{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:5EMETKO762ZJ3U35IZYBFBO22L","short_pith_number":"pith:5EMETKO7","schema_version":"1.0","canonical_sha256":"e91849a9dff6b29dd37d46701285dad2d46d9c8570f755d0d5af1107d619570d","source":{"kind":"arxiv","id":"2103.13990","version":1},"attestation_state":"computed","paper":{"title":"More Photos are All You Need: Semi-Supervised Learning for Fine-Grained Sketch Based Image Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aneeshan Sain, Ayan Kumar Bhunia, Pinaki Nath Chowdhury, Tao Xiang, Yi-Zhe Song, Yongxin Yang","submitted_at":"2021-03-25T17:27:08Z","abstract_excerpt":"A fundamental challenge faced by existing Fine-Grained Sketch-Based Image Retrieval (FG-SBIR) models is the data scarcity -- model performances are largely bottlenecked by the lack of sketch-photo pairs. Whilst the number of photos can be easily scaled, each corresponding sketch still needs to be individually produced. In this paper, we aim to mitigate such an upper-bound on sketch data, and study whether unlabelled photos alone (of which they are many) can be cultivated for performances gain. In particular, we introduce a novel semi-supervised framework for cross-modal retrieval that can addi"},"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":"2103.13990","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-03-25T17:27:08Z","cross_cats_sorted":[],"title_canon_sha256":"83b4af5326ffb0a14a9e9821a635ecb5f019adf7cd08c2ce17b96746a3a9f039","abstract_canon_sha256":"9303a7cef147818b6c65a8999ede31ebb25f501b0de4f8a668f1ed4273988291"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:26:24.465622Z","signature_b64":"EeeWK/Hm7sL6EyFufcXaFJd9EYkxsfHLLrXedvTrWPl0ogRI8Qh1OfREQMMjuQQIt6X9AV4jHeTlUjqMKs0GCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e91849a9dff6b29dd37d46701285dad2d46d9c8570f755d0d5af1107d619570d","last_reissued_at":"2026-07-05T02:26:24.465170Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:26:24.465170Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"More Photos are All You Need: Semi-Supervised Learning for Fine-Grained Sketch Based Image Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aneeshan Sain, Ayan Kumar Bhunia, Pinaki Nath Chowdhury, Tao Xiang, Yi-Zhe Song, Yongxin Yang","submitted_at":"2021-03-25T17:27:08Z","abstract_excerpt":"A fundamental challenge faced by existing Fine-Grained Sketch-Based Image Retrieval (FG-SBIR) models is the data scarcity -- model performances are largely bottlenecked by the lack of sketch-photo pairs. Whilst the number of photos can be easily scaled, each corresponding sketch still needs to be individually produced. In this paper, we aim to mitigate such an upper-bound on sketch data, and study whether unlabelled photos alone (of which they are many) can be cultivated for performances gain. In particular, we introduce a novel semi-supervised framework for cross-modal retrieval that can addi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.13990","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/2103.13990/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":"2103.13990","created_at":"2026-07-05T02:26:24.465229+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.13990v1","created_at":"2026-07-05T02:26:24.465229+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.13990","created_at":"2026-07-05T02:26:24.465229+00:00"},{"alias_kind":"pith_short_12","alias_value":"5EMETKO762ZJ","created_at":"2026-07-05T02:26:24.465229+00:00"},{"alias_kind":"pith_short_16","alias_value":"5EMETKO762ZJ3U35","created_at":"2026-07-05T02:26:24.465229+00:00"},{"alias_kind":"pith_short_8","alias_value":"5EMETKO7","created_at":"2026-07-05T02:26:24.465229+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/5EMETKO762ZJ3U35IZYBFBO22L","json":"https://pith.science/pith/5EMETKO762ZJ3U35IZYBFBO22L.json","graph_json":"https://pith.science/api/pith-number/5EMETKO762ZJ3U35IZYBFBO22L/graph.json","events_json":"https://pith.science/api/pith-number/5EMETKO762ZJ3U35IZYBFBO22L/events.json","paper":"https://pith.science/paper/5EMETKO7"},"agent_actions":{"view_html":"https://pith.science/pith/5EMETKO762ZJ3U35IZYBFBO22L","download_json":"https://pith.science/pith/5EMETKO762ZJ3U35IZYBFBO22L.json","view_paper":"https://pith.science/paper/5EMETKO7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.13990&json=true","fetch_graph":"https://pith.science/api/pith-number/5EMETKO762ZJ3U35IZYBFBO22L/graph.json","fetch_events":"https://pith.science/api/pith-number/5EMETKO762ZJ3U35IZYBFBO22L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5EMETKO762ZJ3U35IZYBFBO22L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5EMETKO762ZJ3U35IZYBFBO22L/action/storage_attestation","attest_author":"https://pith.science/pith/5EMETKO762ZJ3U35IZYBFBO22L/action/author_attestation","sign_citation":"https://pith.science/pith/5EMETKO762ZJ3U35IZYBFBO22L/action/citation_signature","submit_replication":"https://pith.science/pith/5EMETKO762ZJ3U35IZYBFBO22L/action/replication_record"}},"created_at":"2026-07-05T02:26:24.465229+00:00","updated_at":"2026-07-05T02:26:24.465229+00:00"}