{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:FVQKR2P6WAPUXII3KINHENZHWI","short_pith_number":"pith:FVQKR2P6","schema_version":"1.0","canonical_sha256":"2d60a8e9feb01f4ba11b521a723727b217b785253cfda343c2adda388382d15e","source":{"kind":"arxiv","id":"2207.00579","version":1},"attestation_state":"computed","paper":{"title":"Video + CLIP Baseline for Ego4D Long-term Action Anticipation","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Michael S. Ryoo, Srijan Das","submitted_at":"2022-07-01T17:57:28Z","abstract_excerpt":"In this report, we introduce our adaptation of image-text models for long-term action anticipation. Our Video + CLIP framework makes use of a large-scale pre-trained paired image-text model: CLIP and a video encoder Slowfast network. The CLIP embedding provides fine-grained understanding of objects relevant for an action whereas the slowfast network is responsible for modeling temporal information within a video clip of few frames. We show that the features obtained from both encoders are complementary to each other, thus outperforming the baseline on Ego4D for the task of long-term action ant"},"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":"2207.00579","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2022-07-01T17:57:28Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"eb3295ba597f3cb013954cf1e7161c2af7433fbafab1c42ba13f6a87fb35800a","abstract_canon_sha256":"517819361ca5a812ec648b256e8e116bf724001a25f396b0e62fc532c787bdfd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:36:44.696434Z","signature_b64":"/qqSZrlniPKgYghnRn1fF7/AWA4MwrZVvzf2yjuSoqcJH320jJr+12qJ8hsUx2HF4cWftk6ZoC5Z5yKGqP1YCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2d60a8e9feb01f4ba11b521a723727b217b785253cfda343c2adda388382d15e","last_reissued_at":"2026-07-05T04:36:44.695975Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:36:44.695975Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Video + CLIP Baseline for Ego4D Long-term Action Anticipation","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Michael S. Ryoo, Srijan Das","submitted_at":"2022-07-01T17:57:28Z","abstract_excerpt":"In this report, we introduce our adaptation of image-text models for long-term action anticipation. Our Video + CLIP framework makes use of a large-scale pre-trained paired image-text model: CLIP and a video encoder Slowfast network. The CLIP embedding provides fine-grained understanding of objects relevant for an action whereas the slowfast network is responsible for modeling temporal information within a video clip of few frames. We show that the features obtained from both encoders are complementary to each other, thus outperforming the baseline on Ego4D for the task of long-term action ant"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.00579","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/2207.00579/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":"2207.00579","created_at":"2026-07-05T04:36:44.696039+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.00579v1","created_at":"2026-07-05T04:36:44.696039+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.00579","created_at":"2026-07-05T04:36:44.696039+00:00"},{"alias_kind":"pith_short_12","alias_value":"FVQKR2P6WAPU","created_at":"2026-07-05T04:36:44.696039+00:00"},{"alias_kind":"pith_short_16","alias_value":"FVQKR2P6WAPUXII3","created_at":"2026-07-05T04:36:44.696039+00:00"},{"alias_kind":"pith_short_8","alias_value":"FVQKR2P6","created_at":"2026-07-05T04:36:44.696039+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.00374","citing_title":"Bidirectional Action Sequence Learning for Long-term Action Anticipation with Large Language Models","ref_index":4,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FVQKR2P6WAPUXII3KINHENZHWI","json":"https://pith.science/pith/FVQKR2P6WAPUXII3KINHENZHWI.json","graph_json":"https://pith.science/api/pith-number/FVQKR2P6WAPUXII3KINHENZHWI/graph.json","events_json":"https://pith.science/api/pith-number/FVQKR2P6WAPUXII3KINHENZHWI/events.json","paper":"https://pith.science/paper/FVQKR2P6"},"agent_actions":{"view_html":"https://pith.science/pith/FVQKR2P6WAPUXII3KINHENZHWI","download_json":"https://pith.science/pith/FVQKR2P6WAPUXII3KINHENZHWI.json","view_paper":"https://pith.science/paper/FVQKR2P6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.00579&json=true","fetch_graph":"https://pith.science/api/pith-number/FVQKR2P6WAPUXII3KINHENZHWI/graph.json","fetch_events":"https://pith.science/api/pith-number/FVQKR2P6WAPUXII3KINHENZHWI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FVQKR2P6WAPUXII3KINHENZHWI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FVQKR2P6WAPUXII3KINHENZHWI/action/storage_attestation","attest_author":"https://pith.science/pith/FVQKR2P6WAPUXII3KINHENZHWI/action/author_attestation","sign_citation":"https://pith.science/pith/FVQKR2P6WAPUXII3KINHENZHWI/action/citation_signature","submit_replication":"https://pith.science/pith/FVQKR2P6WAPUXII3KINHENZHWI/action/replication_record"}},"created_at":"2026-07-05T04:36:44.696039+00:00","updated_at":"2026-07-05T04:36:44.696039+00:00"}