{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:BHKXQVOEI2ZSY4KS5HB4RXJATZ","short_pith_number":"pith:BHKXQVOE","schema_version":"1.0","canonical_sha256":"09d57855c446b32c7152e9c3c8dd209e4e09a1e0f0036dd8f12f8396d7d081ab","source":{"kind":"arxiv","id":"1806.05372","version":1},"attestation_state":"computed","paper":{"title":"Multi-Attention Multi-Class Constraint for Fine-grained Image Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Errui Ding, Feng Zhou, Ming Sun, Yuchen Yuan","submitted_at":"2018-06-14T05:45:22Z","abstract_excerpt":"Attention-based learning for fine-grained image recognition remains a challenging task, where most of the existing methods treat each object part in isolation, while neglecting the correlations among them. In addition, the multi-stage or multi-scale mechanisms involved make the existing methods less efficient and hard to be trained end-to-end. In this paper, we propose a novel attention-based convolutional neural network (CNN) which regulates multiple object parts among different input images. Our method first learns multiple attention region features of each input image through the one-squeez"},"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":"1806.05372","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-06-14T05:45:22Z","cross_cats_sorted":[],"title_canon_sha256":"35f0f7becc6b55c42c08c0ca2be56266355de6d7312aea27fc600e92f2dd891a","abstract_canon_sha256":"5a7fb0f4331d8d0d07bd4c503290746e9d591b31b3701894a3715e81ddc5511c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:13:16.189649Z","signature_b64":"ftAoWqmqRzmgzdz1jP9M2NR6galcMNsSklsPoiVArENhnzfMWtKSULFWsnU3nFexy6LIwbel5yVRuFAisv4QDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"09d57855c446b32c7152e9c3c8dd209e4e09a1e0f0036dd8f12f8396d7d081ab","last_reissued_at":"2026-05-18T00:13:16.188924Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:13:16.188924Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Attention Multi-Class Constraint for Fine-grained Image Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Errui Ding, Feng Zhou, Ming Sun, Yuchen Yuan","submitted_at":"2018-06-14T05:45:22Z","abstract_excerpt":"Attention-based learning for fine-grained image recognition remains a challenging task, where most of the existing methods treat each object part in isolation, while neglecting the correlations among them. In addition, the multi-stage or multi-scale mechanisms involved make the existing methods less efficient and hard to be trained end-to-end. In this paper, we propose a novel attention-based convolutional neural network (CNN) which regulates multiple object parts among different input images. Our method first learns multiple attention region features of each input image through the one-squeez"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.05372","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":""},"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":"1806.05372","created_at":"2026-05-18T00:13:16.189036+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.05372v1","created_at":"2026-05-18T00:13:16.189036+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.05372","created_at":"2026-05-18T00:13:16.189036+00:00"},{"alias_kind":"pith_short_12","alias_value":"BHKXQVOEI2ZS","created_at":"2026-05-18T12:32:16.446611+00:00"},{"alias_kind":"pith_short_16","alias_value":"BHKXQVOEI2ZSY4KS","created_at":"2026-05-18T12:32:16.446611+00:00"},{"alias_kind":"pith_short_8","alias_value":"BHKXQVOE","created_at":"2026-05-18T12:32:16.446611+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/BHKXQVOEI2ZSY4KS5HB4RXJATZ","json":"https://pith.science/pith/BHKXQVOEI2ZSY4KS5HB4RXJATZ.json","graph_json":"https://pith.science/api/pith-number/BHKXQVOEI2ZSY4KS5HB4RXJATZ/graph.json","events_json":"https://pith.science/api/pith-number/BHKXQVOEI2ZSY4KS5HB4RXJATZ/events.json","paper":"https://pith.science/paper/BHKXQVOE"},"agent_actions":{"view_html":"https://pith.science/pith/BHKXQVOEI2ZSY4KS5HB4RXJATZ","download_json":"https://pith.science/pith/BHKXQVOEI2ZSY4KS5HB4RXJATZ.json","view_paper":"https://pith.science/paper/BHKXQVOE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.05372&json=true","fetch_graph":"https://pith.science/api/pith-number/BHKXQVOEI2ZSY4KS5HB4RXJATZ/graph.json","fetch_events":"https://pith.science/api/pith-number/BHKXQVOEI2ZSY4KS5HB4RXJATZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BHKXQVOEI2ZSY4KS5HB4RXJATZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BHKXQVOEI2ZSY4KS5HB4RXJATZ/action/storage_attestation","attest_author":"https://pith.science/pith/BHKXQVOEI2ZSY4KS5HB4RXJATZ/action/author_attestation","sign_citation":"https://pith.science/pith/BHKXQVOEI2ZSY4KS5HB4RXJATZ/action/citation_signature","submit_replication":"https://pith.science/pith/BHKXQVOEI2ZSY4KS5HB4RXJATZ/action/replication_record"}},"created_at":"2026-05-18T00:13:16.189036+00:00","updated_at":"2026-05-18T00:13:16.189036+00:00"}