{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:DZAKSL77EISCEEQYNDCICBDHP4","short_pith_number":"pith:DZAKSL77","schema_version":"1.0","canonical_sha256":"1e40a92fff222422121868c48104677f304739a4f30bdccde627c520bfd56d3e","source":{"kind":"arxiv","id":"1506.01497","version":3},"attestation_state":"computed","paper":{"title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jian Sun, Kaiming He, Ross Girshick, Shaoqing Ren","submitted_at":"2015-06-04T07:58:34Z","abstract_excerpt":"State-of-the-art object detection networks depend on region proposal algorithms to hypothesize object locations. Advances like SPPnet and Fast R-CNN have reduced the running time of these detection networks, exposing region proposal computation as a bottleneck. In this work, we introduce a Region Proposal Network (RPN) that shares full-image convolutional features with the detection network, thus enabling nearly cost-free region proposals. An RPN is a fully convolutional network that simultaneously predicts object bounds and objectness scores at each position. The RPN is trained end-to-end 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":"1506.01497","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-06-04T07:58:34Z","cross_cats_sorted":[],"title_canon_sha256":"608c63099cac8cf961888c3bfb16d6b63fa6c37e9b306fbea237abe8af393184","abstract_canon_sha256":"569a73b36dcb760438053286553969b08520b0393bc116d8285e0714d0b1ea57"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:23:18.784468Z","signature_b64":"OUYs86YnUi5W8j8vbQcdkviHfmyb7hdWOPqDzSqtsNZPYWg4S+rNLGhSz1IsPmQbpyuo0doMLNb/mA2cGOlpDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1e40a92fff222422121868c48104677f304739a4f30bdccde627c520bfd56d3e","last_reissued_at":"2026-05-18T01:23:18.783836Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:23:18.783836Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jian Sun, Kaiming He, Ross Girshick, Shaoqing Ren","submitted_at":"2015-06-04T07:58:34Z","abstract_excerpt":"State-of-the-art object detection networks depend on region proposal algorithms to hypothesize object locations. Advances like SPPnet and Fast R-CNN have reduced the running time of these detection networks, exposing region proposal computation as a bottleneck. In this work, we introduce a Region Proposal Network (RPN) that shares full-image convolutional features with the detection network, thus enabling nearly cost-free region proposals. An RPN is a fully convolutional network that simultaneously predicts object bounds and objectness scores at each position. The RPN is trained end-to-end to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1506.01497","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":"1506.01497","created_at":"2026-05-18T01:23:18.783947+00:00"},{"alias_kind":"arxiv_version","alias_value":"1506.01497v3","created_at":"2026-05-18T01:23:18.783947+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1506.01497","created_at":"2026-05-18T01:23:18.783947+00:00"},{"alias_kind":"pith_short_12","alias_value":"DZAKSL77EISC","created_at":"2026-05-18T12:29:17.054201+00:00"},{"alias_kind":"pith_short_16","alias_value":"DZAKSL77EISCEEQY","created_at":"2026-05-18T12:29:17.054201+00:00"},{"alias_kind":"pith_short_8","alias_value":"DZAKSL77","created_at":"2026-05-18T12:29:17.054201+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":25,"internal_anchor_count":6,"sample":[{"citing_arxiv_id":"1906.09266","citing_title":"A Multitask Network for Localization and Recognition of Text in Images","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"1907.00408","citing_title":"GarmNet: Improving Global with Local Perception for Robotic Laundry Folding","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"1907.09236","citing_title":"RGB-D image-based Object Detection: from Traditional Methods to Deep Learning Techniques","ref_index":70,"is_internal_anchor":true},{"citing_arxiv_id":"2601.12373","citing_title":"CD-TWINSAFE: A ROS-enabled Digital Twin for Scene Understanding and Safety Emerging V2I Technology","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2506.01942","citing_title":"OD3: Optimization-free Dataset Distillation for Object Detection","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2512.08227","citing_title":"New VVC profiles targeting Feature Coding for Machines","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2001.10773","citing_title":"Virtual KITTI 2","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"1804.02767","citing_title":"YOLOv3: An Incremental Improvement","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12503","citing_title":"Unveiling Hidden Lyman Alpha Emitters in the DESI DR1 Data","ref_index":66,"is_internal_anchor":false},{"citing_arxiv_id":"2104.13478","citing_title":"Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges","ref_index":68,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03968","citing_title":"Label-Efficient School Detection from Aerial Imagery via Weakly Supervised Pretraining and Fine-Tuning","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26869","citing_title":"KAYRA: A Microservice Architecture for AI-Assisted Karyotyping with Cloud and On-Premise Deployment","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09090","citing_title":"Investigating Anisotropy in Visual Grounding under Controlled Counterfactual Perturbations","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22552","citing_title":"Transferable Physical-World Adversarial Patches Against Pedestrian Detection Models","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01563","citing_title":"Multi-Dataset Cross-Domain Knowledge Distillation for Unified Medical Image Segmentation, Classification, and Detection","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20047","citing_title":"PASTA: A Patch-Agnostic Twofold-Stealthy Backdoor Attack on Vision Transformers","ref_index":75,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20030","citing_title":"Learning to count small and clustered objects with application to bacterial colonies","ref_index":68,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20026","citing_title":"Investigation of cardinality classification for bacterial colony counting using explainable artificial intelligence","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13278","citing_title":"DroneScan-YOLO: Redundancy-Aware Lightweight Detection for Tiny Objects in UAV Imagery","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09996","citing_title":"A Comparative Study of Modern Object Detectors for Robust Apple Detection in Orchard Imagery","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11042","citing_title":"Improving Layout Representation Learning Across Inconsistently Annotated Datasets via Agentic Harmonization","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08722","citing_title":"AI Driven Soccer Analysis Using Computer Vision","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05490","citing_title":"A Weak-Signal-Aware Framework for Subsurface Defect Detection: Mechanisms for Enhancing Low-SCR Hyperbolic Signatures","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14779","citing_title":"AIM: Asymmetric Information Masking for Visual Question Answering Continual Learning","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16630","citing_title":"Tri-Modal Fusion Transformers for UAV-based Object Detection","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DZAKSL77EISCEEQYNDCICBDHP4","json":"https://pith.science/pith/DZAKSL77EISCEEQYNDCICBDHP4.json","graph_json":"https://pith.science/api/pith-number/DZAKSL77EISCEEQYNDCICBDHP4/graph.json","events_json":"https://pith.science/api/pith-number/DZAKSL77EISCEEQYNDCICBDHP4/events.json","paper":"https://pith.science/paper/DZAKSL77"},"agent_actions":{"view_html":"https://pith.science/pith/DZAKSL77EISCEEQYNDCICBDHP4","download_json":"https://pith.science/pith/DZAKSL77EISCEEQYNDCICBDHP4.json","view_paper":"https://pith.science/paper/DZAKSL77","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1506.01497&json=true","fetch_graph":"https://pith.science/api/pith-number/DZAKSL77EISCEEQYNDCICBDHP4/graph.json","fetch_events":"https://pith.science/api/pith-number/DZAKSL77EISCEEQYNDCICBDHP4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DZAKSL77EISCEEQYNDCICBDHP4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DZAKSL77EISCEEQYNDCICBDHP4/action/storage_attestation","attest_author":"https://pith.science/pith/DZAKSL77EISCEEQYNDCICBDHP4/action/author_attestation","sign_citation":"https://pith.science/pith/DZAKSL77EISCEEQYNDCICBDHP4/action/citation_signature","submit_replication":"https://pith.science/pith/DZAKSL77EISCEEQYNDCICBDHP4/action/replication_record"}},"created_at":"2026-05-18T01:23:18.783947+00:00","updated_at":"2026-05-18T01:23:18.783947+00:00"}