{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:3P2T5TZWNJD5OEI4TGY7OXWA27","short_pith_number":"pith:3P2T5TZW","schema_version":"1.0","canonical_sha256":"dbf53ecf366a47d7111c99b1f75ec0d7e4ca46953a7ac8fa1cd15e3893ec0a8e","source":{"kind":"arxiv","id":"2309.08365","version":1},"attestation_state":"computed","paper":{"title":"M$^3$Net: Multilevel, Mixed and Multistage Attention Network for Salient Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Pan Gao, Xiaoyang Tan, Yao Yuan","submitted_at":"2023-09-15T12:46:14Z","abstract_excerpt":"Most existing salient object detection methods mostly use U-Net or feature pyramid structure, which simply aggregates feature maps of different scales, ignoring the uniqueness and interdependence of them and their respective contributions to the final prediction. To overcome these, we propose the M$^3$Net, i.e., the Multilevel, Mixed and Multistage attention network for Salient Object Detection (SOD). Firstly, we propose Multiscale Interaction Block which innovatively introduces the cross-attention approach to achieve the interaction between multilevel features, allowing high-level features to"},"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":"2309.08365","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-15T12:46:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"302926bd5016e39737b596a8b84009ce8a83eede7dbfc712e15e61d9fbd1ae96","abstract_canon_sha256":"ab4d380f9003bb11ea70b2f1deb2a5e90c3abe5142f8ca64b8f2ef3ea72c8adf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:51:05.718497Z","signature_b64":"scO2RJfidAZa/fcQ56Y/Qf4jXB8V4D82MvkX+R8WeN7sOUxtIeN5fwMzzHJ+At/08iYltpXluTTplalOUhViCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dbf53ecf366a47d7111c99b1f75ec0d7e4ca46953a7ac8fa1cd15e3893ec0a8e","last_reissued_at":"2026-07-05T06:51:05.718110Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:51:05.718110Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"M$^3$Net: Multilevel, Mixed and Multistage Attention Network for Salient Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Pan Gao, Xiaoyang Tan, Yao Yuan","submitted_at":"2023-09-15T12:46:14Z","abstract_excerpt":"Most existing salient object detection methods mostly use U-Net or feature pyramid structure, which simply aggregates feature maps of different scales, ignoring the uniqueness and interdependence of them and their respective contributions to the final prediction. To overcome these, we propose the M$^3$Net, i.e., the Multilevel, Mixed and Multistage attention network for Salient Object Detection (SOD). Firstly, we propose Multiscale Interaction Block which innovatively introduces the cross-attention approach to achieve the interaction between multilevel features, allowing high-level features to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.08365","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2309.08365/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2309.08365","created_at":"2026-07-05T06:51:05.718160+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.08365v1","created_at":"2026-07-05T06:51:05.718160+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.08365","created_at":"2026-07-05T06:51:05.718160+00:00"},{"alias_kind":"pith_short_12","alias_value":"3P2T5TZWNJD5","created_at":"2026-07-05T06:51:05.718160+00:00"},{"alias_kind":"pith_short_16","alias_value":"3P2T5TZWNJD5OEI4","created_at":"2026-07-05T06:51:05.718160+00:00"},{"alias_kind":"pith_short_8","alias_value":"3P2T5TZW","created_at":"2026-07-05T06:51:05.718160+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.06441","citing_title":"CPDR: Towards Highly-Efficient Salient Object Detection via Crossed Post-decoder Refinement","ref_index":47,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3P2T5TZWNJD5OEI4TGY7OXWA27","json":"https://pith.science/pith/3P2T5TZWNJD5OEI4TGY7OXWA27.json","graph_json":"https://pith.science/api/pith-number/3P2T5TZWNJD5OEI4TGY7OXWA27/graph.json","events_json":"https://pith.science/api/pith-number/3P2T5TZWNJD5OEI4TGY7OXWA27/events.json","paper":"https://pith.science/paper/3P2T5TZW"},"agent_actions":{"view_html":"https://pith.science/pith/3P2T5TZWNJD5OEI4TGY7OXWA27","download_json":"https://pith.science/pith/3P2T5TZWNJD5OEI4TGY7OXWA27.json","view_paper":"https://pith.science/paper/3P2T5TZW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.08365&json=true","fetch_graph":"https://pith.science/api/pith-number/3P2T5TZWNJD5OEI4TGY7OXWA27/graph.json","fetch_events":"https://pith.science/api/pith-number/3P2T5TZWNJD5OEI4TGY7OXWA27/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3P2T5TZWNJD5OEI4TGY7OXWA27/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3P2T5TZWNJD5OEI4TGY7OXWA27/action/storage_attestation","attest_author":"https://pith.science/pith/3P2T5TZWNJD5OEI4TGY7OXWA27/action/author_attestation","sign_citation":"https://pith.science/pith/3P2T5TZWNJD5OEI4TGY7OXWA27/action/citation_signature","submit_replication":"https://pith.science/pith/3P2T5TZWNJD5OEI4TGY7OXWA27/action/replication_record"}},"created_at":"2026-07-05T06:51:05.718160+00:00","updated_at":"2026-07-05T06:51:05.718160+00:00"}