{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:TWKCLV6P6YJQLCCZ5GJGIPGF5F","short_pith_number":"pith:TWKCLV6P","schema_version":"1.0","canonical_sha256":"9d9425d7cff613058859e992643cc5e968a0294f0d68f6ad28aaaa71aa05c3db","source":{"kind":"arxiv","id":"2208.14607","version":1},"attestation_state":"computed","paper":{"title":"SIM-Trans: Structure Information Modeling Transformer for Fine-grained Visual Categorization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hongbo Sun, Xiangteng He, Yuxin Peng","submitted_at":"2022-08-31T03:00:07Z","abstract_excerpt":"Fine-grained visual categorization (FGVC) aims at recognizing objects from similar subordinate categories, which is challenging and practical for human's accurate automatic recognition needs. Most FGVC approaches focus on the attention mechanism research for discriminative regions mining while neglecting their interdependencies and composed holistic object structure, which are essential for model's discriminative information localization and understanding ability. To address the above limitations, we propose the Structure Information Modeling Transformer (SIM-Trans) to incorporate object struc"},"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":"2208.14607","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-08-31T03:00:07Z","cross_cats_sorted":[],"title_canon_sha256":"7305dfa6e0313cf2f15c249f5c3ae992f0834161502460caf812c0631b97d6b3","abstract_canon_sha256":"0c58e64279a93a27de008ae78b42d3acb827082132940d1ada581355527c33f4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:53:32.202092Z","signature_b64":"Dh/scpNuromywyBbYhBnuyCXQjEWZZAjQoPPGteaQd5JZkmBtpDE+9a+1/+h1/BcZE++PUHuLCnpn1mZvmThAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9d9425d7cff613058859e992643cc5e968a0294f0d68f6ad28aaaa71aa05c3db","last_reissued_at":"2026-07-05T04:53:32.201621Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:53:32.201621Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SIM-Trans: Structure Information Modeling Transformer for Fine-grained Visual Categorization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hongbo Sun, Xiangteng He, Yuxin Peng","submitted_at":"2022-08-31T03:00:07Z","abstract_excerpt":"Fine-grained visual categorization (FGVC) aims at recognizing objects from similar subordinate categories, which is challenging and practical for human's accurate automatic recognition needs. Most FGVC approaches focus on the attention mechanism research for discriminative regions mining while neglecting their interdependencies and composed holistic object structure, which are essential for model's discriminative information localization and understanding ability. To address the above limitations, we propose the Structure Information Modeling Transformer (SIM-Trans) to incorporate object struc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.14607","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/2208.14607/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":"2208.14607","created_at":"2026-07-05T04:53:32.201677+00:00"},{"alias_kind":"arxiv_version","alias_value":"2208.14607v1","created_at":"2026-07-05T04:53:32.201677+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.14607","created_at":"2026-07-05T04:53:32.201677+00:00"},{"alias_kind":"pith_short_12","alias_value":"TWKCLV6P6YJQ","created_at":"2026-07-05T04:53:32.201677+00:00"},{"alias_kind":"pith_short_16","alias_value":"TWKCLV6P6YJQLCCZ","created_at":"2026-07-05T04:53:32.201677+00:00"},{"alias_kind":"pith_short_8","alias_value":"TWKCLV6P","created_at":"2026-07-05T04:53:32.201677+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.13884","citing_title":"Navigating limitations with precision: A fine-grained ensemble approach to wrist pathology recognition on a limited x-ray dataset","ref_index":33,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TWKCLV6P6YJQLCCZ5GJGIPGF5F","json":"https://pith.science/pith/TWKCLV6P6YJQLCCZ5GJGIPGF5F.json","graph_json":"https://pith.science/api/pith-number/TWKCLV6P6YJQLCCZ5GJGIPGF5F/graph.json","events_json":"https://pith.science/api/pith-number/TWKCLV6P6YJQLCCZ5GJGIPGF5F/events.json","paper":"https://pith.science/paper/TWKCLV6P"},"agent_actions":{"view_html":"https://pith.science/pith/TWKCLV6P6YJQLCCZ5GJGIPGF5F","download_json":"https://pith.science/pith/TWKCLV6P6YJQLCCZ5GJGIPGF5F.json","view_paper":"https://pith.science/paper/TWKCLV6P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2208.14607&json=true","fetch_graph":"https://pith.science/api/pith-number/TWKCLV6P6YJQLCCZ5GJGIPGF5F/graph.json","fetch_events":"https://pith.science/api/pith-number/TWKCLV6P6YJQLCCZ5GJGIPGF5F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TWKCLV6P6YJQLCCZ5GJGIPGF5F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TWKCLV6P6YJQLCCZ5GJGIPGF5F/action/storage_attestation","attest_author":"https://pith.science/pith/TWKCLV6P6YJQLCCZ5GJGIPGF5F/action/author_attestation","sign_citation":"https://pith.science/pith/TWKCLV6P6YJQLCCZ5GJGIPGF5F/action/citation_signature","submit_replication":"https://pith.science/pith/TWKCLV6P6YJQLCCZ5GJGIPGF5F/action/replication_record"}},"created_at":"2026-07-05T04:53:32.201677+00:00","updated_at":"2026-07-05T04:53:32.201677+00:00"}