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 27,201–27,300 of 51,400
PCRNet: Parent–Child Relation Network for automatic polyp segmentation
Muhammad, Z.-U.-D., Huang, Z., & Gu, N. (2025) · Displays · doi:10.1016/j.displa.2025.102993 · Cited by 3
Recyclable Waste Detection using You Look Only Once (YOLOv8): A Preliminary Study
Hamzah, S., Mangshor, N. N. A., Kamarudin, M. S., Ibrahim, S., & Fadzil, A. F. A. (2024) · IEEE Student Conference on Research and Development (SCOReD) · doi:10.1109/scored64708.2024.10872699 · Cited by 4
Süme, S., Ponomarjova, K.-M., Wendt, T. M., & Rupitsch, S. J. (2025) · Journal of sensors and sensor systems · doi:10.5194/jsss-14-37-2025 · Cited by 4
Zhu, J., Ruan, Y., Jing, D., Fu, Q., & Ma, T. (2025) · Sensors · doi:10.3390/s25051285 · Cited by 4
PIDDN: Pair-Image-Based Defect Detection Network With Template for PCB Inspection
Jiang, Q., Wu, X., Zhou, J., & Cheng, J. S. (2025) · IEEE Transactions on Components Packaging and Manufacturing Technology · doi:10.1109/tcpmt.2025.3543396 · Cited by 4
Enhanced Autonomous Driving: Various YOLO Models for Pothole Detection
Waga, A., Benhlima, S., & Bekri, A. (2025) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3373-1399-3.ch010 · Cited by 5
Yu, H., Yan, K., Li, C., Wang, L., & Li, T. (2025) · Remote Sensing · doi:10.3390/rs17050795 · Cited by 3
Shi, R., Zhang, L., Wang, G., Jia, S., Zhang, N., & Wang, C. (2025) · Remote Sensing · doi:10.3390/rs17050783 · Cited by 5
Huang, W., Gao, Y., Li, G., & Shi, Z. (2025) · Precision Engineering · doi:10.1016/j.precisioneng.2025.02.020 · Cited by 5
An Active Object-Detection Algorithm for Adaptive Attribute Adjustment of Remote-Sensing Images
Wang, J., Zhu, F., Wang, Q., Zhao, P., & Fang, Y. (2025) · Remote Sensing · doi:10.3390/rs17050818 · Cited by 4
Using Deep Neural Networks to Quantify Parking Dwell Time
Ribas, M. M., Mendes, H. B., Oliveira, L. S., Junior, L. A. Z., & de Almeida, P. R. L. (2024) · International Conference on Machine Learning and Applications · doi:10.1109/icmla61862.2024.00232 · Cited by 4
Lei, Y., Chen, S., Wan-cheng, G., et al. (2025) · IEEE Access · doi:10.1109/access.2025.3549298 · Cited by 3
Mapping Wind Turbine Distribution in Forest Areas of China Using Deep Learning Methods
Yang, P., Zou, Z., & Yang, W. (2025) · Remote Sensing · doi:10.3390/rs17050940 · Cited by 5
Improved YOLOv8 Underwater Object Detection Combined with CBAM
Xu, P. Y., Luo, X., & Li, J. (2024) · doi:10.1109/isdh64927.2024.00014 · Cited by 3
Multi-feature fusion for snowy traffic sign detection
Wang, Z., Liu, L., & Du, X. (2025) · Signal Image and Video Processing · doi:10.1007/s11760-025-03983-2 · Cited by 4
Vaccine-YOLOv10: real-time QR code detection model for complex light condition
Zhao, X., & Li, X. (2025) · Journal of Real-Time Image Processing · doi:10.1007/s11554-025-01631-z · Cited by 3
Online Optimization of Offloading Video Analytics Tasks to Multiple Edges for Accuracy Maximization
Liang, Y., Zhang, S., & Wu, J. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10887875 · Cited by 4
Zhang, L., Tong, J., Chen, Y., Wang, N., Li, W., Chen, M., & Tian, J. (2025) · Signal Image and Video Processing · doi:10.1007/s11760-025-03997-w · Cited by 4
DHC-YOLO: An Improved YOLOv8 for Lesion Detection in Medical Images*
Ren, S., Song, J., Yu, L., & Tian, S. (2024) · International Conference on Machine Vision, Image Processing and Imaging Technology (MVIPIT) · doi:10.1109/mvipit65697.2024.00037 · Cited by 4
Waste Classification and Monitoring Using Yolov8 A Deep Learning Object Detection Technique
Sharma, A., Sihag, A., Dixit, T., & Tanwar, P. (2024) · International Conference on Advances in Computation, Communication and Information Technology (ICAICCIT) · doi:10.1109/icaiccit64383.2024.10912312 · Cited by 3
Disaster Image Tagging Using Generative AI for Digital Archives
Yasuda, K., Aritsugi, M., Takeuchi, Y., Shibayama, A., & Mendonça, I. (2024) · ACM/IEEE Joint Conference on Digital Libraries · doi:10.1145/3677389.3702516 · Cited by 5
Smart ANPR: A Checkpoint-Based Toll and Parking Management System Using Hybrid OCR and Blockchain
Samarth, M. N., Gopisetti, S., & Chaitra, M. (2025) · International Conference on Intelligent and Innovative Technologies in Computing, Electrical and Electronics (IITCEE) · doi:10.1109/iitcee64140.2025.10915222 · Cited by 3
Car Paint Defect Detection Based on PMD With Multisource Image Fusion
Liu, J., Zhao, S., Jin, J., & Wang, Q. (2025) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2025.3551922 · Cited by 4
Multi-Scale Graph Channel Attention Detectors for Sonar Images in Smart Ocean
Li, S., Zhang, Y., Ma, Z., Ding, J., & Zou, B. (2025) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2025.3551424 · Cited by 8
ACMSPT: Automated Counting and Monitoring System for Poultry Tracking
Cruz, E., Hidalgo-Rodriguez, M., Acosta-Reyes, A. M., Rangel, J. C., Boniche, K., & González-Olivardía, F. (2025) · AgriEngineering · doi:10.3390/agriengineering7030086 · Cited by 8
Luangluewut, W., Thiennviboon, P., Viriyasatr, K., Maleecharoen, P., & Kasetkasem, T. (2025) · International Conference on Artificial Intelligence in Information and Communication (ICAIIC) · doi:10.1109/icaiic64266.2025.10920826 · Cited by 3
MDDFA-Net: Multi-Scale Dynamic Feature Extraction from Drone-Acquired Thermal Infrared Imagery
Wang, Z., Dang, C., Zhang, R., et al. (2025) · Drones · doi:10.3390/drones9030224 · Cited by 3
Le, V.-H. (2025) · Multimedia Tools and Applications · doi:10.1007/s11042-025-20743-z · Cited by 3
A Color-Based Multispectral Imaging Approach for a Human Detection Camera
Ono, S. (2025) · Journal of Imaging · doi:10.3390/jimaging11040093 · Cited by 4
Bone Fracture Detection Using YoloV9
Nivethitha, V., Sriram, S., Praadeep, G. K., et al. (2024) · doi:10.1109/iipem62726.2024.10925752 · Cited by 3
Dual Prediction-Guided Distillation for Object Detection in Remote Sensing Images
Wang, R., Fu, Y., Xu, Y., Wu, Z., & Wei, Z. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2025.3553128 · Cited by 6
RADNet: Adaptive Spatial-Dilation Learning for Efficient Road Crack Detection
Du, K., & Dai, Y. (2025) · IEEE Access · doi:10.1109/access.2025.3555032 · Cited by 6
Enhanced Long-Range UAV Detection: Leveraging Slicing Aided Hyper Inference with YOLOv8
Khorsand, H., Arezoomandan, S., & Han, D. K. (2025) · International Conference on Consumer Electronics · doi:10.1109/icce63647.2025.10930186 · Cited by 5
Spiking Neural Network based on YOLO-C3 for Object Detection
Bi, T., Rong, H., Zhou, Z., et al. (2024) · International Symposium on Artificial Intelligence and Intelligent Manufacturing (AIIM) · doi:10.1109/aiim64537.2024.10934233 · Cited by 3
Vehicle Detection and Tracking Techniques Using Yolo Detection and Kalman Filter Optimization
Hunain, A., Indrabayu, I., & Ilham, A. A. (2025) · International Conference on Advancement in Data Science, E-learning and Information System (ICADEIS) · doi:10.1109/icadeis65852.2025.10933380 · Cited by 3
Lightweight Helmet-Wearing Detection Algorithm Based on StarNet-YOLOv10
Wang, H., Zong, Q., Liao, Y., Luo, X. Q., Gong, M., Liang, Z., Gu, B., & Yong, L. (2025) · Processes · doi:10.3390/pr13040946 · Cited by 3
Evaluating the FLUX.1 Synthetic Data on YOLOv9 for AI-Powered Poultry Farming
Čakić, S., Popović, T., Krčo, S., Jovović, I., & Babić, D. (2025) · Applied Sciences · doi:10.3390/app15073663 · Cited by 7
YOLO-SAD: Enhancing Small Aircraft Detection With Multi-Scale Context and Improved Gradient Flow
Ning, X., Ding, H., & Guo, X. (2025) · IEEE Access · doi:10.1109/access.2025.3555538 · Cited by 3
Artificial Intelligence in Oral Health
Binod, H., Shithij, T., Tichý, A., & Mishra, S. (2025) · Springer eBooks · doi:10.1007/978-3-031-84047-0_1 · Cited by 3
Target Detection Method for Soil-Dwelling Termite Damage Based on MCD-YOLOv8
Jiang, P., Jiang, L., Wu, F., Che, T., Wang, M., & Zheng, C. (2025) · Sensors · doi:10.3390/s25072199 · Cited by 4
Object Detector Based on Center Keypoints for Behavior Recognition in Classroom Scenes
Dang, M., Liu, G., Li, X. R., Wan, B., Zhang, Y., & Pan, R. (2025) · IEEE Transactions on Computational Social Systems · doi:10.1109/tcss.2025.3552067 · Cited by 7
“1) Center-Based Methods: The center-based object detection directly regresses bounding boxes from points, starting with DenseBox [27] and YOLOv1 [28].”
End-to-End Learning-based Video Streaming Enhancement Pipeline: A Generative AI Approach
Artioli, E., Tashtarian, F., & Timmerer, C. (2025) · doi:10.1145/3712678.3721881 · Cited by 4
Infrared and visible image fusion based on text-image core-semantic alignment and interaction
Li, X., Wang, J., Chen, W., Chen, R., Zhang, G., & Cheng, L. (2025) · Digital Signal Processing · doi:10.1016/j.dsp.2025.105203 · Cited by 4
GMVG-Net: lightweight mul tiscale feature fusion network for welding defect detection
Song, K., & Huang, Q. (2025) · Signal Image and Video Processing · doi:10.1007/s11760-024-03738-5 · Cited by 3
Improved YOLOv8-C2fCA for embryonic cell detection and counting
Talha, O., Zhou, W., Yuan, N., et al. (2025) · Multimedia Systems · doi:10.1007/s00530-025-01731-7 · Cited by 3
Cost-Effective Real-Time Obstacle Detection and Avoidance for AGVs using YOLOv8 and RGB-D Sensors
Medjaldi, A., Slimani, Y., & Karkar, N. (2025) · Engineering Technology & Applied Science Research · doi:10.48084/etasr.10135 · Cited by 3
Butorovа, A. S., & Sergeev, A. (2025) · The European Physical Journal Special Topics · doi:10.1140/epjs/s11734-025-01596-x · Cited by 3
Bordet, T., Redondin, M., Bornhofen, S., Denaës, S., & Histace, A. (2025) · EPJ Web of Conferences · doi:10.1051/epjconf/202532305001 · Cited by 3
Application of Deep Learning in Autonomous Driving
Yang, M. (2025) · Applied and Computational Engineering · doi:10.54254/2755-2721/2025.21902 · Cited by 3
Advancing ultrasonography with AI: recent innovations and future perspectives
Karako, K. (2025) · Holistic Integrative Oncology · doi:10.1007/s44178-025-00160-w · Cited by 5
“With the evolution of Convolutional Neural Networks (CNNs) [1], models designed for image processing, such as ResNet [2], and YOLO [3], have emerged, achieving prediction performance comparable to that of humans.”
Wireless propagation parameter estimation with convolutional neural networks
Schieler, S., Semper, S., & Thomä, R. S. (2025) · International Journal of Microwave and Wireless Technologies · doi:10.1017/s1759078725000431 · Cited by 3
“Our encoding is inspired by [13], and adapted to provide a learnable encoding of the parameters.”
Tanveer, M. H., Fatima, Z., Khan, M. A., et al. (2024) · International Conference on Control, Robotics and Cybernetics (CRC) · doi:10.1109/crc63701.2024.10949895 · Cited by 3
HFGL-Net: High-frequency guided multi-scale non-local network for remote sensing object detection
Dan, Z., Fu, Q., Huang, L., Hu, D., Li, X., & Sun, H. (2025) · Digital Signal Processing · doi:10.1016/j.dsp.2025.105230 · Cited by 4
An Improved YOLOv8-Based Detection Model for Multi-Scale Sea Ice in Satellite Imagery
Liu, Y., Guo, Q., Dong, C., & Luo, Y. (2025) · Chinese journal of information fusion. · doi:10.62762/cjif.2025.695812 · Cited by 4
A YOLOv8‐based method for detecting tea disease in natural environments
Li, X., Zhang, T., Yu, M., Yan, P., Wang, H. E., Dong, X. P., Wen, T., & Xie, B. (2025) · Agronomy Journal · doi:10.1002/agj2.70043 · Cited by 4
Interpretable Dimensionality Reduction in 3D Image Recognition with Small Sample Sizes
Koptev, I. V., Tian, J., Peel, E., Barker, R., Walker, C. G., & Kempa-Liehr, A. W. (2025) · Journal of Nondestructive Evaluation · doi:10.1007/s10921-025-01183-z · Cited by 3
“YOLOv3 [21] used the Feature Pyramid Network architecture to allow for multi-scale detection so that the objects of different sizes can be identified in the image.”
UN-DETR: Promoting Objectness Learning via Joint Supervision for Unknown Object Detection
Liu, H., Hao, X., Yue, C., & Ma, B. (2025) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v39i5.32579 · Cited by 10
Yu, X., Hu, T., & Zhu, H. (2025) · Electronics · doi:10.3390/electronics14081576 · Cited by 4
Improve Nighttime Highway Vehicles and Pedestrian Detection Using Yolov8+CLAHE
Indrayana, I. N. E., Sudarma, M., Putra, I. K. G. D., & Sudana, O. (2024) · International Conference on Informatics and Computing (ICIC) · doi:10.1109/icic64337.2024.10956682 · Cited by 8
Traffic Accident Detection Analysis Using YOLOv9 Algorithm
Samba, S. H., Agranata, I. Y. B., Tsanaullailla, L., & Hamami, F. (2024) · International Conference on Informatics and Computing (ICIC) · doi:10.1109/icic64337.2024.10957461 · Cited by 5
Vision-Based Grasping Method for Prosthetic Hands via Geometry and Symmetry Axis Recognition
Zhang, Y., Xie, Y., Zhao, Q., Xu, X., Deng, H., & Yi, N. (2025) · Biomimetics · doi:10.3390/biomimetics10040242 · Cited by 4
Cross-YOLO: an object detection algorithm for UAV based on improved YOLOv8 model
Dong, Y., Guo, J., & Xu, F. (2025) · Signal Image and Video Processing · doi:10.1007/s11760-025-04084-w · Cited by 3
Utilize Data Augmentation and Flexi Corner Block for Road Damage Detection
Wu, Z., Li, Z., Sun, X., Zhao, R., Bai, Y., & Na, J. (2025) · IEEE Access · doi:10.1109/access.2025.3561831 · Cited by 4
DR-YOLO: dual reconstructed YOLO for logo detection in livestreaming
Yuan, C., Zhang, J., Li, W., et al. (2025) · Multimedia Systems · doi:10.1007/s00530-025-01771-z · Cited by 3
“Although Transformer-based object detection, especially RT-DETR [3], once surpassed YOLO [4] in terms of speed and accuracy, the Transformer model typically requires a large amount of data and computational resources for pre-training and fine-tuning, which puts high demands on hardware, and thus…”
Reliable recommendations for CCTV sewer inspections through multi-label image classification
Cuingnet, R., Bernard, M., Sampaio, P. R., Sakhri, I., Chelouche, K., Jossent, J., Doumi, I., Gaudichet, E., Chenu, D., Maitrot, A., et al. (2025) · Advanced Engineering Informatics · doi:10.1016/j.aei.2025.103317 · Cited by 4
Video Based Real Time Cattle Recognition Using Muzzle Patterns and Yolo
Kumar, N., Arya, R. K., & Singh, S. K. (2024) · IEEE India Council International Conference (INDICON) · doi:10.1109/indicon63790.2024.10958228 · Cited by 3
Recognition of chlorophyll rings using YOLOv8
Xu, G., Lin, Z., Shi, Y., Wu, J., Xu, H., Wang, G., & Zhang, T. (2025) · Scientific Reports · doi:10.1038/s41598-025-98659-9 · Cited by 3
“…the core of YOLO involves transforming the object detection problem into a single regression task, directly predicting the class and location of objects from the input image 24 , rather than partitioning the image into multiple regions for individual detection, as performed by other methods.”
Detection of Transmission Line Insulator Defect Based on Improved YOLOv10
Wang, Z., & Jiang, H. (2025) · International Conference on Advances in Electrical, Electronics and Computing Technology (EECT) · doi:10.1109/eect64505.2025.10966943 · Cited by 3
An Artificial Intelligence–Driven Approach for Real-Time Detection of Traffic-Sign Deficiencies
Karasneh, M. A., Manasreh, D., Matouq, Y., et al. (2025) · Transportation Research Record Journal of the Transportation Research Board · doi:10.1177/03611981241302333 · Cited by 3
“Regression-based methods include single-shot detector and You Only Look Once (YOLO) ( 20 , 21 ).”
A transfer learning approach for college ID card detection
Veerasekar, P. A., Sindha, M. M. R., Pandyan, U. M., et al. (2025) · AIP conference proceedings · doi:10.1063/5.0262339 · Cited by 3
Wang, Y., Wang, F., Qin, Z., Fu, Y., Wang, J., Li, S., & Zhang, D. (2025) · Scientific Reports · doi:10.1038/s41598-025-99451-5 · Cited by 4
Collaborative Knowledge Injection for Concealed Object Detection in MMW Human Inspection
Wang, X., Tong, N., Gou, S., & Mao, S. (2025) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2025.3559141 · Cited by 5
“In contrast, the latter trains a detector to localize and identify concealed objects in human body images [7], [8], [9], [10], [11], [12], [13], [14], [15], primarily building upon well-known frameworks, such as Faster-region-based convolutional neural network (RCNN) [1] and YOLO [16].”
An improved and lightweight small-scale foreign object debris detection model
Zhang, H., Fu, W., Wang, X., Li, D., Zhu, D., & Su, X. (2025) · Cluster Computing · doi:10.1007/s10586-024-05002-4 · Cited by 6
“Currently, the object detector is divided into two major trends: one-stage detectors [7–15] and two-stage detectors [16–20].”
From Colon to Uterus: Potential of YOLOv7 for Real-Time Polyp Detection in Hysteroscopy
Rostami, G., Berneti, S. H. H., Habibzadeh, N., et al. (2025) · InfoScience Trends · doi:10.61186/ist.202502.04.05 · Cited by 3
Steel Defect Detection Based on YOLO-SAFD
Yu, F., Zhang, J., & Mu, D. (2025) · IEEE Access · doi:10.1109/access.2025.3565587 · Cited by 5
AutoFish: Dataset and Benchmark for Fine-Grained Analysis of Fish
Bengtson, S. H., Lehotský, D., Ismiroglou, V., et al. (2025) · IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW) · doi:10.1109/wacvw65960.2025.00174 · Cited by 3
Cai, J., Gao, Y., & Tang, J. (2025) · Applied Sciences · doi:10.3390/app15094950 · Cited by 4
Wang, Z., Ma, H., Wu, C., & Ma, L. (2025) · Signal Image and Video Processing · doi:10.1007/s11760-025-04099-3 · Cited by 4
Ji, X., Liu, X., Chen, X., & Li, R. (2025) · Education and Information Technologies · doi:10.1007/s10639-025-13558-w · Cited by 5
“YOLO (You Only Look Once) (Redmon et al., 2016) is a single-stage real-time target detection algorithm based on deep learning (Liao et al., 2024), the core idea of which is to use the whole image as the input to the network, and regress the location of the bounding box of the target object and its belonging category d…”
Zhang, Y., Liu, X., Shi, Y., et al. (2025) · IET Computers & Digital Techniques · doi:10.1049/cdt2/9984821 · Cited by 3
Gharieb, A., Zidan, H., & Darraj, N. M. (2025) · SPE Conference at Oman Petroleum & Energy Show · doi:10.2118/224821-ms · Cited by 3
IR-ADMDet: An Anisotropic Dynamic-Aware Multi-Scale Network for Infrared Small Target Detection
Li, N., & Wei, D. (2025) · Remote Sensing · doi:10.3390/rs17101694 · Cited by 4
Lightweight LUW-DETR for efficient underwater benthic organism detection
Li, N., Ding, B., Yang, G., Ni, S., & Wang, M. (2025) · The Visual Computer · doi:10.1007/s00371-025-03921-w · Cited by 4
“In contrast, single-stage object detection algorithms, such as SSD [18] and the YOLO [23] series, directly compute detection results from the image, offering faster detection speeds and better real-time performance.”
High-Fidelity Synthetic Data Generation Framework for Unique Objects Detection
Shakhovska, N., Sydor, B., Liaskovska, S., Duran, O., Martyn, Y., & Vira, V. V. (2025) · Computation · doi:10.3390/computation13050120 · Cited by 6
Weather-informed vision enhancement for autonomous vehicles in adverse conditions
Bayramov, E., & Istenes, Z. (2025) · Pollack Periodica · doi:10.1556/606.2025.01240 · Cited by 5
Jia, 赵. Z., Yuelan, 辛. X., Jizhao, 刘. L., & Qingqing, 王. W. (2025) · Laser & Optoelectronics Progress · doi:10.3788/lop242143 · Cited by 3
Multistage Fusion Object Detection With Marine Radar and Camera in Complex Maritime Context
Xu, H., Yu, Y. F., He, J., Pang, C., & Zhang, X. (2025) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2025.3571112 · Cited by 16
Cong, Y., Zhu, H., Guo, L., et al. (2025) · The Visual Computer · doi:10.1007/s00371-025-03985-8 · Cited by 3
“Segment anything model (SAM) [54] has been recently proposed as a highly effective image segmentation model, while YOLO [55] is a stalwart in object detection, widely used across various detection tasks.”
Hazelnut Yield Estimation: A Vision-Based Approach for Automated Counting of Hazelnut Female Flowers
Giulietti, N., Tombesi, S., Bedodi, M., Sergenti, C., Carnevale, M., & Giberti, H. (2025) · Sensors · doi:10.3390/s25103212 · Cited by 4
“Comparing YOLO-based detection (i.e., YOLOv5, YOLOv7, YOLOv8) [13] with density map estimation, the results show that density map prediction outperforms object detection, achieving a Mean Absolute Error (MAE) of 39.13 [14].”
InfluentialRipFinder: real-time rip current detection on mobile devices
Khan, F. H., de Silva, A., Palinkas, A., Dusek, G., Davis, J., & Pang, A. (2025) · Frontiers in Marine Science · doi:10.3389/fmars.2025.1549513 · Cited by 8
Optimized YOLOv5 model for safety helmet and flame detection system
Tang, Z., Hasan, M. M., & Strauss, T. (2025) · Signal Image and Video Processing · doi:10.1007/s11760-025-04073-z · Cited by 7
“YOLO is extremely fast compared to other traditional methods (such as R-CNN, etc.) and produces half as little background error as FAST R-CNN, which demonstrates strong generalization and certain robustness when applied to in novel scenarios [2].”
Ramya, R., & Jebathangam, J. (2025) · International Conference on Inventive Computation Technologies (ICICT) · doi:10.1109/icict64420.2025.11004906 · Cited by 3
Transfer Learning from Simulated to Real Scenes for Monocular 3D Object Detection
Mohamed, S., Zimmer, W. M. X., Greer, R., Ghita, A., Castrillón-Santana, M., Trivedi, M. M., Knoll, A., Carta, S., & Marras, M. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-91813-1_20 · Cited by 6
Silvanus, T. (2025) · International Journal for Research in Applied Science and Engineering Technology · doi:10.22214/ijraset.2025.71284 · Cited by 4
RGE-YOLO enables lightweight road packaging bag detection for enhanced driving safety
Pang, D., Guan, Z., Luo, T., Liang, Y., & Dou, R. (2025) · Scientific Reports · doi:10.1038/s41598-025-03240-z · Cited by 4
“YOLO variants 3,31,33 address speed restrictions through single-stage architectures, but are prone to false positives in cluttered situations and demonstrate instability when detecting low-contrast, small-scale items such as partially occluded or flattened bags.”
Towards Intelligent Pruning of Vineyards by Direct Detection of Cutting Areas
Pacioni, E., Abengózar, E., Macías, M. M., Garcı́a-Orellana, C. J., Gallardo–Caballero, R., & González–Velasco, H. M. (2025) · Agriculture · doi:10.3390/agriculture15111154 · Cited by 3
Khokthong, W., Kritangkoon, P., Sinpoo, C., et al. (2025) · Insects · doi:10.3390/insects16060575 · Cited by 3
“Redmon et al. (2016) [18] introduced YOLO (You Only Look Once), a single-stage deep learning detection algorithm.”
FDN: A Real-Time Ensemble Fire Detection Network
Shin, D. H., Kang, J.-M., & Cheong, T. (2025) · IEEE Access · doi:10.1109/access.2025.3575057 · Cited by 3
Research on pedestrian detection algorithm based on low light environment
Li, J., Shan, K., Wang, J., Ji, S., Fang, Z., & Shan, W. (2025) · Engineering Research Express · doi:10.1088/2631-8695/addfab · Cited by 3
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.