mlsanityData to 7 Oct 2026

CenterNet: Keypoint Triplets for Object Detection

arXiv 1904.08189 ↗First posted 17 Apr 2019cs.CVcited by 654

Not on the map. Why?

Abstract (arXiv)

In object detection, keypoint-based approaches often suffer a large number of incorrect object bounding boxes, arguably due to the lack of an additional look into the cropped regions. This paper presents an efficient solution which explores the visual patterns within each cropped region with minimal costs. We build our framework upon a representative one-stage keypoint-based detector named CornerNet. Our approach, named CenterNet, detects each object as a triplet, rather than a pair, of keypoints, which improves both precision and recall. Accordingly, we design two customized modules named cascade corner pooling and center pooling, which play the roles of enriching information collected by both top-left and bottom-right corners and providing more recognizable information at the central regions, respectively. On the MS-COCO dataset, CenterNet achieves an AP of 47.0%, which outperforms all existing one-stage detectors by at least 4.9%. Meanwhile, with a faster inference speed, CenterNet demonstrates quite comparable performance to the top-ranked two-stage detectors. Code is available at https://github.com/Duankaiwen/CenterNet.

Key facts. Cited by 654 papers in the map (data through 7 Oct 2026). First posted on arXiv 17 Apr 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 146; 2022: 146; 2023: 139; 2024: 124; 2025: 68; 2026: 31.

654 papers.

Sort:

By area:

  1. 2022Exploring Plain Vision Transformer Backbones for Object Detectioncited by 723
  2. 2024YOLOv10: Real-Time End-to-End Object Detectioncited by 508
  3. 2021Conditional DETR for Fast Training Convergencecited by 422
  4. 2022DiffusionDet: Diffusion Model for Object Detectioncited by 354
  5. 2022BoT-SORT: Robust Associations Multi-Pedestrian Trackingcited by 313
  6. 2022ActionFormer: Localizing Moments of Actions with Transformerscited by 308
  7. 2021PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detectioncited by 232
  8. 2023VoxelNeXt: Fully Sparse VoxelNet for 3D Object Detection and Trackingcited by 221
  9. 2021TOOD: Task-aligned One-stage Object Detectioncited by 218
  10. 2021Dynamic Head: Unifying Object Detection Heads with Attentionscited by 185
  11. 2021OTA: Optimal Transport Assignment for Object Detectioncited by 177
  12. 2022Sparse4D: Multi-view 3D Object Detection with Sparse Spatial-Temporal Fusioncited by 161
38 more
  1. 2023A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAScited by 149
  2. 2021Referring Transformer: A One-step Approach to Multi-task Visual Groundingcited by 143
  3. 2022Focal Sparse Convolutional Networks for 3D Object Detectioncited by 142
  4. 2021Focal and Global Knowledge Distillation for Detectorscited by 138
  5. 2021Efficient DETR: Improving End-to-End Object Detector with Dense Priorcited by 128
  6. 2022Towards Large-Scale Small Object Detection: Survey and Benchmarkscited by 119
  7. 2024WiLoR: End-to-end 3D Hand Localization and Reconstruction in-the-wildcited by 117
  8. 2021You Only Look One-level Featurecited by 116
  9. 2021General Instance Distillation for Object Detectioncited by 113
  10. 2021Instant-Teaching: An End-to-End Semi-Supervised Object Detection Frameworkcited by 112
  11. 2021Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regressioncited by 112
  12. 2023DetGPT: Detect What You Need via Reasoningcited by 112
  13. 2021Recent advances and clinical applications of deep learning in medical image analysiscited by 104
  14. 2022CenterFormer: Center-based Transformer for 3D Object Detectioncited by 99
  15. 2022Image Data Augmentation for Deep Learning: A Surveycited by 96
  16. 2021CondLaneNet: a Top-to-down Lane Detection Framework Based on Conditional Convolutioncited by 95
  17. 2021FusionPainting: Multimodal Fusion with Adaptive Attention for 3D Object Detectioncited by 92
  18. 2021Boundary Proposal Network for Two-Stage Natural Language Video Localizationcited by 88
  19. 2021Generalized Few-Shot Object Detection without Forgettingcited by 88
  20. 2023V3Det: Vast Vocabulary Visual Detection Datasetcited by 81
  21. 2022Parallel Rectangle Flip Attack: A Query-based Black-box Attack against Object Detectioncited by 79
  22. 2022AdaMixer: A Fast-Converging Query-Based Object Detectorcited by 78
  23. 2021CBNet: A Composite Backbone Network Architecture for Object Detectioncited by 77
  24. 2022PolarMix: A General Data Augmentation Technique for LiDAR Point Cloudscited by 74
  25. 2021QueryDet: Cascaded Sparse Query for Accelerating High-Resolution Small Object Detectioncited by 70
  26. 2022ShAPO: Implicit Representations for Multi-Object Shape, Appearance, and Pose Optimizationcited by 70
  27. 2025PromptHMR: Promptable Human Mesh Recoverycited by 70
  28. 2022CenterSnap: Single-Shot Multi-Object 3D Shape Reconstruction and Categorical 6D Pose and Size Estimationcited by 69
  29. 2021SOLQ: Segmenting Objects by Learning Queriescited by 68
  30. 2021Back-tracing Representative Points for Voting-based 3D Object Detection in Point Cloudscited by 67
  31. 2021ROCA: Robust CAD Model Retrieval and Alignment from a Single Imagecited by 66
  32. 2025Detect Anything via Next Point Predictioncited by 66
  33. 2022Few Could Be Better Than All: Feature Sampling and Grouping for Scene Text Detectioncited by 65
  34. 2021SiamMOT: Siamese Multi-Object Trackingcited by 62
  35. 2021Points as Queries: Weakly Semi-supervised Object Detection by Pointscited by 60
  36. 2023Radar-Camera Fusion for Object Detection and Semantic Segmentation in Autonomous Driving: A Comprehensive Reviewcited by 57
  37. 2023C2Former: Calibrated and Complementary Transformer for RGB-Infrared Object Detectioncited by 57
  38. 2024Gamba: Marry Gaussian Splatting with Mamba for single view 3D reconstructioncited by 56

50 most cited of 654 All 654 (JSON)