{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:ACROMPJDHOH6ITQFI5BEOMS2UM","short_pith_number":"pith:ACROMPJD","schema_version":"1.0","canonical_sha256":"00a2e63d233b8fe44e05474247325aa33585f8516e0146aef54ad68167b08a00","source":{"kind":"arxiv","id":"2008.05765","version":2},"attestation_state":"computed","paper":{"title":"Revisiting Temporal Modeling for Video Super-resolution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Fang Zhu, Shengjin Wang, Takashi Isobe, Xu Jia","submitted_at":"2020-08-13T09:09:37Z","abstract_excerpt":"Video super-resolution plays an important role in surveillance video analysis and ultra-high-definition video display, which has drawn much attention in both the research and industrial communities. Although many deep learning-based VSR methods have been proposed, it is hard to directly compare these methods since the different loss functions and training datasets have a significant impact on the super-resolution results. In this work, we carefully study and compare three temporal modeling methods (2D CNN with early fusion, 3D CNN with slow fusion and Recurrent Neural Network) for video super-"},"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":"2008.05765","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2020-08-13T09:09:37Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"902eb161cebf213848fd77f1e63f771883eb9756398e4eb2ce907dc2d8d5639d","abstract_canon_sha256":"239956a6222b30ef35556df1d61fb9aacd21e8756368cc6c966058a3fc0b966a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:28:31.855941Z","signature_b64":"HN/vRFn+m9ktaBigFP6wU5x6fc61lLbMwBX/oIoK9gL8lhpAOYYe+Y7j+KUxv8VDfEBnswP3ZfkRXKgB+UgnAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"00a2e63d233b8fe44e05474247325aa33585f8516e0146aef54ad68167b08a00","last_reissued_at":"2026-07-05T01:28:31.855207Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:28:31.855207Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Revisiting Temporal Modeling for Video Super-resolution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Fang Zhu, Shengjin Wang, Takashi Isobe, Xu Jia","submitted_at":"2020-08-13T09:09:37Z","abstract_excerpt":"Video super-resolution plays an important role in surveillance video analysis and ultra-high-definition video display, which has drawn much attention in both the research and industrial communities. Although many deep learning-based VSR methods have been proposed, it is hard to directly compare these methods since the different loss functions and training datasets have a significant impact on the super-resolution results. In this work, we carefully study and compare three temporal modeling methods (2D CNN with early fusion, 3D CNN with slow fusion and Recurrent Neural Network) for video super-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.05765","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2008.05765/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":"2008.05765","created_at":"2026-07-05T01:28:31.855329+00:00"},{"alias_kind":"arxiv_version","alias_value":"2008.05765v2","created_at":"2026-07-05T01:28:31.855329+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.05765","created_at":"2026-07-05T01:28:31.855329+00:00"},{"alias_kind":"pith_short_12","alias_value":"ACROMPJDHOH6","created_at":"2026-07-05T01:28:31.855329+00:00"},{"alias_kind":"pith_short_16","alias_value":"ACROMPJDHOH6ITQF","created_at":"2026-07-05T01:28:31.855329+00:00"},{"alias_kind":"pith_short_8","alias_value":"ACROMPJD","created_at":"2026-07-05T01:28:31.855329+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.12335","citing_title":"All in One: A Unified Synthetic Data Pipeline for Multimodal Video Understanding","ref_index":47,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ACROMPJDHOH6ITQFI5BEOMS2UM","json":"https://pith.science/pith/ACROMPJDHOH6ITQFI5BEOMS2UM.json","graph_json":"https://pith.science/api/pith-number/ACROMPJDHOH6ITQFI5BEOMS2UM/graph.json","events_json":"https://pith.science/api/pith-number/ACROMPJDHOH6ITQFI5BEOMS2UM/events.json","paper":"https://pith.science/paper/ACROMPJD"},"agent_actions":{"view_html":"https://pith.science/pith/ACROMPJDHOH6ITQFI5BEOMS2UM","download_json":"https://pith.science/pith/ACROMPJDHOH6ITQFI5BEOMS2UM.json","view_paper":"https://pith.science/paper/ACROMPJD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2008.05765&json=true","fetch_graph":"https://pith.science/api/pith-number/ACROMPJDHOH6ITQFI5BEOMS2UM/graph.json","fetch_events":"https://pith.science/api/pith-number/ACROMPJDHOH6ITQFI5BEOMS2UM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ACROMPJDHOH6ITQFI5BEOMS2UM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ACROMPJDHOH6ITQFI5BEOMS2UM/action/storage_attestation","attest_author":"https://pith.science/pith/ACROMPJDHOH6ITQFI5BEOMS2UM/action/author_attestation","sign_citation":"https://pith.science/pith/ACROMPJDHOH6ITQFI5BEOMS2UM/action/citation_signature","submit_replication":"https://pith.science/pith/ACROMPJDHOH6ITQFI5BEOMS2UM/action/replication_record"}},"created_at":"2026-07-05T01:28:31.855329+00:00","updated_at":"2026-07-05T01:28:31.855329+00:00"}