{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:PYU2UVAIZHKRAXGMAJQLK5GZNF","short_pith_number":"pith:PYU2UVAI","schema_version":"1.0","canonical_sha256":"7e29aa5408c9d5105ccc0260b574d96940c6571785ad78935df6a4eceb3279c0","source":{"kind":"arxiv","id":"2111.13817","version":3},"attestation_state":"computed","paper":{"title":"Video Frame Interpolation Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jun Chen, Ming-Hsuan Yang, Xiangyu Xu, Xiaohong Liu, Zhihao Shi","submitted_at":"2021-11-27T05:35:10Z","abstract_excerpt":"Existing methods for video interpolation heavily rely on deep convolution neural networks, and thus suffer from their intrinsic limitations, such as content-agnostic kernel weights and restricted receptive field. To address these issues, we propose a Transformer-based video interpolation framework that allows content-aware aggregation weights and considers long-range dependencies with the self-attention operations. To avoid the high computational cost of global self-attention, we introduce the concept of local attention into video interpolation and extend it to the spatial-temporal domain. Fur"},"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":"2111.13817","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-11-27T05:35:10Z","cross_cats_sorted":[],"title_canon_sha256":"3c1c76a760af0f22136da5ca62a96ff923f7763eb245b51c8ea275adf4614f0a","abstract_canon_sha256":"062ebf4ddd93a5ab116d9e80516e9c60946a4dee46e302aefb48220024deffe4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:08:59.936553Z","signature_b64":"HB2Rrj3X8IeyArVHUO5LgnG/6S/0vjfcHj19HApYLHWbs76eVTE9yYv+2aEubJ9CaVLn2FL4yvMN/upyFHNzCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7e29aa5408c9d5105ccc0260b574d96940c6571785ad78935df6a4eceb3279c0","last_reissued_at":"2026-07-05T04:08:59.936085Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:08:59.936085Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Video Frame Interpolation Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jun Chen, Ming-Hsuan Yang, Xiangyu Xu, Xiaohong Liu, Zhihao Shi","submitted_at":"2021-11-27T05:35:10Z","abstract_excerpt":"Existing methods for video interpolation heavily rely on deep convolution neural networks, and thus suffer from their intrinsic limitations, such as content-agnostic kernel weights and restricted receptive field. To address these issues, we propose a Transformer-based video interpolation framework that allows content-aware aggregation weights and considers long-range dependencies with the self-attention operations. To avoid the high computational cost of global self-attention, we introduce the concept of local attention into video interpolation and extend it to the spatial-temporal domain. Fur"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.13817","kind":"arxiv","version":3},"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/2111.13817/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":"2111.13817","created_at":"2026-07-05T04:08:59.936141+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.13817v3","created_at":"2026-07-05T04:08:59.936141+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.13817","created_at":"2026-07-05T04:08:59.936141+00:00"},{"alias_kind":"pith_short_12","alias_value":"PYU2UVAIZHKR","created_at":"2026-07-05T04:08:59.936141+00:00"},{"alias_kind":"pith_short_16","alias_value":"PYU2UVAIZHKRAXGM","created_at":"2026-07-05T04:08:59.936141+00:00"},{"alias_kind":"pith_short_8","alias_value":"PYU2UVAI","created_at":"2026-07-05T04:08:59.936141+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.18570","citing_title":"Streamlining Analysis and Design of Two-Dimensional Electronic Spectroscopy using Machine Learning","ref_index":174,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PYU2UVAIZHKRAXGMAJQLK5GZNF","json":"https://pith.science/pith/PYU2UVAIZHKRAXGMAJQLK5GZNF.json","graph_json":"https://pith.science/api/pith-number/PYU2UVAIZHKRAXGMAJQLK5GZNF/graph.json","events_json":"https://pith.science/api/pith-number/PYU2UVAIZHKRAXGMAJQLK5GZNF/events.json","paper":"https://pith.science/paper/PYU2UVAI"},"agent_actions":{"view_html":"https://pith.science/pith/PYU2UVAIZHKRAXGMAJQLK5GZNF","download_json":"https://pith.science/pith/PYU2UVAIZHKRAXGMAJQLK5GZNF.json","view_paper":"https://pith.science/paper/PYU2UVAI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.13817&json=true","fetch_graph":"https://pith.science/api/pith-number/PYU2UVAIZHKRAXGMAJQLK5GZNF/graph.json","fetch_events":"https://pith.science/api/pith-number/PYU2UVAIZHKRAXGMAJQLK5GZNF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PYU2UVAIZHKRAXGMAJQLK5GZNF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PYU2UVAIZHKRAXGMAJQLK5GZNF/action/storage_attestation","attest_author":"https://pith.science/pith/PYU2UVAIZHKRAXGMAJQLK5GZNF/action/author_attestation","sign_citation":"https://pith.science/pith/PYU2UVAIZHKRAXGMAJQLK5GZNF/action/citation_signature","submit_replication":"https://pith.science/pith/PYU2UVAIZHKRAXGMAJQLK5GZNF/action/replication_record"}},"created_at":"2026-07-05T04:08:59.936141+00:00","updated_at":"2026-07-05T04:08:59.936141+00:00"}