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 37,201–37,300 of 51,399
Anwendungen von Computer Vision in den Sportwissenschaften
Koller, T., & Emmenegger, S. (2025) · Springer eBooks · doi:10.1007/978-3-662-68950-9_16 · Cited by 1
Linear Transformers beat YOLO for Embedded Object Detection
Ancilotto, A., Castagnini, E., & Farella, E. (2025) · IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops) · doi:10.1109/percomworkshops65533.2025.00071 · Cited by 1
Brain Tumor Detection using Deep Learning: YOLO-v8 and VGG-19 in Medical Imaging
Varshini, G. B., Suryanarayana, G., Angel, N. N., et al. (2025) · International Conference on Pervasive Computing and Social Networking (ICPCSN) · doi:10.1109/icpcsn65854.2025.11035070 · Cited by 1
“Conversely, YOLO (You Only Look Once) [11] excels in real-time object detection, enabling simultaneous localization and classification of multiple regions within a single frame [12].”
MMC-YOLO: Application of YOLOv8 in the Detection of Small Lesions in Biomedical Images
Wang, J. Y., & Hsiang, H.-C. (2025) · International Conference on Cloud Computing and Big Data Analytics (ICCCBDA) · doi:10.1109/icccbda64898.2025.11030501 · Cited by 1
Bao, M., Zhao, C., Liu, N., et al. (2025) · IET Intelligent Transport Systems · doi:10.1049/itr2.70039 · Cited by 1
GCE-YOLO: A Lightweight Fire Detection Algorithm Optimized for Edge Devices
Zheng, Y., Lu, J., Shi, W., et al. (2025) · doi:10.1109/ainit65432.2025.11035903 · Cited by 1
“To overcome these limitations, single-stage detection algorithms like YOLO[4] and SSD[5] have emerged.”
YOLOv8-MFT: A Fire Detection Algorithm Based On Improved YOLOv8
Li, Y., Liu, W., & Yu, Q. (2025) · International Seminar on Artificial Intelligence, Networking and Information Technology (AINIT) · doi:10.1109/ainit65432.2025.11035478 · Cited by 2
“In order to optimize the detection of small objects, Zhao et al. improved YOLOv3 and proposed Fire-YOLO[13], introduced EfficientNet[14] to enhance the feature extraction ability, and significantly improved the recognition effect of small flames and smoke.”
Zhao, D., Xing, Z., Lu, Q., Xu, X., & Zhu, L. (2025) · ACM/IEEE International Conference on Software Engineering: Companion Proceedings (ICSE-Companion) · doi:10.1109/icse55347.2025.00144 · Cited by 2
An Efficient Real-Time Safety Helmet Detection Algorithm Based on YOLOv11
Jiang, H., Ran, X., & You, Q. (2025) · doi:10.1109/ainit65432.2025.11034993 · Cited by 1
“Typical algorithms in this field include the YOLO series[2-4], Faster R-CNN[5], and SSD[6].”
Are Edge MicroDCs Equipped to Tackle Memory Contention?
Tran, L., Bartz, R., Durairajan, R., et al. (2025) · ACM Workshop on Hot Topics in Storage and File Systems (HotStorage) · doi:10.1145/3736548.3737827 · Cited by 1
Chemoreception in Aurelia aurita studied by AI-enhanced image analysis
Boyd, W., Ohdera, A. H., Kaufman, L., & Herman, D. (2025) · Journal of Emerging Investigators · doi:10.59720/24-052 · Cited by 1
A Method for Real-Time Vessel Speed Measurement Based on M-YOLOv11 and Visual Tracking
Ma, Z., Hu, Q., Wu, Y., & Wang, W. (2025) · Sensors · doi:10.3390/s25133884 · Cited by 3
“The M-YOLOv11 model comprises three distinct components as follows: Backbone, Neck, and Head [19].”
Corn Disease Detection Based on Improved Lightweight YOLOv5
张, 立. (2025) · Computer Science and Application · doi:10.12677/csa.2025.156161 · Cited by 1
Advanced In-Vehicle Camera Algorithm for High-Density Pedestrian Detection
Raman, R., Vinoth, T., Patel, H., & Pathak, G. P. (2025) · International Conference on Knowledge Engineering and Communication Systems (ICKECS) · doi:10.1109/ickecs65700.2025.11035909 · Cited by 1
Liu, L., Liu, Y., Ning, Y., et al. (2025) · International Conference on Information Science, Electrical and Automation Engineering (ISEAE) · doi:10.1109/iseae64934.2025.11042198 · Cited by 1
“The other is One-Stage target detection algorithms, typically represented by the YOLO series and SSD, which use regression to simultaneously classify targets and predict candidate regions [4].”
Research on bubble defect detection algorithm of epoxy encapsulation products based on YOLOv8
Xie, Y., Xu, H., Guo, M., et al. (2025) · doi:10.1109/dipca65051.2025.11042543 · Cited by 1
Computer vision techniques for high-speed atomic force microscopy of DNA molecules
Driver, N., Mikheikin, A. L., Koebley, S., Mostashari, M., Picco, L., Berger, S., & Reed, J. C. (2025) · Nanotechnology · doi:10.1088/1361-6528/ade888 · Cited by 2
“An in-depth description of the architecture, the loss function, and some of its predecessors [27–30] can be found in the recent paper by Wallace et al [26].”
Sistema de Detecção de Usuários Vulneráveis da Via Robusto à Baixa Iluminação
Avena, V., Couto, R. S., Campista, M. E. M., & Costa, L. H. M. K. (2025) · Anais do Workshop de Computação Urbana (CoUrb) · doi:10.5753/courb.2025.9064 · Cited by 1
Towards a SoIS model for University Surveillance
Figueiredo, R. D. C., Mane, B., Clavijo, D. R., et al. (2025) · doi:10.1109/sesos66601.2025.00009 · Cited by 1
“Frames are sent to CSIS Semantic interoperability for the YOLO (You Only Look Once) models to detect objects that are trained [16].”
DSFPN-YOLOv8: Dynamic Multi-scale Feature Fusion Model for Small Object Detection
Chang, Y., Yang, X., Liang, X., & Zheng, X. (2024) · doi:10.1145/3703935.3704076 · Cited by 2
Closed-Loop Aerial Tracking with Dynamic Detection-Tracking Coordination
Wang, Y., Huang, H., He, J., Han, D., & Zhao, Z. (2025) · Drones · doi:10.3390/drones9070467 · Cited by 1
A Review of Deep Learning-Based Infrared Weak Target Detection Methods
阿, 勒. (2025) · Computer Science and Application · doi:10.12677/csa.2025.156172 · Cited by 1
Intelligent detection methods for miniature defects in metallic materials
Liu, C., Lin, W., & Tseng, F.-S. (2025) · Array · doi:10.1016/j.array.2025.100430 · Cited by 1
Leroy, P., Abisset‐Chavanne, E., Pommier, R., & Montemurro, M. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.111516 · Cited by 4
Li, Y., Wu, P., & Zhang, M. (2025) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2025.104432 · Cited by 1
Real-Time Lightweight Morphological Detection for Chinese Mitten Crab Origin Tracing
Ma, X., Shen, N., He, Y., et al. (2025) · Applied Sciences · doi:10.3390/app15137468 · Cited by 1
An Intelligent Vehicle Detection and Recognition Framework for Traffic Cyber-Physical Systems
Wei, X., & Sejera, M. P. (2025) · International Journal of Computational and Experimental Science and Engineering · doi:10.22399/ijcesen.3180 · Cited by 1
AI-Based Vehicle State Estimation Using Multi-Sensor Perception and Real-World Data
Ruggaber, J., Pölzleitner, D., & Brembeck, J. (2025) · Sensors · doi:10.3390/s25144253 · Cited by 1
“The probably best-known method for one-stage methods is YOLO (You Only Look Once) [23], which is widely used in both research and industry.”
Word recognition during movement under simulated weather conditions
Rocabado, F., Alonso-Bernal, N., & Duñabeitia, J. A. (2025) · PLoS ONE · doi:10.1371/journal.pone.0326945 · Cited by 2
“Additionally, recent advancements in traffic sign recognition, like Zhang et al. [47] algorithm for recognizing traffic signs in rainy conditions and Redmon et al [48].”
Aiming Error Analysis of Controlled Turret System With AI Target Recognition
Karlson, M., Ban, H., Cole, D. G., Abdelhakim, M., & Forsythe, J. (2025) · International Journal of Control Automation and Systems · doi:10.1007/s12555-024-1015-9 · Cited by 2
“We leverage the most popular [12,14,37] in this work: AP50 for η = 0 .”
Evaluating Service-Based Privacy-Protection for Augmented Reality Applications
Rodrígues, M. A., Ribeiro, T., Santos, L., et al. (2025) · Communications in computer and information science · doi:10.1007/978-3-031-93598-5_19 · Cited by 1
Xu, J., Hua, R., Wang, S., et al. (2025) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2025.07.004 · Cited by 1
Intelligence Safety Detection and Hazard Monitoring using YOLO Algorithm
Kumar, V. A., Tarun, Y. S. D. S. K., Reddy, V. K. S., et al. (2025) · International Conference on Self Sustainable Artificial Intelligence Systems (ICSSAS) · doi:10.1109/icssas66150.2025.11081352 · Cited by 1
Sign Recognition in Multiple Sign Languages Using Neural Network Techniques
Alshahrani, A., Aljafri, M., Alsayed, L., et al. (2025) · doi:10.1109/aiit63112.2025.11082856 · Cited by 1
“The first YOLO model [21] as shown in Figure 2, introduced a straightforward yet highly effective architecture that consists of 24 convolutional layers, four max-pooling layers, and two fully connected layers, enabling it to process images with high accuracy.”
Su, C., Yang, W., Pan, Y., et al. (2025) · Remote Sensing · doi:10.3390/rs17152545 · Cited by 1
Marine Organism Detection Algorithm Based on MSPSO-YOLOv8
Wang, G., Yang, J., & Sun, L. (2025) · International Conference on Computer Vision, Image and Deep Learning (CVIDL) · doi:10.1109/cvidl65390.2025.11085432 · Cited by 1
“The current mainstream deep learning detection architectures mainly include representative methods such as the R-CNN series based on region proposals [2-4] and single-stage detectors like SSD[5] and YOLO[6].”
Recognition and Reading Method of Pointer Meters in Hard X-Ray Free-Electron Laser Facility
Liu, W., Fan, L., Li, J., et al. (2025) · International Conference on Computer Vision, Image and Deep Learning (CVIDL) · doi:10.1109/cvidl65390.2025.11085765 · Cited by 1
“The other category is single-stage detection, represented by the YOLO [6]series, with typical algorithms such as the YOLO series (YOLOv3/v5/v8, etc.), SSD, and RetinaNet.”
Wang, S., Li, W., Xu, Z., & Yu, N. (2025) · International Conference on Electronic Engineering and Information Systems (EEISS) · doi:10.1109/eeiss65394.2025.11085508 · Cited by 1
“Compared to traditional methods, Deep Neural Network (DNN)-based techniques, like R-CNN [1] , YOLO [2] and SSD [3], offer significant improvements in accuracy and real-time performance.”
Improving vision-language models through intra-modal contrastive learning-based hard sample mining
Lin, C., Shi, Y., Wang, G., & Liu, S. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.131047 · Cited by 2
MFA-FHS: multiscale feature based self attention network for fetal head segmentation
Kamboj, A., Bhalla, P., & Sunkaria, R. K. (2025) · Multimedia Tools and Applications · doi:10.1007/s11042-025-20824-z · Cited by 2
Adapting Vision Transformer-Based Object Detection Model for Handwritten Text Line Segmentation Task
Karakuş, O. F., Gülcü, A., & Karaca, A. C. (2025) · Journal of Innovative Science and Engineering (JISE) · doi:10.38088/jise.1471047 · Cited by 1
Real-Time Expiry Alert System for Safer Retail using Barcode and QR Code Recognition
Mariammal, G., Swetha, S., & Noorani, J. (2025) · International Conference on Intelligent Communication Technologies and Virtual Mobile Networks (ICICV) · doi:10.1109/icicv64824.2025.11085659 · Cited by 1
Large Language Models for Dummies
Calamo, M., & Marinacci, M. (2025) · Springer eBooks · doi:10.1007/978-3-031-92285-5_3 · Cited by 1
Khan, Q., Mohamed, M. M., Klammler, H. R., Parker, B. L., & Hatfield, K. (2025) · Advances in Water Resources · doi:10.1016/j.advwatres.2025.105058 · Cited by 2
Novel Framework for Real-Time Object Detection with Audio Output Leveraging YOLO and CNN
Sangolgi, V. A., Patil, M. B., Aursang, K., et al. (2025) · Smart innovation, systems and technologies · doi:10.1007/978-981-96-3420-0_16 · Cited by 1
FSDA-YOLO: Frequency-Aware Multi-scale Fusion for Small Object Detection
Guo, H., Wang, Y., Wang, Y., et al. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-9891-2_23 · Cited by 1
Tang, Y., Zhao, S., Qin, H., Ming, P., Fang, T., & Zeng, J. (2025) · Sensors · doi:10.3390/s25154797 · Cited by 1
“In 2023, the YOLOv8 framework was proposed by Ultralytics, which is a variant of the You Only Look Once (YOLO) family, well known for their real-time processing capabilities and outstanding performance of object detection [39–46].”
Wang, C. C., & Yan, S.-J. (2025) · International Journal of Computational and Experimental Science and Engineering · doi:10.22399/ijcesen.3319 · Cited by 1
A comparative analysis of real-time detection algorithms for UAV-assisted maritime rescue
Zilske, F., Harders, L. O., & Hussmann, S. H. (2025) · IEEE International Instrumentation and Measurement Technology Conference · doi:10.1109/i2mtc62753.2025.11079117 · Cited by 1
“This high speed can be achieved because the prediction of bounding boxes and class probabilities is done in one evaluation [15].”
Small Object Detection Based on YOLOv5s in Advanced Driver Assistance System
Kuang, L., Han, H., Pan, H., Li, H., Zhao, S., & Huang, R. (2025) · Chinese Control and Decision Conference (CCDC) · doi:10.1109/ccdc65474.2025.11091253 · Cited by 2
“The other is the one-stage object detection algorithm based on regression, represented by YOLO [3].”
Accelerating on-device visual task adaptation by exploiting hybrid sparsity in DNN training
Park, M., Park, Y., & Choi, S. (2025) · Journal of Systems Architecture · doi:10.1016/j.sysarc.2025.103535 · Cited by 1
Application of YOLO Models for Automated Object Detection: Comparison, Analysis, and Recommendations
Amangeldy, N., Nazyrova, A., Kurmetbek, B., & Gazizova, N. (2025) · Communications in computer and information science · doi:10.1007/978-3-031-98164-7_10 · Cited by 1
Comprehensive Evaluation of Cloaking Backdoor Attacks on Object Detector in Real-World
Ma, H., Abuadbba, A., Gao, Y., Kim, H., & Nepal, . (2025) · ACM Asia Conference on Computer and Communications Security (ASIA CCS) · doi:10.1145/3708821.3710836 · Cited by 2
Advancing Colorectal Polyp Detection and Segmentation Through YOLOv11 Architecture
Gulsoy, T., Kanca, E., Kablan, E. B., & Ayas, S. (2025) · International Symposium on Innovative Approaches in Smart Technologies (ISAS) · doi:10.1109/isas66241.2025.11101948 · Cited by 1
“The YOLO (You Only Look Once) family of models, originally developed for real-time object detection [10], has progressively expanded its capabilities to address more complex tasks such as instance and semantic segmentation.”
Object Detection in Synthetic Aperture Sonar Images Using a Deep Neural Network
Gall, Y. L., Simon, M., Burlet, N., et al. (2025) · doi:10.1109/oceans58557.2025.11104669 · Cited by 1
“We have adopted a region proposal network that incorporates essential elements of the YOLO architecture [19]–[21] (see Fig.”
An Improved RT-DETR Model for Small Object Detection on Construction Sites
Zhang, G., & Zhao, X. B. (2025) · International Conference on Computing and Artificial Intelligence (ICCAI) · doi:10.1109/iccai66501.2025.00015 · Cited by 4
Song, S., & Sun, B. (2025) · Journal of Marine Science and Engineering · doi:10.3390/jmse13081528 · Cited by 2
Locally Grouped and Scale‐Guided Attention for Dense Pest Counting
Son, C. (2025) · International Journal of Intelligent Systems · doi:10.1155/int/4732253
Gunshot entrance recognition by artificial intelligence using computer vision
Rodrigues, C. H. P., Sousa, M. D. D. C., dos Santos, M. A., Filho, P. A. F., Velho, J. A., & Bruni, A. T. (2025) · Forensic Science International · doi:10.1016/j.forsciint.2025.112616 · Cited by 1
Vasić, J., Milić, L., & Raković, M. (2025) · International Conference on Electrical, Electronic and Computing Engineering (IcETRAN) · doi:10.1109/icetran66854.2025.11114197 · Cited by 1
“To meet these challenges, many researchers have turned to detectors based on convolutional neural networks (CNN), such as the YOLO family [1], SSD [2], and Faster R-CNN [3], which balance speed and accuracy for object detection tasks.”
Banayan, N. E., Shalu, H., Hatzoglou, V., Swinburne, N., Holodny, A. I., Zhang, Z., & Stember, J. N. (2025) · American Journal of Neuroradiology · doi:10.3174/ajnr.a8767 · Cited by 1
Cheng, J.-A., Li, Q., Souri, A., Lei, X., Zhang, C., & Gao, M. (2025) · Cluster Computing · doi:10.1007/s10586-025-05226-y · Cited by 2
AR-RTDETR: A Lightweight Real-Time Transformer Network for UAV Infrared Small Target Detection
Sun, S., Feng, X., & Zhang, Y. (2025) · International Conference on Automation, Control and Robotics Engineering (CACRE) · doi:10.1109/cacre66141.2025.11119599 · Cited by 1
“Currently, single-stage target detection algorithms such as YOLO [5], DETR [6], and RT-DETR [7] have attracted much attention in practical applications due to their efficient detection results.”
Liu, Y., Zhao, J., Xu, C., Hou, Y., & Jiang, Y. (2025) · Frontiers in Plant Science · doi:10.3389/fpls.2025.1607492 · Cited by 3
A Scale-Adaptive and Frequency-Aware Attention Network for Precise Detection of Strawberry Diseases
Zhang, K., Ye, Y., Chen, K., Li, Z., & Peng, H. (2025) · Agronomy · doi:10.3390/agronomy15081969 · Cited by 1
Zhao, S. (2025) · Transactions on Computer Science and Intelligent Systems Research · doi:10.62051/fb5aqp52 · Cited by 1
Real-Time Instance Segmentation Method for Submarine Pipeline Leakage Detection Based on YOLOv8-Seg
Zhang, M., Bai, T., Zhou, S. K., et al. (2025) · IEEE International Conference on Mechatronics and Automation (ICMA) · doi:10.1109/icma65362.2025.11120765 · Cited by 1
“In contrast, single-stage algorithms are end-to-end real-time target detection methods, such as the YOLO (You Only Look Once) series [8-13], SSD [14], and RetinaNet [15].”
YOLOv8-DCW: Enhanced Object Detector Based on Deformable Convolution and Coordinate Attention
Guan, X., & Luo, X. (2024) · doi:10.1109/isdh64927.2024.00017 · Cited by 1
Altaif, A. H., Ashoor, A. M., Abdulla, A. M., et al. (2024) · IEEE International Conference on Engineering Technologies and Applied Sciences (ICETAS) · doi:10.1109/icetas62372.2024.11120142 · Cited by 1
Jima, W. D., Desta, S. F., Tarekegn, T. A., Gebremedhin, G. S., Gutema, A. B., & Debelee, T. G. (2025) · Applied AI Letters · doi:10.1002/ail2.70004 · Cited by 3
Zheng, A., & Yan, W. (2025) · Computers · doi:10.3390/computers14090352 · Cited by 3
“Subsequently, researchers have developed specialized architectures for various sports domains, including soccer [18,19], basketball [20,21], and tennis [22,23].”
Nguyen, T. D., Kim, T. D., Le, H. X., et al. (2025) · Lecture notes in networks and systems · doi:10.1007/978-3-032-00267-9_18 · Cited by 1
LLTQ+: A Hardware-Friendly Quantization Framework for Modern YOLO Architectures
Seo, Y., Kim, J., Kang, J.-K., & Kim, Y. (2025) · IEEE Access · doi:10.1109/access.2025.3603536 · Cited by 2
Liu, J., Wei, Y., Sun, R., & Yue, Y. (2025) · Aerospace Science and Technology · doi:10.1016/j.ast.2025.110788 · Cited by 9
Pandey, S. K., & Nair, S. B. (2025) · ACM Journal on Emerging Technologies in Computing Systems · doi:10.1145/3764930 · Cited by 2
“They have not performed on-device training of the model since the YOLO ANN [59] is difficult to train on a Raspberry Pi.”
Detection and Analysis of Electrophoresis Gels Using YOLO
da Silva, C. P., Carvalho, M. F. T., Costa, Y. M. G., et al. (2025) · IEEE Transactions on Computational Biology and Bioinformatics · doi:10.1109/tcbbio.2025.3605844 · Cited by 1
“OneofthemostusedalgorithmsisYOLO( You Only Look Once ), which was developed by Redmon et al. [6].”
Gowda, S. R., & Wolf, P. (2025) · European Dependable Computing Conference · doi:10.1109/edcc-c66476.2025.00058 · Cited by 1
“Therefore, for faster and real-time detection, one-stage detectors, such as YOLO [17], make an ideal choice for autonomous driving applications due to their ability to process the entire image in a single pass, providing quick and accurate predictions (see Fig.”
Lung CT Text Detection with YOLO: Leveraging Synthetic Datasets Over OCR
Górecki, A., G∤ówczewski, J. K., & Mazur-Milecka, M. (2025) · International Conference on Human System Interaction (HSI) · doi:10.1109/hsi66212.2025.11142425 · Cited by 1
“In the context of text label detection in CT lung images, leveraging YOLO (You Only Look Once) [4] presents a promising approach to overcome the limitations of existing OCR tools [5].”
Single camera estimation of microswimmer depth with a convolutional network
Hosseini, A., Fosse, C., Awada, M., et al. (2025) · Journal of The Royal Society Interface · doi:10.1098/rsif.2025.0428 · Cited by 1
2D Human Pose Estimation with Explicit Anatomical Keypoints Structure Constraints
Ji, Z., Wang, Z., & Feng, K. (2025) · Signal Image and Video Processing · doi:10.1007/s11760-025-04699-z · Cited by 3
Improved YOLOv8s-Based Detection for Lifting Hooks and Safety Latches
Guo, Y., Xiao, D., Ruan, X., Li, R., & Wang, Y. (2025) · Applied Sciences · doi:10.3390/app15189878 · Cited by 2
Vit4v: a Video Classification Method for the Detection of Varroa Destructor from Honeybees
Giovannesi, L., Russo, P., & Beraldi, R. (2025) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw67362.2025.00531 · Cited by 1
“Despite the deep model employed, the approach didn’t produced satis-fiable results, with the authors suggesting the use of YOLO v5 [24] to perform a traditional object detection task, while obtaining an F1-score of 0 .”
Almegdadi, O., Monteiro, S., Nóbrega, R., & Marques, N. C. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-05176-9_14 · Cited by 1
HiLEx: Image-Based Hierarchical Layout Extraction from Question Papers
Aich, U., Chakraborty, S., Sadhukhan, D., et al. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-04627-7_28 · Cited by 1
Research on Road Target Detection Algorithm Based on DS-YOLO11
Min, R., & Huang, J. (2025) · International Conference on Computer Science and Blockchain (CCSB) · doi:10.1109/ccsb66722.2025.11154343 · Cited by 1
“Single-stage detection technologies are typified by YOLO [4] and SSD [5] .”
Deep Learning-Based Heritage Building Assessment with Spatial Context
Rattanapitak, W., Khwansuwan, P., Wangsiripitak, S., & Sirikitsathian, P. (2025) · IEEE Symposium on Computers & Informatics (ISCI) · doi:10.1109/isci65687.2025.11167825 · Cited by 1
“For object detection, Redmon et al. [8] developed YOLO enabling real-time processing critical for deployment.”
Real-time Spectrum Analysis with Convolutional Neural Network on Embedded/Edge Hardware Platforms
Zhegulin, M. O., & Karamov, S. V. (2025) · International Conference on Communication Software and Networks · doi:10.1109/iccsn66511.2025.11172595 · Cited by 1
“In [15] a new approach to object detection was first presented.”
Ou, J., Zeng, W., Chen, S., & Lu, S. (2025) · International Annual Conference on Complex Systems and Intelligent Science (CSIS-IAC) · doi:10.1109/csis-iac65538.2025.11161896 · Cited by 1
“State-of-the-art detection algorithms (e.g., YOLO [1], SSD [2], and Faster R-CNN [3]) continue to advance, yet many still struggle with small or closely spaced targets in dense traffic.”
A Multi-Scale Feature Extraction and Attention Mechanism-Based Image Stitching Method
Luo, J., Cheng, X., Zhang, W., et al. (2025) · doi:10.1109/csis-iac65538.2025.11160782 · Cited by 1
“First, we replaced the backbone with VGG16, ResNet50 [25], and DarkNet53 [26] to conduct comparison experiments.”
Unification of Semantic and Instance Segmentation with BoundaryX
Boyadzhiev, T., & Ivanova, K. B. (2025) · Cybernetics and Information Technologies · doi:10.2478/cait-2025-0022 · Cited by 2
Pose Feature Fusion Based Short Track Speed Skaters Multi Object Tracking
Li, Z., Wang, Y., Liu, Y., & Li, H. (2023) · Journal of Computer-Aided Design & Computer Graphics · doi:10.3724/sp.j.1089.2023.19626 · Cited by 1
Low-Illumination Object Detection Method Based on Dark-YOLO
Jiang, Z., Xiao, Y., Zhang, S., Zhu, L., He, Y., & Zhai, F. (2023) · Journal of Computer-Aided Design & Computer Graphics · doi:10.3724/sp.j.1089.2023.19354 · Cited by 16
SAM–Attention Synergistic Enhancement: SAR Image Object Detection Method Based on Visual Large Model
Yuan, Y., Yang, J., Shi, L., et al. (2025) · Remote Sensing · doi:10.3390/rs17193311 · Cited by 1
Deep Learning-Driven Brain Tumor Sectionalisation: Leveraging YOLO11 for MRI Analysis
Khan, M. A., Sutradhar, U., Sarkar, P., Imran, M. I. A., & Dipa, S. A. (2025) · IEEE International Conference on Quantum Photonics, Artificial Intelligence & Networking (QPAIN) · doi:10.1109/qpain66474.2025.11172256 · Cited by 1
Steel surface defect detection algorithm based on EBC-YOLOv8
Wang, G., Dai, Z., & Pan, Y. (2025) · International Conference on Computer Information Science and Application Technology (CISAT) · doi:10.1109/cisat66811.2025.11181972 · Cited by 1
Lee, S.-H., Mun, S.-B., Oh, Y.-J., et al. (2025) · The Journal of Korean Institute of Information Technology · doi:10.14801/jkiit.2025.23.9.75 · Cited by 1
Improved YOLOv10-based real-time helmet detection algorithm for complex scenarios
Dong, H., Wang, Y., & Miao, D. (2025) · Journal of Real-Time Image Processing · doi:10.1007/s11554-025-01775-y · Cited by 3
“Current object detection frameworks primarily consist of two main systems: the DETR series (Detection Trans-former) based on the Transformer architecture [5–7], and the YOLO series based on convolutional neural networks (CNN) [8–19].”
CSST Slitless Spectra: Target Detection and Classification with Yolo
Zhou, Y., Liu, C., Tian, H., et al. (2025) · The Astronomical Journal · doi:10.3847/1538-3881/adee1c · Cited by 1
Mini-Batch Robustness Verification of Deep Neural Networks
Tzour-Shaday, S., & Drachsler-Cohen, D. (2025) · Proceedings of the ACM on Programming Languages · doi:10.1145/3763150 · Cited by 2
“Neural networks are successful in many applications, including object detection, speech recognition, text generation and machine translation [Bahdanau et al. 2015; Graves and Jaitly 2014; Redmon et al. 2016; Sutskever et al. 2014].”
Zeng, Y. (2025) · IEEE International Conference on Computer Communication and Artificial Intelligence (CCAI) · doi:10.1109/ccai65422.2025.11189549 · Cited by 1
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.