{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:PJNFFSBQWFLEHJ3BCLIK2IV5JV","short_pith_number":"pith:PJNFFSBQ","schema_version":"1.0","canonical_sha256":"7a5a52c830b15643a76112d0ad22bd4d684bf749bbb3a43a5556ff47f287c399","source":{"kind":"arxiv","id":"1901.05376","version":2},"attestation_state":"computed","paper":{"title":"Joint Spatial and Layer Attention for Convolutional Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Faisal Z. Qureshi, Konstantinos G. Derpanis, Tony Joseph","submitted_at":"2019-01-16T16:32:31Z","abstract_excerpt":"In this paper, we propose a novel approach that learns to sequentially attend to different Convolutional Neural Networks (CNN) layers (i.e., ``what'' feature abstraction to attend to) and different spatial locations of the selected feature map (i.e., ``where'') to perform the task at hand. Specifically, at each Recurrent Neural Network (RNN) step, both a CNN layer and localized spatial region within it are selected for further processing. We demonstrate the effectiveness of this approach on two computer vision tasks: (i) image-based six degree of freedom camera pose regression and (ii) indoor "},"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":"1901.05376","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-01-16T16:32:31Z","cross_cats_sorted":[],"title_canon_sha256":"a8d79ced1771e9b8832577c31f8c40db67a2ba06c7cf7c0ad1572a4bc9696807","abstract_canon_sha256":"63a8aa092678352747d5a8da6823f6d05b957196a8ba7191b3e18a0d75070bdf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:37.796228Z","signature_b64":"KPzhHqd5qpAe7E02tgmOfmDXM/jApHh71L1bufDxtLtXLuiF1ye4CtER6BgvsQH2M8MG+eJQkgYCXsbcf47YDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7a5a52c830b15643a76112d0ad22bd4d684bf749bbb3a43a5556ff47f287c399","last_reissued_at":"2026-05-17T23:44:37.795847Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:37.795847Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Joint Spatial and Layer Attention for Convolutional Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Faisal Z. Qureshi, Konstantinos G. Derpanis, Tony Joseph","submitted_at":"2019-01-16T16:32:31Z","abstract_excerpt":"In this paper, we propose a novel approach that learns to sequentially attend to different Convolutional Neural Networks (CNN) layers (i.e., ``what'' feature abstraction to attend to) and different spatial locations of the selected feature map (i.e., ``where'') to perform the task at hand. Specifically, at each Recurrent Neural Network (RNN) step, both a CNN layer and localized spatial region within it are selected for further processing. We demonstrate the effectiveness of this approach on two computer vision tasks: (i) image-based six degree of freedom camera pose regression and (ii) indoor "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.05376","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":"1901.05376","created_at":"2026-05-17T23:44:37.795907+00:00"},{"alias_kind":"arxiv_version","alias_value":"1901.05376v2","created_at":"2026-05-17T23:44:37.795907+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.05376","created_at":"2026-05-17T23:44:37.795907+00:00"},{"alias_kind":"pith_short_12","alias_value":"PJNFFSBQWFLE","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_16","alias_value":"PJNFFSBQWFLEHJ3B","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_8","alias_value":"PJNFFSBQ","created_at":"2026-05-18T12:33:24.271573+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/PJNFFSBQWFLEHJ3BCLIK2IV5JV","json":"https://pith.science/pith/PJNFFSBQWFLEHJ3BCLIK2IV5JV.json","graph_json":"https://pith.science/api/pith-number/PJNFFSBQWFLEHJ3BCLIK2IV5JV/graph.json","events_json":"https://pith.science/api/pith-number/PJNFFSBQWFLEHJ3BCLIK2IV5JV/events.json","paper":"https://pith.science/paper/PJNFFSBQ"},"agent_actions":{"view_html":"https://pith.science/pith/PJNFFSBQWFLEHJ3BCLIK2IV5JV","download_json":"https://pith.science/pith/PJNFFSBQWFLEHJ3BCLIK2IV5JV.json","view_paper":"https://pith.science/paper/PJNFFSBQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1901.05376&json=true","fetch_graph":"https://pith.science/api/pith-number/PJNFFSBQWFLEHJ3BCLIK2IV5JV/graph.json","fetch_events":"https://pith.science/api/pith-number/PJNFFSBQWFLEHJ3BCLIK2IV5JV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PJNFFSBQWFLEHJ3BCLIK2IV5JV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PJNFFSBQWFLEHJ3BCLIK2IV5JV/action/storage_attestation","attest_author":"https://pith.science/pith/PJNFFSBQWFLEHJ3BCLIK2IV5JV/action/author_attestation","sign_citation":"https://pith.science/pith/PJNFFSBQWFLEHJ3BCLIK2IV5JV/action/citation_signature","submit_replication":"https://pith.science/pith/PJNFFSBQWFLEHJ3BCLIK2IV5JV/action/replication_record"}},"created_at":"2026-05-17T23:44:37.795907+00:00","updated_at":"2026-05-17T23:44:37.795907+00:00"}