{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:DZSIHJ4IJ7L4SUTS3D475YNBRY","short_pith_number":"pith:DZSIHJ4I","schema_version":"1.0","canonical_sha256":"1e6483a7884fd7c95272d8f9fee1a18e10ad406a30c54ab09127882af629cdb2","source":{"kind":"arxiv","id":"2207.08494","version":2},"attestation_state":"computed","paper":{"title":"Rethinking Alignment in Video Super-Resolution Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chao Dong, Jinjin Gu, Liangbin Xie, Shuwei Shi, Xintao Wang, Yujiu Yang","submitted_at":"2022-07-18T10:20:23Z","abstract_excerpt":"The alignment of adjacent frames is considered an essential operation in video super-resolution (VSR). Advanced VSR models, including the latest VSR Transformers, are generally equipped with well-designed alignment modules. However, the progress of the self-attention mechanism may violate this common sense. In this paper, we rethink the role of alignment in VSR Transformers and make several counter-intuitive observations. Our experiments show that: (i) VSR Transformers can directly utilize multi-frame information from unaligned videos, and (ii) existing alignment methods are sometimes harmful "},"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":"2207.08494","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-07-18T10:20:23Z","cross_cats_sorted":[],"title_canon_sha256":"973c0cfd3aa43ac6d3727088953d41733220ca7cd27768f01431a495da2b0fea","abstract_canon_sha256":"a55b4b5523113a324c7010177c755ad02eb4cd6451054b2f9f2510bc74d4e211"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:04:30.311159Z","signature_b64":"/QAb0j840Cr9MiXCPWry0P78kEwPh+YTvyghX/wksglYwDnnywVVUIMHZByG5lXIE36VF5S6zIZ9NXjXEZRgDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1e6483a7884fd7c95272d8f9fee1a18e10ad406a30c54ab09127882af629cdb2","last_reissued_at":"2026-07-05T05:04:30.310714Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:04:30.310714Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rethinking Alignment in Video Super-Resolution Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chao Dong, Jinjin Gu, Liangbin Xie, Shuwei Shi, Xintao Wang, Yujiu Yang","submitted_at":"2022-07-18T10:20:23Z","abstract_excerpt":"The alignment of adjacent frames is considered an essential operation in video super-resolution (VSR). Advanced VSR models, including the latest VSR Transformers, are generally equipped with well-designed alignment modules. However, the progress of the self-attention mechanism may violate this common sense. In this paper, we rethink the role of alignment in VSR Transformers and make several counter-intuitive observations. Our experiments show that: (i) VSR Transformers can directly utilize multi-frame information from unaligned videos, and (ii) existing alignment methods are sometimes harmful "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.08494","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/2207.08494/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":"2207.08494","created_at":"2026-07-05T05:04:30.310770+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.08494v2","created_at":"2026-07-05T05:04:30.310770+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.08494","created_at":"2026-07-05T05:04:30.310770+00:00"},{"alias_kind":"pith_short_12","alias_value":"DZSIHJ4IJ7L4","created_at":"2026-07-05T05:04:30.310770+00:00"},{"alias_kind":"pith_short_16","alias_value":"DZSIHJ4IJ7L4SUTS","created_at":"2026-07-05T05:04:30.310770+00:00"},{"alias_kind":"pith_short_8","alias_value":"DZSIHJ4I","created_at":"2026-07-05T05:04:30.310770+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.23709","citing_title":"Stream-DiffVSR: Low-Latency Streamable Video Super-Resolution via Auto-Regressive Diffusion","ref_index":63,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DZSIHJ4IJ7L4SUTS3D475YNBRY","json":"https://pith.science/pith/DZSIHJ4IJ7L4SUTS3D475YNBRY.json","graph_json":"https://pith.science/api/pith-number/DZSIHJ4IJ7L4SUTS3D475YNBRY/graph.json","events_json":"https://pith.science/api/pith-number/DZSIHJ4IJ7L4SUTS3D475YNBRY/events.json","paper":"https://pith.science/paper/DZSIHJ4I"},"agent_actions":{"view_html":"https://pith.science/pith/DZSIHJ4IJ7L4SUTS3D475YNBRY","download_json":"https://pith.science/pith/DZSIHJ4IJ7L4SUTS3D475YNBRY.json","view_paper":"https://pith.science/paper/DZSIHJ4I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.08494&json=true","fetch_graph":"https://pith.science/api/pith-number/DZSIHJ4IJ7L4SUTS3D475YNBRY/graph.json","fetch_events":"https://pith.science/api/pith-number/DZSIHJ4IJ7L4SUTS3D475YNBRY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DZSIHJ4IJ7L4SUTS3D475YNBRY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DZSIHJ4IJ7L4SUTS3D475YNBRY/action/storage_attestation","attest_author":"https://pith.science/pith/DZSIHJ4IJ7L4SUTS3D475YNBRY/action/author_attestation","sign_citation":"https://pith.science/pith/DZSIHJ4IJ7L4SUTS3D475YNBRY/action/citation_signature","submit_replication":"https://pith.science/pith/DZSIHJ4IJ7L4SUTS3D475YNBRY/action/replication_record"}},"created_at":"2026-07-05T05:04:30.310770+00:00","updated_at":"2026-07-05T05:04:30.310770+00:00"}