{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:22UL7G2FO347NEDTQUY7YETL7Q","short_pith_number":"pith:22UL7G2F","schema_version":"1.0","canonical_sha256":"d6a8bf9b4576f9f690738531fc126bfc23da73d4a71493b8fbbce14bf716e945","source":{"kind":"arxiv","id":"1808.01634","version":1},"attestation_state":"computed","paper":{"title":"Self-Attention Recurrent Network for Saliency Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fengdong Sun, Wenhui Li, Yuanyuan Guan","submitted_at":"2018-08-05T15:31:22Z","abstract_excerpt":"Feature maps in deep neural network generally contain different semantics. Existing methods often omit their characteristics that may lead to sub-optimal results. In this paper, we propose a novel end-to-end deep saliency network which could effectively utilize multi-scale feature maps according to their characteristics. Shallow layers often contain more local information, and deep layers have advantages in global semantics. Therefore, the network generates elaborate saliency maps by enhancing local and global information of feature maps in different layers. On one hand, local information of s"},"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":"1808.01634","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-08-05T15:31:22Z","cross_cats_sorted":[],"title_canon_sha256":"2c692b0d8c933c56a02ed0139b15bd9ed6abdbc3fc79f665822e1629c1a36806","abstract_canon_sha256":"2609e7ba8200a5fc2431609e51157e478188ce9f7c9e4c73ef03d16ac029b61c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:08:52.348086Z","signature_b64":"EV0wDD3+vtxxfGTW5u1S3W5Y9mjmUZq4kaJveRnqSUaSGpcHo+FuKP9FD9+cTjINliSjb6+VkeL2arKWD0eFDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d6a8bf9b4576f9f690738531fc126bfc23da73d4a71493b8fbbce14bf716e945","last_reissued_at":"2026-05-18T00:08:52.347347Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:08:52.347347Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-Attention Recurrent Network for Saliency Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fengdong Sun, Wenhui Li, Yuanyuan Guan","submitted_at":"2018-08-05T15:31:22Z","abstract_excerpt":"Feature maps in deep neural network generally contain different semantics. Existing methods often omit their characteristics that may lead to sub-optimal results. In this paper, we propose a novel end-to-end deep saliency network which could effectively utilize multi-scale feature maps according to their characteristics. Shallow layers often contain more local information, and deep layers have advantages in global semantics. Therefore, the network generates elaborate saliency maps by enhancing local and global information of feature maps in different layers. On one hand, local information of s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.01634","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":"1808.01634","created_at":"2026-05-18T00:08:52.347458+00:00"},{"alias_kind":"arxiv_version","alias_value":"1808.01634v1","created_at":"2026-05-18T00:08:52.347458+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.01634","created_at":"2026-05-18T00:08:52.347458+00:00"},{"alias_kind":"pith_short_12","alias_value":"22UL7G2FO347","created_at":"2026-05-18T12:31:59.375834+00:00"},{"alias_kind":"pith_short_16","alias_value":"22UL7G2FO347NEDT","created_at":"2026-05-18T12:31:59.375834+00:00"},{"alias_kind":"pith_short_8","alias_value":"22UL7G2F","created_at":"2026-05-18T12:31:59.375834+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/22UL7G2FO347NEDTQUY7YETL7Q","json":"https://pith.science/pith/22UL7G2FO347NEDTQUY7YETL7Q.json","graph_json":"https://pith.science/api/pith-number/22UL7G2FO347NEDTQUY7YETL7Q/graph.json","events_json":"https://pith.science/api/pith-number/22UL7G2FO347NEDTQUY7YETL7Q/events.json","paper":"https://pith.science/paper/22UL7G2F"},"agent_actions":{"view_html":"https://pith.science/pith/22UL7G2FO347NEDTQUY7YETL7Q","download_json":"https://pith.science/pith/22UL7G2FO347NEDTQUY7YETL7Q.json","view_paper":"https://pith.science/paper/22UL7G2F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1808.01634&json=true","fetch_graph":"https://pith.science/api/pith-number/22UL7G2FO347NEDTQUY7YETL7Q/graph.json","fetch_events":"https://pith.science/api/pith-number/22UL7G2FO347NEDTQUY7YETL7Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/22UL7G2FO347NEDTQUY7YETL7Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/22UL7G2FO347NEDTQUY7YETL7Q/action/storage_attestation","attest_author":"https://pith.science/pith/22UL7G2FO347NEDTQUY7YETL7Q/action/author_attestation","sign_citation":"https://pith.science/pith/22UL7G2FO347NEDTQUY7YETL7Q/action/citation_signature","submit_replication":"https://pith.science/pith/22UL7G2FO347NEDTQUY7YETL7Q/action/replication_record"}},"created_at":"2026-05-18T00:08:52.347458+00:00","updated_at":"2026-05-18T00:08:52.347458+00:00"}