{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:B7BJLZ5Z75CPYPYAFDA62NE3RK","short_pith_number":"pith:B7BJLZ5Z","schema_version":"1.0","canonical_sha256":"0fc295e7b9ff44fc3f0028c1ed349b8ab3eac73559f59eaef672070eaca4c17b","source":{"kind":"arxiv","id":"1807.06514","version":2},"attestation_state":"computed","paper":{"title":"BAM: Bottleneck Attention Module","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"In So Kweon, Jongchan Park, Joon-Young Lee, Sanghyun Woo","submitted_at":"2018-07-17T15:55:31Z","abstract_excerpt":"Recent advances in deep neural networks have been developed via architecture search for stronger representational power. In this work, we focus on the effect of attention in general deep neural networks. We propose a simple and effective attention module, named Bottleneck Attention Module (BAM), that can be integrated with any feed-forward convolutional neural networks. Our module infers an attention map along two separate pathways, channel and spatial. We place our module at each bottleneck of models where the downsampling of feature maps occurs. Our module constructs a hierarchical attention"},"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":"1807.06514","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-07-17T15:55:31Z","cross_cats_sorted":[],"title_canon_sha256":"aa62cbcf26190b2a848b4e623319f642e5b31652f2c43fd1ac5690a9731b3153","abstract_canon_sha256":"3ab7437fdd5b400fb993e208017f9d0561caa76f5663e1cb83853cd8ecadce62"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:10:27.498039Z","signature_b64":"/AhGAWvQ/cPxzWxjY5uMmpD/Dsi/nD4aAZoaWArR7bxcwyZM3HIyjXqFHnn9bifCo+HO8o3NQUM0OXgWaJsWCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0fc295e7b9ff44fc3f0028c1ed349b8ab3eac73559f59eaef672070eaca4c17b","last_reissued_at":"2026-05-18T00:10:27.497466Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:10:27.497466Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BAM: Bottleneck Attention Module","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"In So Kweon, Jongchan Park, Joon-Young Lee, Sanghyun Woo","submitted_at":"2018-07-17T15:55:31Z","abstract_excerpt":"Recent advances in deep neural networks have been developed via architecture search for stronger representational power. In this work, we focus on the effect of attention in general deep neural networks. We propose a simple and effective attention module, named Bottleneck Attention Module (BAM), that can be integrated with any feed-forward convolutional neural networks. Our module infers an attention map along two separate pathways, channel and spatial. We place our module at each bottleneck of models where the downsampling of feature maps occurs. Our module constructs a hierarchical attention"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.06514","kind":"arxiv","version":2},"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":"1807.06514","created_at":"2026-05-18T00:10:27.497564+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.06514v2","created_at":"2026-05-18T00:10:27.497564+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.06514","created_at":"2026-05-18T00:10:27.497564+00:00"},{"alias_kind":"pith_short_12","alias_value":"B7BJLZ5Z75CP","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_16","alias_value":"B7BJLZ5Z75CPYPYA","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_8","alias_value":"B7BJLZ5Z","created_at":"2026-05-18T12:32:13.499390+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"1907.06838","citing_title":"Improved Reinforcement Learning through Imitation Learning Pretraining Towards Image-based Autonomous Driving","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2401.04560","citing_title":"Phase-shifted remote photoplethysmography for estimating heart rate and blood pressure from facial video","ref_index":44,"is_internal_anchor":true},{"citing_arxiv_id":"2509.06591","citing_title":"Hybrid Swin Attention Networks for Simultaneously Low-Dose PET and CT Denoising","ref_index":32,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B7BJLZ5Z75CPYPYAFDA62NE3RK","json":"https://pith.science/pith/B7BJLZ5Z75CPYPYAFDA62NE3RK.json","graph_json":"https://pith.science/api/pith-number/B7BJLZ5Z75CPYPYAFDA62NE3RK/graph.json","events_json":"https://pith.science/api/pith-number/B7BJLZ5Z75CPYPYAFDA62NE3RK/events.json","paper":"https://pith.science/paper/B7BJLZ5Z"},"agent_actions":{"view_html":"https://pith.science/pith/B7BJLZ5Z75CPYPYAFDA62NE3RK","download_json":"https://pith.science/pith/B7BJLZ5Z75CPYPYAFDA62NE3RK.json","view_paper":"https://pith.science/paper/B7BJLZ5Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.06514&json=true","fetch_graph":"https://pith.science/api/pith-number/B7BJLZ5Z75CPYPYAFDA62NE3RK/graph.json","fetch_events":"https://pith.science/api/pith-number/B7BJLZ5Z75CPYPYAFDA62NE3RK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B7BJLZ5Z75CPYPYAFDA62NE3RK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B7BJLZ5Z75CPYPYAFDA62NE3RK/action/storage_attestation","attest_author":"https://pith.science/pith/B7BJLZ5Z75CPYPYAFDA62NE3RK/action/author_attestation","sign_citation":"https://pith.science/pith/B7BJLZ5Z75CPYPYAFDA62NE3RK/action/citation_signature","submit_replication":"https://pith.science/pith/B7BJLZ5Z75CPYPYAFDA62NE3RK/action/replication_record"}},"created_at":"2026-05-18T00:10:27.497564+00:00","updated_at":"2026-05-18T00:10:27.497564+00:00"}