{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:7Q6JMS5ZPL6OTQOKXQNVWL6CGG","short_pith_number":"pith:7Q6JMS5Z","schema_version":"1.0","canonical_sha256":"fc3c964bb97afce9c1cabc1b5b2fc23198ef57b10a083303984a2ad17c18512e","source":{"kind":"arxiv","id":"2004.05573","version":1},"attestation_state":"computed","paper":{"title":"YouMakeup VQA Challenge: Towards Fine-grained Action Understanding in Domain-Specific Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Linli Yao, Ludan Ruan, Qin Jin, Shizhe Chen, Weiying Wang","submitted_at":"2020-04-12T09:25:36Z","abstract_excerpt":"The goal of the YouMakeup VQA Challenge 2020 is to provide a common benchmark for fine-grained action understanding in domain-specific videos e.g. makeup instructional videos. We propose two novel question-answering tasks to evaluate models' fine-grained action understanding abilities. The first task is \\textbf{Facial Image Ordering}, which aims to understand visual effects of different actions expressed in natural language to the facial object. The second task is \\textbf{Step Ordering}, which aims to measure cross-modal semantic alignments between untrimmed videos and multi-sentence texts. In"},"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":"2004.05573","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-04-12T09:25:36Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"68e3bb4e805a52bb967ffa5df46b214657478c870f41f00825ea146d24957f99","abstract_canon_sha256":"a885c110428464caf84ea75bd564fa1a03e7db88c739587f58fcf375bc04d097"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:54:38.860123Z","signature_b64":"imp41dn3L2OaND94krHZ7O1ULN+PMu3NXiMVeYJgc40TfLGIM45vOimf0SGoe6MHEplOukPQ9dWdA9ngL/QNAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc3c964bb97afce9c1cabc1b5b2fc23198ef57b10a083303984a2ad17c18512e","last_reissued_at":"2026-07-05T00:54:38.859778Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:54:38.859778Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"YouMakeup VQA Challenge: Towards Fine-grained Action Understanding in Domain-Specific Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Linli Yao, Ludan Ruan, Qin Jin, Shizhe Chen, Weiying Wang","submitted_at":"2020-04-12T09:25:36Z","abstract_excerpt":"The goal of the YouMakeup VQA Challenge 2020 is to provide a common benchmark for fine-grained action understanding in domain-specific videos e.g. makeup instructional videos. We propose two novel question-answering tasks to evaluate models' fine-grained action understanding abilities. The first task is \\textbf{Facial Image Ordering}, which aims to understand visual effects of different actions expressed in natural language to the facial object. The second task is \\textbf{Step Ordering}, which aims to measure cross-modal semantic alignments between untrimmed videos and multi-sentence texts. In"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.05573","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/2004.05573/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":"2004.05573","created_at":"2026-07-05T00:54:38.859840+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.05573v1","created_at":"2026-07-05T00:54:38.859840+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.05573","created_at":"2026-07-05T00:54:38.859840+00:00"},{"alias_kind":"pith_short_12","alias_value":"7Q6JMS5ZPL6O","created_at":"2026-07-05T00:54:38.859840+00:00"},{"alias_kind":"pith_short_16","alias_value":"7Q6JMS5ZPL6OTQOK","created_at":"2026-07-05T00:54:38.859840+00:00"},{"alias_kind":"pith_short_8","alias_value":"7Q6JMS5Z","created_at":"2026-07-05T00:54:38.859840+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/7Q6JMS5ZPL6OTQOKXQNVWL6CGG","json":"https://pith.science/pith/7Q6JMS5ZPL6OTQOKXQNVWL6CGG.json","graph_json":"https://pith.science/api/pith-number/7Q6JMS5ZPL6OTQOKXQNVWL6CGG/graph.json","events_json":"https://pith.science/api/pith-number/7Q6JMS5ZPL6OTQOKXQNVWL6CGG/events.json","paper":"https://pith.science/paper/7Q6JMS5Z"},"agent_actions":{"view_html":"https://pith.science/pith/7Q6JMS5ZPL6OTQOKXQNVWL6CGG","download_json":"https://pith.science/pith/7Q6JMS5ZPL6OTQOKXQNVWL6CGG.json","view_paper":"https://pith.science/paper/7Q6JMS5Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.05573&json=true","fetch_graph":"https://pith.science/api/pith-number/7Q6JMS5ZPL6OTQOKXQNVWL6CGG/graph.json","fetch_events":"https://pith.science/api/pith-number/7Q6JMS5ZPL6OTQOKXQNVWL6CGG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7Q6JMS5ZPL6OTQOKXQNVWL6CGG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7Q6JMS5ZPL6OTQOKXQNVWL6CGG/action/storage_attestation","attest_author":"https://pith.science/pith/7Q6JMS5ZPL6OTQOKXQNVWL6CGG/action/author_attestation","sign_citation":"https://pith.science/pith/7Q6JMS5ZPL6OTQOKXQNVWL6CGG/action/citation_signature","submit_replication":"https://pith.science/pith/7Q6JMS5ZPL6OTQOKXQNVWL6CGG/action/replication_record"}},"created_at":"2026-07-05T00:54:38.859840+00:00","updated_at":"2026-07-05T00:54:38.859840+00:00"}