{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:TXN3GDAYVZFUIBY4ZSPZXS2GT2","short_pith_number":"pith:TXN3GDAY","schema_version":"1.0","canonical_sha256":"9ddbb30c18ae4b44071ccc9f9bcb469e95c87028de7d1bfd7cdfa495566c1050","source":{"kind":"arxiv","id":"2012.11879","version":4},"attestation_state":"computed","paper":{"title":"FcaNet: Frequency Channel Attention Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fei Wu, Pengyi Zhang, Xi Li, Zequn Qin","submitted_at":"2020-12-22T08:33:27Z","abstract_excerpt":"Attention mechanism, especially channel attention, has gained great success in the computer vision field. Many works focus on how to design efficient channel attention mechanisms while ignoring a fundamental problem, i.e., channel attention mechanism uses scalar to represent channel, which is difficult due to massive information loss. In this work, we start from a different view and regard the channel representation problem as a compression process using frequency analysis. Based on the frequency analysis, we mathematically prove that the conventional global average pooling is a special case o"},"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":"2012.11879","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-12-22T08:33:27Z","cross_cats_sorted":[],"title_canon_sha256":"10e7e3a49135f9851f1ee781966c64319b37a56788760dc5d3c624b45cd846bd","abstract_canon_sha256":"03d5666995f32f6af57678cf966cbebd57a786c439baa6453428510aa62b7974"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:00:07.998503Z","signature_b64":"KexJr4fzG48N79B4LAp4bLfOZjmSzzWjnZXkQxLOMSuoa3p5K62NX9qp7//lzqngl4WN5yGuxmL0My0qL7OsBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9ddbb30c18ae4b44071ccc9f9bcb469e95c87028de7d1bfd7cdfa495566c1050","last_reissued_at":"2026-07-05T03:00:07.998024Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:00:07.998024Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FcaNet: Frequency Channel Attention Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fei Wu, Pengyi Zhang, Xi Li, Zequn Qin","submitted_at":"2020-12-22T08:33:27Z","abstract_excerpt":"Attention mechanism, especially channel attention, has gained great success in the computer vision field. Many works focus on how to design efficient channel attention mechanisms while ignoring a fundamental problem, i.e., channel attention mechanism uses scalar to represent channel, which is difficult due to massive information loss. In this work, we start from a different view and regard the channel representation problem as a compression process using frequency analysis. Based on the frequency analysis, we mathematically prove that the conventional global average pooling is a special case o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.11879","kind":"arxiv","version":4},"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/2012.11879/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":"2012.11879","created_at":"2026-07-05T03:00:07.998076+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.11879v4","created_at":"2026-07-05T03:00:07.998076+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.11879","created_at":"2026-07-05T03:00:07.998076+00:00"},{"alias_kind":"pith_short_12","alias_value":"TXN3GDAYVZFU","created_at":"2026-07-05T03:00:07.998076+00:00"},{"alias_kind":"pith_short_16","alias_value":"TXN3GDAYVZFUIBY4","created_at":"2026-07-05T03:00:07.998076+00:00"},{"alias_kind":"pith_short_8","alias_value":"TXN3GDAY","created_at":"2026-07-05T03:00:07.998076+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.07078","citing_title":"DFIR-DETR: Frequency-Domain Iterative Refinement and Dynamic Feature Aggregation for Small Object Detection","ref_index":40,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TXN3GDAYVZFUIBY4ZSPZXS2GT2","json":"https://pith.science/pith/TXN3GDAYVZFUIBY4ZSPZXS2GT2.json","graph_json":"https://pith.science/api/pith-number/TXN3GDAYVZFUIBY4ZSPZXS2GT2/graph.json","events_json":"https://pith.science/api/pith-number/TXN3GDAYVZFUIBY4ZSPZXS2GT2/events.json","paper":"https://pith.science/paper/TXN3GDAY"},"agent_actions":{"view_html":"https://pith.science/pith/TXN3GDAYVZFUIBY4ZSPZXS2GT2","download_json":"https://pith.science/pith/TXN3GDAYVZFUIBY4ZSPZXS2GT2.json","view_paper":"https://pith.science/paper/TXN3GDAY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.11879&json=true","fetch_graph":"https://pith.science/api/pith-number/TXN3GDAYVZFUIBY4ZSPZXS2GT2/graph.json","fetch_events":"https://pith.science/api/pith-number/TXN3GDAYVZFUIBY4ZSPZXS2GT2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TXN3GDAYVZFUIBY4ZSPZXS2GT2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TXN3GDAYVZFUIBY4ZSPZXS2GT2/action/storage_attestation","attest_author":"https://pith.science/pith/TXN3GDAYVZFUIBY4ZSPZXS2GT2/action/author_attestation","sign_citation":"https://pith.science/pith/TXN3GDAYVZFUIBY4ZSPZXS2GT2/action/citation_signature","submit_replication":"https://pith.science/pith/TXN3GDAYVZFUIBY4ZSPZXS2GT2/action/replication_record"}},"created_at":"2026-07-05T03:00:07.998076+00:00","updated_at":"2026-07-05T03:00:07.998076+00:00"}