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 45,601–45,700 of 51,399
Sim-to-Real 6-DoF Pose Estimation for UAVs Using Synthetic RGB-D Data
Rodziewicz-Bielewicz, J., Wernikowski, M., Korzeń, M., et al. (2025) · Communications in computer and information science · doi:10.1007/978-3-032-08049-3_6
Morphological Change Detection for Scanning Electron Microscope Images of Lung Cell Surfaces
Ritu, J., Jefferis, T., Sayes, C. M., & Peeples, J. (2026) · International Conference on Advances in Artificial Intelligence and Machine Learning (AAIML) · doi:10.1109/aaiml67890.2026.11498109
“Additional segmentation models, including U-Net variants [23], transformer-based architectures [24], and YOLO-based segmentation models [25], will also be explored to benchmark MicroSAM against alternative methods and assess robustness across imaging conditions.”
On-Edge Task Planning with Large Language Models for Service Robotics
González-Cantón, A., González-Santamarta, M. Á., Rodríguez-Lera, F. J., Guerrero‐Higueras, Á. M., González-Fernández, I., & Martín, F. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-08462-0_28 · Cited by 1
CBLC-SOOD: contrastive background and label correction for semi-supervised oriented object detection
Zhao, Y., Yong, Z., Gong, Y., Liu, X., & Xu, L. (2025) · Multimedia Systems · doi:10.1007/s00530-025-02028-5
Research on Safety Issues in Intelligent Vehicles
Wang, S., Ge, H., Lv, J., & Lin, Y. (2025) · International Conference on Computer Communication and Artificial Intelligence (CCAI) · doi:10.1109/ccai65422.2025.11189396
A Multimodal Approach for Enhancing Decision Support in Remote Digital Tower
Ahmed, M. U., Barua, S., Islam, M. R., et al. (2025) · International Conference on Machine Learning Technologies (ICMLT) · doi:10.1109/icmlt65785.2025.11193403
“Jiang et al. mentioned in a review study that these type of methods run faster than R-CNN [10] and YOLO [11], although the accuracy might be lower [8].”
Li, W., Bai, X., Qin, Y., et al. (2025) · IEEE International Conference on Computer Communication and Artificial Intelligence (CCAI) · doi:10.1109/ccai65422.2025.11189458
“However, in the field of object detection, the dynamic development of deep learning has provided us with excellent models such as the YOLO[1] series and Faster R-CNN[3].”
A Three-Stage OCR Framework for Ancient Yi Manuscripts via Relation-DETR and ConvNeXt
Zhu, Z., Mao, W., Zhang, D., et al. (2025) · doi:10.1109/icaide65466.2025.11189616
“Traditional anchor-based detectors such as Faster R-CNN [2], SSD [3], and the real-time YOLO family [4] struggle with the small, sparsely arranged characters typical of ancient manuscripts.”
Figueiredo, R. D. C., Leite, J. C. S. D. P., Ralha, C. G., Maciel, P., & Claro, D. B. (2025) · IEEE International Requirements Engineering Conference Workshops (REW) · doi:10.1109/rew66121.2025.00049
“In this new SR model version, as illustrated in Figure 2, a second RCNN [4] detection system is incorporated in addition to the Yolo [5] detection system.”
Monocular Drogue Measurement Based on SiamMask Tracking Model and Feature Point Matching
Ye, F., Zhang, Y., Zhu, R., et al. (2025) · IEEE International Conference on Computer Communication and Artificial Intelligence (CCAI) · doi:10.1109/ccai65422.2025.11189507
“Many detecting and tracking models based on deep learning have been proposed and have high performance such as SSD [21], Faster R-CNN [22], yolov [23]–[25].”
Super resolution of pathology images with hierarchical feature integration and local image patterns
Xu, F., Li, L., Wang, S., Ling, R., Zhang, X., Deng, X., Zhou, M., Ling, J., & Gao, C. (2025) · The Journal of Pathology · doi:10.1002/path.6482 · Cited by 2
Normalized Raman imaging for studies of tissue physiology of the kidney
Trim, W. V., Oh, S., Diakova, M., Petrova, K., Ichimura, T., Takakura, A., Karmakar, R., Nørrelykke, S. F., Peshkin, L., Bonventre, J. V., et al. (2026) · Proceedings of the National Academy of Sciences · doi:10.1101/2025.10.12.681746 · Cited by 1
CHAMPIonS: Conversational Human-AI Methodologies for Performance In Sports
Barra, S., & Bacconi, A. (2025) · Biannual Conference of the Italian SIGCHI Chapter (CHItaly) · doi:10.1145/3750069.3757884
Tiny-YOLOv8 long-distance electric vehicle helmet detection model
Fan, J., Guang, J., Yu, N., Chen, J., & Wang, W. (2025) · International Conference on Computer Vision, Application, and Algorithm (CVAA) · doi:10.1109/cvaa66438.2025.11193203
“In recent years, single-stage target detection algorithms based on the YOLO [2] series have made significant progress in the field of electric vehicle helmet detection, but they still face many challenges.”
Weed29: A Weed Dataset for Machine Learning
Chen, W., Niu, Q., Li, H., et al. (2024) · International Conference on Universal Village (UV) · doi:10.1109/uv63228.2024.11189122
SmartHisto: Bayesian Active Learning for Histology ImagesPreprint
Vijendran, S., Arruda, B. L., Anderson, T. K., et al. (2025) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2025.10.13.681994
Research on non-tobacco related materials recognition method based on YOLOv8
Zhang, C., Yun, L., Wu, M., Luo, R., Chen, Z., & Cheng, F. (2025) · Scientific Reports · doi:10.1038/s41598-025-19653-9 · Cited by 2
“Currently, the YOLO series algorithm 27–35 represent a highly popular and efficient selection within the realm of one-stage methodologies.”
An Effective Vehicle Trajectory Restoration Algorithm Based on Center Trajectory
Shiau, Y.-H., Hung, C., & Tsai, C. (2024) · International Conference on Intelligent Computing and Its Emerging Applications (ICEA) · doi:10.1145/3732437.3732753
Enhanced Chart Detection in Document Images with Segmentation Backbone
Tran, D. H. L., Nguyen, H.-N., Huynh, V. T., Tran, T.-A., Mai, X. T., & Tran, H. T. (2025) · Communications in computer and information science · doi:10.1007/978-981-95-3355-8_30
Improving Rice Disease Segmentation via Iterative Pseudo-label Correction
Nguyen, N.-T.-A., Nguyen, V. H., & Le, T.-P. (2025) · Communications in computer and information science · doi:10.1007/978-981-95-3355-8_2
Rachmahyastuti, K. A., Wibowo, S. A., & Sutyarjoko, M. (2025) · doi:10.1109/icoict66265.2025.11192950 · Cited by 1
Drivers and passengers seatbelt detection for corner-top CCTV using YOLOv8
Dwiputri, M. A., Rachmawati, E., & Ferdian, E. (2025) · doi:10.1109/icoict66265.2025.11192903
“You Only Look Once (YOLO) is an algorithm that used single-stage detector approach [16] [17].”
YOLOv5-based Flame Detection Algorithm Research
Yang, M., & Liu, X. (2025) · International Conference on Computer Vision, Application, and Algorithm (CVAA) · doi:10.1109/cvaa66438.2025.11193247
“It directly divides the image into grids and predicts the object category and location within each grid [3] .”
GatedFusion-Net: A Lightweight and Efficient Network for RGB-Infrared Object Detection
Li, B. (2025) · International Conference on Computer Vision, Application, and Algorithm (CVAA) · doi:10.1109/cvaa66438.2025.11193384
“To address the speed bottleneck, one-stage methods, represented by YOLO (You Only Look Once) [8] and SSD [9], were developed.”
A remote sensing image object detection method ABS-YOLO based on improved YOLOv11
Xian-yi, W., & Ablameyko, S. (2025) · Proceedings of the National Academy of Sciences of Belarus Physics and Mathematics Series · doi:10.29235/1561-2430-2025-61-3-253-264
Dual-Branch Vehicle Detection Model with Global-Local Feature Fusion
Baoli, W., Siwan, Z., Zhang, J., & Pengfei, G. (2025) · International Journal of Intelligent Transportation Systems Research · doi:10.1007/s13177-025-00544-2
“Single-stage object detection algorithms include the Single Shot MultiBox Detector (SSD) [ 8 ] and the You Only Look Once (YOLO) series [ 9–11 ], which are known for their fast detection speed and strong real-time performance.”
Wang, D., Shi, L., Li, Y., Zhang, B., Yang, G., & Viriri, S. (2025) · Agronomy · doi:10.3390/agronomy15102388 · Cited by 1
Positional Analysis Using Monocular Relative Depth and Angular Estimation
Jois, O., Prakash, A., Rao, A. H., Shreya, B., & Shylaja, S. S. (2025) · International Conference on Information Technology in Asia (CITA) · doi:10.1109/cita66455.2025.11198621 · Cited by 1
“The work of Lee et al. [8], which introduced relative depth maps for depth estimation, further validates the effectiveness of using relative depth ratios in structured environments.”
A Multi-Stage Automatic Framework for Fracture Fragments Segmentation of Zygomatic Bone and Arch
Mo, H., Zhang, R., Liu, R., et al. (2025) · WRC Symposium on Advanced Robotics and Automation (WRC SARA) · doi:10.1109/wrcsara68202.2025.11195022
“…categorized into two types: (1) Two-stage detection models represented by the R-CNN series [18], which require initial region proposal extraction followed by classification; (2) Single-stage detection algorithms like YOLO [19] that achieve faster detection speeds through end-to-end processing.”
Bridging XLUUV and MASS – Technologies for Autonomous Multi-Domain Operations
Rethfeldt, C., Klein, A., Riesner, M., Kurowski, M., Stoppe, J., Schubert, S., & Jeinsch, T. (2025) · Journal of Physics Conference Series · doi:10.1088/1742-6596/3123/1/012019 · Cited by 2
“Conventional detection architectures based on convolutional neural networks (CNN) (e.g. [44, 45]) are inherently resolution-specific in their design.”
Mantri, R., & Khan, R. A. H. (2025) · International Research Journal of Multidisciplinary Technovation · doi:10.54392/irjmt2562
“Since the first model of YOLO i.e. YOLOv1 [23] has released in 2015, multiple additional variants of the same model have been developed by different groups with distinct goals, each building on and improving the previous one [8-10].”
ESD-YOLO: a lightweight adaptive multi-scale object detection algorithm for autonomous driving
Wu, D., Guan, W., Zhang, B., et al. (2026) · Measurement Science and Technology · doi:10.1088/1361-6501/ae6c53
“The other is the One-Stage algorithm, whose representative models include you only look once (YOLO) [12], single shot multibox detector [13], RetinaNet [14], fully convolutional one-stage object detection [15], and DETR [16].”
Optimizing Local Computation in Secure Matrix Multiplication for Outsourced Neural Networks
Diamond, J. P., Lin, A., Cunningham, R. N., Homsi, S., Mitchell, J. D., Pandey, A., & Shen, E. (2025) · IEEE High Performance Extreme Computing Conference · doi:10.1109/hpec67600.2025.11196508 · Cited by 1
“We use a state-of-the-art object detection neural network architecture called YOLO (You Only Look Once) [22], which contains over 100 convolutions.”
Yang, J., Zhang, H., Zhang, W., et al. (2025) · Multimedia Systems · doi:10.1007/s00530-025-02026-7
“Single-stage methods: Models including YOLO [ 10] and SSD [11] streamline detection into a single forward pass, simultaneously predicting classes and spatial locations to achieve higher efficiency.”
Application of YOLOv10 in Detection of Brain Tumour from MRI
Tadipatri, Y. R., Manoj, K., Krishna, R., & Raghavan, R. (2025) · Lecture notes in networks and systems · doi:10.1007/978-981-96-8639-1_23
Lee, J.-W., Yu, G.-H., Lee, J., Shin, B.-K., Han, Y., Lee, H., Jang, J.-H., Kim, J., & Kim, K. Y. (2025) · Journal of Digital Contents Society · doi:10.9728/dcs.2025.26.9.2565
Zhou, H., Meng, Z., & Chen, Y. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-02899-0_5 · Cited by 6
PSH‐YOLO: A Detection Method for Small‐Target Thermal Defects in Porcelain Insulators
Pei, S., Tian, X., Wei-qi, W., Li, K., & Chenlong, H. (2025) · Energy Science & Engineering · doi:10.1002/ese3.70315
Mobile Deep Learning: Delving into the Future of Portable AI
Saleem, T., & Sivakumar, V. (2025) · International Conference on Metaverse and Current Trends in Computing (ICMCTC) · doi:10.1109/icmctc62214.2025.11196529 · Cited by 2
Surface Defect Detection Method Based on a Small Number of Labeled Images
Zakharov, A., Shamshin, M., & Львович, Ж. А. (2025) · Pattern Recognition and Image Analysis · doi:10.1134/s1054661825700282 · Cited by 1
“The most popular one-step methods are SSD [22], YOLO [28], RetinaNet [21], CenterNet [8], etc.”
Grundlagen der Künstlichen Intelligenz
Plafky, C. S., & Badertscher, H. (2025) · Springer eBooks · doi:10.1007/978-3-658-49009-6_3
An RGBD Fused Real Time Defect Detection and Size Estimation Method for Sewer RobotsPreprint
Shen, W., ZHANG, J., Wei-ming, J., & Song, A. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5616445
Lu, Z., Wang, X., Liu, S., Yang, Z., Li, H., & He, X. (2025) · SAE technical papers on CD-ROM/SAE technical paper series · doi:10.4271/2025-99-0060
Zhang, Y., Gao, R. H., Ji, M., Zhang, W., Yu, W., & Wang, X. (2025) · Forests · doi:10.3390/f16101595
“Detectors are generally divided into one-stage methods [12] and two-stage methods [13].”
Research on the Safety Judgment of Cuplok Scaffolding Based on the Principle of Image Recognition
Jiang, X., Bai, S., Ruan, G., et al. (2025) · Buildings · doi:10.3390/buildings15203737
Implementation of a Fire Detection System Based on YOLOv5
Lin, Y.-C., Luo, S. N., Kuan, T.-W., et al. (2025) · Smart innovation, systems and technologies · doi:10.1007/978-981-96-7277-6_27
Smart Waste Management: A Case Study on Garbage Container Detection
Köroğlu, F. E., Çakmak, S., Yurtsever, M. M. E., et al. (2025) · Lecture notes in networks and systems · doi:10.1007/978-3-031-90893-4_59
Ambigapathy, N., Idrees, F., Glöwing, K., et al. (2025) · IFIP advances in information and communication technology · doi:10.1007/978-3-032-07102-6_7
Mukisa, R., & Bansal, A. K. (2025) · Lecture notes in networks and systems · doi:10.1007/978-3-032-07995-4_26
Choupani, R., & Doğan, H. (2025) · Lecture notes in networks and systems · doi:10.1007/978-3-032-07995-4_30
Saxena, K., Singh, A., & Saraswat, M. (2025) · Lecture notes in networks and systems · doi:10.1007/978-3-032-04222-4_4
LAXMI: a novel AI-based system for smart, energy-efficient, and secure video footage processing
Bhattacharya, T., Ponaganti, S., Vardhan, A. H., & Venkatesan, Y. S. (2025) · The Journal of Supercomputing · doi:10.1007/s11227-025-07900-9 · Cited by 1
Comparative Evaluation of Anchor-Based YOLOv11 and Anchor-Free FCOS for Small-Object UAV Detection
Yücel, H. İ., Özer, İ., & Dalcalı, A. (2025) · Mühendislik Bilimleri ve Araştırmaları Dergisi · doi:10.46387/bjesr.1739026
KFW-DETR: A Fabric Defect Detection Model Based on RT-DETRPreprint
Zhao, F., Cao, L., & Han, W. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5626140
APPLICATION OF GENERATIVE AI-BASED DATA AUGMENTATION TO RIVERINE FLOATING LITTER DETECTION MODELS
KADOWAKI, D., NAKATANI, Y., & Tatsuya, K. A. I. (2025) · Japanese Journal of JSCE · doi:10.2208/jscejj.25-00172
DPDN-YOLOv8: A Method for Dense Pedestrian Detection in Complex Environments
Liu, Y., Xu, L., Li, B., Lin, Z., & Yuan, D. (2025) · Mathematics · doi:10.3390/math13203325 · Cited by 1
Utilizing the YOLOv8 model for accurate hand recognition with complex background
Purnomo, H., Dewi, C., Kristanto, B., Hartomo, K. D., & Hashim, S. Z. M. (2025) · PeerJ Computer Science · doi:10.7717/peerj-cs.3244 · Cited by 4
Development of an open-source artificial intelligence (AI) anonymizer for electrocardiogram scansPreprint
Tse, G., Liu, H., Aranda, A. A. P., Wong, W. T., Lee, S., Liu, T., Roy, V. A. L., Milovanović, B., & Beni, M. S. (2025) · medRxiv · doi:10.1101/2025.10.19.25338291
ParkIT: Vision-Based Intelligent Parking System
́oci, S. G. G., Zemko, L., Bunca, D. ́., et al. (2025) · Communication and Information Technologies (KIT) · doi:10.1109/kit67756.2025.11205456
“Traditional meth-ods like background subtraction or motion segmentation have been mainly replaced by Convolutional Neural Network (CNN)-based detectors due to their superior performance and robustness [5].”
An Unmanned Surface Vessel Target Detection Algorithm and Lightweight Design
Luo, K., & Zhang, X. (2025) · International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD) · doi:10.1109/icnc-fskd67701.2025.11197999
“The classical one-stage target detection algorithms are YOLO [1] (You Look Only Once) proposed by Redmon et al. and SSD (Single Shot MultiBox Detector) proposed by Liu et al [2] .”
Robust Pedestrian Detection for Autonomous Vehicles Using a Fortified Network Model
Tsai, Y.-Y., & Chang, H.-H. (2025) · International Conference on Man-Machine Systems (ICoMMS) · doi:10.1109/icomms66553.2025.11200432
“One famous technique has been the you-only-look-once (YOLO) [29], which uses a single neural network to process the whole image by dividing it into multiple regions to simultaneously predict the probability and bounding boxes.”
Human Scanpath Prediction in Target-Present Visual Search with Semantic-Foveal Bayesian Attention
Luzio, J., Bernardino, A. J. M., & Moreno, P. (2025) · IEEE International Conference on Development and Learning (ICDL) · doi:10.1109/icdl63968.2025.11204443
“Hence, we incorporate YOLO [19], a state-of-the-art deep detection algorithm, in our methodology to generate object predictions.”
Li, X., Di, X., Liu, M., & Ye, S. (2025) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2025.104519 · Cited by 3
Real-Time Lion Detection In Forest Near Village Area Using YOLO
Jain, R., Kher, P., & Bhatt, C. (2025) · International Conference on Artificial Intelligence and Machine Vision (AIMV) · doi:10.1109/aimv66517.2025.11203611
“Initially introduced in a paper by Redmon et al. in 2016 [9], subsequent iterations such as YOLOv2 [10], YOLOv3, and the latest YOLOv8 [11] [6] have brought significant advancements in object detection capabilities.”
Two-stage Adaptive Traffic Detection System for Adverse Weather
Yu, J., Zhang, M., Yu, X., et al. (2025) · International Joint Conference on Information and Communication Engineering (JCICE) · doi:10.1109/jcice66205.2025.11182043
“Another influential family of methods was the YOLO (You Only Look Once) series [14], which first emerged in 2015 by reimagining object detection as a direct regression task handled by a solitary neural network.”
A Comparative Study of YOLOv8 Models for Road Object Detection
Patel, V., Sarda, J. S., Thakkar, A. R., et al. (2025) · International Conference on Artificial Intelligence and Machine Vision (AIMV) · doi:10.1109/aimv66517.2025.11203387
Mixture of Experts Detection System for Enhanced Automatic Annotation in Photovoltaic Modules
Santos, B., de Pinho, L. S., Sousa, T., et al. (2025) · IEEE International Conference on Emerging Technologies and Factory Automation (ETFA) · doi:10.1109/etfa65518.2025.11205660
“YOLO frames detection as a single regression problem, directly outputting box coordinates and class probabilities from full-image features in one evaluation [2].”
Hosseini, S. M. M., Depaoli, F., Ponzio, F., et al. (2025) · IEEE International Conference on Emerging Technologies and Factory Automation (ETFA) · doi:10.1109/etfa65518.2025.11205639
“…main components: the box loss (Box) , that penalizes errors in the bounding box prediction, the classification loss (Cls) , which penalizes errors in the object type, and distribution focal loss (DFL) , that applies a modulating term in order to focus learning on hard misclassified examples [6].”
InfluentialJun, A., Rahiman, M. H. F., Nayan, N. M., et al. (2025) · doi:10.1109/icomms66553.2025.11200363
“This solution improves pricing accuracy, minimizes reliance on manual labour, and offers a low-cost, offline alternative for small-scale restaurant automation [1], [6], [12].”
Plug-and-Play One-Shot Object Detection Framework for Industrial Applications
Yahya, M., Civitelli, E., Longo, N., & Rizzo, A. (2025) · IEEE International Conference on Emerging Technologies and Factory Automation (ETFA) · doi:10.1109/etfa65518.2025.11205589
“Traditional object detection methods [2], [20], [22], [24], including region-based convolutional networks and transformer-based detectors, encounter challenges in incorporating new object categories.”
Research on Power Line Insulator Defect Detection Method Based on TR-MobileViTcense
Su, S., Zhou, Z., Liu, J., et al. (2025) · doi:10.1109/spml66318.2025.11199753
Robust ViT-enhanced Detection of Sacrificial Anodes in Harsh Underwater Conditions
da Costa, A. V. M., Leite, P. N., & Pinto, A. M. (2025) · IEEE International Conference on Emerging Technologies and Factory Automation (ETFA) · doi:10.1109/etfa65518.2025.11205766
“While models like YOLO [10] [8] [9] and RT-DETR [5] [6] have achieved considerable success in various domains, their direct use in detecting complex and variable underwater structures like anodes is limited and potentially suboptimal.”
Lu, Y., & He, C. (2025) · International Conference on Artificial Intelligence, Internet of Things and Cloud Computing Technology (AIoTC) · doi:10.1109/aiotc66747.2025.11198641
“Against this backdrop, YOLACT [4], drawing inspiration from the YOLO series [5], introduced a pioneering parallel design.”
Siering, T., Steidel, M., & Steger, C. (2025) · Journal of Marine Science and Engineering · doi:10.3390/jmse13102015
FE-YOLO: A Feature Enhancement Model for Remote Sensing Object Detection
Jin, B., Cai, W., Li, H., et al. (2025) · Mechanisms and machine science · doi:10.1007/978-3-031-96732-0_90
Aman, S. S., N'GUESSAN, B. G., Prosper, K. K., & Tiémoman, K. (2025) · Discover Applied Sciences · doi:10.1007/s42452-025-07784-7 · Cited by 1
“Introduced by [28], YOLOv1 proposed a unified framework that simultaneously predicted object classes and locations from a single pass through the network, offering unprecedented speed.”
MRI-Based Brain Tumor Classification Using YOLOv8
Swaminathan, N. K., Rajasekaran, G. R., Rama, V. P. S., et al. (2025) · Springer eBooks · doi:10.1007/978-981-96-9342-9_23
AI-Based Computer Vision Methods to Monitor Emission-Relevant Parameters in Livestock Barns
Mielke, S. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-03281-2_31
Research on Intelligent Management and Control of Production Workshop Based on Deep Learning
柴, 政. (2025) · Hans Journal of Data Mining · doi:10.12677/hjdm.2025.154028
Drainage Pipe Defect Detection and Effect Analysis Based on Improved YOLOv8_DGW
Wang, J., Cui, Z., Wang, H., et al. (2025) · Journal of Pipeline Systems Engineering and Practice · doi:10.1061/jpsea2.pseng-1907
Mud Volcano Detection Algorithm Based on Multiscale Dynamic Sensory Field Mechanism
Qian, Y., Ye, B., Tian, X., & Li, C. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2025.3624086
Li, C.-H., & Hou, H.-S. (2025) · Proceedings of Engineering and Technology Innovation · doi:10.46604/peti.2025.15264 · Cited by 1
A Wavelet-Based Bilateral Segmentation Study for Nanowires
Hou, Y., Zhang, Y., Liang, F., et al. (2025) · Nanomaterials · doi:10.3390/nano15211612
“Linmao Li et al. [29] integrated Mask R-CNN [30] and YOLO [31] to identify and segment nanowire structures in SEM images.”
Hierarchical instance distillation to enhance lightweight object detectors
Liu, Z., & Liu, Y. (2025) · Soft Computing · doi:10.1007/s00500-025-10893-5
Sung, Y.-T., Kim, S., Park, N., Park, G., & Park, J. (2025) · Transportation Research Record Journal of the Transportation Research Board · doi:10.1177/03611981251378132
“It was first published by Redmon et al. ( 21 ) and has gone through several version updates.”
Forest Fire and Smoke Recognition Based on YOLO
He, L., Yu, K., Han, B., et al. (2025) · International Conference on Image, Vision and Computing (ICIVC) · doi:10.1109/icivc66358.2025.11200295
Integrating Knowledge for High-Fidelity Remote Sensing Detection of Cross-River Bridges
Chen, L., Qi, Y., Sun, R., Zhou, H., & Zhang, X. (2025) · International Conference on Image, Vision and Computing (ICIVC) · doi:10.1109/icivc66358.2025.11200418 · Cited by 1
“Meanwhile, real-time object detection algorithms like YOLO (You Only Look Once) gained popularity due to their speed advantages, enabling real-time detection in various applications [9].”
Tan, Y. K., Chin, K. M., Goh, Y. H., Chiew, T. H., Ting, T. S. H., Ma, G., & How, C. K. (2025) · International Conference on Image, Vision and Computing (ICIVC) · doi:10.1109/icivc66358.2025.11200265
“First introduced by Redmon et al. [13] in 2015, YOLO was developed to address the slow detection speeds typical of two-stage object detectors, which require a separate region proposal process.”
An Improved YOLOv8n Algorithm for Small Object Detection in Road Scenes
Song, Q., & Yu, F. (2025) · International Conference on Image, Vision and Computing (ICIVC) · doi:10.1109/icivc66358.2025.11200259
“In contrast, one-stage algorithms such as the YOLO series [7] , SSD [8] , and RetinaNet [9] directly predict object locations and categories in an end-to-end manner, simplifying the detection process and improving detection efficiency, making them suitable for intelligent transportation and…”
Zhang, J., Qian, X., Wang, Y., & Xie, J. (2025) · International Conference on Image, Vision and Computing (ICIVC) · doi:10.1109/icivc66358.2025.11200361
“The YOLOv5s model is a deep learning-based object detection algorithm [1] [2] used for identifying and locating objects within images.”
A Real-Time Detection Method for Surface Defects in 3D Printing Based on YOLOv12 Algorithm
Li, X., Zhang, C., Xu, B., et al. (2025) · International Conference on Image, Vision and Computing (ICIVC) · doi:10.1109/icivc66358.2025.11200408
“The YOLO object detection algorithm [9] divides the input image into an S × S grid, where each grid is responsible for predicting targets whose center points fall within that area.”
Wang, Z., Jiang, J., Li, Y., Cheng, G., Yuan, G., & Wang, S. (2025) · International Conference on Image, Vision and Computing (ICIVC) · doi:10.1109/icivc66358.2025.11200347
“Single-stage detectors, exemplified by YOLO [19]–[21] and SSD [22], adopt a dense gridding strategy to directly generate bounding boxes and class information for objects in images.”
Lychee13-3634: A new lychee image dataset and classification methodological evaluation
Luo, S., Zheng, H., Lin, Z., Zeng, T., Huang, M., Xiao, Y. F., Grau, A., & Huang, J. (2025) · PLoS ONE · doi:10.1371/journal.pone.0334900
Ganie, S. H., Chen, X.-Z., & Chen, Y. (2025) · IEEE Sensors Journal · doi:10.1109/jsen.2025.3623087
“Deep learning technology has been extended to object detection, with notable models such as Faster R-CNN [8], YOLO series [5], [6], [9], [10], [11], [12], [52] utilizing sensor data, primarily camera offering stable detection capabilities surpassing traditional computer vision methods.”
A computer vision-based heuristic framework for estimating traffic sign visibility
Naskar, A. K., & Saha, P. (2026) · Transportation Letters · doi:10.1080/19427867.2026.2680236 · Cited by 1
Zhao, Y., Rose, R. A. C., Choy, L. K., et al. (2025) · International Journal of Pattern Recognition and Artificial Intelligence · doi:10.1142/s0218001425550183
DCD-YOLO: An Improved YOLOv11n Algorithm \for Traffic Participant DetectionPreprint
Lu, X., Wang, D., Xiong, R., Lv, X., Chen, Y., & Li, S. (2025) · Research Square · doi:10.21203/rs.3.rs-7771542/v1
Underwater Object Detection Using YOLOv8 Enhanced with Region-based Feature Aggregation Attention
Yang, R. (2025) · International Journal of Computer Science and Information Technology · doi:10.62051/ijcsit.v7n1.06
Clavero, C., Patricio, M. A., García, J., & Molina, J. M. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.130003 · Cited by 4
AI-Driven Predictive Analytics for Threat Assessment
Singh, H., Bishnoi, A., & Chandra, S. (2025) · Contributions to security and defence studies · doi:10.1007/978-3-031-99235-3_12
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.