{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:5ENFEVSK6RC2L7BR3FNDPJZFS7","short_pith_number":"pith:5ENFEVSK","schema_version":"1.0","canonical_sha256":"e91a52564af445a5fc31d95a37a72597f1918278be2b6581168f467dc79f863b","source":{"kind":"arxiv","id":"2307.12854","version":1},"attestation_state":"computed","paper":{"title":"Multiscale Video Pretraining for Long-Term Activity Forecasting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bryan A. Plummer, Karl Ridgeway, Kate Saenko, Lorenzo Torresani, Matthias De Lange, Michael Iuzzolino, Reuben Tan","submitted_at":"2023-07-24T14:55:15Z","abstract_excerpt":"Long-term activity forecasting is an especially challenging research problem because it requires understanding the temporal relationships between observed actions, as well as the variability and complexity of human activities. Despite relying on strong supervision via expensive human annotations, state-of-the-art forecasting approaches often generalize poorly to unseen data. To alleviate this issue, we propose Multiscale Video Pretraining (MVP), a novel self-supervised pretraining approach that learns robust representations for forecasting by learning to predict contextualized representations "},"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":"2307.12854","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-24T14:55:15Z","cross_cats_sorted":[],"title_canon_sha256":"3134db58f005a433b615490220fd71a12a6e2418656fe56fcbe34eac640ffa81","abstract_canon_sha256":"9ae2f903103ff718c8ae38ec6c57e022dea243a08d46c5e823e90509935dec11"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:33:59.503345Z","signature_b64":"mHEUF8Omvlj9LfVEpwllJyFnnDz4Su7KCRfFfaq7So0N9pXXdvGVrjzxnnwtNFMWRSS0WJVeiCLS+oYBHlpSCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e91a52564af445a5fc31d95a37a72597f1918278be2b6581168f467dc79f863b","last_reissued_at":"2026-07-05T06:33:59.502976Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:33:59.502976Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multiscale Video Pretraining for Long-Term Activity Forecasting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bryan A. Plummer, Karl Ridgeway, Kate Saenko, Lorenzo Torresani, Matthias De Lange, Michael Iuzzolino, Reuben Tan","submitted_at":"2023-07-24T14:55:15Z","abstract_excerpt":"Long-term activity forecasting is an especially challenging research problem because it requires understanding the temporal relationships between observed actions, as well as the variability and complexity of human activities. Despite relying on strong supervision via expensive human annotations, state-of-the-art forecasting approaches often generalize poorly to unseen data. To alleviate this issue, we propose Multiscale Video Pretraining (MVP), a novel self-supervised pretraining approach that learns robust representations for forecasting by learning to predict contextualized representations "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.12854","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/2307.12854/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":"2307.12854","created_at":"2026-07-05T06:33:59.503034+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.12854v1","created_at":"2026-07-05T06:33:59.503034+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.12854","created_at":"2026-07-05T06:33:59.503034+00:00"},{"alias_kind":"pith_short_12","alias_value":"5ENFEVSK6RC2","created_at":"2026-07-05T06:33:59.503034+00:00"},{"alias_kind":"pith_short_16","alias_value":"5ENFEVSK6RC2L7BR","created_at":"2026-07-05T06:33:59.503034+00:00"},{"alias_kind":"pith_short_8","alias_value":"5ENFEVSK","created_at":"2026-07-05T06:33:59.503034+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2309.17257","citing_title":"A Survey on Deep Learning Techniques for Action Anticipation","ref_index":137,"is_internal_anchor":false},{"citing_arxiv_id":"2404.08471","citing_title":"Revisiting Feature Prediction for Learning Visual Representations from Video","ref_index":276,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5ENFEVSK6RC2L7BR3FNDPJZFS7","json":"https://pith.science/pith/5ENFEVSK6RC2L7BR3FNDPJZFS7.json","graph_json":"https://pith.science/api/pith-number/5ENFEVSK6RC2L7BR3FNDPJZFS7/graph.json","events_json":"https://pith.science/api/pith-number/5ENFEVSK6RC2L7BR3FNDPJZFS7/events.json","paper":"https://pith.science/paper/5ENFEVSK"},"agent_actions":{"view_html":"https://pith.science/pith/5ENFEVSK6RC2L7BR3FNDPJZFS7","download_json":"https://pith.science/pith/5ENFEVSK6RC2L7BR3FNDPJZFS7.json","view_paper":"https://pith.science/paper/5ENFEVSK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.12854&json=true","fetch_graph":"https://pith.science/api/pith-number/5ENFEVSK6RC2L7BR3FNDPJZFS7/graph.json","fetch_events":"https://pith.science/api/pith-number/5ENFEVSK6RC2L7BR3FNDPJZFS7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5ENFEVSK6RC2L7BR3FNDPJZFS7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5ENFEVSK6RC2L7BR3FNDPJZFS7/action/storage_attestation","attest_author":"https://pith.science/pith/5ENFEVSK6RC2L7BR3FNDPJZFS7/action/author_attestation","sign_citation":"https://pith.science/pith/5ENFEVSK6RC2L7BR3FNDPJZFS7/action/citation_signature","submit_replication":"https://pith.science/pith/5ENFEVSK6RC2L7BR3FNDPJZFS7/action/replication_record"}},"created_at":"2026-07-05T06:33:59.503034+00:00","updated_at":"2026-07-05T06:33:59.503034+00:00"}