{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:ZBHGMK2TRXGUL5WMMEHD3A3Y4N","short_pith_number":"pith:ZBHGMK2T","schema_version":"1.0","canonical_sha256":"c84e662b538dcd45f6cc610e3d8378e34df8e9f2ae2572e054484bb3aa8401c6","source":{"kind":"arxiv","id":"2101.06635","version":1},"attestation_state":"computed","paper":{"title":"Context-aware Attentional Pooling (CAP) for Fine-grained Visual Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Ardhendu Behera, Asish Bera, Pradeep Hewage, Zachary Wharton","submitted_at":"2021-01-17T10:15:02Z","abstract_excerpt":"Deep convolutional neural networks (CNNs) have shown a strong ability in mining discriminative object pose and parts information for image recognition. For fine-grained recognition, context-aware rich feature representation of object/scene plays a key role since it exhibits a significant variance in the same subcategory and subtle variance among different subcategories. Finding the subtle variance that fully characterizes the object/scene is not straightforward. To address this, we propose a novel context-aware attentional pooling (CAP) that effectively captures subtle changes via sub-pixel gr"},"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":"2101.06635","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-01-17T10:15:02Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"17a3551021d5271bebf447a590a05efde1d1e9dc25fc6a266e1f680301018f19","abstract_canon_sha256":"f236460ff492c7a62948f37b1d6867421129d1f12a56d2c136e55c6ea4c2f1d1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:07:35.585394Z","signature_b64":"ou2HICcLkP4TX0vf3XL8PzBuNp6/WqBVTrFkr/AnzDRjXdMmH3XGFNwfxnvnyLict1dtBkU5GeXdgrG8Hrz3Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c84e662b538dcd45f6cc610e3d8378e34df8e9f2ae2572e054484bb3aa8401c6","last_reissued_at":"2026-07-05T02:07:35.584995Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:07:35.584995Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Context-aware Attentional Pooling (CAP) for Fine-grained Visual Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Ardhendu Behera, Asish Bera, Pradeep Hewage, Zachary Wharton","submitted_at":"2021-01-17T10:15:02Z","abstract_excerpt":"Deep convolutional neural networks (CNNs) have shown a strong ability in mining discriminative object pose and parts information for image recognition. For fine-grained recognition, context-aware rich feature representation of object/scene plays a key role since it exhibits a significant variance in the same subcategory and subtle variance among different subcategories. Finding the subtle variance that fully characterizes the object/scene is not straightforward. To address this, we propose a novel context-aware attentional pooling (CAP) that effectively captures subtle changes via sub-pixel gr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.06635","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/2101.06635/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":"2101.06635","created_at":"2026-07-05T02:07:35.585055+00:00"},{"alias_kind":"arxiv_version","alias_value":"2101.06635v1","created_at":"2026-07-05T02:07:35.585055+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.06635","created_at":"2026-07-05T02:07:35.585055+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZBHGMK2TRXGU","created_at":"2026-07-05T02:07:35.585055+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZBHGMK2TRXGUL5WM","created_at":"2026-07-05T02:07:35.585055+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZBHGMK2T","created_at":"2026-07-05T02:07:35.585055+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.19640","citing_title":"AGNFormer I: Reconstruction of AGN spectra using a probabilistic transformer model","ref_index":143,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZBHGMK2TRXGUL5WMMEHD3A3Y4N","json":"https://pith.science/pith/ZBHGMK2TRXGUL5WMMEHD3A3Y4N.json","graph_json":"https://pith.science/api/pith-number/ZBHGMK2TRXGUL5WMMEHD3A3Y4N/graph.json","events_json":"https://pith.science/api/pith-number/ZBHGMK2TRXGUL5WMMEHD3A3Y4N/events.json","paper":"https://pith.science/paper/ZBHGMK2T"},"agent_actions":{"view_html":"https://pith.science/pith/ZBHGMK2TRXGUL5WMMEHD3A3Y4N","download_json":"https://pith.science/pith/ZBHGMK2TRXGUL5WMMEHD3A3Y4N.json","view_paper":"https://pith.science/paper/ZBHGMK2T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2101.06635&json=true","fetch_graph":"https://pith.science/api/pith-number/ZBHGMK2TRXGUL5WMMEHD3A3Y4N/graph.json","fetch_events":"https://pith.science/api/pith-number/ZBHGMK2TRXGUL5WMMEHD3A3Y4N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZBHGMK2TRXGUL5WMMEHD3A3Y4N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZBHGMK2TRXGUL5WMMEHD3A3Y4N/action/storage_attestation","attest_author":"https://pith.science/pith/ZBHGMK2TRXGUL5WMMEHD3A3Y4N/action/author_attestation","sign_citation":"https://pith.science/pith/ZBHGMK2TRXGUL5WMMEHD3A3Y4N/action/citation_signature","submit_replication":"https://pith.science/pith/ZBHGMK2TRXGUL5WMMEHD3A3Y4N/action/replication_record"}},"created_at":"2026-07-05T02:07:35.585055+00:00","updated_at":"2026-07-05T02:07:35.585055+00:00"}