{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:YR3YA4UKMHSUZLUFP2NPJCFOEK","short_pith_number":"pith:YR3YA4UK","schema_version":"1.0","canonical_sha256":"c47780728a61e54cae857e9af488ae22a8720955f62287492c8e42d35e6b94a1","source":{"kind":"arxiv","id":"2211.09529","version":1},"attestation_state":"computed","paper":{"title":"InternVideo-Ego4D: A Pack of Champion Solutions to Ego4D Challenges","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bingkun Huang, Guo Chen, Hongjie Zhang, Jiahao Wang, Jiashuo Yu, Junting Pan, Kunchang Li, Limin Wang, Sen Xing, Tong Lu, Yali Wang, Yifei Huang, Yi Liu, Yinan He, Yin-Dong Zheng, Yi Wang, Yizhuo Li, Yu Qiao, Zhe Chen, Zhiyu Zhao, Zun Wang","submitted_at":"2022-11-17T13:45:06Z","abstract_excerpt":"In this report, we present our champion solutions to five tracks at Ego4D challenge. We leverage our developed InternVideo, a video foundation model, for five Ego4D tasks, including Moment Queries, Natural Language Queries, Future Hand Prediction, State Change Object Detection, and Short-term Object Interaction Anticipation. InternVideo-Ego4D is an effective paradigm to adapt the strong foundation model to the downstream ego-centric video understanding tasks with simple head designs. In these five tasks, the performance of InternVideo-Ego4D comprehensively surpasses the baseline methods and th"},"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":"2211.09529","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-11-17T13:45:06Z","cross_cats_sorted":[],"title_canon_sha256":"0251aa4efb84dd79c1ae23f192853b07c5ffbf6d8bd28e90d373998f436972de","abstract_canon_sha256":"7fa3e68006900a6a1305d820a305a49c9d132195f77a3b9e4370dcf77638b15b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:17:03.242717Z","signature_b64":"dKBf2VTcUGHivfwfz3ZTVUcjgjIh/CwloXiMN+ivbGJlk+emBAtfhnIW4vQ+YgOfnA/ovcD9Ohoc/xHC72XnBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c47780728a61e54cae857e9af488ae22a8720955f62287492c8e42d35e6b94a1","last_reissued_at":"2026-07-05T05:17:03.242285Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:17:03.242285Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"InternVideo-Ego4D: A Pack of Champion Solutions to Ego4D Challenges","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bingkun Huang, Guo Chen, Hongjie Zhang, Jiahao Wang, Jiashuo Yu, Junting Pan, Kunchang Li, Limin Wang, Sen Xing, Tong Lu, Yali Wang, Yifei Huang, Yi Liu, Yinan He, Yin-Dong Zheng, Yi Wang, Yizhuo Li, Yu Qiao, Zhe Chen, Zhiyu Zhao, Zun Wang","submitted_at":"2022-11-17T13:45:06Z","abstract_excerpt":"In this report, we present our champion solutions to five tracks at Ego4D challenge. We leverage our developed InternVideo, a video foundation model, for five Ego4D tasks, including Moment Queries, Natural Language Queries, Future Hand Prediction, State Change Object Detection, and Short-term Object Interaction Anticipation. InternVideo-Ego4D is an effective paradigm to adapt the strong foundation model to the downstream ego-centric video understanding tasks with simple head designs. In these five tasks, the performance of InternVideo-Ego4D comprehensively surpasses the baseline methods and th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.09529","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/2211.09529/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":"2211.09529","created_at":"2026-07-05T05:17:03.242361+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.09529v1","created_at":"2026-07-05T05:17:03.242361+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.09529","created_at":"2026-07-05T05:17:03.242361+00:00"},{"alias_kind":"pith_short_12","alias_value":"YR3YA4UKMHSU","created_at":"2026-07-05T05:17:03.242361+00:00"},{"alias_kind":"pith_short_16","alias_value":"YR3YA4UKMHSUZLUF","created_at":"2026-07-05T05:17:03.242361+00:00"},{"alias_kind":"pith_short_8","alias_value":"YR3YA4UK","created_at":"2026-07-05T05:17:03.242361+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2212.03191","citing_title":"InternVideo: General Video Foundation Models via Generative and Discriminative Learning","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2307.06942","citing_title":"InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2305.06355","citing_title":"VideoChat: Chat-Centric Video Understanding","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YR3YA4UKMHSUZLUFP2NPJCFOEK","json":"https://pith.science/pith/YR3YA4UKMHSUZLUFP2NPJCFOEK.json","graph_json":"https://pith.science/api/pith-number/YR3YA4UKMHSUZLUFP2NPJCFOEK/graph.json","events_json":"https://pith.science/api/pith-number/YR3YA4UKMHSUZLUFP2NPJCFOEK/events.json","paper":"https://pith.science/paper/YR3YA4UK"},"agent_actions":{"view_html":"https://pith.science/pith/YR3YA4UKMHSUZLUFP2NPJCFOEK","download_json":"https://pith.science/pith/YR3YA4UKMHSUZLUFP2NPJCFOEK.json","view_paper":"https://pith.science/paper/YR3YA4UK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.09529&json=true","fetch_graph":"https://pith.science/api/pith-number/YR3YA4UKMHSUZLUFP2NPJCFOEK/graph.json","fetch_events":"https://pith.science/api/pith-number/YR3YA4UKMHSUZLUFP2NPJCFOEK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YR3YA4UKMHSUZLUFP2NPJCFOEK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YR3YA4UKMHSUZLUFP2NPJCFOEK/action/storage_attestation","attest_author":"https://pith.science/pith/YR3YA4UKMHSUZLUFP2NPJCFOEK/action/author_attestation","sign_citation":"https://pith.science/pith/YR3YA4UKMHSUZLUFP2NPJCFOEK/action/citation_signature","submit_replication":"https://pith.science/pith/YR3YA4UKMHSUZLUFP2NPJCFOEK/action/replication_record"}},"created_at":"2026-07-05T05:17:03.242361+00:00","updated_at":"2026-07-05T05:17:03.242361+00:00"}