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 34,201–34,300 of 51,399
Aiding Novice Chess Moves with YOLO Pose Detection and Augmented Reality
Neto, A. M. D. S., & Góes, C. E. (2025) · Revista Eletrônica de Iniciação Científica em Computação · doi:10.5753/reic.2025.6046 · Cited by 1
“These models started as DL object detection models, i.e., they learned how to detect object in an image, YOLO is a fast, real-time approach to this task [Redmon et al ., 2016].”
Ryu, H. S., Ju, U., & Wallraven, C. (2025) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2025.3616811 · Cited by 3
“To quantify attention allocation, we first tracked the AOIs across video frames using a pretrained YOLO [50] model.”
Li, M., Ding, X. W., Wang, J., & Luo, R. (2025) · AgriEngineering · doi:10.3390/agriengineering7100321 · Cited by 2
Meng, K., Zhang, S., Lu, Z., Lu, W., Che, H., & Li, Z. (2025) · Physica Scripta · doi:10.1088/1402-4896/ae0eca · Cited by 1
Ipalakova, M., Bolatov, Z., Daineko, Y. A., Sharshova, R., Abdugapparova, K., & Tsoy, D. (2025) · PeerJ Computer Science · doi:10.7717/peerj-cs.3207 · Cited by 2
LM3D: Lightweight Multimodal 3D Object Detection with an Efficient Fusion Module and Encoders
Sakai, Y., Shimada, T., Kong, X., & Tomiyama, H. (2025) · Applied Sciences · doi:10.3390/app151910676 · Cited by 1
Li, X., Liu, H., Lan, Y., et al. (2025) · Journal of Food Measurement & Characterization · doi:10.1007/s11694-025-03664-1 · Cited by 1
RIG-YOLOv8n: lightweight wind turbine blade damage detection based on YOLOv8n
Zhang, Y., Ma, J., Liang, K., Jiang, Y. H., & Meng, H. (2025) · The Journal of Supercomputing · doi:10.1007/s11227-025-07862-y · Cited by 1
Dino, H. I., & Hassan, M. M. (2025) · Neuroscience & Biobehavioral Reviews · doi:10.1016/j.neubiorev.2025.106399 · Cited by 3
Matsuoka, K., Konoshima, M., Eto, T., & Ota, I. (2025) · FORMATH · doi:10.15684/formath.24.006 · Cited by 3
Aamir, M. S. B., Ilyas, M. H., Khalique, F., Bashir, B., Mahmood, S., & Khalil, R. A. (2025) · IEEE Access · doi:10.1109/access.2025.3617336 · Cited by 2
DBA-YOLO: A Dense Target Detection Model Based on Lightweight Neural Networks
Zhi-yong, H., Yang, J., Ning, H., Li, C., & Tang, Q. (2025) · Journal of Imaging · doi:10.3390/jimaging11100345 · Cited by 1
“On the YOLO line, designs emphasize lightweight multi-scale fusion and very low end-to-end latency: early versions broadened scale coverage with SPP and PANet [16–18].”
Underwater image classification and object detection using shuffle convolutional channel enhancement
Wu, D., Sun, X., Cheng, G., Hao, L., & Yan, Z. (2025) · Ships and Offshore Structures · doi:10.1080/17445302.2025.2564668 · Cited by 1
Robot arm grasping for cluttered fasteners based on deep learning with synthetic data augmentation
Huang, Y., Yan, Q., Zhang, H., Wang, J., Liu, Q., & Li, Q. (2025) · The International Journal of Advanced Manufacturing Technology · doi:10.1007/s00170-025-16642-0 · Cited by 1
“To improve the speed of image detection, [34] proposed the You Only Look Once (YOLO) algorithm, which pioneered the single-stage object detection approach.”
Poudel, A., Davis, J. D., Purswell, J. L., et al. (2025) · Animal - science proceedings · doi:10.1016/j.anscip.2025.08.252 · Cited by 1
DBYOLO: Dual-Backbone YOLO Network for Lunar Crater Detection
Liu, Y., Chen, F., Qiu, D., Liu, W., & Yan, J. (2025) · Remote Sensing · doi:10.3390/rs17193377 · Cited by 2
“Current object detection algorithms include Convolutional Neural Network (CNN)- based models, like Faster R-CNN [6] and the You Only Look Once (YOLO) [7] series, and Transformer-based [8] models such as RT-DETR [9] and Swin Transformer [10].”
Global impact and thematic evolution of object detection in the deep learning era
Roslin, A. H., & Muhammad, N. (2025) · Discover Artificial Intelligence · doi:10.1007/s44163-025-00528-x · Cited by 1
“‘YOLO’ model is one of the state-of-the-art one-stage detector models that have been widely received in ODM research progress since its initial development [75].”
Sobolevskii, V., & Layshev, K. A. (2025) · ARCTIC AND SUBARCTIC NATURAL RESOURCES · doi:10.31242/2618-9712-2025-30-3-480-485 · Cited by 1
Oriented Racket Database (ORDB): An Annotated Dataset for Rotated Racket Detection in Badminton
Haq, M. A., Xinqi, S., Shahzadi, T., Zhang, B., Tarashima, S., & Tagawa, N. (2025) · ACM International Workshop on Multimedia Content Analysis in Sports (MMSports) · doi:10.1145/3728423.3759409 · Cited by 3
Dual-Branch Discriminative Feature Cross-Attention Network for Lumber Surface Defect Segmentation
Zhang, S., Ling, Z., Peng, P., et al. (2025) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2025.3617405 · Cited by 1
An efficient human pose keypoint detection algorithm base on YOLOv8
Yang, S., Liu, H., Du, Y., Sun, T., Wang, C., Lin, F., & Liu, L. (2025) · The Journal of Supercomputing · doi:10.1007/s11227-025-07953-w · Cited by 1
“Among them, the one-stage detection algorithm You Only Look Once (YOLO) [6] has stood out due to its efficiency and real-time performance.”
Wu, C., Li, J., Shih, P.-Y., Huang, C.-C., Cheng, H., Wu, C., Tay, J., Wu, M., Wang, C., Chen, C., et al. (2025) · Journal of Medical Systems · doi:10.1007/s10916-025-02275-z · Cited by 2
“The object detection model was developed using You Only Look Once (YOLO) [16], a deep convolutional neural network algorithm known for its balance of performance and efficiency in previous studies [ 17].”
FPGA-based Mb2DKDNet for field disease and pest diagnosis
Chen, D., Li, D., Zheng, J., Cai, Y., Wu, K., Huang, X., & Zhang, J. (2025) · Smart Agricultural Technology · doi:10.1016/j.atech.2025.101516 · Cited by 5
Wu, W., Zhang, Z., Xiang, Z., et al. (2025) · Algorithms · doi:10.3390/a18100638 · Cited by 1
Defect Detection Method for Battery CT Image Based on Deep Learning
Zhu, B., Zheng, Y., Jin, M., et al. (2025) · Chinese Control Conference (CCC) · doi:10.23919/ccc64809.2025.11178402 · Cited by 1
“In 2016, Joseph Redmon et al. [11] first proposed the YOLO (You Only Look Once) algorithm, which uses the YOLO algorithm to extract and classify targets in images, achieving automation of image feature extraction and classification recognition, abandoning the traditional method of manually…”
Bian, H., He, Y., Du, P., et al. (2025) · Chinese Control Conference (CCC) · doi:10.23919/ccc64809.2025.11179700 · Cited by 1
“The single-stage detector YOLO [7] series has demonstrated excellent performance.”
Image and Point Cloud Frustum-Based Auxiliary Localization for Agents in Complex Scenes
Huang, Y., Zhang, X., Zhao, B., Jiang, Q., Ou, Q., & Hu, C. (2025) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2025.3613912 · Cited by 1
YOLO-LDIST: Improved YOLOv9 Long Distance Infrared Small Target Detection
Hong, Z., Zhang, X., & Shi, W. (2025) · Chinese Control Conference (CCC) · doi:10.23919/ccc64809.2025.11179736 · Cited by 2
“Representative algorithms include YOLO series [4-13] , SSD [14] , etc.”
CTL-DETR: a landslide detection algorithm for complex terrains
Zang, X., Li, J., Ma, G., et al. (2025) · Machine Vision and Applications · doi:10.1007/s00138-025-01749-x · Cited by 1
“…algorithms such as Fast-RCNN [11], Faster-RCNN [12], and Mask-RCNN [13] detect objects by generating region proposals; one-stage algorithms such as SSD [14], RetinaNet [15], and the YOLO [16] series directly perform object localization and classification with - out requiring candidate regions.”
du Toit, A., Lork, A. A., Ernst, C., & Phan, N. T. N. (2025) · Analytical Chemistry · doi:10.1021/acs.analchem.5c04489 · Cited by 2
“…vision-assisted pipeline for automatic, robust classification and segmentation of ROIs on EM images for correlation with NanoSIMS images using YOLO (you only look once), 15 a popular computer vision model that can be used for object detection, image classification, and instance segmentation tasks.”
CMH-Net: a structured and optimized network for real-time steel surface defect detection
Li, J., Liang-fu, L., & Ai, L. (2025) · Journal of Real-Time Image Processing · doi:10.1007/s11554-025-01786-9 · Cited by 1
“For instance, Hu et al. [17] Building upon the trend toward faster and more efficient detectors, You Only Look Once (YOLO) [19] has emerged as one of the most widely adopted frameworks for defect detection tasks.”
Zuo, C., Wang, L., Dai, Z., Wu, Y., Dong, S., & Chang, Q. (2025) · Transportmetrica A Transport Science · doi:10.1080/23249935.2025.2567626 · Cited by 1
dos Reis, J., Ribeiro, Á. S., Ferreira, P. M., Simões, C. F., & Coelho, G. E. (2025) · Measurement · doi:10.1016/j.measurement.2025.119196 · Cited by 4
Enhancing Autonomous Driving Systems: Integrated Lane and Object Detection Using YOLOv3 and OpenCV
Praneeth, D., Meera, S., Raaman, N., et al. (2025) · International Conference on Inventive Systems and Control (ICISC) · doi:10.1109/icisc65841.2025.11188086 · Cited by 1
“Models like Faster R-CNN [10], Single Shot Detector (SSD) [11], and You Only Look Once (YOLO) [12] have demonstrated significant advancements in real-time detection.”
Integrated License Plate Recognition Using YOLO and CNN for Automated Vehicle Identification
Sahaana Shri, S. K., Nethra, R., Krishna, C. J., et al. (2025) · International Conference on Inventive Systems and Control (ICISC) · doi:10.1109/icisc65841.2025.11187533 · Cited by 1
“Since its introduction in 2015 [15], YOLO has been widely adopted for real-time license plate detection due to its speed and efficiency.”
Automatic chard area detection
Martinez, F., Romaine, J., Johnson, P., et al. (2025) · International Conference on Machine Learning Technologies (ICMLT) · doi:10.1109/icmlt65785.2025.11193387 · Cited by 1
Enhancing Urban Infrastructure Management with UAV-Based Parking Solutions: A Case Study at UCC
O’Shaughnessy, E., Hao, G., Dai, Z., & Li, Z. (2024) · International Conference on Universal Village (UV) · doi:10.1109/uv63228.2024.11189170 · Cited by 1
Huang, Y., & Chen, Z. (2025) · Remote Sensing · doi:10.3390/rs17203410 · Cited by 1
BOAD-YOLO: Optimizing YOLOv8 with Attention and Feature Fusion for Small Object Detection
Xu, J., Wang, Z., Yang, C., Wu, Q., & Zhou, Y. (2025) · International Conference on Computer Vision, Application, and Algorithm (CVAA) · doi:10.1109/cvaa66438.2025.11193348 · Cited by 1
“Originating from the end-to-end detection paradigm established by Redmon et al. in YOLOv1 [10] , the series has undergone critical evolutionary leaps: YOLOv2 [11] enhanced detection accuracy through anchor boxes, while YOLOv3 [12] introduced multi-scale prediction, significantly improving…”
Kriswijanarko, J., Wulandari, G. S., & Wibowo, S. A. (2025) · doi:10.1109/icoict66265.2025.11193012 · Cited by 2
“YOLOv8 is the 8th development of the YOLO algorithm, which is an architecture and algorithm designed to simplify the object detection process resulting in a faster inference model with much better performance compared to other object detection models [7].”
Predictive Modelling of Egg Production Yields on Farms based on Environmental Factors
Nawod, G. A. D., Rathnayake, R. M. D. A., Dodangoda, P. N., et al. (2025) · doi:10.1109/icoict66265.2025.11193017 · Cited by 1
NP-YOLO: A Nighttime Pedestrian Detection Model for Video Surveillance
Huang, Z., & Liu, W. (2025) · International Conference on Computer Vision, Application, and Algorithm (CVAA) · doi:10.1109/cvaa66438.2025.11193302 · Cited by 1
“In recent years, the rapid advancement of deep learning has enabled deep learning-based detection methods [3]-[5] to achieve remarkable performance.”
Machine Learning–Based Correlation Methods for Satellite Thermal Analysis Models
Kang, J., Cho, J. Y., & Kim, J. H. (2025) · Journal of Aerospace Engineering · doi:10.1061/jaeeez.aseng-5755 · Cited by 1
Effect of Post-Processing Methods on CPU-based 3D Object Detection from Camera and LiDAR Data
Masarykova, N., Fech, B., Galinski, M., & Trúchly, P. (2025) · International Symposium ELMAR (ELMAR) · doi:10.1109/elmar66948.2025.11193995 · Cited by 1
“One of the most frequently used object detection model is You Only Look Once (YOLO) [8].”
Wang, H., & Zhou, Y. (2025) · Journal of Real-Time Image Processing · doi:10.1007/s11554-025-01785-w · Cited by 2
“Notable single-stage detection models include the YOLO (You Only Look Once) series [26], SSD (Single Shot MultiBox Detector) [20], and RetinaNet [19].”
Stępnicka, Z., Piórkowska, N., Brożyna, M., Matys, T., & Junka, A. (2026) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2026.1789644 · Cited by 5
S 2 Net: Spatial-Aligned and Semantic-Discriminative Network for Remote Sensing Object Detection
Yao, J., Chen, H., Xie, Y., Zhang, N., Yang, M., & Chen, L. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2025.3622254 · Cited by 4
Deep Learning for Underwater Object Detection: From CNNs to Transformer-Based Real-Time Solutions
Bhandari, H., & Liu, P. (2025) · International Conference on Automation and Computing (ICAC) · doi:10.1109/icac65379.2025.11196382 · Cited by 5
“YOLO (You Only Look Once) [21] sets the stage by treating detection more like a regression problem.”
Yang, F., Lian, B., Li, Y., et al. (2025) · IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC) · doi:10.1109/icspcc66825.2025.11194433 · Cited by 1
Appelle, A., Salvino, L. W., & Lynch, J. P. (2025) · Journal of Computing in Civil Engineering · doi:10.1061/jccee5.cpeng-6869 · Cited by 1
Extracting and Structuring Textbooks for Inclusive Education: A Computer Vision Approach
Lasheb, M. A., Pons, O., Bekkouche, M., Lincker, É., Barbet, I., & Huron, C. (2025) · IEEE International Conference on Advanced Learning Technologies (ICALT) · doi:10.1109/icalt64023.2025.00062 · Cited by 2
Implementation of Embedded System in Effective Recognition: A Study
Kale, R. P., Jadhav, M. S., Chavan, S. B., & Gurav, V. V. (2025) · International Journal of Advanced Research in Science Communication and Technology · doi:10.48175/ijarsct-29263 · Cited by 1
Pavement defect detection algorithm SSC-YOLO for fusing multiscale spatial channels in YOLOv8
Sun, G., & Jin, Y. (2025) · PeerJ Computer Science · doi:10.7717/peerj-cs.3187 · Cited by 1
Development of AI-based garment design process integrating flat sketch and pattern making
Lee, Y., & Kim, S. (2025) · International Journal of Clothing Science and Technology · doi:10.1108/ijcst-03-2025-0048 · Cited by 1
Wang, H., Liu, M., Qu, L., Li, D., & Wang, S. (2025) · Image and Vision Computing · doi:10.1016/j.imavis.2025.105792 · Cited by 2
Cheapconv: efficient parcel segmentation and detection for real-time logistics automation
Zou, B., Wen, L., & Chen, Z. (2025) · Journal of Real-Time Image Processing · doi:10.1007/s11554-025-01779-8 · Cited by 3
“…accuracy through Region Proposal Network (RPN), albeit at a computational cost; and one-stage detectors, such as You Only Look Once (YOLO) [11] and Single Shot MultiBox Detector (SSD) [12], which favor inference speed by defining a group of anchors for fast detection in an end-to-end way.”
Ceviz işleme hatları için YOLOv11 model temelli otomatik tespit ve sınıflandırma sistemleri
Aktaş, H., & Polat, E. (2025) · Ömer Halisdemir Üniversitesi Mühendislik Bilimleri Dergisi · doi:10.28948/ngumuh.1723155 · Cited by 1
Dai, L., Tang, H., Zhang, Y., Xu, B., Bhatti, U. A., & Gao, J. (2025) · The Journal of Supercomputing · doi:10.1007/s11227-025-07961-w · Cited by 2
“In contrast, one-stage detection algorithms represented by YOLO (You Only Look Once) series [6] directly predict target locations and categories from input images, leveraging grid-based parallel processing that aligns optimally with GPU architectures to achieve substantial speed improvements.”
Recognition of Radicals of Guqin Music Notation by YOLOs
Hayami, M., Kuremoto, S., Koshiba, M., et al. (2025) · Communications in computer and information science · doi:10.1007/978-981-95-3141-7_11 · Cited by 1
Standardized evaluation of orthokeratology lens fitting status assisted by deep learning algorithm
Song, W., Zhang, Y., Wan, C., Liu, M., Wang, S., Yin, H., Xue, M., Pan, H., & Lei, S. (2025) · Contact Lens and Anterior Eye · doi:10.1016/j.clae.2025.102519 · Cited by 1
A Lighter and Faster One-Stage Algorithm for Object Detection in Remote Sensing Images
Du, Y., Liu, H., Yang, S., et al. (2025) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2025.3623097 · Cited by 1
MDF-YOLO: A Hölder-Based Regularity-Guided Multi-Domain Fusion Detection Model for Indoor Objects
Luan, F., Yang, J., & Zhang, H. (2025) · Fractal and Fractional · doi:10.3390/fractalfract9100673 · Cited by 2
“This evolution spans from YOLO, which unified detection as a regression problem [15], and RetinaNet, which introduced Focal Loss to effectively resolve the extreme imbalance between positive and negative samples [16], to the rise of anchor-free methods like FCOS [17].”
Beldek, C., Sarıyıldız, E., & Alıcı, G. (2025) · Agriculture · doi:10.3390/agriculture15202170 · Cited by 2
Deep learning finds convergent melanocytic morphology despite noisy archival slides
Tada, M., Gaskins, G., Ghandian, S., Mew, N. C., Keiser, M. J., & Keiser, E. (2025) · Cell Reports Methods · doi:10.1016/j.crmeth.2025.101201 · Cited by 2
DefDeN: A Deformable Denoising-Based LiDAR and Camera Feature Fusion Model for 3D Object Detection
Zhi, P., Xu, X., Nie, H., Yong, B., Shen, J., & Zhou, Q. (2025) · Tsinghua Science & Technology · doi:10.26599/tst.2024.9010173 · Cited by 5
Ibrahim, A. F., Sarker, R. H., & Algarhy, A. (2025) · SPE Eastern Regional Meeting · doi:10.2118/226260-ms · Cited by 1
Jeyamaran, D., Shapri, A. H. M., Rahman, N. A., et al. (2025) · doi:10.1109/icomms66553.2025.11200267 · Cited by 1
“Models such as Single Shot MultiBox Detector (SSD) [5], Deconvolutional Single Shot Detector (DSSD) [6], and You Only Look Once (YOLO) [7] have significantly contributed to progress related to image-based classification and localization.”
Kong, Z., Xu, Q.-Z., Li, Y., et al. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2025.3624033 · Cited by 1
An Uncertainty-aware DETR Enhancement Framework for Object Detection
Chen, X. S., Yu, S., Cheng, C., Wang, H., & Tian, T. (2025) · International Workshop on Multimedia Computing for Health and Medicine (MCHM) · doi:10.1145/3728424.3760769 · Cited by 2
He, Y.-H., Duan, S.-Y., & Su, W. (2025) · Foods · doi:10.3390/foods14203581 · Cited by 1
“The You Only Look Once (YOLO) series [4] has emerged as a dominant paradigm for real-time object detection, striking an effective balance between computational efficiency and detection accuracy [5].”
Integrating Real-ESRGAN with CNN Models for UAV Image Based Plant Disease Detection
Malladi, S., & Kulkarni, P. (2025) · Annals of Computer Science and Information Systems · doi:10.15439/2025f2775 · Cited by 1
Yang, J., & Cheng, R. (2025) · Transportmetrica A Transport Science · doi:10.1080/23249935.2025.2576093 · Cited by 1
Integrating dual-modal camera systems on unmanned aerial vehicles for bridge tower defect detection
Chen, W., & Zhang, J. (2025) · Journal of Civil Structural Health Monitoring · doi:10.1007/s13349-025-01031-8 · Cited by 1
“Against this backdrop, YOLO (You Only Look Once) has emerged as a widely adopted object detection framework due to its remarkable efficiency and high detection accuracy [41].”
Liquid Reservoir Weld Defect Detection Based on Improved YOLOv8s
Li, Z., Song, T., Zhou, B., Zhang, Y., Yu, S., Cao, S., Xu, Z., & Jiang, Q. F. (2025) · Sensors · doi:10.3390/s25216521 · Cited by 2
A Hybrid Framework for Kinematic Vehicle Prediction: YOLOv11 with Unscented Kalman Filter
Pahal, S., & Nandal, P. (2025) · SAE International Journal of Connected and Automated Vehicles · doi:10.4271/12-09-02-0013 · Cited by 1
Adaptive Focusing Multi‐Scale Feature Network for Pinning Defect Detection in Transmission Lines
Hua, G., Pan, M., Yin, S., Yan, J., Chen, Y.-C., & Zhao, H. (2025) · IET Generation Transmission & Distribution · doi:10.1049/gtd2.70177 · Cited by 1
Chen, H., Ni, Y., Huang, W., Oh, H., Liu, Y., Das, T., & Imani, M. (2025) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3746027.3755243 · Cited by 9
“The average number of image tokens ( N avg ) participating in each LLM MHSA layer is given by: 4 Experiment”
Research on intelligent recognition algorithm for subsurface road defects
Li, G., Li, M., Yao, Z., et al. (2025) · Nondestructive Testing And Evaluation · doi:10.1080/10589759.2025.2577833 · Cited by 1
BudCAM: An Edge Computing Camera System for Bud Detection in Muscadine Grapevines
Chiang, C.-E., Liang, W.-Z., Chen, J., Qiao, X., Tsolova, V. M., Yang, Z., & Oboamah, J. (2025) · Agriculture · doi:10.3390/agriculture15212220 · Cited by 3
“Image tiling for both datasets was performed after annotation, and annotations were exported in YOLO format [23].”
Implementation of Apple Quality Automatic Classification System Based on Deep Learning Technique
Chen, C.-L., & Chang, C.-Y. (2025) · IEEE International Conference on Consumer Electronics - Taiwan (ICCE-Taiwan) · doi:10.1109/icce-taiwan66881.2025.11208122 · Cited by 1
“In view of this situation, this paper proposes a novel design of the apple quality automatic classification system, in which the existing YOLOv8 deep learning (DL) model [4], [5] is mainly adopted for the object identification and classification.”
Multimodal Deep Learning Framework for Analyzing Mobile Video Communication Effectiveness
Xu, P., He, Y., Xu, Y., & Liu, W. (2025) · IEEE Access · doi:10.1109/access.2025.3626339 · Cited by 1
Chen, X., Yao, F., Cui, R., Zhang, S., Li, H., Song, C., & Yu, S. (2025) · PLoS ONE · doi:10.1371/journal.pone.0335186 · Cited by 1
“Joseph Redmon [15] proposed You Only Look Once (YOLO), which treats target detection as a regression problem and directly predicts the bounding boxes and their category probabilities in an image, providing a basis for the optimization of the subsequent YOLO series of algorithms.”
Wind Turbine Blade Defect Detection Based on Improved YOLOv9 with CA and AKConv
Shi, J., Zhu, H., Cai, Y., et al. (2025) · International Conference on Internet of Things, Automation and Artificial Intelligence (IoTAAI) · doi:10.1109/iotaai66837.2025.11212955 · Cited by 1
“With advances in deep learning and UAV imaging, automatic defect detection based on You Only Look Once (YOLO) [10] has gradually replaced traditional manual inspections, significantly improving detection efficiency and accuracy.”
Automated coffee plant detection and counting system using machine learning
García-Downing, G., Leitón-Jiménez, J., Barboza-Artavia, L., et al. (2025) · International Conference on Internet of Things, Automation and Artificial Intelligence (IoTAAI) · doi:10.1109/iotaai66837.2025.11213470 · Cited by 1
AI-Powered Autonomous UAV for Power Line Inspection
Vijay, D., Sriram, H. V. R., Pranoy, S., et al. (2025) · doi:10.1109/etaav66793.2025.11212870 · Cited by 1
“Recent advancements such as YOLO-ELA [Redmon et al., 2016] and LMD-YOLO [Howard et al., 2017] further improve defect detection accuracy using attention-enhanced lightweight models suitable for UAV applications.”
GDS-Detector: A lightweight defect detection model for solar cells
Zhang, Y., Wang, J., Wang, S., Zhao, Y. H., & Chen, Z. (2025) · Energy Sources Part A Recovery Utilization and Environmental Effects · doi:10.1080/15567036.2025.2572370 · Cited by 2
“Currently, the predominant detection methods fall into two categories: two-stage detectors exemplified by Faster R-CNN (Region-CNN) (Ren et al. 2016) and single-stage detectors represented by YOLO (You Only Look Once) (Redmon et al. 2016).”
AIoT platform integrated with smart breeding and omics cloud database for Taiwan tilapia
Lai, Y.-C., Huang, C., Wu, T.-Y., Weng, Y.-T., Wang, T.-Y., Huang, C., Chiang, C.-P., & Wang, J.-H. (2025) · Journal of Agriculture and Food Research · doi:10.1016/j.jafr.2025.102490 · Cited by 3
Amokrane, S.-B., Stanković, M. R., Manojlović, S. M., & Benyahia, T.-E. (2025) · Vojnotehnicki glasnik · doi:10.5937/vojtehg73-59271 · Cited by 1
Tao, H.-F., Pan, X., Wang, Y., et al. (2025) · Journal of Real-Time Image Processing · doi:10.1007/s11554-025-01791-y
“In the single-stage object detection technology, the representative are YOLO [9], SSD [10], RetinaNet [11], CornerNet [12], RefineDet [13] and other algorithms.”
Liu, Q., Yang, Z., Su, X. J., Wu, H., Zhou, Y. Z., & Zhang, H. (2025) · Journal of Systems Architecture · doi:10.1016/j.sysarc.2025.103621 · Cited by 1
Prompt-Based Two-Stage Enhancement for Low-Light Object Detection
Xiong, B., Chang, K., Ling, M., Huang, S., Xia, S., & Yuan, Y. (2025) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme59968.2025.11208935 · Cited by 2
“1 illustrates an example of a framework that integrates our PTE modules into the well-known YOLO detector, which can be trained in an end-to-end manner using the standard detection loss [5].”
RDFNet: Real-time Object Detection Framework for Foggy Scenes
Fang, T., Liu, Z., Tang, Y., et al. (2025) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme59968.2025.11209981 · Cited by 1
“The YOLO series [4]–[7] has demonstrated superior real-time performance and has consequently become the dominant methodology in this field.”
Real-Time Smart Bin Overflow Monitoring with YOLOv7
Preethi Salian, K., Salian, S., Shetty, K. A., et al. (2025) · International Conference on Electronics and Sustainable Communication Systems (ICESC) · doi:10.1109/icesc65114.2025.11212318 · Cited by 1
“The YOLO algorithm, introduced by Redmon et al. [6], has evolved significantly since its inception.”
Nighttime Object Detection with Contextual Auxiliary Learning
Hu, X., Zhang, X.-S., Li, Y., & Yang, K.-F. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-3393-0_19 · Cited by 2
Han, L., Chen, L., Zhang, H., Zhao, J., Lin, L., Zhang, Y., & Liu, Y. (2025) · International Journal of Software Engineering and Knowledge Engineering · doi:10.1142/s0218194025500913 · Cited by 2
Dynamic Visual SLAM Algorithm Combined with YOLO
Fu, Q., Zhong, Z., Ji, Y., & Yan, S. (2025) · Lecture notes in mechanical engineering · doi:10.1007/978-981-96-7703-0_8 · Cited by 1
RWD-YOLO: A Novel Approach for Small Object Detection in Aerial Drone Imagery
Hong, W., Yan, H., Wu, W., & Huang, X. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-3729-7_1 · Cited by 1
Real-Time Surface Type Recognition on Airport Runways Using YOLOv8 with Semantic Segmentation
Suder, J., Dyks, M., & Jóźwiak, J. (2025) · Signal Processing: Algorithms, Architectures, Arrangements, and Applications · doi:10.23919/spa65537.2025.11215133 · Cited by 1
“The chosen approach leverages YOLOv8 (You Only Look Once version 8) [4], a state-of-the-art object detection model known for its high speed and accuracy.”
YOLOv8 and FaceNet Algorithm for Real-Time Face Recognition Attendance System
Putra, B. K., Putrada, A. G., & Oktaviani, I. D. (2025) · doi:10.1109/softt67007.2025.11213461 · Cited by 1
Automated Detection and Counting of Oil Palm Trees Using Remote Sensing and Deep Learning
Hasan, H., & Kadim, Z. (2025) · doi:10.1109/icitce65255.2025.11210769 · Cited by 1
“Deep learning techniques, particularly those utilizing YOLO (You Only Look Once) [9], have become transformative tools for automating tasks such as tree crown detection, providing more efficient and accurate solutions than traditional methods.”
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.