{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:6UUTNNDMYYPNQOFDBZKJZCDW2N","short_pith_number":"pith:6UUTNNDM","schema_version":"1.0","canonical_sha256":"f52936b46cc61ed838a30e549c8876d34120dd18cec32bb6cb014b1e23672096","source":{"kind":"arxiv","id":"2311.10873","version":2},"attestation_state":"computed","paper":{"title":"Multi-entity Video Transformers for Fine-Grained Video Representation Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abhinav Shrivastava, Kai Sheng Tai, Keyur Muzumdar, Matthew Walmer, Rose Kanjirathinkal, Taipeng Tian","submitted_at":"2023-11-17T21:23:12Z","abstract_excerpt":"The area of temporally fine-grained video representation learning focuses on generating frame-by-frame representations for temporally dense tasks, such as fine-grained action phase classification and frame retrieval. In this work, we advance the state-of-the-art for self-supervised models in this area by re-examining the design of transformer architectures for video representation learning. A key aspect of our approach is the improved sharing of scene information in the temporal pipeline by representing multiple salient entities per frame. Prior works use late-fusion architectures that reduce "},"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":"2311.10873","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-17T21:23:12Z","cross_cats_sorted":[],"title_canon_sha256":"66d06a82dfc551273a85263670c3c5eb417eab679c35bae0592d0a1b3b292ec2","abstract_canon_sha256":"c1a226a31d549559cd0013948d8508a9d540170832ebf4d21f226ab55b5a4afa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:24:59.947513Z","signature_b64":"/igZkOgjLmUbe9dTCERH2oVbYnrlUiYIjW5Bubk7Q8EoIvZ6XDfPnZyTSsFDbNuyLX+8AjSKtRrB/TwYoKWvCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f52936b46cc61ed838a30e549c8876d34120dd18cec32bb6cb014b1e23672096","last_reissued_at":"2026-07-05T11:24:59.947159Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:24:59.947159Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-entity Video Transformers for Fine-Grained Video Representation Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abhinav Shrivastava, Kai Sheng Tai, Keyur Muzumdar, Matthew Walmer, Rose Kanjirathinkal, Taipeng Tian","submitted_at":"2023-11-17T21:23:12Z","abstract_excerpt":"The area of temporally fine-grained video representation learning focuses on generating frame-by-frame representations for temporally dense tasks, such as fine-grained action phase classification and frame retrieval. In this work, we advance the state-of-the-art for self-supervised models in this area by re-examining the design of transformer architectures for video representation learning. A key aspect of our approach is the improved sharing of scene information in the temporal pipeline by representing multiple salient entities per frame. Prior works use late-fusion architectures that reduce "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.10873","kind":"arxiv","version":2},"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/2311.10873/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":"2311.10873","created_at":"2026-07-05T11:24:59.947216+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.10873v2","created_at":"2026-07-05T11:24:59.947216+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.10873","created_at":"2026-07-05T11:24:59.947216+00:00"},{"alias_kind":"pith_short_12","alias_value":"6UUTNNDMYYPN","created_at":"2026-07-05T11:24:59.947216+00:00"},{"alias_kind":"pith_short_16","alias_value":"6UUTNNDMYYPNQOFD","created_at":"2026-07-05T11:24:59.947216+00:00"},{"alias_kind":"pith_short_8","alias_value":"6UUTNNDM","created_at":"2026-07-05T11:24:59.947216+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/6UUTNNDMYYPNQOFDBZKJZCDW2N","json":"https://pith.science/pith/6UUTNNDMYYPNQOFDBZKJZCDW2N.json","graph_json":"https://pith.science/api/pith-number/6UUTNNDMYYPNQOFDBZKJZCDW2N/graph.json","events_json":"https://pith.science/api/pith-number/6UUTNNDMYYPNQOFDBZKJZCDW2N/events.json","paper":"https://pith.science/paper/6UUTNNDM"},"agent_actions":{"view_html":"https://pith.science/pith/6UUTNNDMYYPNQOFDBZKJZCDW2N","download_json":"https://pith.science/pith/6UUTNNDMYYPNQOFDBZKJZCDW2N.json","view_paper":"https://pith.science/paper/6UUTNNDM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.10873&json=true","fetch_graph":"https://pith.science/api/pith-number/6UUTNNDMYYPNQOFDBZKJZCDW2N/graph.json","fetch_events":"https://pith.science/api/pith-number/6UUTNNDMYYPNQOFDBZKJZCDW2N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6UUTNNDMYYPNQOFDBZKJZCDW2N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6UUTNNDMYYPNQOFDBZKJZCDW2N/action/storage_attestation","attest_author":"https://pith.science/pith/6UUTNNDMYYPNQOFDBZKJZCDW2N/action/author_attestation","sign_citation":"https://pith.science/pith/6UUTNNDMYYPNQOFDBZKJZCDW2N/action/citation_signature","submit_replication":"https://pith.science/pith/6UUTNNDMYYPNQOFDBZKJZCDW2N/action/replication_record"}},"created_at":"2026-07-05T11:24:59.947216+00:00","updated_at":"2026-07-05T11:24:59.947216+00:00"}