNNFWM/action/replication_record"}},"created_at":"2026-05-18T02:19:26.791501+00:00","updated_at":"2026-05-18T02:19:26.791501+00:00"}