{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:HD27OKULKZSERXYQT26C4XZARN","short_pith_number":"pith:HD27OKUL","schema_version":"1.0","canonical_sha256":"38f5f72a8b566448df109ebc2e5f208b420fe349f9f44b9c4adf11f274d547b5","source":{"kind":"arxiv","id":"1810.12348","version":3},"attestation_state":"computed","paper":{"title":"Gather-Excite: Exploiting Feature Context in Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrea Vedaldi, Gang Sun, Jie Hu, Li Shen, Samuel Albanie","submitted_at":"2018-10-29T18:52:37Z","abstract_excerpt":"While the use of bottom-up local operators in convolutional neural networks (CNNs) matches well some of the statistics of natural images, it may also prevent such models from capturing contextual long-range feature interactions. In this work, we propose a simple, lightweight approach for better context exploitation in CNNs. We do so by introducing a pair of operators: gather, which efficiently aggregates feature responses from a large spatial extent, and excite, which redistributes the pooled information to local features. The operators are cheap, both in terms of number of added parameters an"},"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":"1810.12348","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-10-29T18:52:37Z","cross_cats_sorted":[],"title_canon_sha256":"370276f30570a5d0aaec438d1990b487ab109139b2de3e451025559db7831f94","abstract_canon_sha256":"331fc3a069a7fa805e82363a31fd9f90c2d4f6cf902f862b374a28acffb214b1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:56:29.267470Z","signature_b64":"rxSARdYIq4QGGbzAJ1FkhZQqFXL6aDiZkr8UZOGJhD1hp99JRI3AtyGI96fqCcY1lRZ8+3DbZXA+UrXHZ/I3Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"38f5f72a8b566448df109ebc2e5f208b420fe349f9f44b9c4adf11f274d547b5","last_reissued_at":"2026-05-17T23:56:29.267017Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:56:29.267017Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Gather-Excite: Exploiting Feature Context in Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrea Vedaldi, Gang Sun, Jie Hu, Li Shen, Samuel Albanie","submitted_at":"2018-10-29T18:52:37Z","abstract_excerpt":"While the use of bottom-up local operators in convolutional neural networks (CNNs) matches well some of the statistics of natural images, it may also prevent such models from capturing contextual long-range feature interactions. In this work, we propose a simple, lightweight approach for better context exploitation in CNNs. We do so by introducing a pair of operators: gather, which efficiently aggregates feature responses from a large spatial extent, and excite, which redistributes the pooled information to local features. The operators are cheap, both in terms of number of added parameters an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.12348","kind":"arxiv","version":3},"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":"1810.12348","created_at":"2026-05-17T23:56:29.267078+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.12348v3","created_at":"2026-05-17T23:56:29.267078+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.12348","created_at":"2026-05-17T23:56:29.267078+00:00"},{"alias_kind":"pith_short_12","alias_value":"HD27OKULKZSE","created_at":"2026-05-18T12:32:28.185984+00:00"},{"alias_kind":"pith_short_16","alias_value":"HD27OKULKZSERXYQ","created_at":"2026-05-18T12:32:28.185984+00:00"},{"alias_kind":"pith_short_8","alias_value":"HD27OKUL","created_at":"2026-05-18T12:32:28.185984+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/HD27OKULKZSERXYQT26C4XZARN","json":"https://pith.science/pith/HD27OKULKZSERXYQT26C4XZARN.json","graph_json":"https://pith.science/api/pith-number/HD27OKULKZSERXYQT26C4XZARN/graph.json","events_json":"https://pith.science/api/pith-number/HD27OKULKZSERXYQT26C4XZARN/events.json","paper":"https://pith.science/paper/HD27OKUL"},"agent_actions":{"view_html":"https://pith.science/pith/HD27OKULKZSERXYQT26C4XZARN","download_json":"https://pith.science/pith/HD27OKULKZSERXYQT26C4XZARN.json","view_paper":"https://pith.science/paper/HD27OKUL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.12348&json=true","fetch_graph":"https://pith.science/api/pith-number/HD27OKULKZSERXYQT26C4XZARN/graph.json","fetch_events":"https://pith.science/api/pith-number/HD27OKULKZSERXYQT26C4XZARN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HD27OKULKZSERXYQT26C4XZARN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HD27OKULKZSERXYQT26C4XZARN/action/storage_attestation","attest_author":"https://pith.science/pith/HD27OKULKZSERXYQT26C4XZARN/action/author_attestation","sign_citation":"https://pith.science/pith/HD27OKULKZSERXYQT26C4XZARN/action/citation_signature","submit_replication":"https://pith.science/pith/HD27OKULKZSERXYQT26C4XZARN/action/replication_record"}},"created_at":"2026-05-17T23:56:29.267078+00:00","updated_at":"2026-05-17T23:56:29.267078+00:00"}