{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CLIU7H63TJPMJIDUZ62MPUU3S6","short_pith_number":"pith:CLIU7H63","schema_version":"1.0","canonical_sha256":"12d14f9fdb9a5ec4a074cfb4c7d29b97b365b37e1f7332d2bba815479c27eed6","source":{"kind":"arxiv","id":"2407.16244","version":1},"attestation_state":"computed","paper":{"title":"HSVLT: Hierarchical Scale-Aware Vision-Language Transformer for Multi-Label Image Classification","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.MM"],"primary_cat":"cs.CV","authors_text":"Hongyi Wang, Lanfen Lin, Ruofeng Tong, Shiao Xie, Shuyi Ouyang, Yen-Wei Chen, Yingying Xu, Zhenjia Bai, Ziwei Niu","submitted_at":"2024-07-23T07:31:42Z","abstract_excerpt":"The task of multi-label image classification involves recognizing multiple objects within a single image. Considering both valuable semantic information contained in the labels and essential visual features presented in the image, tight visual-linguistic interactions play a vital role in improving classification performance. Moreover, given the potential variance in object size and appearance within a single image, attention to features of different scales can help to discover possible objects in the image. Recently, Transformer-based methods have achieved great success in multi-label image cl"},"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":"2407.16244","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-23T07:31:42Z","cross_cats_sorted":["cs.AI","cs.MM"],"title_canon_sha256":"b179bcda90bf06c4b52eb0ca4571ce3c08296c9f0031646d4bfcb6f8f8c2a5e1","abstract_canon_sha256":"b4773dcf9d6756ac3d6fc3e7b1d54433285119c51160cd4b6d489d886494d3ae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:47:30.258730Z","signature_b64":"NbMpdO50WHqleR0bwYhGRXENczDkRH6k2lAL0dxgWHkDmgtt9iTYFcP4F4CCHcKFGV+cTLMPJrcY65xxaH2sAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"12d14f9fdb9a5ec4a074cfb4c7d29b97b365b37e1f7332d2bba815479c27eed6","last_reissued_at":"2026-07-05T08:47:30.258374Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:47:30.258374Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HSVLT: Hierarchical Scale-Aware Vision-Language Transformer for Multi-Label Image Classification","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.MM"],"primary_cat":"cs.CV","authors_text":"Hongyi Wang, Lanfen Lin, Ruofeng Tong, Shiao Xie, Shuyi Ouyang, Yen-Wei Chen, Yingying Xu, Zhenjia Bai, Ziwei Niu","submitted_at":"2024-07-23T07:31:42Z","abstract_excerpt":"The task of multi-label image classification involves recognizing multiple objects within a single image. Considering both valuable semantic information contained in the labels and essential visual features presented in the image, tight visual-linguistic interactions play a vital role in improving classification performance. Moreover, given the potential variance in object size and appearance within a single image, attention to features of different scales can help to discover possible objects in the image. Recently, Transformer-based methods have achieved great success in multi-label image cl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.16244","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/2407.16244/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":"2407.16244","created_at":"2026-07-05T08:47:30.258430+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.16244v1","created_at":"2026-07-05T08:47:30.258430+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.16244","created_at":"2026-07-05T08:47:30.258430+00:00"},{"alias_kind":"pith_short_12","alias_value":"CLIU7H63TJPM","created_at":"2026-07-05T08:47:30.258430+00:00"},{"alias_kind":"pith_short_16","alias_value":"CLIU7H63TJPMJIDU","created_at":"2026-07-05T08:47:30.258430+00:00"},{"alias_kind":"pith_short_8","alias_value":"CLIU7H63","created_at":"2026-07-05T08:47:30.258430+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/CLIU7H63TJPMJIDUZ62MPUU3S6","json":"https://pith.science/pith/CLIU7H63TJPMJIDUZ62MPUU3S6.json","graph_json":"https://pith.science/api/pith-number/CLIU7H63TJPMJIDUZ62MPUU3S6/graph.json","events_json":"https://pith.science/api/pith-number/CLIU7H63TJPMJIDUZ62MPUU3S6/events.json","paper":"https://pith.science/paper/CLIU7H63"},"agent_actions":{"view_html":"https://pith.science/pith/CLIU7H63TJPMJIDUZ62MPUU3S6","download_json":"https://pith.science/pith/CLIU7H63TJPMJIDUZ62MPUU3S6.json","view_paper":"https://pith.science/paper/CLIU7H63","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.16244&json=true","fetch_graph":"https://pith.science/api/pith-number/CLIU7H63TJPMJIDUZ62MPUU3S6/graph.json","fetch_events":"https://pith.science/api/pith-number/CLIU7H63TJPMJIDUZ62MPUU3S6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CLIU7H63TJPMJIDUZ62MPUU3S6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CLIU7H63TJPMJIDUZ62MPUU3S6/action/storage_attestation","attest_author":"https://pith.science/pith/CLIU7H63TJPMJIDUZ62MPUU3S6/action/author_attestation","sign_citation":"https://pith.science/pith/CLIU7H63TJPMJIDUZ62MPUU3S6/action/citation_signature","submit_replication":"https://pith.science/pith/CLIU7H63TJPMJIDUZ62MPUU3S6/action/replication_record"}},"created_at":"2026-07-05T08:47:30.258430+00:00","updated_at":"2026-07-05T08:47:30.258430+00:00"}