{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:Y3JUZ5CDFKCQBIYV6OWIJIFZFN","short_pith_number":"pith:Y3JUZ5CD","schema_version":"1.0","canonical_sha256":"c6d34cf4432a8500a315f3ac84a0b92b7d2b7cd1558f9a56f68cf34600e67069","source":{"kind":"arxiv","id":"2201.05991","version":3},"attestation_state":"computed","paper":{"title":"Video Transformers: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Albert Clap\\'es, Anders S. Johansen, Javier Selva, Kamal Nasrollahi, Sergio Escalera, Thomas B. Moeslund","submitted_at":"2022-01-16T07:31:55Z","abstract_excerpt":"Transformer models have shown great success handling long-range interactions, making them a promising tool for modeling video. However, they lack inductive biases and scale quadratically with input length. These limitations are further exacerbated when dealing with the high dimensionality introduced by the temporal dimension. While there are surveys analyzing the advances of Transformers for vision, none focus on an in-depth analysis of video-specific designs. In this survey, we analyze the main contributions and trends of works leveraging Transformers to model video. Specifically, we delve in"},"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":"2201.05991","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-01-16T07:31:55Z","cross_cats_sorted":[],"title_canon_sha256":"7e225b4d05b251f0d7b5a4ee4a3c070d7f2ef44c10ce27baa0b6459055e08212","abstract_canon_sha256":"e78aa3760ac89d79e62a4c7d76536ae8c814e9685d8fceaf17695900d3031a64"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:40:44.585993Z","signature_b64":"BWSG/0DfwqOMJ7sRR3IPwX001V1zWGR/W8TpUbE57Xe5fPBZ06w5a1NoKKrB0gtK0QDbnhZpANJvpNvS2CjKCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c6d34cf4432a8500a315f3ac84a0b92b7d2b7cd1558f9a56f68cf34600e67069","last_reissued_at":"2026-07-05T05:40:44.585503Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:40:44.585503Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Video Transformers: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Albert Clap\\'es, Anders S. Johansen, Javier Selva, Kamal Nasrollahi, Sergio Escalera, Thomas B. Moeslund","submitted_at":"2022-01-16T07:31:55Z","abstract_excerpt":"Transformer models have shown great success handling long-range interactions, making them a promising tool for modeling video. However, they lack inductive biases and scale quadratically with input length. These limitations are further exacerbated when dealing with the high dimensionality introduced by the temporal dimension. While there are surveys analyzing the advances of Transformers for vision, none focus on an in-depth analysis of video-specific designs. In this survey, we analyze the main contributions and trends of works leveraging Transformers to model video. Specifically, we delve in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.05991","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/2201.05991/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":"2201.05991","created_at":"2026-07-05T05:40:44.585567+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.05991v3","created_at":"2026-07-05T05:40:44.585567+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.05991","created_at":"2026-07-05T05:40:44.585567+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y3JUZ5CDFKCQ","created_at":"2026-07-05T05:40:44.585567+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y3JUZ5CDFKCQBIYV","created_at":"2026-07-05T05:40:44.585567+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y3JUZ5CD","created_at":"2026-07-05T05:40:44.585567+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.16076","citing_title":"Prompting with Sign Parameters for Low-resource Sign Language Instruction Generation","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Y3JUZ5CDFKCQBIYV6OWIJIFZFN","json":"https://pith.science/pith/Y3JUZ5CDFKCQBIYV6OWIJIFZFN.json","graph_json":"https://pith.science/api/pith-number/Y3JUZ5CDFKCQBIYV6OWIJIFZFN/graph.json","events_json":"https://pith.science/api/pith-number/Y3JUZ5CDFKCQBIYV6OWIJIFZFN/events.json","paper":"https://pith.science/paper/Y3JUZ5CD"},"agent_actions":{"view_html":"https://pith.science/pith/Y3JUZ5CDFKCQBIYV6OWIJIFZFN","download_json":"https://pith.science/pith/Y3JUZ5CDFKCQBIYV6OWIJIFZFN.json","view_paper":"https://pith.science/paper/Y3JUZ5CD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.05991&json=true","fetch_graph":"https://pith.science/api/pith-number/Y3JUZ5CDFKCQBIYV6OWIJIFZFN/graph.json","fetch_events":"https://pith.science/api/pith-number/Y3JUZ5CDFKCQBIYV6OWIJIFZFN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y3JUZ5CDFKCQBIYV6OWIJIFZFN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y3JUZ5CDFKCQBIYV6OWIJIFZFN/action/storage_attestation","attest_author":"https://pith.science/pith/Y3JUZ5CDFKCQBIYV6OWIJIFZFN/action/author_attestation","sign_citation":"https://pith.science/pith/Y3JUZ5CDFKCQBIYV6OWIJIFZFN/action/citation_signature","submit_replication":"https://pith.science/pith/Y3JUZ5CDFKCQBIYV6OWIJIFZFN/action/replication_record"}},"created_at":"2026-07-05T05:40:44.585567+00:00","updated_at":"2026-07-05T05:40:44.585567+00:00"}