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 27,301–27,400 of 51,400
SR-NET: a lightweight enhanced feature extraction network for fabric defect detection
Li, W., Chen, M., Zhang, L., & Tian, J. (2025) · Textile Research Journal · doi:10.1177/00405175241293349 · Cited by 3
“9 The YOLO (You Only Look Once) 10–20 family of algorithms stands out as one of the most popular detection algorithms because of its ability to predict every object present in an image with one forward pass.”
Transformer-based prototype network for Chinese nested named entity recognition
Zhang, K., Lu, J., Ai, Z., et al. (2025) · Scientific Reports · doi:10.1038/s41598-025-04946-w · Cited by 3
Lightweight Domestic Pig Behavior Detection Based on YOLOv8
Zhang, K., Zhang, Y., & Xu, H. (2025) · Applied Sciences · doi:10.3390/app15116340 · Cited by 3
Mohammadzadeh, M., Günay, E. E., Jackman, J. K., et al. (2025) · Journal of Advanced Manufacturing and Processing · doi:10.1002/amp2.70011 · Cited by 3
He, Q., Zhao, L., Luo, R., Zhang, S., Lei, L., Ji, K., & Kuang, G. (2025) · IEEE Transactions on Aerospace and Electronic Systems · doi:10.1109/taes.2025.3574673 · Cited by 4
“In recent years, deep learning (DL) has witnessed an explosive performance in a variety of vision work [9], [10], [11], [12], [13].”
Nilchuen, P., Suwanasopee, T., & Koonawootrittriron, S. (2025) · Smart Agricultural Technology · doi:10.1016/j.atech.2025.101079 · Cited by 6
Improvement of Dam Crack Detection Algorithm for YOLOv9
Zhang, H., Jiang, X., Liu, Y., Qian, J., & Ni, L. (2025) · IET Image Processing · doi:10.1049/ipr2.70124 · Cited by 4
Self-Supervised Monocular Depth Estimation With Depth–Motion Prior for Pseudo-LiDAR
Yuan, S., Liu, H., Liu, Y., & Yang, L. (2025) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2025.3577819 · Cited by 5
Real-time Gun Detection using YOLO: A Deep Learning Approach for Public Safety
Magar, R. T., & Shahadat, N. (2024) · International Conference on Computer and Information Technology (ICCIT) · doi:10.1109/iccit64611.2024.11021758 · Cited by 3
Subbiah, S., Rampavithran, R. P., & Hariraj, P. (2025) · doi:10.1109/iccct63501.2025.11020567 · Cited by 3
Wang, J., Li, J., & Meng, F. (2025) · AgriEngineering · doi:10.3390/agriengineering7060182 · Cited by 4
FLARE: Fine-tuned large LAnguage models for Resource-Efficient action generation in robotics
Maccarini, M., Moroncelli, A., Carpanzano, E., & Roveda, L. (2025) · Procedia CIRP · doi:10.1016/j.procir.2025.02.190 · Cited by 3
MDCFVit-YOLO: A model for nighttime infrared small target vehicle and pedestrian detection
Zhang, H., Zhang, Q., Gong, Y., Yao, F., & Pan, X. (2025) · PLoS ONE · doi:10.1371/journal.pone.0324700 · Cited by 4
“To address the speed deficiencies of two-stage detection algorithms, researchers have proposed single-stage detection algorithms, such as the YOLO series (including YOLOv1 [4], YOLOv2 [5], etc.) and the SSD series [6].”
SEM‐YOLO: A Small Target Defect Detection Model for Photovoltaic Modules
Yun, W., Yin, W., Xie, G., & Zhao, Z. (2025) · IET Image Processing · doi:10.1049/ipr2.70134 · Cited by 3
Peng, C., Li, B., Zou, K., Zhang, B., Dai, G., & Tsoi, A. C. (2025) · Sensors · doi:10.3390/s25123815 · Cited by 4
Kamaras, G., & Ramamoorthy, S. (2025) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2025.3581744 · Cited by 4
RGB-FIR Multimodal Pedestrian Detection with Cross-Modality Context Attentional Model
Wang, H., Jin, L., Wang, G., Liu, W., Shi, Q., Hou, Y., & Liu, J. (2025) · Sensors · doi:10.3390/s25133854 · Cited by 7
“Joseph et al. [37] proposed a YOLO pedestrian detection model achieving higher accuracy by dividing the image into grids and predicting whether each grid contains targets, along with their positions.”
PAF-DETR: enhancing UAV image detection with partial attention and dynamic feature integration
Lei, H., Ren, L., Wu, Z., & Yang, W. (2025) · The Journal of Supercomputing · doi:10.1007/s11227-025-07561-8 · Cited by 3
“The YOLO algorithms [25–27] become a landmark due to outstanding performance and innovation.”
Artificial Intelligence Image-Diagnosis for Female Genital Schistosomiasis
Zhu, J., Noble, J. A., & Gomes, M. (2025) · Mayo Clinic Proceedings Digital Health · doi:10.1016/j.mcpdig.2025.100245 · Cited by 3
Detection of moving small targets in infrared images for urban traffic monitoring
Wang, J., Yang, H., Zhang, Z., Shao, J., Shao, J., Wu, M., Ma, Z., Zhu, J., Wang, X. A., & Song, H. (2025) · Internet of Things · doi:10.1016/j.iot.2025.101673 · Cited by 5
A novel image dataset for detecting and classifying mobility aid users
Dávila-Soberón, S., Morales-Díaz, A. B., & Castelán, M. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.128697 · Cited by 3
YOLO-PWSL-Enhanced Robotic Fish: An Integrated Object Detection System for Underwater Monitoring
Lei, L., Tang, Y., Zhang, W., et al. (2025) · Applied Sciences · doi:10.3390/app15137052 · Cited by 3
EN-YOLO: a featured-enhanced model for precise hot rolled steel surface defect detection
Hao, Z., Liu, B., & Xu, B. (2025) · Nondestructive Testing And Evaluation · doi:10.1080/10589759.2025.2524604 · Cited by 4
Galvez-Aranda, D. E., Saravanan, S., & Franco, A. A. (2025) · Batteries & Supercaps · doi:10.1002/batt.202500292 · Cited by 3
10 Years of Deep Learning for Vehicle Detection at a Smart Parking : What has Changed?
da Luz, G. P. C. P., Sato, G. M., Bannwart, T. G., Gonzalez, L. F. G., & Borin, J. F. (2025) · Anais do Workshop de Computação Urbana (CoUrb) · doi:10.5753/courb.2025.8869 · Cited by 5
UK‐YOLOv10: Deep Learning‐Based Detection of Surgical Instruments
Zhang, L., Guo, G., & Wang, W. (2025) · International Journal of Medical Robotics and Computer Assisted Surgery · doi:10.1002/rcs.70083 · Cited by 5
“In 2016, Joseph Redmon et al. presented YOLOv1, the inaugural version of the YOLO series, marking a pivotal breakthrough in object detection methods [15].”
Evaluating Energy Efficiency of Ai Accelerators Using Two Mlperf Benchmarks
Ferdaus, F., Wu, X., Taylor, V., Lan, Z., Shanmugavelu, S., Vishwanath, V., & Papka, M. E. (2025) · IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGrid) · doi:10.1109/ccgrid64434.2025.00035 · Cited by 5
CREAM: Few-shot Object Counting with Cross REfinement and Adaptive density Map
Xu, Y., Li, M., Ye, Q., Wang, S., Li, L., & Zhang, H. (2025) · Image and Vision Computing · doi:10.1016/j.imavis.2025.105632 · Cited by 5
A Lightweight Deep Learning and Sorting-Based Smart Parking System for Real-Time Edge Deployment
Khan, M. K. U., Raza, M. A., Mozumder, M. A. I., Azam, I. U., Sumon, R. I., & Kim, H. (2025) · AppliedMath · doi:10.3390/appliedmath5030079 · Cited by 5
Wang, G., Han, Y., Xu, F., Gao, Y., & Sang, W. (2025) · Applied Sciences · doi:10.3390/app15137325 · Cited by 3
Li, L., Zuo, Z.-K., Bu, R.-F., Zhang, Y.-J., Wang, R.-M., & Tan, E. (2025) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2025.3586340 · Cited by 11
Potential Time and Recall Benefits for Adaptive AI ‐Based Breast Cancer MRI Screening
Balkenende, L., Ferm, J., van Veldhuizen, V., Brunekreef, J., Teuwen, J., & Mann, R. M. (2025) · Journal of Magnetic Resonance Imaging · doi:10.1002/jmri.70034 · Cited by 3
Complex Patterned Fabric Defects Detector Based on Improved RT-DETR
Jin, Z., & Fang, M. (2025) · Fibers and Polymers · doi:10.1007/s12221-025-01066-0 · Cited by 3
“Convolutional neural network (CNN)-based architectures like the YOLO series [10, 11], Faster R-CNN [12], and SSD [13] have been widely adopted in industrial defect detection.”
Gong, B., Zhang, H., Ma, B., & Tao, Z. (2025) · The Journal of Supercomputing · doi:10.1007/s11227-025-07594-z · Cited by 7
Real-Time Instance Segmentation for Parking Occupancy Detection Using CNNs
Lassen, V., Lübke, M., & Franchi, N. (2025) · doi:10.1109/cism64958.2025.11060860 · Cited by 3
SCCA-YOLO: Spatial Channel Fusion and Context-Aware YOLO for Lunar Crater Detection
Tang, J., Gu, B., Li, T., et al. (2025) · Remote Sensing · doi:10.3390/rs17142380 · Cited by 3
Nighttime Vehicle Detection Algorithm Based on Improved YOLOv7
Zhang, F. (2025) · IEEE Access · doi:10.1109/access.2025.3587717 · Cited by 3
LRSAA: Large-Scale Remote Sensing Image Target Recognition and Automatic Annotation
Dong, W., Zhu, Y., & Zhang, S. (2025) · International Conference on Geology, Mapping and Remote Sensing (ICGMRS) · doi:10.1109/icgmrs66001.2025.11065897 · Cited by 4
Box2Change: A Novel Weakly Supervised Way for Change Detection via Consistency Instance Segmentation
Liu, F., Yin, K., Liu, J., Yang, J., Tang, X., & Xiao, L. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2025.3589090 · Cited by 4
Lu, Z., Liao, L., Li, C., Xie, X., & Yuan, H. L. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.111414 · Cited by 5
Fuchs, L., Diesse, M., Weber, M., et al. (2025) · Electronics · doi:10.3390/electronics14142889 · Cited by 3
“For example, YOLO (You Only Look Once) [23] applies a convolutional neural network to directly predict bounding boxes and class probabilities across an entire image in a single forward pass, enabling fast and robust object detection even under varying conditions.”
Wang, D., Cheng, Y., Shi, L., et al. (2025) · Agronomy · doi:10.3390/agronomy15071755 · Cited by 3
“YOLOv8 achieves real-time processing at 45 FPS, making it ideal for the dynamic field monitoring of crop diseases and pests [22].”
Machine Learning in Basketball
Chen, K., & Caparrós, M. G. (2025) · Springer eBooks · doi:10.1007/978-3-662-70155-3_9 · Cited by 3
Zero-Shot Detection in Satellite Images
Andriyanov, N. A., Tashlinsky, A., & Dementiev, V. (2025) · 2018Systems of Signal Synchronization, Generating and Processing in Telecommunications (SYNCHROINFO) · doi:10.1109/synchroinfo65403.2025.11079342 · Cited by 3
“Classical detector architectures such as Faster R-CNN [7], YOLO [8] or SSD [9], which show outstanding results on standard computer vision datasets, face problems of portability to a specific remote sensing domain precisely because of this high variability and the relative paucity of labeled data…”
Yang, T., Guo, Y., Wang, W.-S., et al. (2025) · IEEE transactions on intelligent transportation systems (Print) · doi:10.1109/tits.2025.3588346 · Cited by 1
“In order to verify the detection performance of CADNet, the two-stage detection model Faster RCNN [45], the one-stage detection model SSD (Single Shot Detector) [46], and the YOLO series of models [39], [40], [47], [48], [49], [50], [51] are used to conduct comparison experiments with CADNet.”
Patrick, M. J., Field, C. R., Grae, L. H. L., et al. (2025) · APL Machine Learning · doi:10.1063/5.0274266 · Cited by 3
YOLOv8-C2fSE- An Improved Accuracy Model for Object Detection
Modupalli, B. M., & Prithvi, P. (2025) · International Conference on Recent Advances in Information Technology · doi:10.1109/rait65068.2025.11089214 · Cited by 3
YOLO-CSS: a lightweight defect detection model for complex substation scenarios
Hui, M., Yao, J., Fu, Z., et al. (2025) · Measurement Science and Technology · doi:10.1088/1361-6501/adf65d · Cited by 3
“Since the original you only look once (YOLO) appeared in 2016 [9], the YOLO family of single-stage detectors has become especially popular for real-time applications, thanks to its favorable trade-off between detection speed and precision.”
Dynamic Hardware Defense for High-Centrality Nodes in Graph Convolutional Networks
Cai, C., Li, P., Wen, W., Huang, Z., Peng, Y., Hu, M., Wu, Z., Shen, L., & Zhang, J. (2025) · IEEE Transactions on Nuclear Science · doi:10.1109/tns.2025.3595388 · Cited by 3
“From object detection and natural language processing to speech recognition, DNNs have achieved groundbreaking advancements across a wide range of tasks, driving technological innovation in multiple engineering fields [3], [4], [5], [6], [7].”
Fool the Stoplight: Realistic Adversarial Patch Attacks on Traffic Light Detectors
Pavlitska, S., Robb, J., Polley, N., Yazgan, M., & Zöllner, J. M. (2025) · IEEE Intelligent Vehicles Symposium · doi:10.1109/iv64158.2025.11097778 · Cited by 3
“In our recent work [20] three categories of CNN-based approaches were analyzed: (1) modifications of generic detectors like YOLO [21] or SSD [22] for the traffic light detection [23]–[30], (2) multi-stage approaches encompassing rule-and CNN-based components [31]–[33], and (3) task-specific…”
Zhao, B., Li, J., Zhao, J., Yu, L., Zhang, X., & Liu, J. (2025) · The Visual Computer · doi:10.1007/s00371-025-04098-y · Cited by 4
Chandra, N. S., Vaidya, H., Chauhan, P., & Shaw, R. (2025) · Journal of the Indian Society of Remote Sensing · doi:10.1007/s12524-025-02251-7 · Cited by 4
“(3 ) Head: The primary feature of YOLOv5 is its multi-scale prediction capability, where the model generates feature maps of three different sizes, allowing it to detect objects of varying scales (Redmon et al., 2016).”
A Cost-Sensitive Small Vessel Detection Method for Maritime Remote Sensing Imagery
Hu, Z., Wu, W., Yang, Z., Zhao, Y., Xu, L., Kong, L., Chen, Y., Chen, L., & Liu, G. (2025) · Remote Sensing · doi:10.3390/rs17142471 · Cited by 6
MFFN: Multiscale Feature Fusion Network with Pruning for photovoltaic cell anomaly detection
He, Z., Chen, G., Ruan, Z., & Wang, L. (2025) · Nondestructive Testing And Evaluation · doi:10.1080/10589759.2025.2533387 · Cited by 3
“These methods are generally classified into two categories: one-stage detection methods, i.e. YOLO [13], SSD [14], RetinaNet [15], and two-stage detection methods, i.e. R-CNN R-CNN [16], and Fast RCNN [17].”
Advancing Object Detection in Remote Sensing: a Rigorous Evaluation of YOLO Models
Kasetty, S. B., & Rajakumar, K. (2025) · International Conference on Communications and Signal Processing (ICCSP) · doi:10.1109/iccsp64183.2025.11088554 · Cited by 5
“The YOLO framework, which was first implemented by Redmon et al. [7], is a fast and unified detecting objects approach by splitting images into grids & predicting bounding boxes directly.”
Automated Detection of Necrotizing Soft Tissue Infection Features by Computed Tomography
Lin, H.-Y., Chiu, M., Kao, T.-L., & Chen, C.-C. (2025) · Diagnostics · doi:10.3390/diagnostics15162030 · Cited by 4
Simplifying Two-Stage Object Detectors for On-Board Remote Sensing
Kang, J., Yang, H., & Kim, H. (2025) · IEEE Access · doi:10.1109/access.2025.3599526 · Cited by 6
Deep Object Recognition-Based Analysis of Diverse Culinary Landscapes
Sanatbyek, A., Karabay, A., Varol, H. A., et al. (2025) · Proceedings - International Conference on Image Processing · doi:10.1109/icip55913.2025.11084477 · Cited by 3
AI-Powered Automated Inspection for Optimized Asset Management in Electrical Distribution Networks
Silva, M. F. D., Santos, M. F. D., Masson, J. E. N., et al. (2025) · Journal of Control Automation and Electrical Systems · doi:10.1007/s40313-025-01197-y · Cited by 3
“The AI architecture is designed where each class is trained separately using you only look once(YOLO), which is a real-time object detection system introduced by Redmon et al. (2016), designed to achieve both high accuracy and fast processing speeds.”
Liu, Q., Wang, X., Su, Y., Jiang, W., Zhang, Z., Shen, F., & Zhu, L. (2025) · Sensors · doi:10.3390/s25165141 · Cited by 5
Optimized Adaptive Multi-Scale Architecture for Surface Defect Recognition
Chang, X., Wang, Y., Zhang, H., Adamyk, B., & Yan, L. (2025) · Algorithms · doi:10.3390/a18080529 · Cited by 4
“Current target detection algorithms are mainly divided into two categories: one-stage algorithms (e.g., YOLO series [5–11], SSD [12], DETR [13]), which offer higher detection speed but relatively lower accuracy, and two-stage algorithms (e.g., R-CNN [14], Fast R-CNN [15], Faster R-CNN [16]), which…”
A Lightweight Object Detection Model for Complex Marine Conditions Based on Improved RT-DETR
Xu, W., Zhang, Y., Ding, B., & Liu, B. (2025) · International Conference on Automation, Control and Robotics Engineering (CACRE) · doi:10.1109/cacre66141.2025.11119590 · Cited by 3
Research on improved YOLOv8 fabric surface defect detection algorithm
Gao, Z., Zhang, S., Su, J., et al. (2025) · Textile Research Journal · doi:10.1177/00405175251356191 · Cited by 3
Unmanned Aerial Vehicles and Edge AI for Power Line Inspection
Fu, Y., Meng, J., & Li, H. (2025) · IEEE International Conference on Mechatronics and Automation (ICMA) · doi:10.1109/icma65362.2025.11120738 · Cited by 4
“This paper explores how TensorFlow Lite deployed on an ARM processor, coupled with the You Only Look Once (YOLO) algorithm, addresses these constraints for effective object detection on autonomous UAVs [53].”
Synergistic-aware cascaded association and trajectory refinement for multi-object tracking
Li, H., Qin, S., Li, S., Gao, Y., & Wu, Y. (2025) · Image and Vision Computing · doi:10.1016/j.imavis.2025.105695 · Cited by 6
Bankole, A. O., Moruzzi, R. B., Negri, R. G., Bridgeman, J. O., & Sharifi, S. (2025) · Journal of Hazardous Materials Advances · doi:10.1016/j.hazadv.2025.100870 · Cited by 3
Rock Joint Segmentation in Drill Core Images via a Boundary-Aware Token-Mixing Network
Lee, S., Kim, Y., Kim, Y., et al. (2025) · Buildings · doi:10.3390/buildings15173022 · Cited by 3
SPyramidLightNet: A Lightweight Shared Pyramid Network for Efficient Underwater Debris Detection
Luo, Y., & Eljamal, O. (2025) · Applied Sciences · doi:10.3390/app15179404 · Cited by 3
Lee, C., Kim, D., & Kim, D. (2025) · Sensors · doi:10.3390/s25175437 · Cited by 7
“…as Faster Region-Based Convolutional Neural Network (Faster RCNN) [11], Single Shot Multibox Detector (SSD) [12], and You Only Look Once (YOLO) [13] are suitable for detecting defect locations and may enable more accurate damage identification in tunnel structures when linked with MTSS. Xue…”
Detection of Fast-Moving Objects with Neuromorphic Hardware
Ziegler, A., Vetter, K., Gossard, T., et al. (2025) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra55743.2025.11127960 · Cited by 3
CBI-YOLO: a lightweight weld detection and evaluation scheme for metal roofs in terminal buildings
Bai, J., Yu, W., Cai, C. S. S., Xin, Z., Lin, X., Huang, Z., & Ke, Z. (2025) · Engineering Research Express · doi:10.1088/2631-8695/ae040d · Cited by 3
Zhang, J., Zhang, C., Lianghao, X., Mao, B., & Chen, Z. (2025) · Signal Image and Video Processing · doi:10.1007/s11760-025-04572-z · Cited by 5
“In contrast, one-stage algorithms (e.g., YOLO [10], SSD [11]) directly predict object These issues threaten road safety: small-object misdetection delays braking in autonomous vehicles, while occlusion errors trigger collisions at intersections classes and locations densely, achieving faster…”
YOLO-MARS for Infrared Target Detection: Towards near Space
Liu, B., Han, Y., Liu, P., Luo, S., Li, J., Zhang, T., & Cui, W. (2025) · Sensors · doi:10.3390/s25175538 · Cited by 4
“Single-stage algorithms, such as the YOLO [21] series proposed by Redmon et al., transform the detection task into a regression problem.”
DCC-DETR: a real-time lightweight gesture recognition network for home human–robot interaction
Chen, X., & Yin, H. (2025) · Journal of Real-Time Image Processing · doi:10.1007/s11554-025-01763-2 · Cited by 4
“These models integrate classification and localization into a unified network, significantly enhancing the speed of inference for real-time applications [15].”
Appel, C. L., Subramanian, A., Koning, J. S., Ngosi, M. S., Sullivan, C. M., Levi, T., & Lesmeister, D. B. (2025) · Ecological Applications · doi:10.1002/eap.70096 · Cited by 11
“Software dependencies for the host machine, or to use the tool locally, include Node.js (for all features) and Darknet (Bochkovskiy et al., 2020; Redmon, 2016) or TensorFlow (Abadi et al., 2015) for model training and image classification.”
Enhanced Multi-View Pedestrian Detection Using Probabilistic Occupancy Volume
Alturki, R., Hilton, A., & Guillemaut, J. (2025) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw67362.2025.00322 · Cited by 3
StrongSiamTracker: A Siamese Tracker with Dynamic Global Detection for Robust Anti-UAV Tracking
Cui, X., Liu, W., Kong, L., Li, J., Zhang, C., Zhao, R., Wu, P., & He, S. (2025) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw67362.2025.00659 · Cited by 4
“Some studies[30, 35, 39, 51] indicate that the effectiveness of tracking is heavily dependent on the performance of UAV target detection, utilizing YOLO series detectors[37] alongside straightforward tracking logic to monitor small targets.”
Multi-level modeling-based amodal instance segmentation network
Yang, B., Zhan, J., Liu, J., & Guo, C. (2025) · The Journal of Supercomputing · doi:10.1007/s11227-025-07667-z · Cited by 3
The Role of Intelligent Data Analysis in Selected Endurance Sports: A Systematic Literature Review
Rajšp, A., Rek, P., Kokol, P., & Fister, I. (2025) · Applied Sciences · doi:10.3390/app151810158 · Cited by 5
Research on Water Surface Object Detection Method Based on Image Fusion
Chen, Y., Ma, X., Wang, Q., He, Y., & Xie, S. (2025) · Journal of Marine Science and Engineering · doi:10.3390/jmse13091832 · Cited by 4
TMSS-YOLO: An industrial tool detection method based on improved YOLOv11
Yang, G., Zhang, Z., Sang, H., Tang, H., & Wang, M. (2025) · Signal Image and Video Processing · doi:10.1007/s11760-025-04816-y · Cited by 5
“In contrast, single-stage models like YOLO [11] and SSD [12] enable faster inference with competitive accuracy.”
Deep learning models for damage type detection in wind turbines
Doğan, F., Oyucu, S., Biçer, E., & Aksöz, A. (2025) · PeerJ Computer Science · doi:10.7717/peerj-cs.3163 · Cited by 5
Research on a Dense Pedestrian-Detection Algorithm Based on an Improved YOLO11
Wu, L., Li, X., Ma, P., & Cai, Y. (2025) · Future Internet · doi:10.3390/fi17100438 · Cited by 6
Huang, Y. J., Li, H., Wang, G., Xu, D., Yang, J., Yue, G., & Liu, X. (2025) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2025.3612628 · Cited by 7
Cui, C., Chen, X., He, L., et al. (2025) · Sensors · doi:10.3390/s25196001 · Cited by 3
“Mainstream one-stage detectors, such as the YOLO series, are faster, but their standard backbones tend to lose critical high-frequency information during downsampling, resulting in low sensitivity [15].”
Detection method for improving shape perception of small object defects on metal surfaces
Zhu, X., Montagne, C., Wang, Q., Hu, L., Yu, J., Tabia, H., & Hu, Q. (2025) · Applied Intelligence · doi:10.1007/s10489-025-06873-9 · Cited by 4
“The You Only Look Once (YOLO) series [26–33 ] is known for its high real-time perfor - mance.”
Khan, A. S., Abbass, M. J., & Khan, A. (2025) · Sensors · doi:10.3390/s25195992 · Cited by 6
“Traditional CNN-based methods include R-CNN series [9–11], YOLO series (v1-v7) [12–19], SSD [20], RetinaNet [21], and Mask R-CNN [22].”
Artificial intelligence for context-aware visual change detection in software test automation
Moradi, M., Yan, K., Colwell, D., & Asgari, R. (2025) · Progress in Artificial Intelligence · doi:10.1007/s13748-025-00408-6 · Cited by 4
Enhanced Lightweight Object Detection Model in Complex Scenes: An Improved YOLOv8n Approach
Hamdouni, S. E., Hdioud, B., & Fkihi, S. E. (2025) · Information · doi:10.3390/info16100871 · Cited by 5
MDSF-YOLO: Advancing Object Detection With a Multiscale Dilated Sequence Fusion Network
Sun, Y. X., Zhang, C., Li, X., Jing, X., Kong, H. F., & Wang, Q. (2025) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2025.3617122 · Cited by 7
“…algorithms, notably the YOLO and SSD series [9], [10], [11], o ff er a better way to cope with its speed and accuracy trade-o ff s. YOLOv1 revolutionized by recasting detection as a regression problem, allowing for simultaneous localization and classification via CNNs in real-time detection [12].”
TOOLS AND METHODS FOR EXPLOSIVE OBJECTS DETECTION USING ARTIFICIAL INTELLIGENCE AND COMPUTER VISION
Levchenko, D., Podorozhniak, A., & Liubchenko, N. (2025) · Системи управління навігації та зв’язку Збірник наукових праць · doi:10.26906/sunz.2025.3.117 · Cited by 3
“In contrast, single-stage models, such as YOLO, detect objects directly without a separate region proposal step [11, 12].”
A Review on AI Miniaturization: Trends and Challenges
Tang, B., Du, S., & Smith, A. J. (2025) · Applied Sciences · doi:10.3390/app152010958 · Cited by 4
Exploring X-Ray Prohibited Item Detection From Long-Tailed Learning Perspective
Wang, B., Zhang, F., Fang, X., Ji, R., Tao, R., Cao, Y., Liu, B., & Liu, J. (2025) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2025.3620642 · Cited by 5
Social Robots for Road Safety: Pedestrian Crossing Assistance Use-Case
Comeca, A. L. F., Masarykova, N., Halinkovič, M., et al. (2025) · International Symposium ELMAR · doi:10.1109/elmar66948.2025.11193979 · Cited by 3
“AT platform, featuring LEDs and perception sensors. system uses the YOLO object detection algorithm [7] to identify road users and signal crossing intentions through red green lights.”
Pantaleo, E., Giannico, V., Cilli, R., Camposeo, S., Elia, M., Lafortezza, R., Monaco, A., Sanesi, G., Tangaro, S., Bellotti, R., et al. (2025) · Smart Agricultural Technology · doi:10.1016/j.atech.2025.101551 · Cited by 3
Quantization Robustness to Input Degradations for Object Detection
Karimov, T., Imani, H., & Kazakov, A. (2025) · Innovations in Intelligent Systems and Applications Conference (ASYU) · doi:10.1109/asyu67174.2025.11208310 · Cited by 4
“Deep Neural Networks (DNNs), especially models like YOLO [1], have revolutionized object detection.”
Ping, L., Cui, R., Yan, Q., Hu, Z., Shi, J., Xu, Q., Wang, H., Wang, H., Hua, S., & Wu, W. (2025) · Journal of Robotic Surgery · doi:10.1007/s11701-025-02922-0 · Cited by 3
Nunkhaw, M., Chitwatkulsiri, D., & Miyamoto, H. (2025) · Water · doi:10.3390/w17223193 · Cited by 4
Tracking temporal progression of benign bone tumors through X-ray based detection and segmentation
Rhyou, S.-Y., Bang, C. H., Cho, Y. J., Bae, H., Ha, Y. J., Baek, S.-Y., Lee, Y. W., Kim, C., & Moon, J. E. (2025) · Scientific Reports · doi:10.1038/s41598-025-23053-4 · Cited by 6
“To evaluate the performance of BBT detection, we conducted comparative experiments using three widely adopted models from the YOLO family.”
InfluentialLehnhoff, L., Glotin, H., Gall, Y. L., Menut, E., Peltier, H., Pochat, A., Pochat, K., Canneyt, O. V., & Mérigot, B. (2025) · Scientific Reports · doi:10.1038/s41598-025-24256-5 · Cited by 6
“The DYOC (“Draw Your Own Contours”) method uses two efficient models: YOLOv8m 41,42 and ResNet18 43 , which are trained and tested on our dataset using PyTorch 44 .”
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.