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 33,701–33,800 of 51,399
Computer vision-based GCC-YOLOv8 for defect detection in light guide plates
Liu, C., Peng, S., Zhang, Y., Li, J., & Gao, J. (2025) · Materials Today Communications · doi:10.1016/j.mtcomm.2025.112386 · Cited by 4
Qu, Z., Yuan, S., Färber, M., Brennfleck, M., Wartha, N., & Stephan, A. (2025) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3690624.3709436 · Cited by 1
DinoQuery: Promoting Small 3D Object Detection With Textual Prompt
Ning, T., Lü, K., Jiang, X., Pei, H., & Xue, J. (2025) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2025.3557950 · Cited by 2
“YOLO [22] predicts bounding boxes and class probabilities directly from full images in one single pass, which makes it significantly faster than previous methods that used a multi-stage pipeline.”
Wei, L., Zhu, Y., Li, Y., Qian, M., Zuo, X., Chen, B., Liang, S., Lin, Z., & Yan, J. (2025) · IEEE Access · doi:10.1109/access.2025.3557947 · Cited by 3
Topological Data Analysis for Robust Classification of Circulating Cancer Cells
Yu, Y., & Wang, J. (2024) · 2018 52nd Asilomar Conference on Signals, Systems, and Computers · doi:10.1109/ieeeconf60004.2024.10942851 · Cited by 1
RT-DEKT: real-time object detector with KAN-Transformer
Jin, Z., Li, C., & Lei, Z. (2025) · Signal Image and Video Processing · doi:10.1007/s11760-025-04016-8 · Cited by 2
Deep Object Occlusion Relationship Detection Based on Associative Embedding Clustering
Gong, P., Zheng, K., Liu, T., Jiang, Y., & Zhao, H. (2025) · Technologies · doi:10.3390/technologies13040143 · Cited by 2
A prompt-free vision-language model for environmental perception in automated driving systems
Lin, C., Ying, S., Hu, Q. X., & Zhang, L. (2025) · Proceedings of the Institution of Mechanical Engineers Part D Journal of Automobile Engineering · doi:10.1177/09544070251327247 · Cited by 1
Zhou, H., Chen, J., Zhu, H., Li, M., & Li, Z. (2025) · Unmanned Systems · doi:10.1142/s2301385026500329 · Cited by 1
Learning Robust and Repeatable Physical Camouflage for Aerial Object Detectors
He, Z., & Zhang, H. (2024) · IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom) · doi:10.1109/trustcom63139.2024.00235 · Cited by 1
Zhenyu, 麻. M., Nini, 王. W., Guolei, 吴. W., Chenlong, 朱. Z., Mingqi, 周. Z., Yongjun, 刘. L., & Yunxiang, 严. Y. (2025) · Laser & Optoelectronics Progress · doi:10.3788/lop241341 · Cited by 1
Implementation of YOLOv11-based Automated Pothole Reporting and Visualization System
Yu, D., Lee, S., & Jeong, D. (2025) · The Journal of Korean Institute of Information Technology · doi:10.14801/jkiit.2025.23.3.89 · Cited by 1
Wang, C.-M., Shao, C.-H., & Lin, Y. (2025) · Sensors · doi:10.3390/s25072315 · Cited by 1
A Lightweight Infrared and Visible Image Fusion Method for Object Detection
Zhang, C., & Ji, W. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-4276-2_19 · Cited by 1
Moradi, K., Haque, E., Kaur, J., Bentz, A. B., Bridge, E. S., & Habibi, G. (2025) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61041.2025.00105 · Cited by 2
A Regional-Level Resource-Saving Model for Winter Road Surface Snow Detection in Extreme Weathers
Zhou, X., Wang, T., Liu, Z., et al. (2025) · IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) · doi:10.1109/wacv61041.2025.00591 · Cited by 1
REDE NEURAL PARA DETECÇÃO DE PNEUS COM YOLOV8: UMA FERRAMENTA PARA O COMBATE À DENGUE
Quadros, A. A., & da Cunha, M. F. (2025) · Revista Foco · doi:10.54751/revistafoco.v18n4-021 · Cited by 1
Ma, F., Jiang, X., Chen, C., Sun, J., Yan, X., & Wang, J. (2025) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2025.3554717 · Cited by 2
“As is widely known that single-stage algorithms represented by the YOLO [11], [12] series have achieved a satisfactory balance between computational speed and detection accuracy, allowing for end-to-end training and widespread adoption in various recognition tasks.”
Intelligent Poultry Health Management Based on Improved YOLOv8 Algorithm
Liu, Y., Johar, M. G. M., Hajamydeen, A. I., & Raya, L. B. (2024) · IEEE International Conference on Agrosystem Engineering, Technology & Applications (AGRETA) · doi:10.1109/agreta61912.2024.10948899 · Cited by 1
Wang, Y., Jia, J., Liu, R., Cao, Q., Feng, J., Li, D., & Wang, L. (2025) · Remote Sensing · doi:10.3390/rs17081350 · Cited by 1
Menjívar, P. J., Pino, A. F. S., Manzano, J. E. M., & Cabrera, E. V. R. (2025) · Microorganisms · doi:10.3390/microorganisms13040860 · Cited by 14
DETECTION AND COUNTING OF GRAZING CATTLE FROM AERIAL IMAGES USING CNN
GEJILETU, H., ULAANKHUU, H., & NYANDAG, B.-E. (2025) · INMATEH Agricultural Engineering · doi:10.35633/inmateh-75-39 · Cited by 1
Small Target Detection in UAV Aerial Images Based on Sliding Window and Improved Yolov8
Hu, Y., & Zeng, Q. (2024) · International Conference on Image Processing, Computer Vision and Machine Learning (ICICML) · doi:10.1109/icicml63543.2024.10958151 · Cited by 1
A High-Precision and Lightweight Method of PCB Defect Based on Enhanced Yolov8
Peng, X., Li, W., Xing, X., et al. (2024) · International Conference on Image Processing, Computer Vision and Machine Learning (ICICML) · doi:10.1109/icicml63543.2024.10957814 · Cited by 1
Recognition of Marine Products Based on SA-YOLOv10
Deng, J., Wang, W., Liu, Y., et al. (2024) · International Conference on Image Processing, Computer Vision and Machine Learning (ICICML) · doi:10.1109/icicml63543.2024.10958074 · Cited by 1
A Highly Transferable Camouflage Attack Against Object Detectors in the Physical World
Wang, Y., Wu, L., Cao, Y., Jin, J., Zhang, Z., Wang, E., Ma, C., & Zhao, Y. D. (2025) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2025.3553847 · Cited by 8
SDF-YOLO: an efficient neural network for detecting surface defects in steel strips
Wang, C., & Xu, K. (2025) · Journal of Physics Conference Series · doi:10.1088/1742-6596/2990/1/012024 · Cited by 1
Wu, X., Shi, Y., & Khishe, M. (2025) · Complexity · doi:10.1155/cplx/6829161 · Cited by 1
EPA-YOLO: A Lightweight Pipeline Leak Detection Algorithm Based on Improved YOLOv7
Zhang, J., Lan, X., Wang, S., et al. (2024) · International Conference on Computers and Artificial Intelligence Technology (CAIT) · doi:10.1109/cait64506.2024.10963109 · Cited by 1
Automode: The Automatic LoRA Based on Stable Diffusion
Wu, Y., & Lu, Y. (2024) · International Conference on Vision, Image and Signal Processing (ICVISP) · doi:10.1109/icvisp64524.2024.10959379 · Cited by 2
Real-Time Video Stream Processing: Spark-Based Sub-Stream Generation for Scalable Analytics
Demiral, Y., & Sayar, A. (2025) · Lecture notes on data engineering and communications technologies · doi:10.1007/978-3-031-87781-0_40 · Cited by 1
TinyCompNet: Minimal Computational Load for Mobile Devices
Wang, J., Bai, Z., Zhang, X., & Qiu, Y. (2024) · International Conference on Vision, Image and Signal Processing (ICVISP) · doi:10.1109/icvisp64524.2024.10959446 · Cited by 1
Array-Based Faster R-CNN for Underwater Acoustic Communication Signal Detection
Cheng, L., Liu, Y., Wei, J., et al. (2024) · doi:10.1109/icvisp64524.2024.10959565 · Cited by 1
CTTrack: Leveraging Cross-Transformer for Multi-Scale Feature Fusion in Multi-Object Tracking
Zhang, Z., Cao, C., & Zheng, F. (2024) · International Conference on Computers and Artificial Intelligence Technology (CAIT) · doi:10.1109/cait64506.2024.10963082 · Cited by 1
Exploring the interpretability of Vision GCN with a multi-method approach
Zhao, H., Sui, Y., & Wu, L. J. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.127624 · Cited by 3
Object Detection for Product Arrangement Robot Using Anomaly Detection
Kondo, R., & Tasaki, T. (2025) · Journal of Robotics and Mechatronics · doi:10.20965/jrm.2025.p0284 · Cited by 1
Image to Audio Using LLM for Blind People
Kumaresan, T., Geetha, A. V., Rajeshkumar, G., et al. (2024) · doi:10.1109/icdcc62744.2024.10961841 · Cited by 1
An Attention-Based Risk-Driven Approach to Object Detection for Autonomous Vehicles
Mohammadi, K., & Ferdowsi, H. (2025) · International Journal of Intelligent Transportation Systems Research · doi:10.1007/s13177-025-00485-w · Cited by 1
“Its inception dates to 2015, when Redmon et al. introduced the initial version of YOLO [37].”
Cheng, Y., Lai, X., & Xia, Y. (2025) · Applied Sciences · doi:10.3390/app15094634 · Cited by 1
Infrared and Visible Image Fusion Based on Autoencoder Network
Wang, H., Lu, X., Wu, Z., Li, R., & Wang, J. (2025) · IET Image Processing · doi:10.1049/ipr2.70086 · Cited by 2
Enhanced YOLOv7 Based on Channel Attention Mechanism for Nearshore Ship Detection
Zhu, Q., Zhang, Z., & Mu, R. (2025) · Electronics · doi:10.3390/electronics14091739 · Cited by 1
Convex Hull-ish Object Detection
Khan, K., Agarwal, I., & Jerripothula, K. R. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-88223-4_22 · Cited by 1
Improving Traffic Sign Detection Using Synthetic Data and Automatic Labeling
Chang, K., & Lu, E. H.-C. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-6008-7_4 · Cited by 3
Lorenz, M., Okoniewski, M., Own, A., et al. (2025) · IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW) · doi:10.1109/vrw66409.2025.00338 · Cited by 1
Transfer Learning with Yolo for Object Detection in Remote Sensing
Pandilova, E., Petrov, M., Spasev, V., Dimitrovski, I., & Kitanovski, I. (2025) · Communications in computer and information science · doi:10.1007/978-3-031-86162-8_9 · Cited by 6
Kassjański, M., Kulawiak, M., Przewoźny, T., et al. (2025) · Scientific Reports · doi:10.1038/s41598-025-99338-5 · Cited by 1
“This study utilized three detection models to analyze audiograms, symbols, and labels, employing the You Only Look Once (YOLO) model, first introduced in 2016 by Redmon et al. 29 .”
YOLO-BCD: A Lightweight Multi-Module Fusion Network for Real-Time Sheep Pose Estimation
Sun, C., Hu, J., Wang, Q., et al. (2025) · Sensors · doi:10.3390/s25092687 · Cited by 1
“YOLO, proposed by Joseph Redmon and colleagues in 2016 [31,32], is a popular single-stage detection algorithm. single-stage detection algorithm.”
Nguyen, D., Hoang, V.-D., & Le, V.-T.-L. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-5884-8_16 · Cited by 1
Tank Target Detection Based on Improved YOLOv8
Shan, Y., Liu, S., & Nie, J. (2024) · doi:10.1145/3718441.3718447 · Cited by 1
Bhattacharjee, S. (2025) · Computology Journal of Applied Computer Science and Intelligent Technologies · doi:10.17492/computology.v4i2.2402 · Cited by 2
Zhang, Q., Ge, J., Tian, S., & Xi, L. (2025) · Remote Sensing · doi:10.3390/rs17091572 · Cited by 3
YOLOV8X-HICAUPS: AN ATTENTION BASED APPROACH FOR ACCURATE PCB DEFECT DETECTION
Mounika, M., Gokulprasanth, M., & Vadivu, D. G. (2025) · International Journal of Engineering Applied Sciences and Technology · doi:10.33564/ijeast.2025.v09i11.013 · Cited by 1
Multimodal Road Traffic Detection Algorithm based on Improved YOLOv8
Wei, X., & Zhou, J. (2025) · Frontiers in Computing and Intelligent Systems · doi:10.54097/2m386f32 · Cited by 1
“Such models are led by R-NCC [2], the first deep learning model to use convolutional neural networks for target detection proposed by Girshick et al. in 2014.”
Implementation of Autonomous Navigation for Solar-Panel-Cleaning Vehicle Based on YOLOv4-Tiny
Cheng, W.-C., & Chen, X.-D. (2025) · IEEE Eurasia Conference on IOT, Communication and Engineering (ECICE) · doi:10.3390/engproc2025092031 · Cited by 1
“This method was introduced by Redmon in 2016 [7].”
Li, K., & Lin, Y. (2025) · Buildings · doi:10.3390/buildings15091522 · Cited by 1
P2Object: Single Point Supervised Object Detection and Instance Segmentation
Chen, P., Yu, X., Han, X., Wang, K., Li, G., Xie, L., Han, Z., & Jiao, J. (2025) · International Journal of Computer Vision · doi:10.1007/s11263-025-02441-3 · Cited by 6
“Girshick (2015), Ren et al. (2017), Redmon et al. (2016), Liu et al. (2016), Lin et al. (2017b), Carion et al. (2020), Sun et al. (2021), Yu et al. (2020) and Chen et al. (2023) gives the network a specific category and box information.”
Autonomous Navigation Using Deep Learning
Kumar, A. (2025) · International Journal for Research in Applied Science and Engineering Technology · doi:10.22214/ijraset.2025.70152 · Cited by 1
Offload Rethinking by Cloud Assistance for Efficient Environmental Sound Recognition on LPWANs
Zhang, L., Zhao, Q., Wang, R., Bian, S., Güngör, O., Ponzina, F., & Rosing, T. (2025) · ACM Conference on Embedded Networked Sensor Systems (SenSys) · doi:10.1145/3715014.3722078 · Cited by 1
Wu, T., Guo, H., Wang, X., et al. (2025) · IEEE Sensors Journal · doi:10.1109/jsen.2025.3564622 · Cited by 1
“Compared to Faster R-CNN [23], SSD [24], and YOLO [25], DETR eliminates the reliance on anchor boxes and nonmaximum suppression postprocessing steps and demonstrates favorable detection performance.”
Multi-Classes Object Detection and Manipulation for Industrial Robots Using Deep Learning
Pechbooranin, A., Chaisirithungnaklang, T., Tantrairatn, S., & Chamniprasart, K. (2025) · International Conference on Automation, Robotics and Applications · doi:10.1109/icara64554.2025.10977592 · Cited by 1
WHEAT IMPURITY DETECTION ALGORITHM BASED ON IMPROVED YOLO v8
Liqing, Z. H. A. O., Rui, Q. I. A. N., Liu, C., et al. (2025) · INMATEH Agricultural Engineering · doi:10.35633/inmateh-75-62 · Cited by 1
A Deep Learning Approach for Mandibular Condyle Segmentation on Ultrasonography
Keser, G., Yülek, H., Talmaç, A. G. Ö., Bayrakdar, İ. Ş., Pekiner, F. N., & Çelik, Ö. (2025) · Journal of Imaging Informatics in Medicine · doi:10.1007/s10278-025-01527-1 · Cited by 1
“YOLO separates the image into sections and creates boxes with objects in these sections, whereas other algorithms use the entire image to detect objects [44, 45].”
Gong, Y., Wei, H., Guo, H., et al. (2025) · IEEE Transactions on Very Large Scale Integration (VLSI) Systems · doi:10.1109/tvlsi.2025.3559389 · Cited by 1
Yang, J., Chen, C., He, Q., Li, J., Li, H., Peng, J., Cheng, J., Li, M., Zhou, X., He, Y., et al. (2025) · Medical & Biological Engineering & Computing · doi:10.1007/s11517-025-03360-8 · Cited by 2
Long-Tailed Traffic Sign Detection Using Local Cross-Channel Interaction for Complex Scenes
Zhao, Y., & Zhao, H. (2025) · IEEE Sensors Journal · doi:10.1109/jsen.2025.3566603 · Cited by 1
“This improved model is compared with Faster RCNN [2], SSD [37], YOLOv5 [3], YOLOv7 [38] YOLOv8 [39], and DETR algorithms on the self-made TT100K_2021LT dataset.”
Unsupervised Domain Adaptation for SAR Ship Detection Based on Multitask Decoupling
Yang, Y., Yang, X., & Yang, D. (2025) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2025.3568212 · Cited by 10
A multimodal recognition and detection method for road scenes based on the improved YOLOv11
Xia, X., Zhang, W., & Tao, L. (2025) · Conference on Electronic Information Engineering and Data Processing · doi:10.1117/12.3067173 · Cited by 1
“The representative algorithms of the first stage mainly include SSD [6] , YOLO (You Only Look Once) [7-10] series, YOLOF [11] etc.”
BPCS: Multi-view Bus Passenger Counting System
Mokin, A., Gayer, A. V., Ingacheva, A. S., Sheshkus, A. V., & Arlazarov, V. V. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-87663-9_22 · Cited by 1
Enhanced pallet detection in complex environments: an AM-Mask R-CNN method
Shao, Y., Xu, Z., Chen, J., Lu, J., & Shen, W. (2025) · International Journal of Computer Integrated Manufacturing · doi:10.1080/0951192x.2025.2501587 · Cited by 1
“The YOLO network proposed by Redmon et al. (2016) is a classic single-stage object detection network with higher detection efficiency and a simpler framework, but it is prone to localization errors.”
Research on a Computer Vision-Based Guide Glasses System for the Visually Impaired
Wang, E., Cai, X., & Chen, S. (2025) · Highlights in Science Engineering and Technology · doi:10.54097/zm9d0r75 · Cited by 1
“In contrast, single-stage algorithms (e.g., YOLO [10], SSD (Single Shot MultiBox Detector) [11]) streamline the detection process, improving speed while still meeting real-time detection requirements, albeit with slightly reduced accuracy in more complex scenarios.”
Al‐Hmouz, R., Alawasa, K., Maashri, A. A., & Abdulhussain, M. A. (2025) · International Conference for Artificial Intelligence, Applications, Innovation and Ethics (AI2E) · doi:10.1109/ai2e64943.2025.10983068 · Cited by 1
Anomaly Detection in Logistics Warehouses Based on YOLOv8
Shi, T. (2024) · Smart City Challenges & Outcomes for Urban Transformation (SCOUT) · doi:10.1109/scout64349.2024.00016 · Cited by 1
Malik, D., Xuan, X., & Ma, K. (2025) · IEEE International Symposium on Biomedical Imaging (ISBI) · doi:10.1109/isbi60581.2025.10980975 · Cited by 1
“The dataset underwent pre-processing, starting with training the YOLOv8 model [11] for instance segmentation on a dataset labeled with AnyLabeling [12] for real-time binary mask extraction.”
Jeon, H.-G., & Lee, K.-H. (2025) · Applied Sciences · doi:10.3390/app15105328 · Cited by 1
Sweet spots discrimination in carbonate reservoirs based on weakly supervised learning
Wang, H., Xue, Z., Cai, S., Kang, Z., Wang, H., & Xiao, Y. (2025) · Geoenergy Science and Engineering · doi:10.1016/j.geoen.2025.213965 · Cited by 1
Han, F., Notani, M. A., Cho, S., et al. (2025) · Transportation Research Record Journal of the Transportation Research Board · doi:10.1177/03611981251328987 · Cited by 1
“…based image-processing techniques, a different approach for GPR analysis has been emerged that utilizes a deep convolutional neural network (DCNN)–based object-detection framework, such as You Only Look Once (YOLO) ( 34 – 37 ) and region-based convoluntional neural networks (R-CNN) ( 38 – 40 ).”
The Use of Machine Learning in the Automotive Industry
Shrivastava, Y., Sethi, A. K., & Vikash, O. (2024) · International Conference on Communication, Computing and Energy Efficient Technologies (I3CEET) · doi:10.1109/i3ceet61722.2024.10994036 · Cited by 1
Qiu, X., Shi, C., Li, X., Wu, M., Abdullahi, S. M., & Liu, Y. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3569678 · Cited by 2
“Therefore, One-Stage’s object detection algorithm (e.g., YOLO [49]) will cause our designed module to not work as well as it should.”
Multi-Vehicle Object Recognition Method Based on YOLOv7-W
Liu, X., Zhao, J., Zhang, Z., Wu, R., & Li, X. (2025) · IEEE Access · doi:10.1109/access.2025.3569849 · Cited by 1
Zhou, Q., Liu, Y., Wu, L., et al. (2025) · IEEE Transactions on AgriFood Electronics · doi:10.1109/tafe.2025.3566254 · Cited by 1
“Traditional frameworks, including region-based convolutional neural network (R-CNN) [10], single shot multibox detector (SSD) [11], and you only look once (YOLO) [12],havefoundapplicationinagriculturaldomains,suchaspest control[13],detectionofcropmaturity[14],andagricultural statistics[15].”
Liang, H., Wang, Y., Liu, K., et al. (2024) · IEEE Conference on Energy Internet and Energy System Integration (EI2) · doi:10.1109/ei264398.2024.10990857 · Cited by 1
Improved Pedestrian Detection Algorithm for Traffic Vehicles Based on YOLOv8
Lei, J., Song, G., Xia, M., et al. (2025) · International Conference on Consumer Electronics and Computer Engineering (ICCECE) · doi:10.1109/iccece65250.2025.10984528 · Cited by 1
Research on Vehicle Target Detection Method Based on Improved YOLOv8
Zhang, M., & Zhang, Z. (2025) · Applied Sciences · doi:10.3390/app15105546 · Cited by 6
Swim VQA: A Multimodal Approach to Drowning Detection by Fusing VQA and LiDAR
Khan, M. Z., Gaddam, A., Thiruvady, D., & Story, A. (2024) · International Conference on Sensing Technology · doi:10.1109/icst62759.2024.10992006 · Cited by 1
An Efficient Attention Mechanism Model
Messaoud, W., Trabelsi, R., Cabani, A., & Abdelkefi, F. (2023) · doi:10.1109/i2cit57984.2023.11004318 · Cited by 1
A Call to Arms: Automated Methods for Identifying Weapons in Social Media Analysis of Conflict Zones
Abedin, A. F., Bais, A., Buntain, C., Courchesne, L., McQuinn, B., Taylor, M. E., & Ullah, M. (2025) · ACM Web Science Conference (WebSci) · doi:10.1145/3717867.3717886 · Cited by 2
Deep Learning for Weak Feature Defect Detection in MLCC Inspection System
Wang, J., Cao, X., Wang, Q., Zhang, D., & Chen, M. (2025) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2025.3571167 · Cited by 3
Fire Detection System Based On YOLOv5
Huang, Z., Wu, F., Jin, W., et al. (2025) · IEEE Conference on Big Data Security on Cloud (BigDataSecurity) · doi:10.1109/bigdatasecurity66063.2025.00009 · Cited by 1
Foreground-Aware Knowledge Distillation for Enhanced Damage Detection
Menteidis, P., Papaioannidis, C., & Pitas, I. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-92805-5_7 · Cited by 1
DFE-YOLO: A Multi-Scale-Enhanced Detection Network for Dense Object Detection in Traffic Monitoring
Li, Q., Li, Y., & Lu, Y. (2025) · Electronics · doi:10.3390/electronics14112108 · Cited by 1
Chen, Z., Pan, S., Guo, P., & Gao, W. (2025) · Pattern Analysis and Applications · doi:10.1007/s10044-025-01467-0 · Cited by 1
“…pipeline of point cloud object detection, semantics and regression are typically directly divided into two independent branches in the detection head [19–21], while in the two-stage pipeline, the semantic branch is further extracted and determined from the features of the detected RoI [22, 23].”
Adaptive Modality Selection Drone-Based RGBT Detector for Tiny Targets
Tang, Y., Tong, X., He, Z., Yang, J., & Cao, Y. (2025) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2025.3569003 · Cited by 6
A Comprehensive Evaluation of YOLO Networks for Extracting Words from Persian Handwritten Text
Paz, M., & Okhovat, R. S. (2025) · International Conference on Web Research (ICWR) · doi:10.1109/icwr65219.2025.11006209 · Cited by 1
User-Centered Design of Internet of Robotic Things (IoRT) for People Living with Dementia
Akinrintoyo, E., Garate, V. R., & Bremner, P. (2025) · International Journal of Social Robotics · doi:10.1007/s12369-025-01261-2 · Cited by 4
Synthetic training data for crack propagation measurement by neural networks
Hartmann, C., & Klauck, S. (2025) · Neural Computing and Applications · doi:10.1007/s00521-025-11292-5 · Cited by 2
“Region-based CNNs (R-CNN, Fast R-CNN, Faster R-CNN) [61–63] and single-shot methods like YOLO [64] and SSD [65] offer real-time detection.”
HFMIDet: Hierarchical Feature Fusion-Guided Multidimensional Infrared Pedestrian Detection Network
Liu, Y., Zhang, M., Fan, F., Yu, D., & Li, J. (2025) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2025.3573003 · Cited by 6
To the Point: From Dynamic Heatmap Video to Gaze Points
Gnanaraj, B., Manivasagam, S., & Sreevalsan‐Nair, J. (2025) · ACM Symposium on Eye Tracking Research and Applications (ETRA) · doi:10.1145/3715669.3725873 · Cited by 3
“YOLO [Redmon et al. 2016] performs faster than selective search-based algorithms.”
GazeLog: Optimizing Eye-Tracking with Fixation Keyframes & LLM Insights
Mardanbegi, D., Hylands, N., Sarkar, N., et al. (2025) · ACM Symposium on Eye Tracking Research and Applications (ETRA) · doi:10.1145/3715669.3726786 · Cited by 1
“Others have looked at enhancing the object detection process using YOLO (You Only Look Once)[Kumari et al. 2021; Redmon 2016; Zhu et al. 2021] for object detection by defining regions of interest in the image around the gaze point.”
Foundation Model or Finetune? Evaluation of Few-Shot Semantic Segmentation for River Pollution
Don, M., Pinson, S., Cebrian, B. G., & Asano, Y. M. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-92089-9_21 · Cited by 2
Hamid, M. Z. A., Daud, K., Soh, Z. H. C., et al. (2025) · Journal of Electrical & Electronic Systems Research · doi:10.24191/jeesr.v26i1.004 · Cited by 1
“In contrast to previous research that employed separate deep learning models such as You Only Look Once (YOLO) [20], Single Shot MultiBox Detector (SSD) [21] or others for object detection and segmentation tasks separately, this study improves segmentation accuracy by performing thermal hotspot…”
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.