You Only Look Once: Unified, Real-Time Object Detection
Open accessThe DOI matches its Crossref record; 53 of the 53 references it cites were found in a registry or an index; 8 of the 25 sources its claims cite were checked for support.
Abstract
We present YOLO, a new approach to object detection. Prior work on object detection repurposes classifiers to perform detection. Instead, we frame object detection as a regression problem to spatially separated bounding boxes and associated class probabilities. A single neural network predicts bounding boxes and class probabilities directly from full images in one evaluation. Since the whole detection pipeline is a single network, it can be optimized end-to-end directly on detection performance. Our unified architecture is extremely fast. Our base YOLO model processes images in real-time at 45 frames per second. A smaller version of the network, Fast YOLO, processes an astounding 155 frames per second while still achieving double the mAP of other real-time detectors. Compared to state-of-the-art detection systems, YOLO makes more localization errors but is less likely to predict false positives on background. Finally, YOLO learns very general representations of objects. It outperforms other detection methods, including DPM and R-CNN, when generalizing from natural images to other domains like artwork.
Overview
CoChat Summary
TL;DR
YOLO reframes object detection as a single regression problem, using one convolutional network to predict bounding boxes and class probabilities directly from full images. It achieves real-time detection speeds while remaining competitive with, and complementary to, slower region-based detectors.
Key findings
- YOLO runs at 45 FPS on a Titan X GPU, and Fast YOLO runs at 155 FPS; Fast YOLO reaches 52.7% mAP on PASCAL VOC 2007, more than double prior real-time detectors, while YOLO reaches 63.4% mAP.
- On PASCAL VOC 2012, YOLO scores 57.9% mAP; combining Fast R-CNN with YOLO raises Fast R-CNN from 71.8% to 75.0% mAP on VOC 2007, a 3.2% gain.
- YOLO makes fewer background false positives than Fast R-CNN: Fast R-CNN has 13.6% background false positives among top detections and is almost 3× more likely to predict background detections than YOLO.
- YOLO generalizes better to artwork: on Picasso, YOLO gets 53.3 AP versus R-CNN’s 10.4 AP and DPM’s 37.8 AP; on People-Art, YOLO gets 45 AP versus R-CNN’s 26 AP and DPM’s 32 AP.
Methods
- Detection is modeled as a single CNN regression: the image is divided into an S×S grid; for PASCAL VOC, S=7, B=2, C=20, producing a 7×7×30 tensor of bounding boxes, confidence scores, and class probabilities.
- The base network has 24 convolutional layers followed by 2 fully connected layers; Fast YOLO uses 9 convolutional layers. Convolutional layers are pretrained on ImageNet at 224×224, then detection training uses 448×448 input.
- Training uses PASCAL VOC 2007 and 2012 for about 135 epochs, batch size 64, momentum 0.9, decay 0.0005, sum-squared error with λ_coord=5 and λ_noobj=0.5, dropout, and data augmentation.
Limitations
- The paper states YOLO imposes strong spatial constraints because each grid cell predicts only two boxes and one class, limiting nearby objects and struggling with small objects in groups such as flocks of birds.
- The paper states YOLO struggles to generalize to objects in new or unusual aspect ratios or configurations, uses relatively coarse features due to downsampling, and its loss treats small and large box errors equally; its main error source is incorrect localization.
- The paper states YOLO still lags state-of-the-art detection accuracy and struggles to precisely localize some objects, especially small ones.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Figures





Verification
Claims the paper makes
6 Valid · 8 Not valid · 15 Not checked · 92 Own results and interpretations
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“While it is much faster than R-CNN, it still falls short of real-time and takes a significant accuracy hit from not having good proposals.”
What the sources say
- Could not verifycites [20] [20] K. Lenc and A. Vedaldi. R-cnn minus r. arXiv preprint arXiv:1506.06981 , 2015. 5, 6 - sourceExperimental — accuracy not yet measured
The ConvNet-based Object Detection section identifies R-CNN minus R as a method that uses predefined regions instead of region proposals. It gives no runtime measurement or assessment of whether the method achieves real-time detection; searches for real-time performance and speed did not establish that claim. (LLM, conf=0.76)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Could not verify
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“To avoid overfitting we use dropout and extensive data augmentation.”
What the sources say
- Partly supportedcites [18] [18] G. E. Hinton, N. Srivastava, A. Krizhevsky, I. Sutskever, and R. R. Salakhutdinov. Improving neural networks by preventing co-adaptation of feature detectors. arXiv preprint arXiv:1207.0580 , 2012. 4 - sourceExperimental — accuracy not yet measured
The paper states that dropout reduces overfitting (p. 1) and describes using dropout with data augmentation for its ImageNet model (H Models for ImageNet, p. 18). It does not establish that YOLO uses either technique or describe YOLO’s augmentation as extensive. (LLM, conf=0.88)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“However, only 30Hz DPM [31] actually runs in real-time.”
What the sources say
- Supportedcites [31] [31] M. A. Sadeghi and D. Forsyth. 30hz object detection with dpm v5. In Computer Vision-ECCV 2014 , pages 65-79. Springer, 2014. 5, 6 - source
The Introduction (p.1) states that 'except for certain objects including face, pedestrians and certain rigid objects, detectors do not currently run at video rate' and that the presented architecture detects the 20 PASCAL VOC categories simultaneously at 30Hz, i.e. at video/real-time rate. The Abstract (p.1) and Table 2 (Method) bound the comparison to other DPM speed-up efforts: reference DPM at 0.07Hz, the fastest GPU 'Vanilla DPM' at ~1Hz, FTVQ at 0.53s, and 'over an order of magnitude faster than the previous fastest DPM implementation', so none of the listed variants reaches real-time. Thus our copy supports both parts of the attribution: that this 30Hz DPM runs in real-time and that it is the only such DPM among the speed-up efforts compared. (LLM, conf=0.82)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“While it is much faster than R-CNN, it still falls short of real-time and takes a significant accuracy hit from not having good proposals.”
What the sources say
- Could not verifycites [20] [20] K. Lenc and A. Vedaldi. R-cnn minus r. arXiv preprint arXiv:1506.06981 , 2015. 5, 6 - sourceExperimental — accuracy not yet measured
The ConvNet-based Object Detection section identifies R-CNN minus R and says it uses predefined regions in an SPPnet system, but gives no speed comparison with R-CNN. A search for R-CNN minus R and speed found no passage in our copy establishing that it is much faster. (LLM, conf=0.73)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Could not verify
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“While it is much faster than R-CNN, it still falls short of real-time and takes a significant accuracy hit from not having good proposals.”
What the sources say
- Partly supportedcites [20] [20] K. Lenc and A. Vedaldi. R-cnn minus r. arXiv preprint arXiv:1506.06981 , 2015. 5, 6 - sourceExperimental — accuracy not yet measured
The “ConvNet-based Object Detection” section (page unavailable) says R-CNN minus R uses predefined regions instead of region proposals. It does not say that this causes a significant accuracy loss; the paper’s discussion of low accuracy concerns a different system, naïve Faster R-CNN. (LLM, conf=0.83)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
84 more claims
Create a free account to see all 121 claims and to verify the 2 references still open.
- Probably not a substantial claim. 17
- It may state two separate claims as one. 15
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“which was not thoroughly investigated in prevIoUs work such as YOLOv1 [20] and YOLOv2 [51] employing MSE/L2 loss (Mean Squared Error).”
From Object Detection in 20 Years: A Survey (2023) · cites this paper as [20]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“the YOLO series models v2-v5 [144-147] are some of the most advanced object detection methods based on DNN, which have good performance in terms of speed and precision.”
From A survey of model compression strategies for object detection (2023) · cites this paper as [144]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“As a typical and more widely used new form of applications [9], various deep learning-based intelligent services and applications have changed many aspects of people's lives due to the great advantages of Deep Learning (DL) in the fields of Computer Vision (CV) and Natural Language Processing (NLP) [10].”
From Convergence of Edge Computing and Deep Learning: A Comprehensive Survey (2020) · cites this paper as [9]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“A convolutional neural network predicts the bounding boxes as well as class probabilities for all the objects depicted in an image.”
From Object detection using YOLO: challenges, architectural successors, datasets and applications (2023) · cites this paper as [56]
The cited source says what the claim attributes to it.
In the citing paper
“Authors of YOLO [56] have reframed the problem of object detection as a regression problem instead of classification problem.”
From Object detection using YOLO: challenges, architectural successors, datasets and applications (2023) · cites this paper as [56]
6 more claims about this paper
Create a free account to see every claim other papers make about this one.
Citations
Cites
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2577031 · Cited by 73,472
Self-citationFaster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2015) · arXiv · doi:10.48550/arxiv.1506.01497 · Cited by 70,812
Self-citationGoing deeper with convolutions
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298594 · Cited by 48,562
ImageNet Large Scale Visual Recognition Challenge
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-015-0816-y · Cited by 39,380 · cited 1×
“We pretrain our convolutional layers on the ImageNet 1000-class competition dataset [29].”
MethodHistograms of Oriented Gradients for Human Detection
Dalal, N., & Triggs, B. (2005) · 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) · doi:10.1109/cvpr.2005.177 · Cited by 33,584 · cited 2×
“Detection pipelines generally start by extracting a set of robust features from input images (Haar [25], SIFT [23], HOG [4], convolutional features [6]).”
MethodRich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
Girshick, R., Donahue, J., Darrell, T., & Malik, J. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.81 · Cited by 32,684 · cited 2×
“Then, classifiers [35, 21, 13, 10] or localizers [1, 31] are used to identify objects in the feature space.”
MethodSelf-citationGirshick, R. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.169 · Cited by 28,105
Self-citationDelving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
He, K., Zhang, X., Ren, S., & Sun, J. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.123 · Cited by 19,741 · cited 1×
“Convolutional neural networks (CNNs) achieve impressive performance on classification tasks at real-time speeds [13].”
Object recognition from local scale-invariant features
Lowe, D. G. (1999) · Proceedings of the Seventh IEEE International Conference on Computer Vision · doi:10.1109/iccv.1999.790410 · Cited by 16,472 · cited 1×
“Detection pipelines generally start by extracting a set of robust features from input images (Haar [25], SIFT [23], HOG [4], convolutional features [6]).”
MethodRobust Real-Time Face Detection
Viola, P., & Jones, M. J. (2004) · International Journal of Computer Vision · doi:10.1023/b:visi.0000013087.49260.fb · Cited by 14,097 · cited 1×
“Detectors for single classes like faces or people can be highly optimized since they have to deal with much less variation [36].”
Background
Cited by
Items 46,301–46,400 of 51,399
Infrared Small Target Detection Method Based on Improved YOLOv11n
Wang, C., Chen, M., Zhang, K., et al. (2025) · doi:10.1109/icaidm66813.2025.11293392
Real-Time Suspicious Activity Detection for Exam Proctoring Using YOLOv8 and Multi-Angle Datasets
Finantyo, B. A. A., Waworuntu, A., Istiono, W., et al. (2025) · International Conference on New Media Studies (CONMEDIA) · doi:10.1109/conmedia67140.2025.11290221
“While two-stage models like Faster R-CNN are highly accurate, their speed makes them unsuitable for real-time detection compared to one-stage models like YOLO [11][12][13].”
Visual Quality Enhancement of Adversarial Examples based on Adaptive Visible Watermarking
Shen, Q., Wang, J., Li, X., Li, J., Ma, B., & Zhao, Y. (2025) · International Conference on Computer Science and Network Technology (ICCSNT) · doi:10.1109/iccsnt67644.2025.11291294
Research on Conveyor Belt Surface Quality Detection Method Based on VGG16-Unet Model
Chang, D. (2025) · International Conference on Computer Vision and Data Mining (ICCVDM) · doi:10.1109/iccvdm66874.2025.11290402
Intelligent Plagiarism Detection System for Online Exams Based on Multimodal Feature Fusion
Zhu, B., & Chen, Z. (2025) · International Conference on Algorithm, Image Processing and Machine Vision (AIPMV) · doi:10.1109/aipmv67185.2025.11290090
Semi-Supervised Greenhouse Film Damage Detection
Zhang, Y., Huang, Z., Wang, H., et al. (2025) · International Conference on Computer Vision and Data Mining (ICCVDM) · doi:10.1109/iccvdm66874.2025.11290086
“R ELATED W ORK Object detection methods are broadly divided into one-stage (e.g., YOLO [1], SSD [2]) and two-stage approaches (e.g., R-2025 CNN [4], Faster R-CNN[6]).”
Real-Time Cascaded Pre-Processing for User-Generated Images in Counterfeit Identification Systems
Peng, J., Zou, B., & Li, H. (2025) · International Conference on Computer Vision and Data Mining (ICCVDM) · doi:10.1109/iccvdm66874.2025.11290088
PEAN-YOLO: Improved YOLO11 for Small-Scale PCB Defect Detection
Feng, S., & Zhang, Y. (2025) · International Conference on Algorithm, Image Processing and Machine Vision (AIPMV) · doi:10.1109/aipmv67185.2025.11290098
“In contrast, CNN-based single-stage detectors including the YOLO series [3]–[14] streamline the pipeline through direct prediction of bounding box locations and class probabilities, enabling real-time inference.”
IU-DINO: Improved Detection Method for UAVs Based on DINO
Tong, X., Dan, S., Duan, B., et al. (2025) · International Conference on Computer Science and Network Technology · doi:10.1109/iccsnt67644.2025.11291501
Discount Eye-Tracking for Usability Testing 2.0: Multimodal CNN with Geometric Features
Kolidov, I. A., & Bakaev, M. (2025) · International Scientific-Technical Conference on Actual Problems of Electronic Instrument Engineering (APEIE) · doi:10.1109/apeie66761.2025.11289300
“In classical CNN models such as ResNet [20], VGG [21], or YOLO [22], the input typically consists of images of size 224×224×3 or 448×448×3.”
Xue, Z., Lin, C., Fan, X., et al. (2025) · International Conference on Artificial Intelligence, Automation and High Performance Computing (AIAHPC) · doi:10.1109/aiahpc66801.2025.11290267
“To improve speed, one-stage detectors like YOLO [3] and SSD [4] emerged, framing detection as a regression problem for real-time performance.”
A Space-based Maritime Surveillance Radar Ship Detection Model Based on Improved YOLOv8n
Zhu, M., Zhan, M., Yuan, H., et al. (2025) · International Conference on Electronic Information Engineering and Computer Science (EIECS) · doi:10.1109/eiecs67708.2025.11283535
PADet: Prediction Alignment Learning for One-Stage Object Detection
Zhu, B., Liu, C., Su, J., Zhou, X., Mao, C., & Li, X. (2025) · International Conference on Artificial Intelligence, Automation and High Performance Computing (AIAHPC) · doi:10.1109/aiahpc66801.2025.11290292
Research on Low-Slow-Small Target Detection Technology Based on Improved YOLOv10n
Tan, C. L., Chen, J., Wang, L., Zhang, A., Ran, X., & Ju, H. (2025) · International Conference on Electronic Information Engineering and Computer Science (EIECS) · doi:10.1109/eiecs67708.2025.11283525
“The YOLO family of algorithms proposed by Redmon et al [2] transforms the target detection into a regression problem, achieving a better balance between speed and accuracy.”
Enhanced UAV Detection via Multi-Scale Feature Fusion in Complex Environments
Shen, Z., Wu, Y., Sun, P., et al. (2025) · International Conference on Artificial Intelligence, Automation and High Performance Computing (AIAHPC) · doi:10.1109/aiahpc66801.2025.11290607
“Among vision-based solutions, two-stage detectors like Faster R-CNN [2] achieve high accuracy but suffer from computational overhead, operating at merely 20.7 FPS. Single-stage detectors, particularly the YOLO series [3], offer better speed-accuracy trade-offs but struggle with small UAV targets.”
InfluentialLiu, Z., Guo, Y., An, G., et al. (2025) · International Conference on Artificial Intelligence, Automation and High Performance Computing (AIAHPC) · doi:10.1109/aiahpc66801.2025.11290413
“In contrast, single-stage algorithms represented by YOLO [4] and SSD [5] model the detection task as an end-to-end regression problem, significantly improving detection speed while maintaining high accuracy, making them more suitable for real-time demanding scenarios such as autonomous driving.”
Intelligent Technologies of Remote Identification of Dynamic Objects
Кондратов, О. М., Severyn, V., & Nikulina, O. (2025) · IEEE KhPI Week on Advanced Technology (KhPIWeek) · doi:10.1109/khpiweek61436.2025.11288651 · Cited by 1
“In 2015, the “You Only Look Once” (YOLO) method was proposed [23].”
ACC-YOLOv8: A Transmission Line Insulator Defect Detection Algorithm Based on Improved YOLOv8
Liang, J., Jin, F., Zhang, Y., et al. (2025) · International Conference on Electronic Information Engineering and Computer Science (EIECS) · doi:10.1109/eiecs67708.2025.11283497
Animal Detection and Recognition Using the ZooSnap Image Collection
Xie, Z., Yu, T., Xu, P., & Yang, S. (2025) · International Conference on Artificial Intelligence, Automation and High Performance Computing (AIAHPC) · doi:10.1109/aiahpc66801.2025.11290522
“To streamline the creation process, an automated tool based on YOLO object detection [1] was developed to efficiently crop animal faces from images.”
Automated detection of HER2 gene copy number in breast cancer using deep learning techniques
Micaraseth, T., Shuangshoti, S., Prommaouan, S., Shuangshoti, S., Ullah, R., & Phanomchoeng, G. (2025) · Intelligence-Based Medicine · doi:10.1016/j.ibmed.2025.100333
Li, Y., Fang, Y., Deng, H., Xu, Y., & Yang, J. (2025) · Signal Image and Video Processing · doi:10.1007/s11760-025-05035-1 · Cited by 2
“Deep learning-based methods have evolved from two-stage detectors like Faster R-CNN [11] to more efficient one-stage detectors such as SSD [12] and the YOLO series [9, 13–18], which strike an excellent balance between speed and accuracy.”
Research on Aircraft Target Detection and Instance Segmentation Model Based on RT-DETR
Ren, Y., Mao, Q., Zheng, C., et al. (2025) · International Conference on Computer Information Science and Artificial Intelligence (CISAI) · doi:10.1145/3773365.3773461
“From early two-stage detectors such as R-CNN [2] and Fast R-CNN [3], to single-stage detectors like YOLO [4] and SSD [5], and more recently, Transformer-based models such as DETR [6], Deformable DETR [7], as well as YOLACT [8], SOLOv2 [9], and QueryInst [10], accuracy, speed, and instance…”
Smart Wearable for Real-Time Object Detection and Assistive Navigation
Sharma, S., Vyas, B., Charki, S. B., et al. (2025) · 2025 9th International Conference on Computational System and Information Technology for Sustainable Solutions (CSITSS) · doi:10.1109/csitss67709.2025.11295712 · Cited by 1
Hybrid Long-Term Multi Object Tracking (HLT-MOT) System
Ahmed, N., Schäfer, B., & Tchouankem, H. (2025) · doi:10.1109/csitss67709.2025.11295337
“Traditional tracking systems, which often couple a detector like YOLO [1] with a motion-centric tracker such as DeepSORT [2], [3], perform well in short-term scenarios but often fail when an object reappears after a long absence, as their underlying feature representations lack the robustness to…”
Automated Train Control Using Machine Vision for Red Flag Detection in Railway Safety
Rahman, S., Rahman, K. E., Shuva, J. S., et al. (2025) · doi:10.1109/icsit65336.2025.11294664
“Redmon et al. [9] introduced YOLO, balancing speed and accuracy.”
Pneumonia Detection and Severity Grading Using YOLOv8
Kollu, P. K., Praveen, A., Ranganath, A., et al. (2025) · doi:10.1109/icsit65336.2025.11295105
“Although earlier versions like YOLOv3 [3] struggled with fine features, YOLOv8 introduces anchor-free detection and decoupled classification heads [11], [13], [14], making it ideal for medical diagnostics.”
Developing Robust AI Models for Identification Friend and Foe
Bokisha, H. O., Zemerly, J., Martino, L., et al. (2025) · International Conference Control and Robots · doi:10.1109/iccr67387.2025.11291957
“YOLO Family: The ”You Only Look Once” (YOLO) framework revolutionized real-time detection by treating it as a single regression problem [6].”
Safe Robot Handover Using YOLO and Voice Commands or Visual Triggers
Abdelkader, A. B., Mohammad, A. A., Weaver, J. M. R., et al. (2025) · doi:10.1109/aibthings66987.2025.11296183
“The YOLO (You Only Look Once) framework, introduced in 2016 by Redmon et al. [13], marked a major shift in object detection by framing the task as a single regression problem rather than a multi-step pipeline involving region proposals and classification.”
Crowd-Aware Smart Weapon Detection with Multi-Camera Fusion and Real-Time Threat Prioritization
Rohith Amalan, J., Vigneshraj, D., Priscilla, R., et al. (2025) · doi:10.1109/csitss67709.2025.11295035
Automated Detection and Localization of Branding Logos in Industrial Product Images
T, S. B., & Sagar, B. M. (2025) · doi:10.1109/csitss67709.2025.11294366
“Through this work, we demonstrate that combining a custom deep learning detector with a cloud-based vision service provides a robust and flexible solution for automated logo detection and analysis in industrial contexts [1][4].”
InfluentialBW-YOLO: small target vehicle detection based on improved YOLOv8
Nai-ning, W., & Lü, Q. (2025) · doi:10.1109/iccs67844.2025.11291653
“For example, SSD [9] and YOLO [10].”
Deep Learning-Based Aircraft Surface Painting Quality Inspection
Qu, S. (2025) · doi:10.1109/iccs67844.2025.11291958
“Algorithms such as SSD [2] and the YOLO series [3] have achieved one-stage object detection.”
Shangguan, J., & Xue, T. (2025) · doi:10.1109/iccs67844.2025.11292052
“Existing deep learning-based object detection algorithms are mainly categorized into two-stage methods, such as Faster R-CNN [1], and one-stage methods, represented by the YOLO series [2].”
Enhancing UAV Small Target Detection via SPD-Conv and Hybrid Attention in YOLOv8
Chen, Y., Shen, X., Xu, Y., et al. (2025) · International Conference on Intelligent Computing and Human-Computer Interaction (ICHCI) · doi:10.1109/ichci67614.2025.11291748
“…layer, and the YOLO series achieved a major breakthrough in the field of single-stage target detection - from the single regression frame of YOLOv1 [8] to the use of residual structure to enhance small target detection of YOLOv3 [9], and then to YOLOv4 [10] combined with CSPDarknet and other data…”
GAM-YOLO: An Enhanced Small Object Detection Model Integrating Global Attention Mechanism
Yang, Y. (2025) · International Conference on Intelligent Computing and Human-Computer Interaction (ICHCI) · doi:10.1109/ichci67614.2025.11291985
“From YOLOv1 [6], through key iterations like YOLOv3 [7] and YOLOv4 [8], to YOLOv5 [2], they progressively improved via CSPNet and PANet [9].”
Chen, Y., Lu, S., & Zhou, W. (2025) · 2025 6th International Conference on Intelligent Computing and Human-Computer Interaction (ICHCI) · doi:10.1109/ichci67614.2025.11292408
“The torso tilt detection is an orientated bounding box detection problem, which can be solved through YOLO [13], [14].”
Tunnel Lighting Detection Based on Lightweight Network and Boundary Interaction
Chen, J., Liu, F., Lin, J., et al. (2025) · International Conference on Electronic Information Technology and Computer Engineering (EITCE) · doi:10.1145/3766671.3766672
“After improvements and innovations, the single-stage object detection methods exemplified by YOLO [5] series can achieve fast response and multi-scale detection in an end-to-end manner, but still suffer from weak localization accuracy and degraded performance in the face of complex backgrounds.”
Wang, D., Zhou, X.-F., Zhang, L., liu, Y., & Liu, S. (2025) · International Conference on Electronic Information Technology and Computer Engineering (EITCE) · doi:10.1145/3766671.3766709
“…network method Regional Proposals (R-CNN, Fast R-CNN, Faster R-CNN, Grade RCNN) Single Shot MultiBox Detector (SSD) You Only Look Once (YOLO) [ 11 ] Single Refined Divine network for Object Detection (RefineDet) Retina-Net Deformable convolutional network [ 12 - 13 ] Similarly, square…”
Deteksi Kerusakan Jalan Menggunakan Model Deep Learning YOLOv8 dengan DDS2022
Prastyo, E. H. A. (2025) · Inovate Jurnal Ilmiah Inovasi Teknologi Informasi · doi:10.33752/inovate.v10i1.11198
High-Low Frequency Feature Alignment for Few-Shot Object Detection
Yao, X., Liu, J., Li, Q., et al. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-9964-3_35
Li, Y. E., Yang, W., Tian, H., Wang, Z., & Wang, Y. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-9849-3_8
NOFTrack: Efficient Multi-Object Tracking with a Speed Advantage
Jiang, M. Y., Ke, J., & Guo, B. (2024) · doi:10.1109/isdh64927.2024.00043
Xiao, F., Li, X., Xiang, H., Cai, J., Pu, Z., & Gao, X. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5165809
Red Grape Detection with Accelerated Artificial Neural Networks in the FPGA’s Programmable Logic
Magalhães, S. C., Almeida, M., dos Santos, F. N., Moreira, A. P., Dias, J., & Cunha, M. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-30156-7_3
Li, J., Sangi, A. R., Sun, T., & Li, C. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-9964-3_33
Automated strabismus diagnosis: A deep learning approach using cover test video analysis
Santos, R. D. D. A., de Almeida, J. D. S., Teixeira, J. A. M., Valente, T. L. A., Braz, G., & de Paiva, A. C. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.111161 · Cited by 1
Chen, J., Zhao, W., Liu, X., et al. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-9964-3_1
EIL-YOLO: A Lightweight Model for Enhanced Small Object Detection in UAV Images
Gong, L., Cheng, Y., Deng, Z., Li, K., & Yin, J. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-9964-3_20
Research on Workpiece Recognition Algorithm based on Deep Learning
Xia, X., Li, R., Gao, Y., et al. (2024) · doi:10.1109/ictech63197.2024.00032
Underwater Organism Detection Based on Hybrid Attention and Boundary Mining
Zhang, X., Xu, S., & Li, J. (2024) · doi:10.1109/isdh64927.2024.00035
Pig Detection Method Based on Improved YOLOv5
Li, L., & Li, F. (2024) · doi:10.1109/isdh64927.2024.00022
Cotton University (2024) · Zenodo (CERN European Organization for Nuclear Research) · doi:10.5281/zenodo.13731366
Focusing by Contrastive Attention: Enhancing VLMs’ Visual Reasoning
Ge, Y., Liu, S., Wang, Y., Mei, L., Bi, B., Zhou, X., Yao, J., Guo, J., & Cheng, X. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37383-0_32 · Cited by 12
Semantic Segmentation Everything Model for Point‐Prompted Oriented Object Detection
Lu, X., & Bie, Z. (2025) · Electronics Letters · doi:10.1049/ell2.70254
Lu, C., Liu, Y., He, T., et al. (2025) · Optics Communications · doi:10.1016/j.optcom.2025.132460
Physics-Guided Synthetic Aperture Radar Image Generation and Target Detection Enhancement Framework
Shang, Y., Houjin, C., Li, Y. X., Chen, Z., Sun, J., & Zhao, Y. (2025) · IEEE Sensors Journal · doi:10.1109/jsen.2025.3610886 · Cited by 2
“The advancement of convolutional neural networks (CNNs) has fundamentally transformed SAR image processing, particularly in advancing target detection methodologies [2], [3], [4].”
Dental caries detection with cone beam computed tomography and multiscale wavelet attention network
Yuan, K., Ding, J., Zeng, X., et al. (2025) · Optics and Lasers in Engineering · doi:10.1016/j.optlaseng.2025.109366
A Real-Time Deep Learning-Based Framework for Physical Asset Management in Smart Cities
Kashyap, N., Sandilya, B., Sharma, U., et al. (2025) · Lecture notes in networks and systems · doi:10.1007/978-981-96-4536-7_36
Weapon Detection in Video Surveillance Systems
Bhandari, M., Naidu, V., Lawhale, M., & Kakade, M. (2025) · Lecture notes in networks and systems · doi:10.1007/978-981-96-5604-2_24
Harris, J., & Er, Ş. (2025) · South African Journal of Science · doi:10.17159/sajs.2025/18277
“You Only Look Once (YOLO) 14,16-18 and its versions (YOLOv2-v8) 19 , single shot detection (SSD) 20,21 , Deconvolutional Single Shot Detector (DSSD), RetinaNet, M2Det, DCN, DCNv2, NAS-FPN, CornerNet512, EfficientDet and Fast-D – feed forward in a single pass 1 .”
A Fall Detection Algorithm Based on Convolutional Neural Network and Multi- Discriminant Feature
Wang, X., Zheng, X., Gao, H., et al. (2023) · Journal of Computer-Aided Design & Computer Graphics · doi:10.3724/sp.j.1089.2023.19361
Household Items Detection Method Based on Multi-Sensory Mechanism Fusion
Guo, T., Xue, Y., & Wu, J. (2023) · Journal of Computer-Aided Design & Computer Graphics · doi:10.3724/sp.j.1089.2023.20035
YOLOv4 Multi-Scale Object Detection Algorithm Based on Adaptive Weighting Module
Nie, S., Cheng, D., Kou, Q., et al. (2023) · Journal of Computer-Aided Design & Computer Graphics · doi:10.3724/sp.j.1089.2023.19599
Sustainable Vehicle Detection Technology Based on Self-Powered Sensor Data and Improved YOLOv8
Ning, C., Chen, N., Wei, Y., et al. (2025) · Journal of Transportation Engineering Part A Systems · doi:10.1061/jtepbs.teeng-9092
闵, 哲. (2025) · Operations Research and Fuzziology · doi:10.12677/orf.2025.155226
Residual manganese blocks detection algorithm based on CD-SSD
Chen, D., Huang, S., Xu, X., et al. (2025) · Engineering Research Express · doi:10.1088/2631-8695/ae0d42
Self-Rectification Faster R-CNN: Enhancing Object Detection in Complex-Background Aerial Images
Zhang, Y., Feng, Y., & Shang, Y. (2025) · IEEE International Conference on Information Reuse and Integration (IRI) · doi:10.1109/iri66576.2025.00044
“On the other hand, one-stage detectors like RetinaNet [19] and YOLO [20]–[26] benefit from their one-stage design and usually achieve a faster detection speed than two-stage detectors.”
MBMS-Net: A Multi-Branch and Multi-Scale Perception Infrared Small Target Detection Network
Ma, T., Li, S., Kai, Z., et al. (2025) · Youth Academic Annual Conference of Chinese Association of Automation (YAC) · doi:10.1109/yac66630.2025.11149704
“Mainstream detection frameworks, such as Faster R-CNN [6] and YOLO [7], have achieved accurate positioning and classification of multi-scale targets within visible-spectrum imagery using deep convolutional networks.”
Detection of Hyperbolic Reflections in GPR Data Using Faster R-CNN and Point Extraction
Bugarinović, Ž., Ristić, A., Radulović, A., et al. (2025) · International Workshop on Advanced Ground Penetrating Radar · doi:10.1109/iwagpr65621.2025.11108986
“The most commonly used algorithms for recognizing characteristic shapes in images are those based on CNN, including R-CNN [21], Faster R-CNN [22], and the YOLO [23] algorithm.”
YOLO-Slim:A Lightweight Small Object Detection Algorithm for Drone Images
Ou, L., Cao, Y., Su, Y., et al. (2025) · Youth Academic Annual Conference of Chinese Association of Automation (YAC) · doi:10.1109/yac66630.2025.11150156
“Single-stage detectors like YOLO series [4] and SSD [8] provide efficient detection through end-to-end regression, offering significant advantages in real-time performance.”
Khater, A., Abdelkhalek, A., Metwally, M., et al. (2025) · doi:10.1109/cleo/europe-eqec65582.2025.11111439
“The workflow involved image pre-processing, orientation correction via Hough lines [3], region-of-interest (ROI) detection using YOLO [4], and alignment assessment.”
AttPD: Adversarial Patch Integrating Attention Mechanism and Dropout
Ye, S., Yu, H., Zhang, X., et al. (2025) · Youth Academic Annual Conference of Chinese Association of Automation (YAC) · doi:10.1109/yac66630.2025.11149693
“Single-stage methods, such as the YOLO series, perform classification and localization tasks within a single network, significantly improving detection speed [16].”
An Improved YOLOv11-Based Algorithm for Blood Cell Detection
Chen, Y., & Lyu, H. (2025) · International Symposium on Intelligent Robotics and Systems (ISoIRS) · doi:10.1109/isoirs65690.2025.11168090
“In contrast, one-stage methods such as the YOLO series [8] and the RT-DETR (Real-Time Detection Transformer) algorithms [9].”
Brain Tumor Detection Using YOLOv11 on Edge Computing for Decision Support
Teixeira, E. H., Cruz, M. R., & Pimenta, T. C. (2025) · International Conference on Artificial Intelligence, Computer, Data Sciences and Applications (ACDSA) · doi:10.1109/acdsa65407.2025.11165825
“Among the most used architectures are SSD [9], RCNN [10], and the YOLO family [11], each offering distinct trade-offs between accuracy and computational efficiency.”
(2025) · Elsevier eBooks · doi:10.1016/b978-0-443-33532-7.10000-x
YOLO-MoE: Multi-Scenario Cigarette Defect Detection with a Mixture of Experts
Chen, X., Li, M., Chen, G., Li, Q., Chen, S., Chen, Y., Li, J., Pan, L., & Liang, D. (2025) · IEEE International Conference on Software Engineering and Artificial Intelligence (SEAI) · doi:10.1109/seai65851.2025.11108945 · Cited by 1
“Meanwhile, single-stage detectors, such as SSD [9], RetinaNet [10] and YOLO [11]–[16], achieved a balance between speed and accuracy in an end-to-end manner, making them more suitable for real-time applications.”
Adaptive Ensemble Learning for Object Counting under varying Environmental Conditions
Gombos, S. P., & Gulyás, L. (2025) · Intelligent Robotics FAIR · doi:10.1145/3759355.3759634
“One-stagedetectors such as YOLO (“You Only Look Once”) [27] collapse proposal and classification into a single pass, achieving real-time inference by dividing the image into a grid and directly regressing box coordinates and confidence scores.”
A SAM-Based Small-Scale Attention Network for Lunar Impact Crater Detection with DEM Data
Lan, Y., Zheng, Y., Xu, Z., Zhang, F., & Wan, Z. (2025) · International Conference on IoT, Data Science and Advanced Computing (IDSAC) · doi:10.1109/idsac65763.2025.11170288
MSFAEGD: Efficient Forest Smoke Detection Network Based on Grounding Dino
Zhang, T., & Lu, X. (2025) · IEEE International Conference on Software Engineering and Artificial Intelligence (SEAI) · doi:10.1109/seai65851.2025.11108826 · Cited by 1
“Early general-purpose object detection algorithms based on CNN mainly include two-stage methods (such as R-CNN [15], Faster R-CNN [16] and Mask R-CNN [17]) and single-stage methods (such as SSD [18], RetinaNet [19] and the well-known YOLO series [20]–[22]).”
An Adaptive FD-Former Network For Tobacco Impurity Detection
Zhang, J., Wang, X., Li, D., et al. (2025) · Youth Academic Annual Conference of Chinese Association of Automation (YAC) · doi:10.1109/yac66630.2025.11150129
“To deal with the problems stated above and improve the accuracy of identifying tobacco impurities, this article introduces a brand - new on - the - fly detection technique for tobacco impurities in tobacco - processing robots [4] .”
LFS-YOLO: A Lightweight Forest Smoke Detection Network Based on YOLOv8-n
Xu, R., & Lu, X. (2025) · IEEE International Conference on Software Engineering and Artificial Intelligence (SEAI) · doi:10.1109/seai65851.2025.11108900
“YOLOv1–v3 [11]–[13] introduce the first generation of YOLO models, establishing the backbone-neck-head architecture of single-stage detection.”
Simulating Attachment Behavior in Mobile Robots Through Toy Following Tasks
Lonklang, A., Abdessemed, A., Amdouni, I., et al. (2025) · doi:10.1145/3759355.3759371
“The trained model achieves real-time performance, enabling continuous position tracking of both entities [14].”
Wu, Y., Xie, X., Yu, L., Ruan, X., Li, R., Cheng, L., Ye, S., Deng, D., Zhang, H., & Wu, Y. (2025) · ACM Symposium on User Interface Software and Technology (UIST) · doi:10.1145/3746059.3747762 · Cited by 1
“We start with a lightweight YOLO detection model [45], processing video frames at 77 FPS on our server, to locate the basketball in the 2D frames (Fig.”
An Improved YOLOv10 for Helmet Detection in Complex Scenarios
Cao, S., Zhou, L., & Ma, X. (2025) · Youth Academic Annual Conference of Chinese Association of Automation (YAC) · doi:10.1109/yac66630.2025.11149854
Automated Shape Classification Using SAR Imaging and Machine Learning
Wadde, C., Pondala, V. R. M., Chinnaraj, G., et al. (2025) · doi:10.1109/space65882.2025.11171100
“Previous work has focused on optical imaging and simpler radar systems [10].”
Deep Learning-based Soldier Detection in Forested Environments
Kim, D., Kim, Y., Lee, G., et al. (2025) · Journal of the Korea Institute of Military Science and Technology · doi:10.9766/kimst.2025.28.5.496
Small Objects Detection Using Yolov8 Deep Learning Model and Custom Database
Yaseen, W. Y., Mahmood, S. A., & Abid, A. M. (2025) · Lecture notes in networks and systems · doi:10.1007/978-981-96-4319-6_55
Enhancing Ovarian Tumor Diagnosis Through Transfer Learning in Convolutional Neural Networks
Saeid, S., Almabruk, T. A. A., & Abdulsamad, M. (2025) · Lecture notes in networks and systems · doi:10.1007/978-981-96-6429-0_37
Outdoor Robot Geo-Localization Using Vision Technics
Ramanana, H. M. B., Jessel, J.-P., Andriamarozakaniaina, T. F., et al. (2025) · Communications in computer and information science · doi:10.1007/978-3-032-00986-9_33
MCD-YOLO: an efficient model for detecting surface defects of electroplated safety buckles
Song, H., Wu, X., & Dong, H. (2025) · Signal Image and Video Processing · doi:10.1007/s11760-025-04849-3
“Single-stage algorithms include SSD [7] and YOLO [8–17], and two-stage algorithms include R-CNN [18], Fast-RCNN [19], and Mask-RCNN [20].”
Interpretable and Fine-Grained Brain Tumor MRI Detection based on Progressive Pruning (Preprint)Preprint
Liu, Y., Song, S., Lian, S., et al. (2025) · doi:10.2196/preprints.84095
MWIRGas-YOWO: Real-Time Gas Detection via Spatio-Temporal Fusion in Mid-Wave Infrared Video
Wang, L., Yang, H., Long, Y., et al. (2025) · IEEE International Conference on Computer Communication and Artificial Intelligence (CCAI) · doi:10.1109/ccai65422.2025.11189522
EAP4EMSIG – enhancing event-driven microscopy for microfluidic single-cell analysis
Friederich, N., Sitcheu, A. J. Y., Nassal, A., Yildiz, E., Pesch, M., Beichter, M., Scholtes, L., Akbaba, B., Lautenschlager, T., Neumann, O., et al. (2025) · at - Automatisierungstechnik · doi:10.1515/auto-2025-0018
An Effective and Robust Similarity-Based Phishing Website Detector in Cyber-Physical Systems
Sit, H. C., Esmradi, A., Yip, D. W. K., et al. (2025) · IEEE Conference on Communications and Network Security · doi:10.1109/cns66487.2025.11195039
“Redmon et al. [13] introduced YOLO for real-time object detection, which we adapt for screenshot analysis in our framework.”
AI-Based Health Monitoring System for Old Buildings
Jo, S. M., & Kim, E. S. (2025) · Communications in computer and information science · doi:10.1007/978-981-95-3141-7_17
Towards an Architectural Approach of Insurance Fraud Detection System
Nabi, R., Traore, Y., & Diop, I. (2025) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-032-01904-2_12
A Content-Adaptive Rate-Control Parameter Selection Scheme for Intra Coding
Xie, J., Li, X., & Ma, N. (2025) · International Conference on Artificial Intelligence, Internet of Things and Cloud Computing Technology (AIoTC) · doi:10.1109/aiotc66747.2025.11198699
“Recently, deep learning tools have shown great potential in video-related tasks such as object detection[4], image classification[5], and semantic segmentation[6].”
AI-Driven Smart Detection of Diverse Pallet Types Using RGB and Depth Camera
Hofer, C., Kaineder, G., Salmen, D., et al. (2025) · International Conference on Intelligent Data Science Technologies and Applications (IDSTA) · doi:10.1109/idsta66210.2025.11202819
“The primary advantage of YOLO lies in its capability to balance detection speed and accuracy, rendering it a preferred choice for object detection tasks [12].”
DeepUIFuzz: A Guided Fuzzing Strategy for Testing UI Component Detection Models
Chowdhury, P., & Sakib, K. M. (2025) · IEEE/ACM International Workshop on Search-Based Software Testing (SBST) · doi:10.1109/sbft66712.2025.00016
“Additionally, we evaluated the Error Finding Rates (EFR) of four object detection models: You Only Look Once (YOLO) version 3 and 5 [8], Single Shot MultiBox Detector (SSD) [9], and Fully Convolutional One-Stage Object Detector (FCOS) [10], achieving 0.93, 0.85, 0.95, and 0.95, respectively.”
InfluentialOriented Fish Detection for Enhanced Localization
Salie, D., Brown, D., & Chieza, K. (2025) · International Conference on Artificial Intelligence, Big Data, Computing and Data Communication Systems (icABCD) · doi:10.1145/3759023.3759123
“TheoriginalYOLOmodel [29]introducedthesingle-stageconcept,dividingtheimageinto agridandpredictingboundingboxesandclassprobabilitiesfor eachcell.”
Metadata
- Authors
- Redmon, J., Divvala, S., Girshick, R., & Farhadi, A.
- Affiliations
- University of Washington (US)
- Meta (United States) (US)
- Venue
- 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2016-06
- Pages
- 779-788
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W1483870316
- Cited by
- 53,803
- References
- 42
- Citations by year
- 2026: 5347 · 2025: 8912 · 2024: 8953 · 2023: 8264 · 2022: 6785 · 2021: 5741 · 2020: 4223 · 2019: 3286 · 2018: 1560 · 2017: 635 · 2016: 90
- FWCI
- 644.23
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Zenodo (CERN European Organization for Nuclear Research) (cc-by)
- Funders
- National Science Foundation (1338054)
- Office of Naval Research (N00014-13-1-0720, N00014)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image and Video Retrieval Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Visual Attention and Saliency Detection
- Keywords
- object detection, YOLO, real-time detection, bounding box regression, end-to-end learning, false positive reduction, domain generalization
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol and qwen3.8-omni-flash).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.