{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:R6OC5CJVMCZF4EZ6JVAPBNJC3Y","short_pith_number":"pith:R6OC5CJV","schema_version":"1.0","canonical_sha256":"8f9c2e893560b25e133e4d40f0b522de170fa7f88aa715b64c10f0108ea33bb1","source":{"kind":"arxiv","id":"1702.00372","version":1},"attestation_state":"computed","paper":{"title":"Visual Saliency Prediction Using a Mixture of Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lina Karam, Samuel Dodge","submitted_at":"2017-02-01T17:45:55Z","abstract_excerpt":"Visual saliency models have recently begun to incorporate deep learning to achieve predictive capacity much greater than previous unsupervised methods. However, most existing models predict saliency using local mechanisms limited to the receptive field of the network. We propose a model that incorporates global scene semantic information in addition to local information gathered by a convolutional neural network. Our model is formulated as a mixture of experts. Each expert network is trained to predict saliency for a set of closely related images. The final saliency map is computed as a weight"},"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":"1702.00372","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-02-01T17:45:55Z","cross_cats_sorted":[],"title_canon_sha256":"c3ae41bbe884c76292626a9ec88745f0b0531623827a76e4637879f413d49cdb","abstract_canon_sha256":"b32e6a429c879944d3c67d83bcef085dd633f5b960f41e2e7550f9d79cf98425"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:11:44.071628Z","signature_b64":"8dzZ9J/+e7EQuuF4C2si9AC0HN3+wD7+9d2fonQKDa68vre3JDgmqdXfja/sOvF0BrXhAjCL5j2SDJPRY7VmCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f9c2e893560b25e133e4d40f0b522de170fa7f88aa715b64c10f0108ea33bb1","last_reissued_at":"2026-05-18T00:11:44.070903Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:11:44.070903Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Visual Saliency Prediction Using a Mixture of Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lina Karam, Samuel Dodge","submitted_at":"2017-02-01T17:45:55Z","abstract_excerpt":"Visual saliency models have recently begun to incorporate deep learning to achieve predictive capacity much greater than previous unsupervised methods. However, most existing models predict saliency using local mechanisms limited to the receptive field of the network. We propose a model that incorporates global scene semantic information in addition to local information gathered by a convolutional neural network. Our model is formulated as a mixture of experts. Each expert network is trained to predict saliency for a set of closely related images. The final saliency map is computed as a weight"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.00372","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":""},"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":"1702.00372","created_at":"2026-05-18T00:11:44.071017+00:00"},{"alias_kind":"arxiv_version","alias_value":"1702.00372v1","created_at":"2026-05-18T00:11:44.071017+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.00372","created_at":"2026-05-18T00:11:44.071017+00:00"},{"alias_kind":"pith_short_12","alias_value":"R6OC5CJVMCZF","created_at":"2026-05-18T12:31:39.905425+00:00"},{"alias_kind":"pith_short_16","alias_value":"R6OC5CJVMCZF4EZ6","created_at":"2026-05-18T12:31:39.905425+00:00"},{"alias_kind":"pith_short_8","alias_value":"R6OC5CJV","created_at":"2026-05-18T12:31:39.905425+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/R6OC5CJVMCZF4EZ6JVAPBNJC3Y","json":"https://pith.science/pith/R6OC5CJVMCZF4EZ6JVAPBNJC3Y.json","graph_json":"https://pith.science/api/pith-number/R6OC5CJVMCZF4EZ6JVAPBNJC3Y/graph.json","events_json":"https://pith.science/api/pith-number/R6OC5CJVMCZF4EZ6JVAPBNJC3Y/events.json","paper":"https://pith.science/paper/R6OC5CJV"},"agent_actions":{"view_html":"https://pith.science/pith/R6OC5CJVMCZF4EZ6JVAPBNJC3Y","download_json":"https://pith.science/pith/R6OC5CJVMCZF4EZ6JVAPBNJC3Y.json","view_paper":"https://pith.science/paper/R6OC5CJV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1702.00372&json=true","fetch_graph":"https://pith.science/api/pith-number/R6OC5CJVMCZF4EZ6JVAPBNJC3Y/graph.json","fetch_events":"https://pith.science/api/pith-number/R6OC5CJVMCZF4EZ6JVAPBNJC3Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R6OC5CJVMCZF4EZ6JVAPBNJC3Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R6OC5CJVMCZF4EZ6JVAPBNJC3Y/action/storage_attestation","attest_author":"https://pith.science/pith/R6OC5CJVMCZF4EZ6JVAPBNJC3Y/action/author_attestation","sign_citation":"https://pith.science/pith/R6OC5CJVMCZF4EZ6JVAPBNJC3Y/action/citation_signature","submit_replication":"https://pith.science/pith/R6OC5CJVMCZF4EZ6JVAPBNJC3Y/action/replication_record"}},"created_at":"2026-05-18T00:11:44.071017+00:00","updated_at":"2026-05-18T00:11:44.071017+00:00"}