{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:VJPDGNQ3RXR6IPEWDRTYS3KO7Y","short_pith_number":"pith:VJPDGNQ3","schema_version":"1.0","canonical_sha256":"aa5e33361b8de3e43c961c67896d4efe03a4aad9660685302dbfbb49e62fb3a7","source":{"kind":"arxiv","id":"1904.01355","version":5},"attestation_state":"computed","paper":{"title":"FCOS: Fully Convolutional One-Stage Object Detection","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chunhua Shen, Hao Chen, Tong He, Zhi Tian","submitted_at":"2019-04-02T11:56:36Z","abstract_excerpt":"We propose a fully convolutional one-stage object detector (FCOS) to solve object detection in a per-pixel prediction fashion, analogue to semantic segmentation. Almost all state-of-the-art object detectors such as RetinaNet, SSD, YOLOv3, and Faster R-CNN rely on pre-defined anchor boxes. In contrast, our proposed detector FCOS is anchor box free, as well as proposal free. By eliminating the predefined set of anchor boxes, FCOS completely avoids the complicated computation related to anchor boxes such as calculating overlapping during training. More importantly, we also avoid all hyper-paramet"},"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":"1904.01355","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2019-04-02T11:56:36Z","cross_cats_sorted":[],"title_canon_sha256":"53ed011a6b3a807bc30b8645a43c56c4e89d108f9f088e11be19a720717b04f2","abstract_canon_sha256":"8dc56d85eb8db776775543aeeda6f7da7a397b35e8801af54f185bfd92f5b2ba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:58:25.941659Z","signature_b64":"0DZC3ByW8jI2kYD5CA2udn6nRxurIyclI8GhdQu74mAD8PBroXKPWXyd8uKEYmVPQ/YxmYk9Vy0tC7FJJZdDAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aa5e33361b8de3e43c961c67896d4efe03a4aad9660685302dbfbb49e62fb3a7","last_reissued_at":"2026-07-04T23:58:25.941192Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:58:25.941192Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FCOS: Fully Convolutional One-Stage Object Detection","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chunhua Shen, Hao Chen, Tong He, Zhi Tian","submitted_at":"2019-04-02T11:56:36Z","abstract_excerpt":"We propose a fully convolutional one-stage object detector (FCOS) to solve object detection in a per-pixel prediction fashion, analogue to semantic segmentation. Almost all state-of-the-art object detectors such as RetinaNet, SSD, YOLOv3, and Faster R-CNN rely on pre-defined anchor boxes. In contrast, our proposed detector FCOS is anchor box free, as well as proposal free. By eliminating the predefined set of anchor boxes, FCOS completely avoids the complicated computation related to anchor boxes such as calculating overlapping during training. More importantly, we also avoid all hyper-paramet"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.01355","kind":"arxiv","version":5},"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/1904.01355/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":"1904.01355","created_at":"2026-07-04T23:58:25.941248+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.01355v5","created_at":"2026-07-04T23:58:25.941248+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.01355","created_at":"2026-07-04T23:58:25.941248+00:00"},{"alias_kind":"pith_short_12","alias_value":"VJPDGNQ3RXR6","created_at":"2026-07-04T23:58:25.941248+00:00"},{"alias_kind":"pith_short_16","alias_value":"VJPDGNQ3RXR6IPEW","created_at":"2026-07-04T23:58:25.941248+00:00"},{"alias_kind":"pith_short_8","alias_value":"VJPDGNQ3","created_at":"2026-07-04T23:58:25.941248+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.18848","citing_title":"Exact Linear Attention","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"1907.03465","citing_title":"A unified neural network for object detection, multiple object tracking and vehicle re-identification","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04086","citing_title":"LAA-X: Unified Localized Artifact Attention for Quality-Agnostic and Generalizable Face Forgery Detection","ref_index":80,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02169","citing_title":"Heterogeneous Model Fusion for Privacy-Aware Multi-Camera Surveillance via Synthetic Domain Adaptation","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02169","citing_title":"Heterogeneous Model Fusion for Privacy-Aware Multi-Camera Surveillance via Synthetic Domain Adaptation","ref_index":42,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VJPDGNQ3RXR6IPEWDRTYS3KO7Y","json":"https://pith.science/pith/VJPDGNQ3RXR6IPEWDRTYS3KO7Y.json","graph_json":"https://pith.science/api/pith-number/VJPDGNQ3RXR6IPEWDRTYS3KO7Y/graph.json","events_json":"https://pith.science/api/pith-number/VJPDGNQ3RXR6IPEWDRTYS3KO7Y/events.json","paper":"https://pith.science/paper/VJPDGNQ3"},"agent_actions":{"view_html":"https://pith.science/pith/VJPDGNQ3RXR6IPEWDRTYS3KO7Y","download_json":"https://pith.science/pith/VJPDGNQ3RXR6IPEWDRTYS3KO7Y.json","view_paper":"https://pith.science/paper/VJPDGNQ3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.01355&json=true","fetch_graph":"https://pith.science/api/pith-number/VJPDGNQ3RXR6IPEWDRTYS3KO7Y/graph.json","fetch_events":"https://pith.science/api/pith-number/VJPDGNQ3RXR6IPEWDRTYS3KO7Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VJPDGNQ3RXR6IPEWDRTYS3KO7Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VJPDGNQ3RXR6IPEWDRTYS3KO7Y/action/storage_attestation","attest_author":"https://pith.science/pith/VJPDGNQ3RXR6IPEWDRTYS3KO7Y/action/author_attestation","sign_citation":"https://pith.science/pith/VJPDGNQ3RXR6IPEWDRTYS3KO7Y/action/citation_signature","submit_replication":"https://pith.science/pith/VJPDGNQ3RXR6IPEWDRTYS3KO7Y/action/replication_record"}},"created_at":"2026-07-04T23:58:25.941248+00:00","updated_at":"2026-07-04T23:58:25.941248+00:00"}