{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:M2AWXZV5A4GDASSSABPRZMFVV4","short_pith_number":"pith:M2AWXZV5","schema_version":"1.0","canonical_sha256":"66816be6bd070c304a52005f1cb0b5af3fb14dbd2ab03a68ec5416c865dffb88","source":{"kind":"arxiv","id":"2110.06476","version":1},"attestation_state":"computed","paper":{"title":"Winning the ICCV'2021 VALUE Challenge: Task-aware Ensemble and Transfer Learning with Visual Concepts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Eun-Sol Kim, Gunsoo Han, Jonghwan Mun, Kyoung-Woon On, Minchul Shin, Woo-Young Kang","submitted_at":"2021-10-13T03:50:07Z","abstract_excerpt":"The VALUE (Video-And-Language Understanding Evaluation) benchmark is newly introduced to evaluate and analyze multi-modal representation learning algorithms on three video-and-language tasks: Retrieval, QA, and Captioning. The main objective of the VALUE challenge is to train a task-agnostic model that is simultaneously applicable for various tasks with different characteristics. This technical report describes our winning strategies for the VALUE challenge: 1) single model optimization, 2) transfer learning with visual concepts, and 3) task-aware ensemble. The first and third strategies are d"},"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":"2110.06476","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-10-13T03:50:07Z","cross_cats_sorted":[],"title_canon_sha256":"77a8a8afac5d28c0076973e2b09d645f2ffd41101ffe5583455942b2d30d2a9d","abstract_canon_sha256":"2bc759c62123890f9482b794f072a99663829c3fdafc505cbc6f6b24e2e1a7df"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:22:26.383616Z","signature_b64":"7NedO9nmaOcx1Ko2mQY0r8oiuAU+JaCbvmMbjtN7jBWaw8Blt63COCTV2cfHgoxkl6N37pEYTU2qjZeVatsIBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"66816be6bd070c304a52005f1cb0b5af3fb14dbd2ab03a68ec5416c865dffb88","last_reissued_at":"2026-07-05T03:22:26.383195Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:22:26.383195Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Winning the ICCV'2021 VALUE Challenge: Task-aware Ensemble and Transfer Learning with Visual Concepts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Eun-Sol Kim, Gunsoo Han, Jonghwan Mun, Kyoung-Woon On, Minchul Shin, Woo-Young Kang","submitted_at":"2021-10-13T03:50:07Z","abstract_excerpt":"The VALUE (Video-And-Language Understanding Evaluation) benchmark is newly introduced to evaluate and analyze multi-modal representation learning algorithms on three video-and-language tasks: Retrieval, QA, and Captioning. The main objective of the VALUE challenge is to train a task-agnostic model that is simultaneously applicable for various tasks with different characteristics. This technical report describes our winning strategies for the VALUE challenge: 1) single model optimization, 2) transfer learning with visual concepts, and 3) task-aware ensemble. The first and third strategies are d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.06476","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/2110.06476/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":"2110.06476","created_at":"2026-07-05T03:22:26.383252+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.06476v1","created_at":"2026-07-05T03:22:26.383252+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.06476","created_at":"2026-07-05T03:22:26.383252+00:00"},{"alias_kind":"pith_short_12","alias_value":"M2AWXZV5A4GD","created_at":"2026-07-05T03:22:26.383252+00:00"},{"alias_kind":"pith_short_16","alias_value":"M2AWXZV5A4GDASSS","created_at":"2026-07-05T03:22:26.383252+00:00"},{"alias_kind":"pith_short_8","alias_value":"M2AWXZV5","created_at":"2026-07-05T03:22:26.383252+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/M2AWXZV5A4GDASSSABPRZMFVV4","json":"https://pith.science/pith/M2AWXZV5A4GDASSSABPRZMFVV4.json","graph_json":"https://pith.science/api/pith-number/M2AWXZV5A4GDASSSABPRZMFVV4/graph.json","events_json":"https://pith.science/api/pith-number/M2AWXZV5A4GDASSSABPRZMFVV4/events.json","paper":"https://pith.science/paper/M2AWXZV5"},"agent_actions":{"view_html":"https://pith.science/pith/M2AWXZV5A4GDASSSABPRZMFVV4","download_json":"https://pith.science/pith/M2AWXZV5A4GDASSSABPRZMFVV4.json","view_paper":"https://pith.science/paper/M2AWXZV5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.06476&json=true","fetch_graph":"https://pith.science/api/pith-number/M2AWXZV5A4GDASSSABPRZMFVV4/graph.json","fetch_events":"https://pith.science/api/pith-number/M2AWXZV5A4GDASSSABPRZMFVV4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M2AWXZV5A4GDASSSABPRZMFVV4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M2AWXZV5A4GDASSSABPRZMFVV4/action/storage_attestation","attest_author":"https://pith.science/pith/M2AWXZV5A4GDASSSABPRZMFVV4/action/author_attestation","sign_citation":"https://pith.science/pith/M2AWXZV5A4GDASSSABPRZMFVV4/action/citation_signature","submit_replication":"https://pith.science/pith/M2AWXZV5A4GDASSSABPRZMFVV4/action/replication_record"}},"created_at":"2026-07-05T03:22:26.383252+00:00","updated_at":"2026-07-05T03:22:26.383252+00:00"}