{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:HT4T6FIMXZPAA4JXEPJZ656XII","short_pith_number":"pith:HT4T6FIM","schema_version":"1.0","canonical_sha256":"3cf93f150cbe5e00713723d39f77d7422d6198d87f1926e2c771552e53824143","source":{"kind":"arxiv","id":"2111.13196","version":4},"attestation_state":"computed","paper":{"title":"SwinBERT: End-to-End Transformers with Sparse Attention for Video Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chung-Ching Lin, Faisal Ahmed, Kevin Lin, Lijuan Wang, Linjie Li, Yumao Lu, Zhe Gan, Zicheng Liu","submitted_at":"2021-11-25T18:02:12Z","abstract_excerpt":"The canonical approach to video captioning dictates a caption generation model to learn from offline-extracted dense video features. These feature extractors usually operate on video frames sampled at a fixed frame rate and are often trained on image/video understanding tasks, without adaption to video captioning data. In this work, we present SwinBERT, an end-to-end transformer-based model for video captioning, which takes video frame patches directly as inputs, and outputs a natural language description. Instead of leveraging multiple 2D/3D feature extractors, our method adopts a video trans"},"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":"2111.13196","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-11-25T18:02:12Z","cross_cats_sorted":[],"title_canon_sha256":"cc89fe419599ebe5827524fd5a04bb0df4cc1fa19d9682d4413de3163f101e84","abstract_canon_sha256":"3a925f650450bec7b1c887b30e27f4252b13d6cdeeb42fe8aa058715d4403f26"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:32:53.091008Z","signature_b64":"ZXjrBWq3A38If1y0hPXWS+tMJ5yOwGuAoxoqLiVizK7c+7JGpinpt6gcRUxjXmRRtCat+Lm7v2aoEM4v+RvuAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3cf93f150cbe5e00713723d39f77d7422d6198d87f1926e2c771552e53824143","last_reissued_at":"2026-07-05T04:32:53.090527Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:32:53.090527Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SwinBERT: End-to-End Transformers with Sparse Attention for Video Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chung-Ching Lin, Faisal Ahmed, Kevin Lin, Lijuan Wang, Linjie Li, Yumao Lu, Zhe Gan, Zicheng Liu","submitted_at":"2021-11-25T18:02:12Z","abstract_excerpt":"The canonical approach to video captioning dictates a caption generation model to learn from offline-extracted dense video features. These feature extractors usually operate on video frames sampled at a fixed frame rate and are often trained on image/video understanding tasks, without adaption to video captioning data. In this work, we present SwinBERT, an end-to-end transformer-based model for video captioning, which takes video frame patches directly as inputs, and outputs a natural language description. Instead of leveraging multiple 2D/3D feature extractors, our method adopts a video trans"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.13196","kind":"arxiv","version":4},"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/2111.13196/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":"2111.13196","created_at":"2026-07-05T04:32:53.090586+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.13196v4","created_at":"2026-07-05T04:32:53.090586+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.13196","created_at":"2026-07-05T04:32:53.090586+00:00"},{"alias_kind":"pith_short_12","alias_value":"HT4T6FIMXZPA","created_at":"2026-07-05T04:32:53.090586+00:00"},{"alias_kind":"pith_short_16","alias_value":"HT4T6FIMXZPAA4JX","created_at":"2026-07-05T04:32:53.090586+00:00"},{"alias_kind":"pith_short_8","alias_value":"HT4T6FIM","created_at":"2026-07-05T04:32:53.090586+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2205.14100","citing_title":"GIT: A Generative Image-to-text Transformer for Vision and Language","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HT4T6FIMXZPAA4JXEPJZ656XII","json":"https://pith.science/pith/HT4T6FIMXZPAA4JXEPJZ656XII.json","graph_json":"https://pith.science/api/pith-number/HT4T6FIMXZPAA4JXEPJZ656XII/graph.json","events_json":"https://pith.science/api/pith-number/HT4T6FIMXZPAA4JXEPJZ656XII/events.json","paper":"https://pith.science/paper/HT4T6FIM"},"agent_actions":{"view_html":"https://pith.science/pith/HT4T6FIMXZPAA4JXEPJZ656XII","download_json":"https://pith.science/pith/HT4T6FIMXZPAA4JXEPJZ656XII.json","view_paper":"https://pith.science/paper/HT4T6FIM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.13196&json=true","fetch_graph":"https://pith.science/api/pith-number/HT4T6FIMXZPAA4JXEPJZ656XII/graph.json","fetch_events":"https://pith.science/api/pith-number/HT4T6FIMXZPAA4JXEPJZ656XII/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HT4T6FIMXZPAA4JXEPJZ656XII/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HT4T6FIMXZPAA4JXEPJZ656XII/action/storage_attestation","attest_author":"https://pith.science/pith/HT4T6FIMXZPAA4JXEPJZ656XII/action/author_attestation","sign_citation":"https://pith.science/pith/HT4T6FIMXZPAA4JXEPJZ656XII/action/citation_signature","submit_replication":"https://pith.science/pith/HT4T6FIMXZPAA4JXEPJZ656XII/action/replication_record"}},"created_at":"2026-07-05T04:32:53.090586+00:00","updated_at":"2026-07-05T04:32:53.090586+00:00"}