{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:X626QF6Y6GHMSKQAUM4YCJCPHV","short_pith_number":"pith:X626QF6Y","schema_version":"1.0","canonical_sha256":"bfb5e817d8f18ec92a00a33981244f3d5bf4d9dba9e2c4f39b33919009a556f1","source":{"kind":"arxiv","id":"2106.11841","version":1},"attestation_state":"computed","paper":{"title":"Domain-Smoothing Network for Zero-Shot Sketch-Based Image Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aming Wu, Cheng Deng, Hao Wang, Jiexi Yan, Zhipeng Wang","submitted_at":"2021-06-22T14:58:08Z","abstract_excerpt":"Zero-Shot Sketch-Based Image Retrieval (ZS-SBIR) is a novel cross-modal retrieval task, where abstract sketches are used as queries to retrieve natural images under zero-shot scenario. Most existing methods regard ZS-SBIR as a traditional classification problem and employ a cross-entropy or triplet-based loss to achieve retrieval, which neglect the problems of the domain gap between sketches and natural images and the large intra-class diversity in sketches. Toward this end, we propose a novel Domain-Smoothing Network (DSN) for ZS-SBIR. Specifically, a cross-modal contrastive method is propose"},"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":"2106.11841","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-22T14:58:08Z","cross_cats_sorted":[],"title_canon_sha256":"3ec92d48b59d451872ff39017d0a126e3d2c3f0a83dfdca92aa694841b48b6f5","abstract_canon_sha256":"b50853c110a68164c9fbda29a7ad9d7277358e6152eb8cfab56a5caa8863a491"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:51:33.604406Z","signature_b64":"VbRbuk7Bc+nB4YPwaxdBz3qM7EL7qFNFRkupGjPPD1GyfimA2/XE0NVVSgmt42OYHFDMFI095J5NyWmxkW9HAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bfb5e817d8f18ec92a00a33981244f3d5bf4d9dba9e2c4f39b33919009a556f1","last_reissued_at":"2026-07-05T02:51:33.603915Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:51:33.603915Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Domain-Smoothing Network for Zero-Shot Sketch-Based Image Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aming Wu, Cheng Deng, Hao Wang, Jiexi Yan, Zhipeng Wang","submitted_at":"2021-06-22T14:58:08Z","abstract_excerpt":"Zero-Shot Sketch-Based Image Retrieval (ZS-SBIR) is a novel cross-modal retrieval task, where abstract sketches are used as queries to retrieve natural images under zero-shot scenario. Most existing methods regard ZS-SBIR as a traditional classification problem and employ a cross-entropy or triplet-based loss to achieve retrieval, which neglect the problems of the domain gap between sketches and natural images and the large intra-class diversity in sketches. Toward this end, we propose a novel Domain-Smoothing Network (DSN) for ZS-SBIR. Specifically, a cross-modal contrastive method is propose"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.11841","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/2106.11841/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":"2106.11841","created_at":"2026-07-05T02:51:33.603979+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.11841v1","created_at":"2026-07-05T02:51:33.603979+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.11841","created_at":"2026-07-05T02:51:33.603979+00:00"},{"alias_kind":"pith_short_12","alias_value":"X626QF6Y6GHM","created_at":"2026-07-05T02:51:33.603979+00:00"},{"alias_kind":"pith_short_16","alias_value":"X626QF6Y6GHMSKQA","created_at":"2026-07-05T02:51:33.603979+00:00"},{"alias_kind":"pith_short_8","alias_value":"X626QF6Y","created_at":"2026-07-05T02:51:33.603979+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.10009","citing_title":"Hystar: Hypernetwork-driven Style-adaptive Retrieval via Dynamic SVD Modulation","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/X626QF6Y6GHMSKQAUM4YCJCPHV","json":"https://pith.science/pith/X626QF6Y6GHMSKQAUM4YCJCPHV.json","graph_json":"https://pith.science/api/pith-number/X626QF6Y6GHMSKQAUM4YCJCPHV/graph.json","events_json":"https://pith.science/api/pith-number/X626QF6Y6GHMSKQAUM4YCJCPHV/events.json","paper":"https://pith.science/paper/X626QF6Y"},"agent_actions":{"view_html":"https://pith.science/pith/X626QF6Y6GHMSKQAUM4YCJCPHV","download_json":"https://pith.science/pith/X626QF6Y6GHMSKQAUM4YCJCPHV.json","view_paper":"https://pith.science/paper/X626QF6Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.11841&json=true","fetch_graph":"https://pith.science/api/pith-number/X626QF6Y6GHMSKQAUM4YCJCPHV/graph.json","fetch_events":"https://pith.science/api/pith-number/X626QF6Y6GHMSKQAUM4YCJCPHV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X626QF6Y6GHMSKQAUM4YCJCPHV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X626QF6Y6GHMSKQAUM4YCJCPHV/action/storage_attestation","attest_author":"https://pith.science/pith/X626QF6Y6GHMSKQAUM4YCJCPHV/action/author_attestation","sign_citation":"https://pith.science/pith/X626QF6Y6GHMSKQAUM4YCJCPHV/action/citation_signature","submit_replication":"https://pith.science/pith/X626QF6Y6GHMSKQAUM4YCJCPHV/action/replication_record"}},"created_at":"2026-07-05T02:51:33.603979+00:00","updated_at":"2026-07-05T02:51:33.603979+00:00"}