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 45,501–45,600 of 51,399
Keypoint-Guided Ophidian Transformation for String-Shaped Data Augmentation
Kwok, T., Park, B., Yagi, K., Yagi, A. R., Yang, C., Liao, M., & Li, Y. (2025) · IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB) · doi:10.1109/cibcb66090.2025.11177064
“Additionally, we evaluated convolution-based classifiers, specifically ResNet-50 [12] and YOLOv11 [13], [14].”
Mubeen, S., Sravani, P., Parvathi, E., Prasad, A. S., & Rao, I. N. (2025) · AIP conference proceedings · doi:10.1063/5.0296689
Building a Universal Detector of AI‐Generated Images Without Training on Them
Li, J., & Wang, K. (2025) · International Journal of Intelligent Systems · doi:10.1155/int/8530953 · Cited by 1
Uchenna, O. B., Michael, D. O., Udeogu, C., Bardi, I., & Odoemene, I. O. (2025) · Faculty of Natural and Applied Sciences Journal of Computing and Applications · doi:10.63561/jca.v2i3.836
Research on Monocular Vision Indoor Construction Positioning Method Based on YOLOv5
Yang, H., Sun, B., Lin, W., et al. (2025) · Lecture notes in mechanical engineering · doi:10.1007/978-981-96-5527-4_54
SADAMB: Advancing Spatially-Aware Vision-Language Modeling Through Datasets, Metrics, and Benchmarks
Papadopoulos, G. T., Drakoulis, P., Ntovas, A., et al. (2025) · Computers · doi:10.3390/computers14100413
“The construction process begins with object detection using the yolov8 [23] model.”
Zhang, B., Zhang, F., Hui, J., Peng, X., Zhang, J., & Zhang, Y. (2025) · Marine Environmental Research · doi:10.1016/j.marenvres.2025.107563
Shi, W., & He, Y. (2025) · Springer eBooks · doi:10.1007/978-3-031-99485-2_5
Robot Vision System for Retail Shelf Monitoring
Latha, A. V., Rahimipour, M., & Merabet, A. (2025) · Communications in computer and information science · doi:10.1007/978-3-032-00986-9_7
Xu, K., Guo, Z., Chen, Z., Li, M., Chen, Z., Zhang, D., Wang, Y., Chai, Y., Zhang, J., Wang, H., et al. (2025) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2025.09.29.679168
Modeling Economic Viability for Scalable AI Deployment in Emerging Regions
Asim, R., Bhardwaj, A., Sathiaseelan, A., et al. (2025) · doi:10.1145/3766882.3767183
“Compared to traditional cloud services, AI applications such as large language models [4], real-time vision systems [8], and recommendation engines [6] demand significantly higher compute power, memory, and energy.”
Rule-Driven Telecommunications Dumb Resource Image Distribution Software
Li, Y., Liu, W., Chen, Y., et al. (2025) · doi:10.1109/ngdn66208.2025.11182104
MediaPipe Pose Estimation for Basic Human Movement Patterns Across Different Camera Views
Valença, T. S. F., Silva, T. V., Chaves, L. M. D. S., et al. (2025) · International Symposium on Instrumentation Systems, Circuits and Transducers (INSCIT) · doi:10.1109/inscit66472.2025.11181013
“Frameworks such as YOLO [23], OpenPose [24], and MediaPipe [17] are machine learning-based solutions, often implemented as deep neural networks trained on large datasets, showing satisfactory results, especially in controlled scenarios [18].”
Research on Foreign Object Detection Algorithm for Coal Conveyor Belt Based on Deep Learning
Liang, Z., & Li, M. (2025) · International Conference on Computer Information Science and Application Technology (CISAT) · doi:10.1109/cisat66811.2025.11181939
“Traditional object detection algorithms, such as the Faster-RCNN [1] , SSD [2] and YOLO [2] series, perform well in general scenarios.”
Xiao, R., Zhu, X., Zhang, Y., Shen, H., & Huang, K. (2025) · IEEE Transactions on Components Packaging and Manufacturing Technology · doi:10.1109/tcpmt.2025.3616638
“D EEP neural networks (DNNs) have made remarkable strides in fields, such as image classification [1], [2], [3], speech recognition [4], and object detection [5].”
Yang, L., & Liu, J. (2025) · Journal of Stored Products Research · doi:10.1016/j.jspr.2025.102823
Deep CNNs for Image Classification, Object Detection, and Segmentation
Chen, Y., Lin, L., & Jain, R. K. (2025) · Intelligent systems reference library · doi:10.1007/978-3-031-94791-9_2 · Cited by 1
Yelicherla, T., Kandasamy, J., Ujwal, V. S., et al. (2025) · Artificial intelligence-enhanced software and systems engineering · doi:10.1007/978-3-031-99882-9_1
End-to-end Go (Weiqi) game record reconstruction from live broadcast videos
Lin, C., Ou, H., Chen, L. H., & Kuo, C. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.112455
A Novel Approach to Image Classification: Integrating DNN and CBIR for High-Precision RetrievalPreprint
Kumar, N., Kumar, A., & Kumar, N. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5551784
CEM-FBGTinyDet: Context-Enhanced Foreground Balance with Gradient Tuning for tiny ObjectsPreprint
Liu, T., & Cui, Z. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5551788
Sherin, B. C., & Poovammal, E. (2025) · Lecture notes in networks and systems · doi:10.1007/978-981-96-6435-1_19
Balancing Innovation and Accountability: Threats and Challenges of AI in Remote Sensing Applications
Khan, M. N., Suhail, M., Batyrova, O., Ali, D., & Jafri, S. M. W. H. (2025) · Lecture notes in networks and systems · doi:10.1007/978-3-032-05548-4_21 · Cited by 1
MORENA: Empty Images Detection Based on Unsupervised Reconstruction Error Analysis
de la Rosa, D., del Jesús, M. J., Pérez-Godoy, M. D., & Charte, F. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-02725-2_44
FPS-For-All: A Fusion Solution for Upper-Limb Disability People to Play FPS Games
Quan, B. H., Phong, T. T., & Thanh, B. T. (2025) · Lecture notes in networks and systems · doi:10.1007/978-3-032-05548-4_20
Smart Surveillance for Classroom Management
Nawandar, V., Rokade, S., & Patil, N. B. (2025) · Lecture notes in networks and systems · doi:10.1007/978-981-96-7505-0_11
DE-OVDR: Depth Estimation and Open Vocabulary Detection for Object Removal
Wang, C.-H., Hsiang, Y.-H., Lin, Y., & Lin, C.-H. (2025) · Lecture notes in networks and systems · doi:10.1007/978-981-96-6438-2_23
δ-ATP: Towards Fast and Reliable Aerial Traffic Patrol
Du, J., & Peng, C. (2025) · International Conference on Mobile Systems, Applications, and Services · doi:10.1145/3711875.3737658
“It decouples detection and its subsequent tracking; Typically, it uses an object detector (e.g., YOLO [12]), followed by tracking algorithms (e.g., DeepSort [19] or ByteTrack [20]); (2) Segmentation-then-tracking .”
Detection of Railway Worker’s Trespassing During Skylight Process Based on Computer Vision Algorithm
Liu, H., Zheng, Y., & Zhang, L. (2025) · Transportation Research Record Journal of the Transportation Research Board · doi:10.1177/03611981251365897
“The initial version, YOLOv1, was introduced by Redmon ( 10 ).”
PhishVision2.0: An Improved Visual Brand Impersonation Detector for Identifying Phishing Attacks
Graziano, G., Clavarezza, B., Sobrero, F., Ucci, D., Bisio, F., & Oneto, L. (2025) · Communications in computer and information science · doi:10.1007/978-3-032-00137-5_18
Research on Identification of Apple Leaf Diseases Based on an Improved YOLOv5s Model
Lin, K., Li, C., Mei, F., et al. (2025) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-032-00218-1_27
YOLO Algorithm-Based Effective Orange Detection and Localization with Improved Data Augmentation
Shankarpure, M. R., & Patil, D. D. (2025) · Lecture notes in networks and systems · doi:10.1007/978-981-96-7807-5_32
Pipeline Inspection a Case Study for Human Cognition Inspired Condition Management System
Dhungana, H. (2025) · Communications in computer and information science · doi:10.1007/978-3-032-00986-9_25
Suzuki, T., & Hashimoto, M. (2025) · Communications in computer and information science · doi:10.1007/978-3-032-00986-9_10
YOLOv5-TS: Channel-Spatial Attention Guided Bidirectional Feature Fusion for Traffic Sign Detection
Zhang, Y., Zhang, F., Gao, Y., et al. (2025) · Communications in computer and information science · doi:10.1007/978-3-031-99879-9_6
DCA-YOLO: Non-Prominent Feature Object Detection Using the Dynamic Convolution Attention YOLO Model
Li, Y., Yang, X., Hei, Y., & Duan, X. (2025) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-031-96146-5_9
Enhanced Obstacle Detection in Adverse Weather Condition for Autonomous Vehicles
Aswini, N., & Kavitha, D. (2025) · Lecture notes in networks and systems · doi:10.1007/978-981-96-7508-1_34 · Cited by 1
Image-Based Automated Attendance System Designing Leveraging Multi-task Convolutional Neural Network
Das, S. S., Roy, S., & Ghoshal, A. K. (2025) · Lecture notes in networks and systems · doi:10.1007/978-981-96-6534-1_7
Comparison of circular and rectangular bounding boxes for apple detection in orchards
Maliszewski, P., & Sztyber, A. (2025) · Lecture notes in networks and systems · doi:10.1007/978-3-032-05802-7_2
Optic Disc and Optic Cup Image Segmentation for Glaucoma Detection
de Assis, D. F., Cortez, P. C., Motta, P. C., et al. (2025) · World Congress on Medical Physics and Biomedical Engineering, September 7 - 12, 2009, Munich, Germany · doi:10.1007/978-3-031-94934-0_106
AI-Integrated Robotic Pollinator for Sustainable Agriculture
Bavasa, A., & Brinson, M. (2025) · Lecture notes in networks and systems · doi:10.1007/978-3-032-03751-0_33
Real-time object recognition using deep learning with tensor flow
Kumar, M., Kumar, P. P., Srinivas, V., Sugumar, R., & Preethi, P. (2025) · AIP conference proceedings · doi:10.1063/5.0291951
Wang, T., Li, Y., Ding, Y., Hao, Y., Liu, Z., Zhuang, C., & Zhang, W. (2025) · Materials Today Communications · doi:10.1016/j.mtcomm.2025.113938
Shwetha, V., Banerjee, B., Laxmi, V., & Kamath, P. R. (2025) · International Journal of Biomedical Imaging · doi:10.1155/ijbi/3559598 · Cited by 1
Guan, J., Li, C., Xiao, Y., et al. (2025) · Signals and communication technology · doi:10.1007/978-3-032-03632-2_2
Improved Small Target Detection Algorithm from the Perspective of Drones
Wang, Z., Qian, Y., Zhou, L., et al. (2025) · Signals and communication technology · doi:10.1007/978-3-032-03632-2_3
Model-Free Transformer Framework for 6-DoF Pose Estimation of Textureless Tableware Objects
Lee, J., Kim, H., Kwon, J., Yun, S., Lee, N.-H., Choi, Y., Chung, G., & Suh, J.-H. (2025) · Sensors · doi:10.3390/s25196167 · Cited by 2
“This unified approach allows YOLO to make predictions with a single network evaluation [7].”
ENDLESS: An End-to-End Framework for Urban Synthetic Dataset Generation
Neto, A. T. C., Costa, W. D. L., Teichrieb, V., & Teixeira, J. M. (2025) · Journal of the Brazilian Computer Society · doi:10.5753/jbcs.2025.5869
“The location of the objects is given by enclosing the object in bounding-boxes [Redmon et al ., 2016], which will be better explained in Section 2.3.1.”
InfluentialA Comparison of YOLO V8 and R-CNN Algorithm—A VQA Object Detection Method Survey
Devaki, K., & Bakiyalakshmi, S. (2025) · Algorithms for intelligent systems · doi:10.1007/978-981-96-5265-5_10
Siow, C. Y., Yang, Y.-H., Tsai, C.-J., Yang, W.-W., Hu, C., Sung, J., & Tani, J. (2025) · JMIR Serious Games · doi:10.2196/74157
Active Learning and the Various Flavors of Supervision for Object Detection
Bischoff, N., & Tomforde, S. (2025) · Communications in computer and information science · doi:10.1007/978-3-032-01169-5_19
Deep Learning in Satellite and Aerial-Based Image Processing
Sbriglio, A., & Palmerini, G. B. (2025) · Communications in computer and information science · doi:10.1007/978-3-032-01169-5_12
Zou, X., Wang, Z., Song, Y., et al. (2025) · Applied Intelligence · doi:10.1007/s10489-025-06881-9
“Visual perception techniques, such as YOLO (You Only Look Once) [ 6] and various encoder-decoder networks, rely on images captured by cameras and employ machine learning (ML) models for object detection.”
ODDNet-Object Detection in Dark with Attention-Driven RGB-Event Fusion
Sayyad, S. I., Satihal, J. M., & Patil, U. (2025) · Lecture notes in networks and systems · doi:10.1007/978-3-032-06665-7_4
Nasiri, A., Zhao, Y., & Gan, H. (2025) · Animal - science proceedings · doi:10.1016/j.anscip.2025.08.281
Kadhim, A. N., Anuar, S., & Ismail, S. A. (2025) · Engineering Technology & Applied Science Research · doi:10.48084/etasr.11830 · Cited by 1
“For ResNet50 residual blocks: [45, 46]: where (cid:23) (cid:12) is the output of the residual block, (cid:26) (cid:12) is the function representing the operations within the residual block (such as convolution, batch normalization, and activation), is the input to the residual block, and are the…”
Gan, T., Zhang, C., Wang, P., Liang, X., & Ye, X. (2025) · Journal of Medical Systems · doi:10.1007/s10916-025-02271-3
“The You Only Look Once (YOLO) algorithm, initially unveiled in 2016 by [22], stands as a prominent object detection method.”
Semi-Automatic Estimation of Body Orientation in Football
Husan, S. U., Merino, M. V., & Nieto, E. (2025) · doi:10.1145/3728423.3759407
Nakamura, Y. (2025) · doi:10.1145/3728423.3759415
“We apply a confidence threshold to suppress false positives and consistently outperform YOLO [24] and Faster R-CNN [25] baselines on small object detection.”
Ravikrishna, S., Santhosh, C., Lakshma Narayanan, J. B., et al. (2025) · doi:10.1109/icngcs64900.2025.11182710
“With recent advancements in artificial intelligence (AI), particularly deep learning and computer vision, it has become technically feasible to deploy automated systems for real-time traffic monitoring and enforcement [2].”
Santhosh, C., Kalimuthu, S., Adhithyaa, N., et al. (2025) · doi:10.1109/icngcs64900.2025.11183037
“Restrictions apply. orientations, and lighting conditions with the help of supermarket-specific data [10].”
XAI for Automated Grading of Circuit Diagrams and Drawings
Swetha, P., & Kumar, L. A. (2025) · International Conference on Next Generation Computing Systems (ICNGCS) · doi:10.1109/icngcs64900.2025.11183008
Research and Development of Aerodrome Control Systems using Digital Technology
Inoue, S. (2025) · Marine Engineering · doi:10.5988/jime.60.467
Non-Destructive Testing of Printed Circuit Boards Using Ultrasonic Imaging and CNNs
Venkatesh, D., Surya, R., Thiru Murugan, A., et al. (2025) · doi:10.1109/icngcs64900.2025.11182977
Fijian ID Card Classification with Convolutional Neural Networks for Industrial Use
Narube, P., & Sharma, A. (2025) · Communications in computer and information science · doi:10.1007/978-3-032-04657-4_22
Yang, T., Chen, J., Xie, L., Yang, L., Ye, C., & Zhao, H. (2025) · Frontiers in Medicine · doi:10.3389/fmed.2025.1660445
Artificial Intelligence in Cosmetic Product Development
Shukla, A. K., Tiwari, A., Yadav, V. K., Dubey, R. S., & Mishra, M. K. (2025) · BENTHAM SCIENCE PUBLISHERS eBooks · doi:10.2174/9798898810726125010006
Detection Of Pufferfish Using Computer Vision And Deep Learning Methods
Yüksel, H. U., & Tonguç, G. (2025) · El-Cezeri Fen ve Mühendislik Dergisi · doi:10.31202/ecjse.1628790 · Cited by 1
ЦИФРОВА ТРАНСФОРМАЦІЯ В ЗАДАЧАХ УПРАВЛІННЯ СУЧАСНОЮ ПОРТОВОЮ ІНФРАСТРУКТУРОЮ
Topalov, A. (2025) · Збірник наукових праць Харківського національного університету Повітряних Сил · doi:10.30748/zhups.2025.85.07
Eggenkemper, F., Feldmann, L., Sontowski, N., Kiel, A., Rothkopf, C. A., & Mertens, R. (2025) · International Journal of Semantic Computing · doi:10.1142/s1793351x25450011
Graph Element Recognition Networks DAGRN Based on Shuffle Attention and Criss Cross Attention
Zhang, Z., Zhao, H., Sun, P., & Weng, L. (2025) · International Conference on Artificial Intelligence, Big Data and Algorithms (CAIBDA) · doi:10.1109/caibda65784.2025.11183085
“In 2016, Redmon et al. proposed a real-time target detection algorithm, YOLO [1], which is characterized by its fast detection speed and its ability to predict both classification and localization of targets.”
Smarter Animal Detection: Upgrading YOLOv8 with Scalable Attention and Loss Optimization
Wang, Z., Feng, Z., & Kobayashi, H. (2025) · International Conference on Artificial Intelligence, Big Data and Algorithms (CAIBDA) · doi:10.1109/caibda65784.2025.11182845
“YOLOv1 introduced the single-stage detection paradigm using a fully convolutional network [7], while YOLOv2 [8] improved results via anchor boxes, batch normalization, and multi-scale training [17].”
Crowd Counting with Latent Diffusion Model
Wang, Y. (2025) · International Conference on Artificial Intelligence, Big Data and Algorithms (CAIBDA) · doi:10.1109/caibda65784.2025.11183043 · Cited by 1
“This type of method typically uses object detection models such as YOLO[21].”
Design of an Indoor Search Robot
Xing, Z. (2025) · International Symposium on Semiconductor and Electronic Technology (ISSET) · doi:10.1109/isset66828.2025.11185034
“YOLOv8, a real-time object detection algorithm introduced in 2015 by Joseph Redmon et al., is widely used in computer vision [12].”
EBI-YOLO: A Hardware-Efficient Detector with Cross-Spatial Attention for Steel Surface Defects
Lu, Y., Wu, J., & Su, J. (2025) · International Conference on Artificial Intelligence, Big Data and Algorithms (CAIBDA) · doi:10.1109/caibda65784.2025.11183408
“…many kinds of steel defects of different sizes, and at the same time to meet the requirements of fast and high accuracy of surface defects detection, we chose to further optimise YOLOv8n, a commonly used version of YOLO [11][12] , in order to improve the ability of steel surface defects detection.”
Algorithm for Detecting Defects on Steel Surfaces Based on DMO-YOLO
Li, G., & Zhu, F. (2025) · International Joint Conference on Information and Communication Engineering (JCICE) · doi:10.1109/jcice66205.2025.11182070
“The YOLO [8][9][10][11][12][13] series has been continuously innovating and breaking through in target detection tasks.”
Real-Time Crowd Monitoring Using Lightweight AI for Secure Zones
Hashmi, H., Kumar, A., & Singh, P. (2025) · doi:10.1109/ciacon65473.2025.11189725
“Models like YOLO [4], Faster R-CNN [5], and SSD [6] have achieved remarkable results in object detection and crowd analysis.”
Development of advanced progress recognition algorithms for construction monitoring
Yingdong, L., Zhijun, L., Zhijie, Y., & Zhang, J. (2025) · PLoS ONE · doi:10.1371/journal.pone.0333262 · Cited by 2
“Its applications span numerous industries, including autonomous vehicles [30] and robotics [31], and are increasingly relevant to our study, i.e., construction progress monitoring.”
Mendoza-Bautista, K. J., Torres-Méndez, L. A., & Chaírez, I. (2025) · International Journal of Systems Science · doi:10.1080/00207721.2025.2562188
“This technique uses a deep learning method to predict location and characteristics provided by using a database for its training (Redmon et al., 2016).”
Grasso, D., & Luppino, G. (2025) · Lecture notes in mobility · doi:10.1007/978-3-032-06763-0_22
Automatic Spatial Localization of Coronary Stenosis in X-Ray Angiograms Using Deep Learning
Gonzalez-Valadez, U. A., García-Ramírez, R. A., Cruz-Aceves, I., Hernández-González, M. A., & Solorio, S. (2025) · Studies in computational intelligence · doi:10.1007/978-3-031-96328-5_5
Supporting a SOTIF Safety Argument by Activation Pattern Monitoring with Statistical Guarantees
Ehlers, R., Deameni, L. K., & Maslov, N. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-07132-3_12
Deep learning for object detection and instance segmentation
Maxwell, A. E., Ramezan, C. A., & He, Y. (2025) · Elsevier eBooks · doi:10.1016/b978-0-443-29306-1.00013-2
Pothole Detection and Classification Using YOLO Models
Ngoc, T. T. T., Thanh, T., Ngoc, L. A., et al. (2025) · Lecture notes in electrical engineering · doi:10.1007/978-981-95-1999-6_6
Janapa, V. S. S. L. D., Thummalapenta, V., Vamsidhar, P., Maddu, L. S. G., Avasarala, S. P. A., Chitra, K., & Prasanna, K. S. L. (2025) · International Conference on Networks, Multimedia and Information Technology (NMITCON) · doi:10.1109/nmitcon65824.2025.11188142
“YOLO as a unified model that predicts bounding boxes and class probabilities simultaneously, achieving impressive speed and accuracy in a single pass over the image [1].”
A Lightweight Wind Turbine Blade Defect Detection Algorithm Based on GBC-YOLO
Xue, M., Yao, C., Wang, F., et al. (2025) · Chinese Control Conference (CCC) · doi:10.23919/ccc64809.2025.11178440
“One-stage object detection algorithms, represented by the You Only Look Once(YOLO)[11], stand out among detection algorithms due to their elimination of the candidate region generation process, instead directly performing object classification and localization regression, significantly enhancing…”
Hu, R., Tang, X., & Hao, K. (2025) · Chinese Control Conference (CCC) · doi:10.23919/ccc64809.2025.11179068
“Convolutional neural networks (CNNs) have become a dominant framework in deep learning for processing computer vision tasks such as image classification [1–3], object detection [4–7], and segmentation [8–10].”
Qiao, Y., Miao, L., Zhou, Z., et al. (2025) · Chinese Control Conference (CCC) · doi:10.23919/ccc64809.2025.11178560
“Inspired by many existing object detection methods in nat-ural images [6, 7], many researchers try to use the similar methodologies for object detection in remote sensing images.”
Wu, M., Song, X., Fang, X., & Han, X. D. (2025) · Chinese Control Conference (CCC) · doi:10.23919/ccc64809.2025.11179168
“One-stage detectors like YOLO[12–17] and SSD[18] predict boxes and classes in a single forward pass, offering better speed-accuracy trade-offs.”
Deepa, S. S., & S, V. C. S. (2025) · International Conference on Networks & Advances in Computational Technologies (NetACT) · doi:10.1109/netact65906.2025.11188201
“Further,many object detection models usually create multiple bounding boxes for a given object [15] [16].”
Kapusta, J., Bauer, W., & Baranowski, J. (2025) · Algorithms · doi:10.3390/a18100642 · Cited by 1
“The field has progressed from classical feature-based approaches like SIFT [2] through CNN breakthroughs including AlexNet [3], VGG [4], and ResNet [5], to modern object detection frameworks such as R-CNN [6], YOLO [7], and recent vision-language models [8].”
Path Planning Algorithm for Orchard Scene Based on Road Edge Fitting
Wang, A., Xiong, J., Gao, L., et al. (2025) · Chinese Control Conference (CCC) · doi:10.23919/ccc64809.2025.11179456
“The principle of the YOLO algorithm is to transform the target recognition problem into a regression problem [17] .”
Multi-Sensor Fusion Based Railway Transit Environment Intelligent Perception
Wu, Y., & Han, D. (2025) · Chinese Control Conference (CCC) · doi:10.23919/ccc64809.2025.11178822
“Among the rapidly evolving object detection technologies, the YOLO series stands out for its excellent balance of speed and accuracy [13].”
DeFRCN-AOE: Anti-Overfitting Enhanced Unexploded Ordnance Few-Shot Object Detection
Weng, Z., Xing, S., Yu, Z., et al. (2025) · Chinese Control Conference (CCC) · doi:10.23919/ccc64809.2025.11179718
“Taking the YOLO series as an example[4, 5], one-stage detection networks directly generate final detection results from feature maps.”
Small Scale Target Tracking Method Based on Deep Learning for UAV
Yang, R., Hu, C., Jv, Y., et al. (2025) · Chinese Control Conference (CCC) · doi:10.23919/ccc64809.2025.11179124
“The YOLO series of algorithms were first proposed by the Redmon team in 2015 [7] and have undergone multiple improvements.”
Ship Recognition Based on Body and Critical Area Features with Ensemble Learning
Gong, Z., & Han, D. (2025) · Chinese Control Conference (CCC) · doi:10.23919/ccc64809.2025.11178477
“Specifically, we first design a re-detection framework based on YOLOv7[11][12] to detect both the ship body and key components.”
Research on Small Target Detection Algorithm for Outdoor Complex Environment Based on STB-YOLOv8
Liu, R., Yang, Q., Li, D., et al. (2025) · Chinese Control Conference (CCC) · doi:10.23919/ccc64809.2025.11178405
Lightweight Rotated Object Detection Model for Pallets
Sun, M., Ge, A., & Sun, M. (2025) · Chinese Control Conference (CCC) · doi:10.23919/ccc64809.2025.11179445
“There is also the continuously updated YOLO [8] series and RT-DETR (Real-Time Detection Transformer) [9], which is based on the Transformer architecture.”
Yu, Z., & Jin, H. (2025) · Chinese Control Conference (CCC) · doi:10.23919/ccc64809.2025.11179516
“For instance, the YOLO series models[15] and Faster R-CNN[16] have been widely applied in 2D object detection tasks and have provided effective feature extraction tools for subsequent 3D object detection.”
Xin, L., & Li, Y. (2025) · Chinese Control Conference (CCC) · doi:10.23919/ccc64809.2025.11178470
“The YOLO series was launched in 2016 with a ground-breaking advancement [19].”
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.