{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:NPIDZ47OX3VP7EJPSBWVXUESFH","short_pith_number":"pith:NPIDZ47O","schema_version":"1.0","canonical_sha256":"6bd03cf3eebeeaff912f906d5bd09229dd5f43838b49f0419d37b25b27dd5e99","source":{"kind":"arxiv","id":"1701.01081","version":3},"attestation_state":"computed","paper":{"title":"SalGAN: Visual Saliency Prediction with Generative Adversarial Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cristian Canton Ferrer, Elisa Sayrol, Jordi Torres, Junting Pan, Kevin McGuinness, Noel E. O'Connor, Xavier Giro-i-Nieto","submitted_at":"2017-01-04T17:16:54Z","abstract_excerpt":"We introduce SalGAN, a deep convolutional neural network for visual saliency prediction trained with adversarial examples. The first stage of the network consists of a generator model whose weights are learned by back-propagation computed from a binary cross entropy (BCE) loss over downsampled versions of the saliency maps. The resulting prediction is processed by a discriminator network trained to solve a binary classification task between the saliency maps generated by the generative stage and the ground truth ones. Our experiments show how adversarial training allows reaching state-of-the-a"},"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":"1701.01081","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-01-04T17:16:54Z","cross_cats_sorted":[],"title_canon_sha256":"f1a315b2b9d3e2f13c34ca4dc5e9fc4ebfe1fc858fcb018eb9a0a5feff85724e","abstract_canon_sha256":"7ae5294d9fc4944da4d16db186aea024c6ff5c5430c34215cb27335e52ffe7f5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:12:00.712689Z","signature_b64":"LE1M3NbBJBPKTYSqp0nghrHBjEhaCbVH8s55xZEu7vUaNM8u3tVR1wsQvmuKEY0OFrFA6U77T3yZ+lW4PAkPCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6bd03cf3eebeeaff912f906d5bd09229dd5f43838b49f0419d37b25b27dd5e99","last_reissued_at":"2026-05-18T00:12:00.711988Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:12:00.711988Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SalGAN: Visual Saliency Prediction with Generative Adversarial Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cristian Canton Ferrer, Elisa Sayrol, Jordi Torres, Junting Pan, Kevin McGuinness, Noel E. O'Connor, Xavier Giro-i-Nieto","submitted_at":"2017-01-04T17:16:54Z","abstract_excerpt":"We introduce SalGAN, a deep convolutional neural network for visual saliency prediction trained with adversarial examples. The first stage of the network consists of a generator model whose weights are learned by back-propagation computed from a binary cross entropy (BCE) loss over downsampled versions of the saliency maps. The resulting prediction is processed by a discriminator network trained to solve a binary classification task between the saliency maps generated by the generative stage and the ground truth ones. Our experiments show how adversarial training allows reaching state-of-the-a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1701.01081","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":"1701.01081","created_at":"2026-05-18T00:12:00.712084+00:00"},{"alias_kind":"arxiv_version","alias_value":"1701.01081v3","created_at":"2026-05-18T00:12:00.712084+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1701.01081","created_at":"2026-05-18T00:12:00.712084+00:00"},{"alias_kind":"pith_short_12","alias_value":"NPIDZ47OX3VP","created_at":"2026-05-18T12:31:34.259226+00:00"},{"alias_kind":"pith_short_16","alias_value":"NPIDZ47OX3VP7EJP","created_at":"2026-05-18T12:31:34.259226+00:00"},{"alias_kind":"pith_short_8","alias_value":"NPIDZ47O","created_at":"2026-05-18T12:31:34.259226+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2602.09259","citing_title":"Data-centric Design of Learning-based Surgical Gaze Perception Models in Multi-Task Simulation","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NPIDZ47OX3VP7EJPSBWVXUESFH","json":"https://pith.science/pith/NPIDZ47OX3VP7EJPSBWVXUESFH.json","graph_json":"https://pith.science/api/pith-number/NPIDZ47OX3VP7EJPSBWVXUESFH/graph.json","events_json":"https://pith.science/api/pith-number/NPIDZ47OX3VP7EJPSBWVXUESFH/events.json","paper":"https://pith.science/paper/NPIDZ47O"},"agent_actions":{"view_html":"https://pith.science/pith/NPIDZ47OX3VP7EJPSBWVXUESFH","download_json":"https://pith.science/pith/NPIDZ47OX3VP7EJPSBWVXUESFH.json","view_paper":"https://pith.science/paper/NPIDZ47O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1701.01081&json=true","fetch_graph":"https://pith.science/api/pith-number/NPIDZ47OX3VP7EJPSBWVXUESFH/graph.json","fetch_events":"https://pith.science/api/pith-number/NPIDZ47OX3VP7EJPSBWVXUESFH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NPIDZ47OX3VP7EJPSBWVXUESFH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NPIDZ47OX3VP7EJPSBWVXUESFH/action/storage_attestation","attest_author":"https://pith.science/pith/NPIDZ47OX3VP7EJPSBWVXUESFH/action/author_attestation","sign_citation":"https://pith.science/pith/NPIDZ47OX3VP7EJPSBWVXUESFH/action/citation_signature","submit_replication":"https://pith.science/pith/NPIDZ47OX3VP7EJPSBWVXUESFH/action/replication_record"}},"created_at":"2026-05-18T00:12:00.712084+00:00","updated_at":"2026-05-18T00:12:00.712084+00:00"}