{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:W6GU7GPQS4NYCVO4KXDIYNIHBO","short_pith_number":"pith:W6GU7GPQ","schema_version":"1.0","canonical_sha256":"b78d4f99f0971b8155dc55c68c35070b9ef5be475163383b7c1cf1539e59b715","source":{"kind":"arxiv","id":"2401.08609","version":1},"attestation_state":"computed","paper":{"title":"F4D: Factorized 4D Convolutional Neural Network for Efficient Video-level Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lakshmish Ramaswamy, Mohammad Al-Saad, Suchendra Bhandarkar","submitted_at":"2023-11-28T19:21:57Z","abstract_excerpt":"Recent studies have shown that video-level representation learning is crucial to the capture and understanding of the long-range temporal structure for video action recognition. Most existing 3D convolutional neural network (CNN)-based methods for video-level representation learning are clip-based and focus only on short-term motion and appearances. These CNN-based methods lack the capacity to incorporate and model the long-range spatiotemporal representation of the underlying video and ignore the long-range video-level context during training. In this study, we propose a factorized 4D CNN arc"},"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":"2401.08609","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-28T19:21:57Z","cross_cats_sorted":[],"title_canon_sha256":"c2bfdd164bd4a9e2816172cc32801a665905f31aa25ff059654b1e2c7a7f9fda","abstract_canon_sha256":"0ed8c3a1a27651b06f0ba198f5651cfffd5ca8e68593244b544ae0c9b21eb009"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:34:18.903416Z","signature_b64":"XG+Evwsw/62JbTY3BVqHQ0gTzJnHEI6UDiKZ204PFE/RSa5h3n6RfcPVmCt4QwgB/UnrabTrdumDeXZ/IumKAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b78d4f99f0971b8155dc55c68c35070b9ef5be475163383b7c1cf1539e59b715","last_reissued_at":"2026-07-05T07:34:18.902973Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:34:18.902973Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"F4D: Factorized 4D Convolutional Neural Network for Efficient Video-level Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lakshmish Ramaswamy, Mohammad Al-Saad, Suchendra Bhandarkar","submitted_at":"2023-11-28T19:21:57Z","abstract_excerpt":"Recent studies have shown that video-level representation learning is crucial to the capture and understanding of the long-range temporal structure for video action recognition. Most existing 3D convolutional neural network (CNN)-based methods for video-level representation learning are clip-based and focus only on short-term motion and appearances. These CNN-based methods lack the capacity to incorporate and model the long-range spatiotemporal representation of the underlying video and ignore the long-range video-level context during training. In this study, we propose a factorized 4D CNN arc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.08609","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2401.08609/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2401.08609","created_at":"2026-07-05T07:34:18.903034+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.08609v1","created_at":"2026-07-05T07:34:18.903034+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.08609","created_at":"2026-07-05T07:34:18.903034+00:00"},{"alias_kind":"pith_short_12","alias_value":"W6GU7GPQS4NY","created_at":"2026-07-05T07:34:18.903034+00:00"},{"alias_kind":"pith_short_16","alias_value":"W6GU7GPQS4NYCVO4","created_at":"2026-07-05T07:34:18.903034+00:00"},{"alias_kind":"pith_short_8","alias_value":"W6GU7GPQ","created_at":"2026-07-05T07:34:18.903034+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.05695","citing_title":"Leveraging Vision-Language Large Models for Interpretable Video Action Recognition with Semantic Tokenization","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/W6GU7GPQS4NYCVO4KXDIYNIHBO","json":"https://pith.science/pith/W6GU7GPQS4NYCVO4KXDIYNIHBO.json","graph_json":"https://pith.science/api/pith-number/W6GU7GPQS4NYCVO4KXDIYNIHBO/graph.json","events_json":"https://pith.science/api/pith-number/W6GU7GPQS4NYCVO4KXDIYNIHBO/events.json","paper":"https://pith.science/paper/W6GU7GPQ"},"agent_actions":{"view_html":"https://pith.science/pith/W6GU7GPQS4NYCVO4KXDIYNIHBO","download_json":"https://pith.science/pith/W6GU7GPQS4NYCVO4KXDIYNIHBO.json","view_paper":"https://pith.science/paper/W6GU7GPQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.08609&json=true","fetch_graph":"https://pith.science/api/pith-number/W6GU7GPQS4NYCVO4KXDIYNIHBO/graph.json","fetch_events":"https://pith.science/api/pith-number/W6GU7GPQS4NYCVO4KXDIYNIHBO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W6GU7GPQS4NYCVO4KXDIYNIHBO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W6GU7GPQS4NYCVO4KXDIYNIHBO/action/storage_attestation","attest_author":"https://pith.science/pith/W6GU7GPQS4NYCVO4KXDIYNIHBO/action/author_attestation","sign_citation":"https://pith.science/pith/W6GU7GPQS4NYCVO4KXDIYNIHBO/action/citation_signature","submit_replication":"https://pith.science/pith/W6GU7GPQS4NYCVO4KXDIYNIHBO/action/replication_record"}},"created_at":"2026-07-05T07:34:18.903034+00:00","updated_at":"2026-07-05T07:34:18.903034+00:00"}