{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:2IFDIDQFVHPRRDYE324STMVYKW","short_pith_number":"pith:2IFDIDQF","schema_version":"1.0","canonical_sha256":"d20a340e05a9df188f04deb929b2b855a7fbfe3ecbee2a7aa8b94e05595df19b","source":{"kind":"arxiv","id":"1904.07850","version":2},"attestation_state":"computed","paper":{"title":"Objects as Points","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dequan Wang, Philipp Kr\\\"ahenb\\\"uhl, Xingyi Zhou","submitted_at":"2019-04-16T17:54:26Z","abstract_excerpt":"Detection identifies objects as axis-aligned boxes in an image. Most successful object detectors enumerate a nearly exhaustive list of potential object locations and classify each. This is wasteful, inefficient, and requires additional post-processing. In this paper, we take a different approach. We model an object as a single point --- the center point of its bounding box. Our detector uses keypoint estimation to find center points and regresses to all other object properties, such as size, 3D location, orientation, and even pose. Our center point based approach, CenterNet, is end-to-end diff"},"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":"1904.07850","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-16T17:54:26Z","cross_cats_sorted":[],"title_canon_sha256":"6f137fec373dd608249aba970d93998cab3bb38d6832eb78b3eef31cf8c7e686","abstract_canon_sha256":"45afff3a0592c19c4574359193ca620de6b4d39c115944276d78bd9ed9d5d321"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:47:48.133432Z","signature_b64":"ll3uGCYK3e6vPtdFJQq1Uk9LYLivcOaMDcoK15LdI2iJgu/CGBLCVaYGIUpe5xEGv8BwWg5LRppOM02C/K9CBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d20a340e05a9df188f04deb929b2b855a7fbfe3ecbee2a7aa8b94e05595df19b","last_reissued_at":"2026-05-17T23:47:48.132915Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:47:48.132915Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Objects as Points","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dequan Wang, Philipp Kr\\\"ahenb\\\"uhl, Xingyi Zhou","submitted_at":"2019-04-16T17:54:26Z","abstract_excerpt":"Detection identifies objects as axis-aligned boxes in an image. Most successful object detectors enumerate a nearly exhaustive list of potential object locations and classify each. This is wasteful, inefficient, and requires additional post-processing. In this paper, we take a different approach. We model an object as a single point --- the center point of its bounding box. Our detector uses keypoint estimation to find center points and regresses to all other object properties, such as size, 3D location, orientation, and even pose. Our center point based approach, CenterNet, is end-to-end diff"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.07850","kind":"arxiv","version":2},"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":"1904.07850","created_at":"2026-05-17T23:47:48.132996+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.07850v2","created_at":"2026-05-17T23:47:48.132996+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.07850","created_at":"2026-05-17T23:47:48.132996+00:00"},{"alias_kind":"pith_short_12","alias_value":"2IFDIDQFVHPR","created_at":"2026-05-18T12:33:07.085635+00:00"},{"alias_kind":"pith_short_16","alias_value":"2IFDIDQFVHPRRDYE","created_at":"2026-05-18T12:33:07.085635+00:00"},{"alias_kind":"pith_short_8","alias_value":"2IFDIDQF","created_at":"2026-05-18T12:33:07.085635+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":25,"internal_anchor_count":10,"sample":[{"citing_arxiv_id":"2605.22997","citing_title":"Scene Reconstruction as Mapping Priors for 3D Detection","ref_index":66,"is_internal_anchor":true},{"citing_arxiv_id":"2002.09053","citing_title":"Adapted Center and Scale Prediction: More Stable and More Accurate","ref_index":55,"is_internal_anchor":true},{"citing_arxiv_id":"2509.17931","citing_title":"Multi-needle Localization for Pelvic Seed Implant Brachytherapy based on Tip-handle Detection and Matching","ref_index":44,"is_internal_anchor":true},{"citing_arxiv_id":"2603.19538","citing_title":"MoCA3D: Monocular 3D Bounding Box Prediction in the Image Plane","ref_index":58,"is_internal_anchor":true},{"citing_arxiv_id":"2605.20963","citing_title":"Towards UAV Detection in the Real World: A New Multispectral Dataset UAVNet-MS and a New Method","ref_index":31,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19420","citing_title":"Beyond Waypoints: Dual-Heatmap Grounding for Cross-Embodiment Semantic Navigation","ref_index":32,"is_internal_anchor":true},{"citing_arxiv_id":"2512.03454","citing_title":"Think Before You Drive: World Model-Inspired Multimodal Grounding for Autonomous Vehicles","ref_index":70,"is_internal_anchor":true},{"citing_arxiv_id":"2602.04583","citing_title":"PEPR: Privileged Event-based Predictive Regularization for Domain Generalization","ref_index":64,"is_internal_anchor":true},{"citing_arxiv_id":"2603.03577","citing_title":"From Local Matches to Global Masks: Template-Guided Instance Detection and Segmentation in Open-World Scenes","ref_index":51,"is_internal_anchor":true},{"citing_arxiv_id":"2112.11790","citing_title":"BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-View","ref_index":59,"is_internal_anchor":true},{"citing_arxiv_id":"2604.03176","citing_title":"SFFNet: Synergistic Feature Fusion Network With Dual-Domain Edge Enhancement for UAV Image Object Detection","ref_index":64,"is_internal_anchor":false},{"citing_arxiv_id":"2107.08430","citing_title":"YOLOX: Exceeding YOLO Series in 2021","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08233","citing_title":"Inverse Design of Multi-Layer Sub-Pixel-Resolution RF Passives Through Grayscale Diffusion with Flexible S-Parameter Conditioning","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08781","citing_title":"Contour-Native Bridge Defect Detection and Compact Digital Archiving with Frequency-Supervised Fourier Contours","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23718","citing_title":"Caries DETR: Tooth Structure-aware Prior and Lesion-aware Dynamic Loss Refinement for DETR Based Caries Detection","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00362","citing_title":"Time-series Meets Complex Motion Modeling: Robust and Computational-effective Motion Predictor for Multi-object Tracking","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2303.05499","citing_title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10305","citing_title":"Class-Adaptive Cooperative Perception for Multi-Class LiDAR-based 3D Object Detection in V2X Systems","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10391","citing_title":"FishRoPE: Projective Rotary Position Embeddings for Omnidirectional Visual Perception","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08074","citing_title":"DinoRADE: Full Spectral Radar-Camera Fusion with Vision Foundation Model Features for Multi-class Object Detection in Adverse Weather","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07759","citing_title":"WUTDet: A 100K-Scale Ship Detection Dataset and Benchmarks with Dense Small Objects","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06332","citing_title":"Telescope: Learnable Hyperbolic Foveation for Ultra-Long-Range Object Detection","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16758","citing_title":"Frozen Vision Transformers for Dense Prediction on Small Datasets: A Case Study in Arrow Localization","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18208","citing_title":"Towards Symmetry-sensitive Pose Estimation: A Rotation Representation for Symmetric Object Classes","ref_index":65,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04606","citing_title":"Reference-based Category Discovery: Unsupervised Object Detection with Category Awareness","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2IFDIDQFVHPRRDYE324STMVYKW","json":"https://pith.science/pith/2IFDIDQFVHPRRDYE324STMVYKW.json","graph_json":"https://pith.science/api/pith-number/2IFDIDQFVHPRRDYE324STMVYKW/graph.json","events_json":"https://pith.science/api/pith-number/2IFDIDQFVHPRRDYE324STMVYKW/events.json","paper":"https://pith.science/paper/2IFDIDQF"},"agent_actions":{"view_html":"https://pith.science/pith/2IFDIDQFVHPRRDYE324STMVYKW","download_json":"https://pith.science/pith/2IFDIDQFVHPRRDYE324STMVYKW.json","view_paper":"https://pith.science/paper/2IFDIDQF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.07850&json=true","fetch_graph":"https://pith.science/api/pith-number/2IFDIDQFVHPRRDYE324STMVYKW/graph.json","fetch_events":"https://pith.science/api/pith-number/2IFDIDQFVHPRRDYE324STMVYKW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2IFDIDQFVHPRRDYE324STMVYKW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2IFDIDQFVHPRRDYE324STMVYKW/action/storage_attestation","attest_author":"https://pith.science/pith/2IFDIDQFVHPRRDYE324STMVYKW/action/author_attestation","sign_citation":"https://pith.science/pith/2IFDIDQFVHPRRDYE324STMVYKW/action/citation_signature","submit_replication":"https://pith.science/pith/2IFDIDQFVHPRRDYE324STMVYKW/action/replication_record"}},"created_at":"2026-05-17T23:47:48.132996+00:00","updated_at":"2026-05-17T23:47:48.132996+00:00"}