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 29,401–29,500 of 51,399
Han, J., Chen, H. Y., Ding, Y., Zhuang, S., Zhou, C., & Chen, H. (2025) · Symmetry · doi:10.3390/sym17050724 · Cited by 6
SFEF-Net: Scattering Feature Extraction and Fusion Network for Aircraft Detection in SAR Images
Zhou, Q., Pan, Z., & Niu, B. (2025) · Sensors · doi:10.3390/s25102988 · Cited by 2
“Representative single-stage detectors comprise the YOLO series [24–31], SSD [32], and RetinaNet [33].”
A Large-Scale Dataset for Small and Tiny Object Detection from Aerial Imagery
Verma, S., Gupta, H., & Verma, O. P. (2025) · Procedia Computer Science · doi:10.1016/j.procs.2025.04.672 · Cited by 3
Al-Kailani, O. Z., Ahmed, M. A., Abdalla, T. A., et al. (2025) · doi:10.1109/ai2e64943.2025.10983519 · Cited by 2
Digitization of Medical Device Displays Using Deep Learning Models: A Comparative Study
Ferreira, P., Lobo, P. L. S., Reis, F., Vilaça, J. L., & Morais, P. (2025) · Applied Sciences · doi:10.3390/app15105436 · Cited by 3
Enhanced wildfire detection and semantic segmentation via fine-tuned deep learning models
Quang, N. H., Lee, H., Ahn, S., & Kim, G. (2025) · Earth Science Informatics · doi:10.1007/s12145-025-01863-4 · Cited by 4
“To segment images, the YOLO network architecture was inspired by GoogleNet and consists of 24 convolution layers (Redmon et al. 2016).”
Innovative fast and low-cost method for the detection of living bacteria based on trajectory
Perronno, P., Claudinon, J., Senin, C., Elçin-Guinot, S., Wolter, L., Makshakova, O., Dumas, N., Klockenbring, D., Lam-Weil, J., Noblet, V., et al. (2025) · Scientific Reports · doi:10.1038/s41598-025-95069-9 · Cited by 3
“Similarly, U-NET detection models and YOLO 34 often used in real-time applications, are transposable to our context.”
An efficient network for object detection in scale-imbalanced remote sensing images
Li, Z., Jing, X., Sun, R., Yang, Y., Wang, W., & Zhu, H. (2025) · Open Geosciences · doi:10.1515/geo-2025-0805 · Cited by 2
Traffic Sign Localization and Orientation Classification for Automated Map Updating
Han, X., Hu, W., Song, X., Kruppa, H., Ng, S.-K., & Zimmermann, R. (2025) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2025.3570488 · Cited by 2
“With the success of deep learning in computer vision, several deep learning-based tra ffi c sign detection and recognition methods have been developed based on mainstream object detection models (e.g., Faster R-CNN [19], YOLO [20], and SSD [21]).”
LAM-YOLOv10: lightweight and multiscale feature enhancement for paint surface defect detection model
Zhao, D., Sun, R. F., Li, W., Ma, Y., Tong, T., Yuan, X., Wang, D., Liu, P., Li, B., Kong, D., et al. (2025) · Journal of Electronic Imaging · doi:10.1117/1.jei.34.3.033022 · Cited by 2
Duan, Y., Zhang, S., Zhao, S., Gu, X., Meng, Y., Li, D., & Zhao, R. (2025) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2025.110438 · Cited by 4
EN-YOLO: A Ship Enhanced Detection Network Based on YOLOv8
Yuan, Y., Yu, X., & Rong, X. (2024) · doi:10.1109/aisomt64170.2024.10992221 · Cited by 2
System for Analyzing User Interest Based on Eye Gaze Responses to Enhance Empathy with Users
Woo, J., & Hu, J. (2025) · Journal of Advanced Computational Intelligence and Intelligent Informatics · doi:10.20965/jaciii.2025.p0641 · Cited by 2
Balakrishna, S., Yadao, S., & Solanki, V. K. (2025) · Annals of Computer Science and Information Systems · doi:10.15439/2024r115 · Cited by 4
Niu, Y., & Zhang, J. (2025) · IEEE Access · doi:10.1109/access.2025.3572331 · Cited by 3
Alferidah, D. K., Algosaibi, A. A., Sagheer, A., Afifi, A., & Algosaibi, A. (2025) · International Conference on IT Innovation and Knowledge Discovery (ITIKD) · doi:10.1109/itikd63574.2025.11004796 · Cited by 2
“The second method used is Faster R-CNN [12] that is known to be good for real time objects detection and the third one is the famous method You Only Look Once (YOLO) [13].”
Wenxing, 刘. L., Huilin, 单. S., Xingtao, 王. W., et al. (2025) · Acta Optica Sinica · doi:10.3788/aos241731 · Cited by 2
Yang, W., Li, Z., & He, Q. (2025) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2025.104479 · Cited by 2
Xu, S., Zhang, W., Tao, S., Chai, Y., Bahri, P. A., & Wang, H. (2025) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2025.3573344 · Cited by 4
DETR for traffic sign detection
Cui, S., & Deng, H. (2025) · Physica Scripta · doi:10.1088/1402-4896/addd70 · Cited by 4
Ichi, A. E., Kaddah, W., Elbouz, M., & Badoc, I. (2025) · Signal Image and Video Processing · doi:10.1007/s11760-025-04283-5 · Cited by 2
“The most well-known One Stage methods are You Only Look Once (YOLO) in different versions [26, 27, 37].”
Zhong, H., Hu, Z., Liu, J., Wang, H., Hu, Y., & Shi, T. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.130601 · Cited by 3
Vision-Based Collision Avoidance and Path Planning for UAVs Using Bearing and Pixel Area
Liu, J.-J., Evans, C. P., & Beard, R. W. (2025) · International Conference on Unmanned Aircraft Systems (ICUAS) · doi:10.1109/icuas65942.2025.11007929 · Cited by 2
“Recentadvancements in object detection, such as recursive RANSAC for multiple target tracking [10], the You Only Look Once (YOLO) family of algorithms [11], [12], and computer vision techniques like optical flow [13], have significantly improved the ability to detect and track moving objects.”
Putra, M. A., Harjoko, A., & Wahyono, W. (2025) · IET Intelligent Transport Systems · doi:10.1049/itr2.70038 · Cited by 4
Improved YOLOv8n Models for Object Detection in Remote Sensing Images
Chen, Y.-L., Hung, K.-C., Zhang, J., & Lin, L.-W. (2025) · IEEE Access · doi:10.1109/access.2025.3574856 · Cited by 4
Sun, Q., Li, Z., Ma, R., Wang, Y., Zhao, Z., & Lv, X. (2024) · International Conference on Communication and Information Processing (ICCIP) · doi:10.1145/3708657.3708752 · Cited by 2
A Hyperspectral Imaging Guided Robotic Grasping System
Sun, Z., Dong, Z., Wang, S., Chu, Z., & Chen, F. (2025) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2025.3575654 · Cited by 4
“Early research primarily relied on RGB vision systems to capture an object’s external shape and basic visual features such as color and texture [11], [12], [13].”
Pseudo-Label Guided Object Detection in Sparsely Annotated Underwater Optical Images
Chen, G., Mao, Z., Shen, J., & Cheng, Z. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2025.3575841 · Cited by 4
Fourier-modulated CLIP for zero-shot vehicle counting
Luo, Y., Zhang, Q., Luo, J., Huang, S., Wan, X., & Nie, X. (2025) · Scientific Reports · doi:10.1038/s41598-025-04876-7 · Cited by 2
FD-YOLOv8:An Improved Fire Detection Model Base on YOLOv8n
Li, L., Liu, Z., Ruan, Y., & Chen, B. (2025) · International Conference on Advanced Algorithms and Control Engineering (ICAACE) · doi:10.1109/icaace65325.2025.11019411 · Cited by 2
Real-Time Road Object Detection and Traffic Sign Recognition on a Standard GPU Platform
Bouazizi, O., Oussouaddi, M., & Mourabit, A. E. (2025) · Lecture notes in networks and systems · doi:10.1007/978-3-031-91337-2_37 · Cited by 2
Yang, S., & Kim, H. (2025) · Applied Sciences · doi:10.3390/app15126499 · Cited by 2
Applying machine learning to safe vascular anastomosis
Umezawa, H., Kondo, A., Taga, M., et al. (2025) · JPRAS Open · doi:10.1016/j.jpra.2025.06.008 · Cited by 2
“6 , 8 The recent emergence of publically accessible tools such as Python, Google Colaboratory TM , Google Gemini TM , and ChatGPT TM has also greatly simplified and democratized the development of machine-learning algorithms, thus allowing people without extensive programming backgrounds to develop…”
Machine learning assisted analysis of rice flower opening times using a low-cost time-lapse camera
Muranaka, T., Matsuura, M., Yokoyama, K., et al. (2025) · Journal of Plant Research · doi:10.1007/s10265-025-01650-8 · Cited by 2
“Due to its high performance and ease of installation, YOLO (You Only Look Once) has become a popular tool for object detection (Redmon et al. 2016).”
Yogamani, S. K., Sistu, G., Denny, P., & Courtney, J. (2025) · Sensors · doi:10.3390/s25123735 · Cited by 2
“YOLO [20] divides the input image into grids and predicts bounding boxes directly by regression and classification at each grid.”
Real-time process monitoring in additive manufacturing using machine learning
Ghansiyal, S., Schmitz, M., Kirsch, T., et al. (2025) · Procedia CIRP · doi:10.1016/j.procir.2025.03.046 · Cited by 2
Improved Face Mask Wearing Detection Based on YOLOv5
Gao, Z., & Wang, J. (2025) · International Journal of Advanced Network Monitoring and Controls · doi:10.2478/ijanmc-2025-0008 · Cited by 3
Rsw-YOLOv8: an improved model for in-vehicle vision multi-object detection in complex traffic scenes
Lin, P., Li, Q., & Mao, J. (2025) · The Journal of Supercomputing · doi:10.1007/s11227-025-07540-z · Cited by 3
“In contrast, single-stage detectors—especially the YOLO series [9–20]—offer low-latency inference and are well-suited for embedded and in-vehicle deployments.”
STF-Net: a model for detecting transmission line fittings in UAV images
Lv, W., Nie, M., Yue, Y., et al. (2025) · Electrical Engineering · doi:10.1007/s00202-025-03198-1 · Cited by 2
“Single-stage networks such as YOLO [23] and RetinaNet [24] provide faster processing speeds while maintaining reasonable accuracy.”
Chrintz-Gath, G., Daivadanam, M., Matta, L., & McKeever, S. (2025) · JMIR Formative Research · doi:10.2196/70124 · Cited by 9
Eddahmani, I., Napoléon, T., Pham, C.-H., et al. (2025) · Applied Intelligence · doi:10.1007/s10489-025-06621-z · Cited by 2
Wang, C., & Liu, F. (2025) · IEEE Access · doi:10.1109/access.2025.3581428 · Cited by 4
Evaluation of YOLO for Automatic Radar Waveform Detection and Classification in Congested EME
White, R., Winter, R. S. C., Horne, C. P., et al. (2025) · IEEE International Radar Conference · doi:10.1109/radar52380.2025.11031686 · Cited by 2
“Real-time image object detection using YOLO was first proposed by Redmon et al. [10] of Facebook AI Research.”
InfluentialHarmful Animal Detection Using Visual Information for Wire-Type Mobile Robots
Doi, T., Mizuta, A., & Nagumo, K. (2025) · Journal of Robotics and Mechatronics · doi:10.20965/jrm.2025.p0742 · Cited by 2
GSTD-DETR: A Detection Algorithm for Small Space Targets Based on RT-DETR
Zhang, Y., Guo, H., Zhao, Y., Zhang, L., Luan, C., Li, Y., & Zhang, X. (2025) · Electronics · doi:10.3390/electronics14122488 · Cited by 2
Physical Adversarial Camouflage Generation in Optical Remote Sensing Images
Peng, Z., Chen, J., Shi, Z., & Zou, Z. (2025) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2025.3581771 · Cited by 11
Fu, H., & Hsiang, H.-C. (2025) · International Conference on Cloud Computing and Big Data Analytics (ICCCBDA) · doi:10.1109/icccbda64898.2025.11030463 · Cited by 2
A lightweight small object detection network inspired by the visual area V2
Zhang, D., Lin, C., & Pan, Y. (2025) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2025.110471 · Cited by 4
Yang, X., Huang, L., Ke, F., Liu, C., Yang, R., & Xie, S. (2025) · ISPRS International Journal of Geo-Information · doi:10.3390/ijgi14070238 · Cited by 2
Fabric defect detection based on improved YOLOv8s and machine vision
Hao, C., Wang, Y., Cui, C., Dengfeng, D., & Mei, D. (2025) · Textile Research Journal · doi:10.1177/00405175251348141 · Cited by 3
Cheng, H. D., Zhang, J., Yan, H., Wang, Y., & Dong, L. (2025) · Multiscale and Multidisciplinary Modeling Experiments and Design · doi:10.1007/s41939-025-00950-9 · Cited by 4
Real-Time Green View Index Assessment: AI-Driven Analysis of Urban Vegetation Using Dashcam Videos
Masad, K., & Filali, F. (2025) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2025.3582867 · Cited by 2
Liao, T., Chen, Y., Tang, W., Chen, Z., Wang, Y., Yang, H., & Li, X. (2025) · IEEE International Symposium on Circuits and Systems proceedings · doi:10.1109/iscas56072.2025.11043740 · Cited by 2
“DNN models, exemplified by YOLO [1] and Llama [2], have achieved remarkable success in computer vision (CV), natural language processing (NLP), and multi-modal tasks.”
Advances in Neural Network-Based Image, Thermal, Infrared, and X-Ray Technologies
Wilk-Jakubowski, J. Ł., Pawlik, Ł., Ciopiński, L., & Wilk-Jakubowski, G. (2025) · Applied Sciences · doi:10.3390/app15137198 · Cited by 4
Enhanced child face anonymization using YOLO framework for real-time privacy protection in videos
Ahmed, H. A., Ahmed, M. H., Majidpour, J., & Omer, S. M. (2025) · Neural Computing and Applications · doi:10.1007/s00521-025-11424-x · Cited by 2
Zang, P., He, J., Yang, Y., Li, Y., & Zhang, H. (2025) · Remote Sensing · doi:10.3390/rs17132252 · Cited by 2
Huang, J., Ariffin, S. A., Zhu, Q., et al. (2025) · PLoS ONE · doi:10.1371/journal.pone.0327001 · Cited by 2
“In this study, we conducted a comprehensive evaluation of the proposed SAMF-YOLO algo-rithm against mainstream object detection models—including YOLOv5s [35], YOLOv6n [36], YOLOv7-tiny [37], YOLOv8n, RT-DETR-R18 [38], YOLOv9s [39], YOLOv10s [40], and YOLOv11s.”
Bai, Y., Yang, C., Li, G., He, X. Y., Xiao, Q., & Li, Z. (2025) · Information Sciences · doi:10.1016/j.ins.2025.122474 · Cited by 3
SD-YOLOv8: Automated Motion Detection System for Aerobics Students
Tang, L.-A., Li, Y., Du, Q., et al. (2025) · IEEE Access · doi:10.1109/access.2025.3585561 · Cited by 2
Dense point-wise line voting for robust 6D Pose estimation in industrial bin-picking
Wang, J., Yi, G., Zhang, S., Wang, Y., Wang, Z., Zhang, X., Zhou, Z., & Xu, J. (2025) · The Visual Computer · doi:10.1007/s00371-025-04052-y · Cited by 3
“OP-Net OP-Net [13] takes a depth map as input and employs a fully convolutional network to conduct pose estimation in the pre-defined spatially discretized 3D volumes in the YOLO-style fashion [26–28].”
Identification of leaves of wild Ussurian Pear (Pyrus ussuriensis) based on YOLOv10n-MCS
Li, N., Dong, X., Wu, Y., et al. (2025) · Frontiers in Plant Science · doi:10.3389/fpls.2025.1588626 · Cited by 2
“In recent years, with the continuous innovation of the YOLO series (Redmon, 2016; Redmon and Farhadi, 2017; Farhadi and Redmon, 2018; Bochkovskiy et al., 2020; Jocher, 2020; Li et al., 2022; Wang et al., 2023a; Jocher et al., 2023; Wang et al., 2025a, 2024), its performance has gradually improved,…”
Zhang, X., Dong, H., Yang, J., Lu, Z., Gong, L., & Zhang, L. (2025) · Journal of Phytopathology · doi:10.1111/jph.70106 · Cited by 4
Wu, Y. H., Zheng, Y., Zhu, J., Chen, X., Dong, F., He, L., Zhu, J., Cheng, G., Wang, P., & Zhou, S. (2025) · European Spine Journal · doi:10.1007/s00586-025-09075-6 · Cited by 2
CFI-YOLO: A Lightweight Algorithm for Fire Detection
Zheng, Y., Lu, J., Shi, W., Chen, Q., Lin, Z., & Wu, J. (2025) · International Conference on Communications, Information System and Computer Engineering (CISCE) · doi:10.1109/cisce65916.2025.11065790 · Cited by 2
“Deep learning-based object detection algorithms are generally categorized into two types: two-stage methods, represented by Fast R-CNN[4], and one-stage methods, exemplified by the YOLO[5].”
Li, Q., Li, H., Huang, Y., & Ji, H. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2025.3587755 · Cited by 6
Zhao, N., & Tong, J. (2025) · Measurement Science and Technology · doi:10.1088/1361-6501/adee37 · Cited by 3
“Although publicly available datasets have enabled these models to perform well under controlled conditions, performance often deteriorates in actual field environments characterized by complex backgrounds, symptom overlaps, and dense target distribution [5].”
Improving Moving Insect Detection with Difference of Features Maps in YOLO Architecture
Gomez-Canales, A., Avila, J. E. G., Hernández-Barragán, J., López-Franco, C., Villaseñor, C., & Arana‐Daniel, N. (2025) · Applied Sciences · doi:10.3390/app15147697 · Cited by 2
A False-Positive-Centric Framework for Object Detection Disambiguation
Baur, J., & Nitsche, F. O. (2025) · Remote Sensing · doi:10.3390/rs17142429 · Cited by 3
Adversarial Patches for Fooling Positive–Negative Obstacle Detectors on Unstructured Roads
Duan, Y., Meng, L., Zhu, J., Meng, Y., Liang, Y., Zhang, J., & Wu, J. (2025) · IEEE Sensors Journal · doi:10.1109/jsen.2025.3586858 · Cited by 3
“We evaluated the transferability of our method in a black-box setting across various detectors, including YOLOv5 [44], YOLOv7 [45], SSD [46], Faster RCNN [47], and DETR [48].”
Kanadath, A., Jothi, J. A. A., & Urolagin, S. (2025) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2025.110680 · Cited by 5
Detection and segmentation of brain metastases on MRI using 3D‐MedDCNet
Wu, Y., Li, Y., Hu, M., Chang, C., Qiu, R. L. J., Wang, T., Shu, H. G., Mao, H. Z., Tian, Z., & Yang, X. (2025) · Medical Physics · doi:10.1002/mp.18001 · Cited by 3
PCENet: A Method for SAR Ship Detection Based on Pixel Confidence Estimation
Hu, J., Liu, Z., Ran, L., et al. (2025) · IEEE Transactions on Aerospace and Electronic Systems · doi:10.1109/taes.2025.3589544 · Cited by 2
“The you-only-look-once (YOLO) network [24], initially proposed, simplified the target detection task by directly regressing anchor box parameters, significantly improving detection speed over two-stage networks.”
Automated Child Rescue System from Borewells using Artificial Intelligence and Wireless Tech
Gopi, K., Anjum, P. A., Kalyan, C., & Nandivardhan, M. (2025) · International Conference on Self Sustainable Artificial Intelligence Systems (ICSSAS) · doi:10.1109/icssas66150.2025.11080731 · Cited by 2
YOLO-SSFA: A Lightweight Real-Time Infrared Detection Method for Small Targets
Wang, Y., Cao, M., Yang, Q., et al. (2025) · Information · doi:10.3390/info16070618 · Cited by 2
Sestito, C., Agwa, S. O., & Prodromakis, T. (2025) · IEEE transactions on circuits and systems for artificial intelligence. · doi:10.1109/tcasai.2025.3591073 · Cited by 4
Smart Parking Space Detection Using YoLo and Computer Vision for Open-Space University Parking
Gallego, L. O. G., Fuertes, C. A. C., Ta-aca, V. K. C., Cruzada, J. G., Jeco, B. M. F. Y., & Giner, M. G. (2025) · IEEE Symposium on Computer Applications & Industrial Electronics (ISCAIE) · doi:10.1109/iscaie64985.2025.11081004 · Cited by 4
“In predicting detections, a neural network on a new image is simply run during test time [22].”
Intelligent Battery-Designed System for Edge-Computing-Based Farmland Pest Monitoring System
Hung, C., Wang, C., Liao, Z.-J., et al. (2025) · Electronics · doi:10.3390/electronics14152927 · Cited by 2
Liu, B., Zhao, Q., Wang, C., Li, M., Xie, H., & Chen, L. (2025) · International Journal of Applied Earth Observation and Geoinformation · doi:10.1016/j.jag.2025.104741 · Cited by 5
A Study on Deep Learning-Based All-Day Port Ship Detection Algorithms
Qu, A., Yu, H., & Zhou, Z. (2025) · International Conference on Computer Vision, Image and Deep Learning (CVIDL) · doi:10.1109/cvidl65390.2025.11085604 · Cited by 3
“…detection accuracy but suffer from slow detection speed due to high computational complexity; and one-stage detectors, such as the YOLO series [3][4][5] and SSD [6] which adopt an end-to-end learning strategy, offering fast detection speed and suitability for deployment on devices with limited…”
Huang, X., Qin, G., Zhang, H., Min, F., Li, D., & Luo, G. (2025) · Applied Sciences · doi:10.3390/app15158377 · Cited by 2
Divide-and-conquer routing for learning heterogeneous individualized capsules
Yuan, H., & Ren, Q. (2025) · PLoS ONE · doi:10.1371/journal.pone.0329202 · Cited by 2
DSONet: A Lightweight Framework for the Detection of Multiscale Dense Ship Occlusion
Qu, C., Shi, Y., Chen, H., Ye, Q., Cai, Y., Chang, Y., Chen, C., Wang, F., & Zeng, W. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3593829 · Cited by 4
“Single-stage detectors like YOLO [9] and SSD [10] enable faster inference through end-to-end regression, but struggle with small object detection and densely crowded scenes.”
MMT-NET: a lightweight multi-modal fusion network for UAV target detection in adverse environments
Wang, C., Zhou, M., Sun, D., Gao, Q., Li, Z., & Wang, T. (2025) · Journal of Real-Time Image Processing · doi:10.1007/s11554-025-01741-8 · Cited by 3
“To address this, single-stage detectors such as YOLO [13–15] reformulated detection as a regression problem, achieving faster inference.”
A task offloading and batch scheduling framework for Edge-assisted inference
Spatharakis, D., Pelekis, C., Dechouniotis, D., & Papavasileiou, S. (2025) · Future Generation Computer Systems · doi:10.1016/j.future.2025.108030 · Cited by 3
Zhenghu, 朱. Z., Zhen, 苏. S., & Wei, 王. W. (2025) · Laser & Optoelectronics Progress · doi:10.3788/lop250721 · Cited by 3
MDRNet: Multiscale Dual Residual Network for Small Object Detection on UAV Aerial Images
Zong, H., Ni, T., Wang, H., & Zhu, Q. (2025) · Signal Image and Video Processing · doi:10.1007/s11760-025-04584-9 · Cited by 2
“Deep neural networks have led to significant advances in object detection, with models such as Faster R-CNN [1], YOLO [2], RetinaNet [3], and DETR [4] achieving state-of-the-art performance on widely-used benchmarks.”
Performance validation of deep-learning-based approach in stool examination
Corpuz, K. D. F., Kusolsuk, T., Wongphan, B., Chonsawat, P., Naing, K. M., Boonsang, S., Kittichai, V., Fan, C., Chuwongin, S., & Watthanakulpanich, D. (2025) · Parasites & Vectors · doi:10.1186/s13071-025-06878-w · Cited by 2
“Redmon et al. reframed object detection as a single regression problem directly from image pixels to bounding boxes and class probabilities, streamlining the process compared with previous systems that required multiple evaluations [16–18].”
Detection of Dens Invaginatus on Panoramic Radiographs Using Deep Learning Algorithms
Akgül, E. N., & Topal, B. G. (2025) · International Journal of Paediatric Dentistry · doi:10.1111/ipd.70027 · Cited by 2
Zhao, Y., Paul, R., Li, Q., Wu, Y., Qin, X., Zhou, Y., & Liu, Y. (2025) · Chemical Engineering Journal · doi:10.1016/j.cej.2025.166597 · Cited by 4
FFG-YOLO: Improved YOLOv8 for Target Detection of Lightweight Unmanned Aerial Vehicles
Wang, T., Yang, S., Wan, M., & Liu, Y. (2025) · Applied System Innovation · doi:10.3390/asi8040109 · Cited by 2
“Single-stage algorithms, such as the You Only Look Once (YOLO) series [1–8], single-shot multiBox detector (SSD) [9], and RetinaNet [10], rapidly output target locations and categories, making them well-suited for fast processing, such as unmanned aerial vehicles (UAVs) aerial photography.”
Mamapule, S., Esiefarienrhe, B. M., & Obagbuwa, I. C. (2025) · International Journal of Intelligent Systems · doi:10.1155/int/1561380 · Cited by 5
Zhao, Z., Lu, B., Zhang, S., Wang, D., Wan, J., Liu, R., Li, H., & Wang, Z. (2026) · Water Resources Management · doi:10.1007/s11269-026-04632-0 · Cited by 4
“Consequently, the limitations of traditional methods have motivated a shift toward artificial intelligence (AI) (Redmon et al. 2016).”
GEF-YOLO: an enhanced model for detecting drowning risks at sea
Yuan, J., Liu, F., Jiang, L., Jiang, S., Liu, S., & Cai, B. (2025) · Journal of Real-Time Image Processing · doi:10.1007/s11554-025-01736-5 · Cited by 5
“The other category consists of single-stage algorithms, such as YOLO [19] and SSD [25], which directly regress object classes and spatial locations, making them more suitable for real-time detection.”
Deep Equilibrium Object Detection and Segmentation
Wang, S., Teng, Y., & Wang, L. (2025) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2025.3595380 · Cited by 4
“P ,especiallyforhigh-level understandingtasks,suchasobjectdetection[7],[24],[26],[49], [50], [52] and instance segmentation [15], [18], [21], [29], [61], [62].”
Alarcon, J. L. A., Zhang, Y. R., Suarez, H., et al. (2025) · Aerospace · doi:10.3390/aerospace12080686 · Cited by 2
CEL-YOLO: An Improved Apple Leaf Disease Detection Model Based on YOLOv10
Wu, W., Tao, J., Wei, Y., Hou, S., Yuan, D., & Li, J. (2025) · Chinese Control and Decision Conference (CCDC) · doi:10.1109/ccdc65474.2025.11090389 · Cited by 2
LRHAR: A Lightweight Rule-based Framework for Human Activity Recognition at the Edge
Dhake, M., Tripathi, S., Pal, A., Banerjea, S., & Yamjala, R. (2025) · International Conference on Distributed Computing in Smart Systems and the Internet of Things (DCOSS-IoT) · doi:10.1109/dcoss-iot65416.2025.00016 · Cited by 2
“Various pose estimation models are studied in the literature, such as OpenPose [29], YOLO Pose Estimation [30], MediaPipe [31] etc.”
LiDAR-Guided Monocular 3D Object Detection for Long-Range Railway Monitoring
Sanchez, R. D. D., Ortiz, X. D., Zhou, X., et al. (2025) · IEEE Intelligent Vehicles Symposium · doi:10.1109/iv64158.2025.11097785 · Cited by 2
“Classical methods relied on geometric cues such as structure-from-motion and multi-view stereo, but deep learning now dominates due to its ability to infer depth from single images.”
Cuixia, 郭. G., Yongtao, 徐. X., Zhanghuang, 邹. Z., Zhijie, 潘. P., & Feng, 黄. H. (2025) · ACTA PHOTONICA SINICA · doi:10.3788/gzxb20255406.0610001 · Cited by 2
Hu, Y., Zhao, X., Wu, Z., Yang, X., Xie, L., Liu, Y., Yu, Z., Zheng, L., Ma, D., Zhang, R., et al. (2025) · Translational Vision Science & Technology · doi:10.1167/tvst.14.8.15 · Cited by 4
“To address the aforementioned deficiencies of the existing AI models, we rigorously screened and processed the images of patients with RB and chose a mature and stable algorithm, the latest version of YOLO, as a basis, and performed many times of algorithm training and parameter adjustments, as well as integrated self…”
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.