{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:42T635CWFGPWQZN2EDDEWIQIVU","short_pith_number":"pith:42T635CW","schema_version":"1.0","canonical_sha256":"e6a7edf456299f6865ba20c64b2208ad3bce9446c8592ab9aef0f583a8c34a9a","source":{"kind":"arxiv","id":"2207.02255","version":3},"attestation_state":"computed","paper":{"title":"OSFormer: One-Stage Camouflaged Instance Segmentation with Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chuanbo Chen, Deng-Ping Fan, He Tang, Jialun Pei, Luc Van Gool, Tianyang Cheng","submitted_at":"2022-07-05T18:32:21Z","abstract_excerpt":"We present OSFormer, the first one-stage transformer framework for camouflaged instance segmentation (CIS). OSFormer is based on two key designs. First, we design a location-sensing transformer (LST) to obtain the location label and instance-aware parameters by introducing the location-guided queries and the blend-convolution feedforward network. Second, we develop a coarse-to-fine fusion (CFF) to merge diverse context information from the LST encoder and CNN backbone. Coupling these two components enables OSFormer to efficiently blend local features and long-range context dependencies for pre"},"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":"2207.02255","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-07-05T18:32:21Z","cross_cats_sorted":[],"title_canon_sha256":"5a1ca6ef4ac2c0ac536975c5fe34f253a212c18c0e6798e3a94c84517581227f","abstract_canon_sha256":"386404a986d8548be7aac4b9d095a09e1c4b468e4ef64f5a89fdfcce48f321cd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:45:24.904481Z","signature_b64":"LWvlfu7Nrk27xh/nkTVVNM8VsE6rXW5mhNarnal9bhjOSzUA0tsBGVdcLg0VVUFuMPbmUdmX86ztPbF06yRrAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e6a7edf456299f6865ba20c64b2208ad3bce9446c8592ab9aef0f583a8c34a9a","last_reissued_at":"2026-07-05T04:45:24.903971Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:45:24.903971Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OSFormer: One-Stage Camouflaged Instance Segmentation with Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chuanbo Chen, Deng-Ping Fan, He Tang, Jialun Pei, Luc Van Gool, Tianyang Cheng","submitted_at":"2022-07-05T18:32:21Z","abstract_excerpt":"We present OSFormer, the first one-stage transformer framework for camouflaged instance segmentation (CIS). OSFormer is based on two key designs. First, we design a location-sensing transformer (LST) to obtain the location label and instance-aware parameters by introducing the location-guided queries and the blend-convolution feedforward network. Second, we develop a coarse-to-fine fusion (CFF) to merge diverse context information from the LST encoder and CNN backbone. Coupling these two components enables OSFormer to efficiently blend local features and long-range context dependencies for pre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.02255","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2207.02255/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":"2207.02255","created_at":"2026-07-05T04:45:24.904037+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.02255v3","created_at":"2026-07-05T04:45:24.904037+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.02255","created_at":"2026-07-05T04:45:24.904037+00:00"},{"alias_kind":"pith_short_12","alias_value":"42T635CWFGPW","created_at":"2026-07-05T04:45:24.904037+00:00"},{"alias_kind":"pith_short_16","alias_value":"42T635CWFGPWQZN2","created_at":"2026-07-05T04:45:24.904037+00:00"},{"alias_kind":"pith_short_8","alias_value":"42T635CW","created_at":"2026-07-05T04:45:24.904037+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.09168","citing_title":"DRRNet: Macro-Micro Feature Fusion and Dual Reverse Refinement for Camouflaged Object Detection","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/42T635CWFGPWQZN2EDDEWIQIVU","json":"https://pith.science/pith/42T635CWFGPWQZN2EDDEWIQIVU.json","graph_json":"https://pith.science/api/pith-number/42T635CWFGPWQZN2EDDEWIQIVU/graph.json","events_json":"https://pith.science/api/pith-number/42T635CWFGPWQZN2EDDEWIQIVU/events.json","paper":"https://pith.science/paper/42T635CW"},"agent_actions":{"view_html":"https://pith.science/pith/42T635CWFGPWQZN2EDDEWIQIVU","download_json":"https://pith.science/pith/42T635CWFGPWQZN2EDDEWIQIVU.json","view_paper":"https://pith.science/paper/42T635CW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.02255&json=true","fetch_graph":"https://pith.science/api/pith-number/42T635CWFGPWQZN2EDDEWIQIVU/graph.json","fetch_events":"https://pith.science/api/pith-number/42T635CWFGPWQZN2EDDEWIQIVU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/42T635CWFGPWQZN2EDDEWIQIVU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/42T635CWFGPWQZN2EDDEWIQIVU/action/storage_attestation","attest_author":"https://pith.science/pith/42T635CWFGPWQZN2EDDEWIQIVU/action/author_attestation","sign_citation":"https://pith.science/pith/42T635CWFGPWQZN2EDDEWIQIVU/action/citation_signature","submit_replication":"https://pith.science/pith/42T635CWFGPWQZN2EDDEWIQIVU/action/replication_record"}},"created_at":"2026-07-05T04:45:24.904037+00:00","updated_at":"2026-07-05T04:45:24.904037+00:00"}