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 34,301–34,400 of 51,399
Poleshchenko, D., Михайлов, Ю. В., & Petrov, V. A. (2025) · Communications in computer and information science · doi:10.1007/978-3-032-04764-9_1 · Cited by 1
Itzamná: A Prototype for Accessible Mobility Analysis with AI Using Sensor Data
Plata-Salinas, E.-O., Trejo-Arriaga, R.-G., Hernández-Hernández, A., et al. (2025) · Communications in computer and information science · doi:10.1007/978-3-032-09738-5_23 · Cited by 1
NCENet: Nonlinear Contrast Enhancement Network for infrared small target detection
Wu, C., Zhang, Y., Wu, J., et al. (2025) · Infrared Physics & Technology · doi:10.1016/j.infrared.2025.106241 · Cited by 1
Elnady, M., & Ožana, Š. (2026) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2026.105610 · Cited by 2
Eliza, A., & Baskaran, D. (2025) · Aquacultural Engineering · doi:10.1016/j.aquaeng.2025.102659 · Cited by 1
Mmereki, W., Jamisola, R. S., Jewell, Z. C., et al. (2025) · Forensic Sciences · doi:10.3390/forensicsci5040056 · Cited by 1
“YOLO is an object detection algorithm that processes the entire image in a single pass to detect objects and their locations [44].”
Perimeter Security Utilizing Thermal Object Detection
Orfanidis, G., Ioannidis, K., Vrochidis, S., & Kompatsiaris, I. Y. (2025) · Sensors · doi:10.3390/s25216680 · Cited by 1
“Pioneering works include Faster RCNN [1], Single Shot Detector (SSD) [2]—an innovative single-step network, and You Only Look Once (Yolo)—an efficient oriented model [3].”
Kim, D. H., Jo, M., Kim, G., Ha, D. G., Oh, U. B., Ko, D. H., Lee, J., Kang, M., & Jung, S. (2025) · IEEE Journal of Solid-State Circuits · doi:10.1109/jssc.2025.3623117 · Cited by 1
“R ECENTLY, deep learning has been widely applied to various tasks in artificial intelligence (AI), such as computer vision [1], natural language processing [2], and object detection [3].”
Thyagarajan, C., Yogadinesh, S., Krishnamoorthy, M., et al. (2025) · doi:10.1109/iccds64403.2025.11209560 · Cited by 1
“One of the most popular models, YOLO (You Only Look Once), is particularly favored for its rapid processing speed and accuracy [1], [2].”
Visual Moral Inference and Communication
Zhu, W., Ramezani, A., & Xu, Y. (2025) · Annual Meeting of the Cognitive Science Society · doi:10.1111/tops.70031 · Cited by 1
“Here we summarize the landscape of the literature relevant to the development of our framework.”
PICU Face and Thoracoabdominal Detection Using Self-Supervised Divided Space–Time Mamba
Salah, M., Jouvet, P. A., & Noumeir, R. (2025) · Life · doi:10.3390/life15111706 · Cited by 1
“Single-stage detectors, including the YOLO family of models [25–27] and the Single Shot Multibox Detector (SSD) [28], and highly efficient architectures like EfficientDet [29], emerged as faster alternatives by predicting bounding boxes and class probabilities in a single pass.”
Zhao, Y., Lu, J., Xu, J., Miu, J., & Hua, H. (2025) · Signals · doi:10.3390/signals6040063 · Cited by 1
“The YOLO series algorithms developed by Redmon et al. [13–15] in 2015 pioneered the single-stage detection paradigm, achieving real-time detection speeds through end-to-end training, followed by subsequent versions like YOLOv2 and YOLOv3.”
Local Vectorized High Definition Map Construction for Autonomous Driving: A Comprehensive Review
Zhang, Y., Qian, Y., Meng, C., Zhang, R., Yi, H., Wang, C., & Yang, M. Z. (2025) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2025.3623833 · Cited by 2
“Examples include single-stage networks like YOLO [35] and two-stage networks such as Mask R-CNN [36], as well as bottom-up approaches like SIS [37].”
Multi-Dimensional Statistical Attention for Target Detection With Channel Weights and Spatial Cross
Ding, Y., He, W., Chen, Y., & Zhang, J. (2025) · International Conference on Mechatronics and Computer Technology Engineering (MCTE) · doi:10.1109/mcte67374.2025.11213841 · Cited by 1
“Based on the yolo11-nano baseline model [11,12], we used the NEU-DET dataset provided by Northeastern University for object detection training and testing.”
Large Vision-Language Model-Assisted Information-Rich Semantic Segmentation
Liu, H., Huang, S., Sun, C., Pompili, D., & Gong, J. (2025) · IEEE International Conference on Mobile Ad-Hoc and Sensor Systems (MASS) · doi:10.1109/mass66014.2025.00029 · Cited by 1
“Models such as You Only Look Once (YOLO) [10] have advanced the field by providing segmentation masks and associated class labels, allowing systems not only to locate but also to identify objects within an image.”
Autonomous classification of wave breaker type in a large wave flume
Robertson, I., Alvaro, A., Verma, S., Jones, B., Levy, J., Gökdepe, M., & Huang, Z. (2025) · Coastal Engineering · doi:10.1016/j.coastaleng.2025.104902 · Cited by 1
Detection of anomalous activities around telecommunications infrastructure based on YOLOv8s
Edozie, E., Shuaibu, A. N., John, U. K., & Sadiq, B. O. (2025) · Scientific Reports · doi:10.1038/s41598-025-22680-1 · Cited by 2
“YOLOv8 (You Only Look Once version 8) is a cutting-edge one-stage object detection method that transforms the object detection task into a regression issue, considerably increasing speed and accuracy over prior versions 30 .”
Xiao, C., & Chen, C. (2025) · Indoor Environments · doi:10.1016/j.indenv.2025.100135 · Cited by 1
A bird target detection model designed for substation scenarios
Shao, C. Y., Huang, J., Fan, X., et al. (2025) · Scientific Reports · doi:10.1038/s41598-025-22829-y · Cited by 1
DMC-YOLOv11: an improved pavement damage detection model based on YOLOv11
Li, B., Wang, K., Liu, Z., Huang, M., & Zhang, S. (2025) · Systems Science & Control Engineering · doi:10.1080/21642583.2025.2579987 · Cited by 6
“Popular single-stage models include YOLO (Redmon et al., 2016), Single Shot Multibox Detector (SSD) (W. Liu et al., 2016), and RetinaNet (Lin et al., 2017).”
You, D., Bingbing, Z., Lei, D., & Mao, Y. (2025) · The Journal of Supercomputing · doi:10.1007/s11227-025-08026-8 · Cited by 4
“The YOLO model, originally designed by Redmon et al. in 2016 as the YOLOv1 version [49], transforms target detection into a simple regression task and uses a convolutional architecture to simultaneously predict multiple bounding boxes and category confidence scores, greatly improving detection…”
Swift-YOLO: A Lightweight Architecture for Small Target Detection in Drone Optical Sensors
Sui, Q., Hosoda, Y., & Lee, J. (2025) · IEEE Sensors Journal · doi:10.1109/jsen.2025.3628166 · Cited by 3
“Shallow features use a small-size convolution kernel combination of [ 1 , 3 , 5 ] , middle-layer features use a medium size of [ 3 , 5 , 7 ] , and deep features use a large size of [ 5 , 7 , 9 ] .”
Artificial Intelligence–Based Evaluation System With Domain Adaptation for Ultrathin Wafer Detaping
Jan, G. E., Wu, H.-L., Zhao, J.-X., et al. (2025) · IEEE Transactions on Semiconductor Manufacturing · doi:10.1109/tsm.2025.3630127 · Cited by 1
“Unlike these approaches, one-stage detection methods, as represented by the YOLO model proposed by Redmon et al. in 2016 [10], can directly predict object categories and locations through a single neural network, considerably increasing detection speed.”
OFIA: An Object-centric Fine-grained Alignment Enhancement for Video-Text Retrieval
Huang, Z., Li, W., Dong, C., & Liu, M. (2025) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3746252.3761041 · Cited by 1
“Closed-set object detection involves identifying objects within pre-defined categories, where CNN was served a prominent backbone in prior works [33, 34] in the domain of closed-set object detection.”
Xu, J., Jiang, W., Wang, L., Wang, H., Wu, J., Shen, Y., Zhu, C., Hao, S., & Liu, C. (2025) · Information Processing in Agriculture · doi:10.1016/j.inpa.2025.10.003 · Cited by 35
Do, T. T., Nguyen, B. D., Nguyen, D. D., et al. (2025) · Communications in computer and information science · doi:10.1007/978-3-032-10209-6_2 · Cited by 1
Liu, N., Liu, S., Feng, K., Jia, L., & Kong, B. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.113091 · Cited by 1
Xu, Y., Zhao, X., & Xiao, X. (2025) · Journal of Real-Time Image Processing · doi:10.1007/s11554-025-01798-5 · Cited by 1
Zhang, H., Dong, Y., Hou, Y., et al. (2025) · Infrastructures · doi:10.3390/infrastructures10110299 · Cited by 1
FDW-YOLO: An Improved YOLOv12 for Oracle Bone Inscriptions Detection
Xiong, R., Liu, J., Zhang, S., et al. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-4378-6_18 · Cited by 1
Yang, X., Mao, J., Kong, S., & Lin, P. (2025) · The Journal of Supercomputing · doi:10.1007/s11227-025-08041-9 · Cited by 1
“Regarding real-time deployment feasibility, the obtained FPS (32.5/34.2) indicates that the model can process over 30 frames per second on a standard GPU, which satisfies the requirement for many real-time applications [47].”
InfluentialUncertainty Quantification for Semi-Supervised Object Detection in Remote Sensing Images
Yang, X., Li, P., Zhou, Q., Wang, N., & Gao, X. (2025) · IEEE Transactions on Image Processing · doi:10.1109/tip.2025.3629033 · Cited by 2
GaitAsset: In Defense of Regarding Gait as a Set
Hou, S., Wang, C., Li, A., Wang, J., Wang, L., & Huang, Y. (2025) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2025.3630892 · Cited by 4
An artificial intelligence-based approach for human parasite egg segmentation and classification
Mondal, S. K., Islam, M., & Yusuf, M. S. U. (2025) · Healthcare Analytics · doi:10.1016/j.health.2025.100432 · Cited by 1
Liang, G., Shi, J., Liu, Y., et al. (2025) · Transportation Research Record Journal of the Transportation Research Board · doi:10.1177/03611981251367704 · Cited by 1
“The YOLOv8 is a version of YOLO ( 49 ), which represents the next major update to the YOLOv5 series released by Ultralytics on January 10, 2023.”
AI-Driven Vehicle Damage Detection: A Saliency-Based Segmentation Approach
Khalid, S., Aamir, M., Ayaz, H., et al. (2025) · doi:10.1109/ipta66025.2025.11222026 · Cited by 1
“One-stage detectors such as YOLO [2] have been adapted to detect damage regions in car images.”
A lightweight detection model for gummosis on tree branches based on an improved YOLO algorithm
Zhang, P., Ma, Z., Yang, Y., Zhang, C., & Li, S. (2025) · Scientific Reports · doi:10.1038/s41598-025-23357-5 · Cited by 1
Few-Shot Learning for CT Lung Nodule Detection Based on Open-Set Object Detection
Li, L.-M., Zhang, H., Yu, H.-T., Cui, B., & Wang, Z. (2025) · Current Medical Science · doi:10.1007/s11596-025-00135-y · Cited by 1
“In particular, single-stage object detection methods like You Only Look Once (YOLO) series [15–17] have advanced rapidly, enabling real-time applications and gaining wide adoption in medical image detection in recent years [18–22].”
Automated Synthetic Data for Computer Vision: Blender-COCO Pipeline Enhancing Yolov8
Souza, V. R., Christ, D. C. F., Wiese, I., et al. (2025) · SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI) · doi:10.1109/sibgrapi67909.2025.11223399 · Cited by 1
“A. YOLO Algorithm YOLO (You Only Look Once) performs object detection through a single forward pass of a convolutional neural network, partitioning the input image into a grid and simultaneously predicting bounding boxes and class probabilities for each cell [8], [9].”
A Synthetic Data Pipeline for Supporting Manufacturing SMEs in Visual Assembly Control
Werheid, J., He, S., Gannouni, A., et al. (2025) · doi:10.1109/gaclm67198.2025.11232427 · Cited by 1
“The camera resolution is fixed at 640×640, as this resolution provides a good balance between computational efficiency and object detection accuracy for the YOLO-series algorithms [29].”
Investigating Traffic Accident Detection by Using Multimodal Large Language Models
Skender, I., Tong, K., Solmaz, S., et al. (2025) · IEEE International Automated Vehicle Validation Conference (IAVVC) · doi:10.1109/iavvc61942.2025.11219530 · Cited by 1
“Various approaches have used the YOLO detector [9] previously, among which are YOLOv4 [10] and YOLOv5 [11].”
Li, C., Liu, S., & Peng, Z. (2025) · PLoS ONE · doi:10.1371/journal.pone.0336863 · Cited by 5
“In 2016, Redmon et al. [6] introduced the YOLOv1, the first work in the YOLO series, which became the first real-time, end-to-end object detector.”
Wang, H., Gao, G., Zhang, W., Li, K., Che, N., Yan, C., & Wang, L. (2025) · Sensors · doi:10.3390/s25226972 · Cited by 3
Computer Vision for Cover Crop Seed-Mix Detection and Quantification
Kumari, K., Won, K., & Nafchi, A. M. (2025) · Seeds · doi:10.3390/seeds4040059 · Cited by 1
Mizoguchi, T. (2025) · Sensors · doi:10.3390/s25226937 · Cited by 1
“In recent years, in the field of object recognition, methods that simultaneously perform object detection and classification, such as YOLO [37], have become mainstream.”
AI-Driven Collaborative Satellite Object Detection for Space Sustainability
Hu, P., & Zhang, W. (2025) · IEEE International Conference on Wireless for Space and Extreme Environments (WiSEE) · doi:10.1109/wisee57913.2025.11229836 · Cited by 1
“Among the most widely used CNN-based architectures are Faster R-CNN [10] and the You Only Look Once (YOLO) family of models [6].”
MOT-STM: Maritime Object Tracking: A Spatial-Temporal and Metadata-based approach
Nageli, V. S., Jamal, A., Goyal, P., & Gorthi, R. K. (2025) · Image and Vision Computing · doi:10.1016/j.imavis.2025.105826 · Cited by 3
Ye, C., Chen, W., & Zhao, L. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11228124 · Cited by 1
“YOLOv1 [10] uses single-stage detection, which is fast, but the detection of small objects is poor.”
Stealthy Backdoor Attack against Object Detection
Ning, X., Xie, Q., Xu, J., Jiang, W., Liu, X., Li, J., & Ma, Y. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11227680 · Cited by 2
“One-stage detectors, such as YOLO series [5], [12], [13], and SSD [14] directly predict object classes and locations.”
ARNet: An Aggregation and Recalibration Network for Small Object Detection in Aerial Imagery
Deng, X., Zheng, X., Yang, W., Li, Z., & Zhou, T. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11227755 · Cited by 2
Industrial Digital Twin Integration with ERP and Computer Vision for Real-Time Synchronization
Ali, I., Badr, H., Yasser, H., et al. (2025) · Novel Intelligent and Leading Emerging Sciences Conference (NILES) · doi:10.1109/niles68063.2025.11231848 · Cited by 1
“Another key pillar of Industry 4.0 is the adoption of AI-powered perception systems , particularly computer vision, to replace or augment traditional sensor networks [3].”
InfluentialGuo, T., Song, Q., Xue, Y., & Qiao, F. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11228989 · Cited by 3
“The emergence of models like Faster R-CNN [1] and YOLO [2] signifies the extensive application of deep learning in UAV target detection tasks.”
Rethinking Multi-scale Feature Enhancement and Learning Mechanism for Real-time Object Detection
Li, C., & Zhang, T. (2025) · doi:10.1109/ijcnn64981.2025.11228253 · Cited by 1
“Some popular deep learning object detection algorithms, such as R-CNN (Region-based Convolutional Neural Networks) series [2], [5]–[7], YOLO (You Only Look Once) [1], [8], Reti-naNet [3], and FCOS [4], have made substantial improvements in both accuracy and speed.”
EAS-YOLOv5: Enhancing YOLOv5’s Attention on Small Objects via Large Objects
Li, Y., Zhou, P., Du, J., & Zhu, J. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11228789 · Cited by 1
“As one-stage method, the YOLO (You Only Look Once) [8] series has been updated to YOLOv11 [9].”
Neuromorphic eye tracking: a survey
Mentasti, S., Simpsi, A., Aspesi, A., Tognoli, A., Merigo, L., & Matteucci, M. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11229414 · Cited by 1
“It demonstrates that transforming event data into frame format enables robust integration with deep-learning-based models like YOLO [23].”
YOLOv8 model for monitoring ghout degradation in the El Oued region, southeastern Algeria
Lacheheb, F. M., Mega, N., Seddiki, A. M., et al. (2025) · RENDICONTI LINCEI · doi:10.1007/s12210-025-01379-5 · Cited by 1
“YOLOv8’s improved architecture, with higher frames per second (FPS) and lower inference times compared to models like R-CNN or SSD (Girshick 2015 ; Redmon et al. 2016 ), makes it ideal for monitoring dynamic ecosystems like the Ghouts.”
Multimodal Data Fusion and Deep Learning for Predicting Air Pollution at Construction Sites
Zhang, R., Sapkota, J., & Krall, J. R. (2025) · Journal of Computing in Civil Engineering · doi:10.1061/jccee5.cpeng-7003 · Cited by 3
Concrete slump detection based on light-AWGAM-YOLOv8n
Hao, Y., Hao, Y., Wang, B., et al. (2025) · Scientific Reports · doi:10.1038/s41598-025-23983-z · Cited by 1
TOODIB: Task-aligned one-stage object detection with interactions between branches
Chen, S., Hu, Q., Zhu, M., Wu, Q., & Hu, X. G. (2025) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2025.104567 · Cited by 1
Lin, K., Zhao, Z., & Niu, N. (2025) · Remote Sensing · doi:10.3390/rs17223750 · Cited by 3
A Modular Algorithmic Architecture for Small UAV Detection and Tracking
Smith, E., & Diskin, Y. (2025) · IEEE National Aerospace and Electronics Conference (NAECON) · doi:10.1109/naecon65708.2025.11235331 · Cited by 1
“Recent efforts have focused on leveraging computer vision and machine learning techniques, especially convolutional neural networks (CNNs) [1]–[4] and vision transformers (ViTs) [5]–[10], for this purpose.”
Real-Time Traffic Signal Optimization with Bi-LSTM: A Case Study at KIIT University, Bhubaneswar
Haq, S., Mishra, S. R., Sinha, R., Dhabhai, H., Singh, A., & Rani, A. (2025) · International Conference on Next Generation of Green Information and Emerging Technologies (GIET) · doi:10.1109/giet65294.2025.11234826 · Cited by 1
“Their model processed video at 45 FPS with high precision, laying the groundwork for traffic applications [9].”
An Improved YOLOv11-Based Method for Defect Detection in Lyophilized Vial
Jiang, D., Zhu, K., Tao, N., et al. (2025) · Electronics · doi:10.3390/electronics14224526 · Cited by 1
Li, H., Huang, B., & Lv, J. (2025) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2025.3634593 · Cited by 1
Multi-task class-aware adversarial training for remote sensing object detection robustness
Ci, Z., Liu, Z., Song, Y., et al. (2025) · Connection Science · doi:10.1080/09540091.2025.2581373 · Cited by 1
“BCE loss compares the predicted object confidence score with the ground truth label indicating the presence or absence of an object, calculating the probability of the object’s existence within the predicted bounding box.”
InfluentialAn investigation of visual foundation models robustness
Gupta, S. K., & Passerone, R. (2025) · Machine Learning · doi:10.1007/s10994-025-06853-7 · Cited by 4
“ResNet introduces residual connections to enable training of deeper networks.”
InfluentialYu, Y., Li, Y., & Li, S. (2025) · Fishes · doi:10.3390/fishes10110592 · Cited by 2
Wu, L., Wang, Z., Zheng, Z., Ke, X., Zhou, Z., Zuo, P., Zheng, Z., & Wu, P. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.130468 · Cited by 3
Improved RT-DETR pedestrian detection system for dense occlusion in surveillance scenes
Kong, X., Li, J., Wu, J., et al. (2025) · doi:10.1109/icamtms66452.2025.11239795 · Cited by 1
“Among them, the two-stage algorithm is represented by the R-CNN series ( such as Faster R-CNN [5] , Mask R-CNN [6] ) ; single-stage algorithms include SSD [7] , YOLO [8] and DETR [9] series (such as RT-DETR [10] ).”
PCOS Detection Using YOLOv8 in Ultrasound Imaging
Krithik Naren, S., Rajakumar, K., Vs, S., Jayakanthan, O., Kasetty, S. B., & Margret, I. N. (2025) · International Conference on Circuits, Power and Intelligent Systems (CCPIS) · doi:10.1109/ccpis65231.2025.11234253 · Cited by 1
“CNNs – Convolutional neural networks, established as a potent Dl framework, have made enormous strides in the examination of medical images, with further improving feature extraction capability [6].”
AI-Driven Waste Detection in Russia: Towards a National Environmental Monitoring System
Макаров, А. А., & Shabunin, A. (2025) · Conference of Open Innovations Association (FRUCT) · doi:10.23919/fruct67853.2025.11239218 · Cited by 1
Better early detector for high-performance detection transformer
Hu, B., Liao, B., Qi, J., Yang, S., & Liu, W. (2025) · Image and Vision Computing · doi:10.1016/j.imavis.2025.105829 · Cited by 2
Kwon, D., Lee, J., Kim, J., Kim, J. W., Yoon, S., Jeong, S., & Oh, C. (2025) · Mathematics · doi:10.3390/math13223720 · Cited by 1
KFGOD: A Fine-Grained Object Detection Dataset in KOMPSAT Satellite Imagery
Lee, D., Hong, J. H., Seo, H. W., & Oh, H. (2025) · Remote Sensing · doi:10.3390/rs17223774 · Cited by 3
Semantics-Driven 3D Scene Retrieval via Joint Loss Deep Learning
Yuan, J., Wang, T., Zhe, S., Lu, Y., Zhou, Z., & Li, B. (2025) · Mathematics · doi:10.3390/math13223726 · Cited by 1
Garimella, K., Neda, N., Ebel, A., Jha, N. K., & Reagen, B. (2025) · doi:10.1109/iccad66269.2025.11240733 · Cited by 1
“More recently, compilers such as Dacapo, HeLayers, Fhe-lipe, and Orion [15], [16], [57], [58] include support for automatically inserting bootstrap operations into deep learning applications to enable deep computations such as ResNet-50 and YOLO networks [59], [60].”
Ugolnikova, E. A. (2025) · Systems and Technologies of the Digital HealthCare (STDH) · doi:10.1109/stdh66836.2025.11227524 · Cited by 1
“The initial model for vertebrae detection is a state-of-the-art real-time object detection algorithm YOLO (You Only Look Once) presented in 2015 [7].”
A lightweight optimization framework for real-time pedestrian detection in dense and occluded scenes
Cui, C., Li, J., Shuai, Z., Wang, Y., & Wang, Y. (2025) · Mechanical sciences · doi:10.5194/ms-16-877-2025 · Cited by 3
“A promising finding is the potential of a hierarchical approach: introducing an intermediate “teaching network” (e.g., YOLOv5l-m) as a semantic bridge to ease capacity transitions.”
InfluentialA Novel Road Crack Detection Method Based on the YOLO Algorithm
Fan, L., Xia, Q., & Zou, J. (2025) · Applied Sciences · doi:10.3390/app152312354 · Cited by 1
Accelerated Shapley Based Pruning with Data Synthesis and Channel Dependency Grouping
Huang, Z. Q., & Chen, Y. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-4367-0_34 · Cited by 2
Multi-angle feature enhancement for multi-defect category insulator defect detection in the wild
Yang, Z., Guo, Z., & Wang, L. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.113297 · Cited by 1
An Efficient Model for Fracture Detection in Wrist Trauma Images
Nguyen, T. T., Tran, H.-L., & Vu, D.-L. (2025) · Communications in computer and information science · doi:10.1007/978-981-95-4724-1_29 · Cited by 1
Unsupervised Learning for Industrial Defect Detection: A Case Study on Shearographic Data
Plassmann, J., Schuler, N., von Freymann, G., & Schuth, M. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-11442-6_22 · Cited by 3
“A critical challenge in automating shearographic inspection is the reliance on supervised learning approaches, such as convolutional neural networks (CNNs) and object detection models like YOLO[20,11].”
LGNet: A Lightweight Ghost-Enhanced Network for Efficient SAR Ship Detection
Chen, J., Huang, J., Tan, Y., et al. (2025) · Remote Sensing · doi:10.3390/rs17233800 · Cited by 1
Sun, Y., Liu, C., He, Z., & Zhang, Z. (2025) · Journal of Marine Science and Engineering · doi:10.3390/jmse13122234 · Cited by 1
Yousef, K. M. A., El-Haj, A., Mohd, B. J., Dawoud, N., Alnaimat, S., & Saleh, A. (2025) · Procedia Computer Science · doi:10.1016/j.procs.2025.10.176 · Cited by 4
Mobile Robot Obstacle Avoidance Based on Optical Flow Images in Motion Planning
Hoshino, S., & Sugata, R. (2025) · SICE Annual Conference (SICE) · doi:10.23919/sicefes67750.2025.11236592 · Cited by 1
“YOLO [9] is employed for object detection.”
When Language Model Guides Vision: Grounding DINO for Cattle Muzzle Detection
Dulal, R., Zheng, L., & Kabir, M. A. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-4972-6_13 · Cited by 1
Attention-guided YOLOv5s-SDF model for accurate detection of strip steel surface defects
Liu, K., Chang, X., Ma, H., Lv, L., & Chen, H. (2025) · Scientific Reports · doi:10.1038/s41598-025-26313-5 · Cited by 3
Wang, W., Liang, S., Xie, M., Ying, L., & Wang, Z. (2025) · IEEE Access · doi:10.1109/access.2025.3637213 · Cited by 3
Zhang, S., Pu, X., & Xu, F. (2025) · IEEE International Geoscience and Remote Sensing Symposium (IGARSS) · doi:10.1109/igarss55030.2025.11244072 · Cited by 1
“Existing deep learning object detection algorithms, including single-stage YOLO models[2] and two-stage detectors, demonstrate strong performance in general detection tasks but often underperform in scenarios involving small objects.”
Khandelwal, P., Chandrakar, R., Sahu, D., Khan, A. N., Roy, A., Pandit, M., Banchhor, R., Khanang, S. V., & Talwekar, R. H. (2025) · IEEE International Geoscience and Remote Sensing Symposium (IGARSS) · doi:10.1109/igarss55030.2025.11243226 · Cited by 1
“This state-of-the-art model, which has shown superior performance in object detection tasks [7][8], is trained to accurately detect whales, achieving high precision and recall rates in distinguishing whales from non-whale objects.”
FM-YOLO: A Novel Approach to Small Object Detection for Dense Vehicle Scenarios in UAV Images
Qiu, W., Dong, C., Liu, X., et al. (2025) · IEEE International Geoscience and Remote Sensing Symposium (IGARSS) · doi:10.1109/igarss55030.2025.11243620 · Cited by 1
“Recent advancements, particularly within the YOLO series, have focused on optimizing both speed and accuracy, with YOLOv8, YOLOv9, and YOLOv10 offering notable improvements in detection performance and efficiency [3-5].”
A Ship Target Detection Method for SAR Images Based on Backbone Lightweight and Feature Enhancement
Shi, Z., Chen, S., Wu, L., Liu, M., Sun, X., & Zhao, K. (2025) · IEEE International Geoscience and Remote Sensing Symposium (IGARSS) · doi:10.1109/igarss55030.2025.11243465 · Cited by 1
“To address the challenges, in this article, based on YOLO (you only look once) [2], a SAR image ship target detection method based on backbone lightweight and feature enhancement is proposed.”
Tien, C., Tsai, H.-H., Shih, H.-F., & Yen, C.-C. (2025) · Coatings · doi:10.3390/coatings15121390 · Cited by 1
A DCT-Based Contrastive Approach for Learning Visual Representations
Moraes, D. D. S., Santos, P. C. D. D., Busson, A., et al. (2025) · Brazilian Symposium on Multimedia and the Web · doi:10.5753/webmedia.2025.14963 · Cited by 1
“Visual representation learning is fundamental for many computer vision tasks, including image classification [29], tagging [13], object detection [27], semantic and instance segmentation [15], and image restoration [9].”
Go-SLAM: Grounded Object Segmentation and Localization with Gaussian Splatting SLAM
Pham, P., Patel, D., Conover, D., & Bera, A. (2025) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros60139.2025.11246048 · Cited by 8
Collaborative Dynamic 3D Scene Graphs for Open-Vocabulary Urban Scene Understanding
Steinke, T., Büchner, M., Vödisch, N., & Valada, A. (2025) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros60139.2025.11245861 · Cited by 14
Lee, J., Lee, S., Kim, J., Park, J., & Lee, K. (2025) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros60139.2025.11246177 · Cited by 3
“One-stage detectors like YOLO [23], RetinaNet [24], and FCOS [25] bypass region proposals by directly performing bounding box regression.”
Reusing Attention for One-stage Lane Topology Understanding
Li, Y., Zhang, Z., Qiu, X., Li, X., Liu, Z., Wang, L., Li, R., Zhu, Z., Gao, H.-A., Lin, X., et al. (2025) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros60139.2025.11246905 · Cited by 5
“Two-stage methods [20], [29]–[40] usually first detect objects from conventional object detectors such as FasterRCNN [41] and YOLO [42], and then feed all detected objects into the relation prediction model to estimate the relation between each object pair.”
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.