{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:SVZHIJD6R6CRH2PXC3ZXWWJWF4","short_pith_number":"pith:SVZHIJD6","schema_version":"1.0","canonical_sha256":"957274247e8f8513e9f716f37b59362f0b9525064b41cb65fe4b1467a30ae16b","source":{"kind":"arxiv","id":"2207.01334","version":2},"attestation_state":"computed","paper":{"title":"Egocentric Video-Language Pretraining @ EPIC-KITCHENS-100 Multi-Instance Retrieval Challenge 2022","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alex Jinpeng Wang, Chengfei Cai, Eric Zhongcong Xu, Hongfa Wang, Kevin Qinghong Lin, Mike Zheng Shou, Rongcheng Tu, Rui Yan, Weijie Kong, Wei Liu, Wenzhe Zhao, Yanru Zhu","submitted_at":"2022-07-04T11:32:48Z","abstract_excerpt":"In this report, we propose a video-language pretraining (VLP) based solution \\cite{kevin2022egovlp} for the EPIC-KITCHENS-100 Multi-Instance Retrieval (MIR) challenge. Especially, we exploit the recently released Ego4D dataset \\cite{grauman2021ego4d} to pioneer Egocentric VLP from pretraining dataset, pretraining objective, and development set. Based on the above three designs, we develop a pretrained video-language model that is able to transfer its egocentric video-text representation to MIR benchmark. Furthermore, we devise an adaptive multi-instance max-margin loss to effectively fine-tune"},"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":"2207.01334","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-07-04T11:32:48Z","cross_cats_sorted":[],"title_canon_sha256":"9a93531011b448609469e35436b2a67292f34f0b75cd445f087a4348d56f9cb7","abstract_canon_sha256":"9a11e793a4a6fa3ba2fd3b29ad25b9d9a5daf8ca5df4869864c7a1f7d3b157f4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:45:49.497651Z","signature_b64":"RvpDF8725kllZGWR9PjMSMzaDhqIr2tvuSCnu/9bZpGwliiv9CvXFB3OrNUk0fEux5AOqLHfHoSAA1pcmsmzBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"957274247e8f8513e9f716f37b59362f0b9525064b41cb65fe4b1467a30ae16b","last_reissued_at":"2026-07-05T04:45:49.497209Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:45:49.497209Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Egocentric Video-Language Pretraining @ EPIC-KITCHENS-100 Multi-Instance Retrieval Challenge 2022","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alex Jinpeng Wang, Chengfei Cai, Eric Zhongcong Xu, Hongfa Wang, Kevin Qinghong Lin, Mike Zheng Shou, Rongcheng Tu, Rui Yan, Weijie Kong, Wei Liu, Wenzhe Zhao, Yanru Zhu","submitted_at":"2022-07-04T11:32:48Z","abstract_excerpt":"In this report, we propose a video-language pretraining (VLP) based solution \\cite{kevin2022egovlp} for the EPIC-KITCHENS-100 Multi-Instance Retrieval (MIR) challenge. Especially, we exploit the recently released Ego4D dataset \\cite{grauman2021ego4d} to pioneer Egocentric VLP from pretraining dataset, pretraining objective, and development set. Based on the above three designs, we develop a pretrained video-language model that is able to transfer its egocentric video-text representation to MIR benchmark. Furthermore, we devise an adaptive multi-instance max-margin loss to effectively fine-tune"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.01334","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/2207.01334/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":"2207.01334","created_at":"2026-07-05T04:45:49.497265+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.01334v2","created_at":"2026-07-05T04:45:49.497265+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.01334","created_at":"2026-07-05T04:45:49.497265+00:00"},{"alias_kind":"pith_short_12","alias_value":"SVZHIJD6R6CR","created_at":"2026-07-05T04:45:49.497265+00:00"},{"alias_kind":"pith_short_16","alias_value":"SVZHIJD6R6CRH2PX","created_at":"2026-07-05T04:45:49.497265+00:00"},{"alias_kind":"pith_short_8","alias_value":"SVZHIJD6","created_at":"2026-07-05T04:45:49.497265+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.14356","citing_title":"EVA02-AT: Egocentric Video-Language Understanding with Spatial-Temporal Rotary Positional Embeddings and Symmetric Optimization","ref_index":43,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SVZHIJD6R6CRH2PXC3ZXWWJWF4","json":"https://pith.science/pith/SVZHIJD6R6CRH2PXC3ZXWWJWF4.json","graph_json":"https://pith.science/api/pith-number/SVZHIJD6R6CRH2PXC3ZXWWJWF4/graph.json","events_json":"https://pith.science/api/pith-number/SVZHIJD6R6CRH2PXC3ZXWWJWF4/events.json","paper":"https://pith.science/paper/SVZHIJD6"},"agent_actions":{"view_html":"https://pith.science/pith/SVZHIJD6R6CRH2PXC3ZXWWJWF4","download_json":"https://pith.science/pith/SVZHIJD6R6CRH2PXC3ZXWWJWF4.json","view_paper":"https://pith.science/paper/SVZHIJD6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.01334&json=true","fetch_graph":"https://pith.science/api/pith-number/SVZHIJD6R6CRH2PXC3ZXWWJWF4/graph.json","fetch_events":"https://pith.science/api/pith-number/SVZHIJD6R6CRH2PXC3ZXWWJWF4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SVZHIJD6R6CRH2PXC3ZXWWJWF4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SVZHIJD6R6CRH2PXC3ZXWWJWF4/action/storage_attestation","attest_author":"https://pith.science/pith/SVZHIJD6R6CRH2PXC3ZXWWJWF4/action/author_attestation","sign_citation":"https://pith.science/pith/SVZHIJD6R6CRH2PXC3ZXWWJWF4/action/citation_signature","submit_replication":"https://pith.science/pith/SVZHIJD6R6CRH2PXC3ZXWWJWF4/action/replication_record"}},"created_at":"2026-07-05T04:45:49.497265+00:00","updated_at":"2026-07-05T04:45:49.497265+00:00"}