{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:CGQKBJ3MI5OGEMK7TXZEGZXKJH","short_pith_number":"pith:CGQKBJ3M","schema_version":"1.0","canonical_sha256":"11a0a0a76c475c62315f9df24366ea49c61f6c9c4a43fbfeba0e508dd2df8678","source":{"kind":"arxiv","id":"2308.09775","version":1},"attestation_state":"computed","paper":{"title":"Long-range Multimodal Pretraining for Movie Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dawit Mureja Argaw, Fabian Caba Heilbron, In So Kweon, Joon-Young Lee, Markus Woodson","submitted_at":"2023-08-18T18:52:59Z","abstract_excerpt":"Learning computer vision models from (and for) movies has a long-standing history. While great progress has been attained, there is still a need for a pretrained multimodal model that can perform well in the ever-growing set of movie understanding tasks the community has been establishing. In this work, we introduce Long-range Multimodal Pretraining, a strategy, and a model that leverages movie data to train transferable multimodal and cross-modal encoders. Our key idea is to learn from all modalities in a movie by observing and extracting relationships over a long-range. After pretraining, we"},"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":"2308.09775","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-18T18:52:59Z","cross_cats_sorted":[],"title_canon_sha256":"6e76ea88740aa454e40da9d38a6ba9234bbc01a2c14f3219dd4cf0236c256ac1","abstract_canon_sha256":"d842706c8f5594ff3ebc935c2e8c62b88f8fda72752112a4581b16f8be494775"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:42:46.680523Z","signature_b64":"0JU9qsVMKEUh3Ea41J/zE8n2DPjW09k0/9m+KeyXf2gIxd6LRZ6pSF0uJO+sf/P3KixCTlpoS/TzC/rCXyE8Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"11a0a0a76c475c62315f9df24366ea49c61f6c9c4a43fbfeba0e508dd2df8678","last_reissued_at":"2026-07-05T06:42:46.680007Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:42:46.680007Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Long-range Multimodal Pretraining for Movie Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dawit Mureja Argaw, Fabian Caba Heilbron, In So Kweon, Joon-Young Lee, Markus Woodson","submitted_at":"2023-08-18T18:52:59Z","abstract_excerpt":"Learning computer vision models from (and for) movies has a long-standing history. While great progress has been attained, there is still a need for a pretrained multimodal model that can perform well in the ever-growing set of movie understanding tasks the community has been establishing. In this work, we introduce Long-range Multimodal Pretraining, a strategy, and a model that leverages movie data to train transferable multimodal and cross-modal encoders. Our key idea is to learn from all modalities in a movie by observing and extracting relationships over a long-range. After pretraining, we"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.09775","kind":"arxiv","version":1},"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/2308.09775/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":"2308.09775","created_at":"2026-07-05T06:42:46.680079+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.09775v1","created_at":"2026-07-05T06:42:46.680079+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.09775","created_at":"2026-07-05T06:42:46.680079+00:00"},{"alias_kind":"pith_short_12","alias_value":"CGQKBJ3MI5OG","created_at":"2026-07-05T06:42:46.680079+00:00"},{"alias_kind":"pith_short_16","alias_value":"CGQKBJ3MI5OGEMK7","created_at":"2026-07-05T06:42:46.680079+00:00"},{"alias_kind":"pith_short_8","alias_value":"CGQKBJ3M","created_at":"2026-07-05T06:42:46.680079+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CGQKBJ3MI5OGEMK7TXZEGZXKJH","json":"https://pith.science/pith/CGQKBJ3MI5OGEMK7TXZEGZXKJH.json","graph_json":"https://pith.science/api/pith-number/CGQKBJ3MI5OGEMK7TXZEGZXKJH/graph.json","events_json":"https://pith.science/api/pith-number/CGQKBJ3MI5OGEMK7TXZEGZXKJH/events.json","paper":"https://pith.science/paper/CGQKBJ3M"},"agent_actions":{"view_html":"https://pith.science/pith/CGQKBJ3MI5OGEMK7TXZEGZXKJH","download_json":"https://pith.science/pith/CGQKBJ3MI5OGEMK7TXZEGZXKJH.json","view_paper":"https://pith.science/paper/CGQKBJ3M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.09775&json=true","fetch_graph":"https://pith.science/api/pith-number/CGQKBJ3MI5OGEMK7TXZEGZXKJH/graph.json","fetch_events":"https://pith.science/api/pith-number/CGQKBJ3MI5OGEMK7TXZEGZXKJH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CGQKBJ3MI5OGEMK7TXZEGZXKJH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CGQKBJ3MI5OGEMK7TXZEGZXKJH/action/storage_attestation","attest_author":"https://pith.science/pith/CGQKBJ3MI5OGEMK7TXZEGZXKJH/action/author_attestation","sign_citation":"https://pith.science/pith/CGQKBJ3MI5OGEMK7TXZEGZXKJH/action/citation_signature","submit_replication":"https://pith.science/pith/CGQKBJ3MI5OGEMK7TXZEGZXKJH/action/replication_record"}},"created_at":"2026-07-05T06:42:46.680079+00:00","updated_at":"2026-07-05T06:42:46.680079+00:00"}