{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:7LL2BV7QP5GTH7XJ7WURO3G23I","short_pith_number":"pith:7LL2BV7Q","schema_version":"1.0","canonical_sha256":"fad7a0d7f07f4d33fee9fda9176cdada20a30eafc872775effc4b5e19845c331","source":{"kind":"arxiv","id":"1708.06495","version":2},"attestation_state":"computed","paper":{"title":"Towards Automatic Construction of Diverse, High-quality Image Dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Dongxiang Zhang, Fan Zhu, Fumin Shen, Heng-Tao Shen, Jian Zhang, Li Liu, Yazhou Yao","submitted_at":"2017-08-22T04:36:12Z","abstract_excerpt":"The availability of labeled image datasets has been shown critical for high-level image understanding, which continuously drives the progress of feature designing and models developing. However, constructing labeled image datasets is laborious and monotonous. To eliminate manual annotation, in this work, we propose a novel image dataset construction framework by employing multiple textual queries. We aim at collecting diverse and accurate images for given queries from the Web. Specifically, we formulate noisy textual queries removing and noisy images filtering as a multi-view and multi-instanc"},"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":"1708.06495","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-08-22T04:36:12Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"e57e0086e2fe5be2099326f8f49f72f1d6ecd455f68adcb11a0c0d47e39e0570","abstract_canon_sha256":"4461322b9580481e1e1b49566b6c41399a88018784eb719904aa23d6d80880d5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:52:24.674298Z","signature_b64":"kt9u0RgFni09oyL65gtH82751fFl63HmPxwoSLQGpYoAOL/YFEVWULsrwmHzhA1atJHgapL0ziRh4mtRmI5JAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fad7a0d7f07f4d33fee9fda9176cdada20a30eafc872775effc4b5e19845c331","last_reissued_at":"2026-05-17T23:52:24.673766Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:52:24.673766Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Automatic Construction of Diverse, High-quality Image Dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Dongxiang Zhang, Fan Zhu, Fumin Shen, Heng-Tao Shen, Jian Zhang, Li Liu, Yazhou Yao","submitted_at":"2017-08-22T04:36:12Z","abstract_excerpt":"The availability of labeled image datasets has been shown critical for high-level image understanding, which continuously drives the progress of feature designing and models developing. However, constructing labeled image datasets is laborious and monotonous. To eliminate manual annotation, in this work, we propose a novel image dataset construction framework by employing multiple textual queries. We aim at collecting diverse and accurate images for given queries from the Web. Specifically, we formulate noisy textual queries removing and noisy images filtering as a multi-view and multi-instanc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.06495","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":""},"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":"1708.06495","created_at":"2026-05-17T23:52:24.673845+00:00"},{"alias_kind":"arxiv_version","alias_value":"1708.06495v2","created_at":"2026-05-17T23:52:24.673845+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.06495","created_at":"2026-05-17T23:52:24.673845+00:00"},{"alias_kind":"pith_short_12","alias_value":"7LL2BV7QP5GT","created_at":"2026-05-18T12:31:05.417338+00:00"},{"alias_kind":"pith_short_16","alias_value":"7LL2BV7QP5GTH7XJ","created_at":"2026-05-18T12:31:05.417338+00:00"},{"alias_kind":"pith_short_8","alias_value":"7LL2BV7Q","created_at":"2026-05-18T12:31:05.417338+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/7LL2BV7QP5GTH7XJ7WURO3G23I","json":"https://pith.science/pith/7LL2BV7QP5GTH7XJ7WURO3G23I.json","graph_json":"https://pith.science/api/pith-number/7LL2BV7QP5GTH7XJ7WURO3G23I/graph.json","events_json":"https://pith.science/api/pith-number/7LL2BV7QP5GTH7XJ7WURO3G23I/events.json","paper":"https://pith.science/paper/7LL2BV7Q"},"agent_actions":{"view_html":"https://pith.science/pith/7LL2BV7QP5GTH7XJ7WURO3G23I","download_json":"https://pith.science/pith/7LL2BV7QP5GTH7XJ7WURO3G23I.json","view_paper":"https://pith.science/paper/7LL2BV7Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1708.06495&json=true","fetch_graph":"https://pith.science/api/pith-number/7LL2BV7QP5GTH7XJ7WURO3G23I/graph.json","fetch_events":"https://pith.science/api/pith-number/7LL2BV7QP5GTH7XJ7WURO3G23I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7LL2BV7QP5GTH7XJ7WURO3G23I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7LL2BV7QP5GTH7XJ7WURO3G23I/action/storage_attestation","attest_author":"https://pith.science/pith/7LL2BV7QP5GTH7XJ7WURO3G23I/action/author_attestation","sign_citation":"https://pith.science/pith/7LL2BV7QP5GTH7XJ7WURO3G23I/action/citation_signature","submit_replication":"https://pith.science/pith/7LL2BV7QP5GTH7XJ7WURO3G23I/action/replication_record"}},"created_at":"2026-05-17T23:52:24.673845+00:00","updated_at":"2026-05-17T23:52:24.673845+00:00"}