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 45,401–45,500 of 51,399
Yu, D., Han, B., Zhao, X., et al. (2025) · Sensors · doi:10.3390/s25185788
“Convolutional Neural Networks (CNNs), including seminal works like Faster R-CNN [7] and YOLO [8], established robust frameworks for feature extraction and bounding box regression.”
Fine-Tuning Yolov8 for Accurate Unmanned Aerial Vehicle Detection with Digital Twin Simulation
Mejia, F., Shah, S., Young, & Brunk, A. T. (2025) · SAE technical papers on CD-ROM/SAE technical paper series · doi:10.4271/2025-01-0473
“Among these, the You Only Look Once (YOLO) family of models has demonstrated exceptional speed and accuracy, making it a preferred choice for real-time applications [1].”
DFF: Dynamic Feature Fusion for Fault Diagnosis of High Voltage GIS
Wang, J., Fang, Y., He, Y., Zhou, D., Long, Z., & Zhang, J. (2025) · IEEE Joint International Information Technology and Artificial Intelligence Conference (ITAIC) · doi:10.1109/itaic64559.2025.11163276
“Deep learning has achieved great success in image classification [7], object detection [8], and natural language processing [9].”
Fault Diagnosis of High Voltage GIS via Deep Learning and Data Augmentation Method
Wang, J., Long, Z., Sha, S., He, Y., Zhou, D., & Zhang, J. (2025) · IEEE Joint International Information Technology and Artificial Intelligence Conference (ITAIC) · doi:10.1109/itaic64559.2025.11163222
“Deep learning has achieved great success in image classification [13], [14], object detection [15], and natural language processing [16].”
An Efficient Model for Small-object Traffic Sign Detection
He, J., Wang, H., Lu, Y., Fang, J., Li, Z., Zhang, Z., Wei, W., & Zhang, X. (2025) · International Conference on Intelligent Transportation and New Energy Technology (ITNET) · doi:10.1109/itnet65199.2025.11162923
“While YOLO [1] performed slightly worse in detection accuracy, it excels in real-time performance.”
LC-PestVit: A Lightweight Pest and Disease Classification Model
Lai, J., & Hsiang, H.-C. (2025) · IEEE Joint International Information Technology and Artificial Intelligence Conference (ITAIC) · doi:10.1109/itaic64559.2025.11163058
“In recent years, deep learning technologies, including CNN[1], YOLO[2], Vit[3], and other model series, have demonstrated considerable advantages in the identification of pests and diseases[4].”
The First WARA Robotics Mobile Manipulation Challenge - Lessons Learned
Domínguez, D. C., Iannotta, M., Kashyap, A., Sun, S., Yang, Y., Cella, C., Colombo, M., Pelosi, M., Preziosa, G. F., Tafuro, A., et al. (2025) · European Conference on Mobile Robots · doi:10.1109/ecmr65884.2025.11163319
“For this purpose, the robot grabbed the suction cup from its holder with the gripper and moved above the bin-picking area to allow a proper view of the entire bin with the in-hand camera.”
Practice and Research on Behavioral Health Monitoring of Cattle Based on Improved YOLOv8n-Pose
Wu, M., Hu, X., Gong, Z., et al. (2025) · IEEE Joint International Information Technology and Artificial Intelligence Conference (ITAIC) · doi:10.1109/itaic64559.2025.11163076
“YOLO has fast detection speed and high accuracy, so it can meet the actual needs of herd health monitoring [4].”
Qi, J., & Wang, J. (2025) · Electronic Research Archive · doi:10.3934/era.2025249
STC-YOLO: small target defect detection method for surface texture of Si 3 N 4 ceramic balls
Li, X., Chen, L., Liu, S., et al. (2025) · Nondestructive Testing And Evaluation · doi:10.1080/10589759.2025.2561217
Investigating Action Recognition Approaches for Accident Detection in Smart City Transport Systems
Kumar, M., Verma, L., Vardhan, H., et al. (2025) · doi:10.1109/mrie66930.2025.11156524
Domingo, J. D., Caccavale, R., Finzi, A., Zalama, E., & Gómez‐García‐Bermejo, J. (2025) · Journal of Intelligent Manufacturing · doi:10.1007/s10845-025-02673-7 · Cited by 1
Deng, W., Yan, L., & Wang, C. (2025) · The Journal of Supercomputing · doi:10.1007/s11227-025-07853-z
Zhou, S., Fan, W., Li, S., et al. (2025) · Integration · doi:10.1016/j.vlsi.2025.102561
Machine learning based prediction of dynamical clustering in granular gasesPreprint
Sata, S. P., Stannarius, R., Noack, B., & Puzyrev, D. (2025) · Research Square · doi:10.21203/rs.3.rs-7474100/v1 · Cited by 1
A Web-Based Platform for Korean Calligraphy Learners Using Deep Learning
Yang, C., Osman, M. A., & Sarvghadi, M. A. (2025) · IEEE Access · doi:10.1109/access.2025.3612578 · Cited by 2
YOLO-DSE: PCB surface defect detection with the improved YOLO
Chen, J., & Liu, W. (2025) · International Symposium on Advances in Electrical, Electronics and Computer Engineering (ISAEECE) · doi:10.1109/isaeece66033.2025.11159692
“The other type is one-stage methods, like SSD [9] and YOLO [10] series, which are faster and more efficient.”
Wavelet-Enhanced Multi-scale Swin-Deformable DETR for SAR Ship Detection
Zeng, J., & Tang, X. (2025) · International Symposium on Advances in Electrical, Electronics and Computer Engineering (ISAEECE) · doi:10.1109/isaeece66033.2025.11160184
“Subsequently, one-stage detectors like You Only Look Once (YOLO) [5]and Single Shot MultiBox Detector (SSD) revolutionized real-time object detection by eliminating the region proposal step, achieving a balance between speed and precision.”
AQ-CSL: Attention Querying Facial Action Unit Detection Net with Cross Subject Learning
Zeng, W., Ji, Y., Chen, D., & Zhang, H. (2025) · Signal Image and Video Processing · doi:10.1007/s11760-025-04627-1 · Cited by 1
Tahtouh, M., Bernoux, G., Brunet, A., Standarovski, D., Nguyen, G., & Sicard, A. (2025) · Journal of Geophysical Research Machine Learning and Computation · doi:10.1029/2024jh000566 · Cited by 2
Tao, Y., Bao, Z., & Ma, F. (2025) · Applied Computing and Geosciences · doi:10.1016/j.acags.2025.100293
Rizzieri, N., Dall’Asta, L., & Ozolinsh, M. (2025) · Life · doi:10.3390/life15101495
A Method for Improving the Efficiency and Effectiveness of Automatic Image Analysis of Water Pipes
Wang, Q., Lü, L., Liu, S., Hu, Q., Zhong, G., Su, Z., & Xu, S. (2025) · Water · doi:10.3390/w17182781
“Conversely, single-stage frameworks, such as the You Only Look Once (YOLO) series [19,22,29,30], were developed to address the slow inference speeds of two-stage models.”
Smart Classroom Learning Analytics System Based on YOLOv5
Xia, S., & Qu, C. (2025) · IEEE Advanced Information Technology, Electronic and Automation Control Conference (IAEAC) · doi:10.1109/iaeac65194.2025.11165900
Efficient Maritime Traffic Flow Analysis Using YOLOv8 and DeepSORT for Vessel Detection and Tracking
Wang, W.-Y., Wang, Y., Liu, X., Zou, X., & Zhong, X. (2025) · IEEE Advanced Information Technology, Electronic and Automation Control Conference (IAEAC) · doi:10.1109/iaeac65194.2025.11166335
Enhanced Object Identification Through Deep Learning Techniques
-, R. K. P., Konni, S. R., Sakunthala, K., et al. (2025) · IEEE Wireless Antenna and Microwave Symposium (WAMS) · doi:10.1109/wams64402.2025.11158134
Roleda, J. C., Cruz, A. J., Geronimo, M. R., & Ilao, J. P. (2025) · International Conference on Mechatronics and Machine Vision in Practice (M2VIP) · doi:10.1109/m2vip67511.2025.11165629
“Widely used meth-ods for object detection are Faster Region-based Convolutional Neural Networks (Faster RCNN) [25] and You Only Look Once (YOLO) [23], which focus on general object detection by using CNN-based architectures to estimate bounding boxes of detected objects.”
An Improved YOLOv8 Algorithm for TGV Microvia Defect Detection
Wei, J., Shen, C., Li, S., Hu, Z., Xu, C., Chen, C., & Liu, Y. (2025) · International Conference on Artificial Intelligence and Electromechanical Automation (AIEA) · doi:10.1109/aiea66061.2025.11160598
“The algorithm treats the position regression and category classification of the target as a unified task, using a single convolutional neural network to directly predict the position and category probability of the bounding box from the input image [6] .”
Echo Vision: AI Voice Assisted Navigation for Visually Impaired
Bala Velan, M., Jayanth Balraj, A., Jerusha Angel, K., et al. (2025) · doi:10.38124/ijisrt/25sep880
The Application of Single Shot MultiBox Detector in multiple-object QR codes recognition
Cai, C., Li, J., & Wen, J. (2025) · International Conference on Image Processing and Media Computing (ICIPMC) · doi:10.1109/icipmc66319.2025.11170684
“Its training and prediction are end-to-end, so the Yolo algorithm is relatively simple and fast[11].”
EdgeYOLO+Depth: Extending object detection for real-time depth estimation on smartphones
Ilse, C., Ketzler, F., Pfeifer, N., Massow, K., Maiwald, F., & Radusch, I. (2025) · International Conference on Artificial Intelligence, Computer, Data Sciences and Applications (ACDSA) · doi:10.1109/acdsa65407.2025.11166075
“Among these, YOLO has emerged as a widely used standard, evolving through multiple generations—from the original YOLO [6] to advanced variants like YOLOv7 [7] and edge-optimized models such as EdgeYOLO [8].”
Gueye, M., Diop, A. K., & Gueye, A. D. (2025) · International Conference on Artificial Intelligence, Computer, Data Sciences and Applications (ACDSA) · doi:10.1109/acdsa65407.2025.11166667
“Despite their speed, the first versions of YOLO (YOLOv1 [24] and YOLOv2 [26]), suffered from a drop in accuracy, especially on small objects, compared with 2-stage detectors.”
Enhancing Road Safety with YOLOv8: Deep Learning for Accurate Brake Light Detection
Shaik, K., Khasim, S., Verma, P., Maity, S., & Solanki, K. (2025) · Advanced Computing and Communication Technologies for High Performance Applications (ACCTHPA) · doi:10.1109/accthpa65749.2025.11168634
“YOLO (You Only Look Once) is a popular object detection framework that performs real-time detection by processing the entire image in a single forward pass [20].”
InfluentialAlshammari, A. (2025) · International Conference on Artificial Intelligence, Computer, Data Sciences and Applications (ACDSA) · doi:10.1109/acdsa65407.2025.11166227
“Among several object identification methods, Redmon et al. [25] created YOLO (You Only Look Once), which stands out for its speed and accuracy.”
An AI-based Sperm Assessment System for Analyzing Human Sperm’s Reproductivity
Trinh, V., Pham, A., & Tran, T.-H. (2025) · doi:10.1109/isci65687.2025.11167885
“Each frame is then passed into the stack of 3 YOLO v10 neural networks [36] in which each network architecture is responsible for a separate task of sperm detection, sperm movement tracking, and sperm segmentation.”
SAR Ship Detection with Large-Kernel Convolution and Channel Weighted Multi-Scale Feature Fusion
Yan, Y., Fu, X., Ning, L., & Gu, Y. (2025) · IEEE International Conference on Cyber Technology in Automation, Control, and Intelligent Systems · doi:10.1109/cyber67662.2025.11168349 · Cited by 1
“On the other hand, one-stage detectors, including You Only Look Once (YOLO) [8], Single Shot MultiBox Detector (SSD), and RetinaNet, directly predict object classes and bounding boxes given an input image.”
Essam, M., & Mohammed, A. (2025) · Intelligent Methods, Systems, and Applications (IMSA) · doi:10.1109/imsa65733.2025.11167126
“Following the success of convolutional neural networks (CNNs) on natural image datasets [3], [4], many CNN-based detectors were adapted to medical data.”
Assessing Sperm Motility Through a Multi-Modal Correlation
Trinh, V. D., Nguyen-Huynh, N.-Y., Bui-Quang, P., et al. (2025) · IEEE Symposium on Computers & Informatics (ISCI) · doi:10.1109/isci65687.2025.11167457
AI Model: Deep Learning Model to Classify the Tennis Ball Position and Create the Sports Commentary
Gokila, S., Hariharan, K., Sudharsanan, G., et al. (2025) · International Conference on Sustainable Computing and Data Communication Systems (ICSCDS) · doi:10.1109/icscds65426.2025.11167696
“One of the key contributions to the area of object detection is the YOLO framework presented by Redmon et al. [1].”
A Real-Time Advisory Tool for Supporting the Use of Helmets in Construction Sites
Işıkdağ, Ü., Çemrek, H. A., SÖNMEZ, S., Aydın, Y., Bekdaş, G., & Geem, Z. W. (2025) · Information · doi:10.3390/info16100824 · Cited by 4
Multi-Scale Attention-Augmented YOLOv8 for Real-Time Surface Defect Detection in Fresh Soybeans
Wu, Z., He, Y., Huo, D., et al. (2025) · Processes · doi:10.3390/pr13103040
Maeda, S., & Akiba, T. (2025) · Sustainability · doi:10.3390/su17198578
Wang, X., Xiao, R., Hao, W., Song, Y., Chen, S., & Xie, Y. (2025) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2025.108677
CPU Implementation of SAM based Maritime Object Segmentation and Detection
Meenakshi, K., Joshi, S., Dhipu, T. M., et al. (2025) · doi:10.1109/space65882.2025.11170617
“The dataset was then used to finetune SAM [5] [6] model for object segmentation, and train YOLO[7] and RT-DETR[13] through targeted augmentations to enhance model performance for maritime object detection, which were then integrated into a single pipeline.”
The 6-DOF Pose Estimation Algorithm Based on YOLO11-BiFormer-Robust ICP Model
Wang, G., Hou, C., Li, L., & Zhou, S. (2025) · IEEE International Conference on Communication Software and Networks · doi:10.1109/iccsn66511.2025.11172584
“YOLO series models[8] have gained widespread attention due to their end-to-end detection approach and efficient performance.”
Shi, C., Liu, G., Lu, Z., & Tian, G. (2025) · International Annual Conference on Complex Systems and Intelligent Science (CSIS-IAC) · doi:10.1109/csis-iac65538.2025.11161129 · Cited by 1
“One-stage algorithms, such as SSD [6] and YOLO series [7], predict the target position and category through direct regression, with fast detection speed and meeting real-time requirements.”
Qing, S., Liu, Q., Zhao, F., et al. (2025) · doi:10.1109/idsac65763.2025.11170305
“R ELATED W ORKS YOLO (You Only Look Once)[3] is a deep learning algorithm designed for object detection.”
Improved YOLOv8-based video supervision technology for ulva prolifera salvage safety operations
Shang, H., Yang, K., Liu, Y., Ai, B., Liu, X., & Li, T. (2025) · International Conference on Electronics and Communication, Network and Computer Technology (ECNCT) · doi:10.1109/ecnct66493.2025.11172538
“YOLOv1 introduces the regression idea into the detection task for the first time and achieves fast detection [12].”
Leaf Disease Detection using Deep Learning and IoT Automation
Devi, S. K. C., Shivamani, P., & Lakshya, R. (2025) · International Conference on Soft Computing for Security Applications (ICSCSA) · doi:10.1109/icscsa66339.2025.11170845
“Similarly, Redmon et al. [3] introduced the YOLO (You Only Look Once) framework, enabling real-time object detection, which has been adopted for plant disease recognition due to its speed and accuracy.”
A Novel Approach to Identify and Interpret License Plates with YOLOv5 and Tesseract
Bhuvneshwari, B., Kaur, N., Kaur, A., et al. (2025) · doi:10.1109/icscsa66339.2025.11171393
“Since YOLOv5 is both fast and accurate, it works well for embedded and mobile devices that have limited computing power [5] [14].”
Exploring Voronoi-based area-weighted network fundamental diagrams in shared urban spaces
Pan, D., Beigi, P., Daamen, W., et al. (2025) · Transportmetrica A Transport Science · doi:10.1080/23249935.2025.2558149
Benchmarking ML, DL, and Transformer Models for Document Classification
Santiago, R. R., Ortiz, A. C., Tona, C., & Lopez-Montiel, M. A. (2025) · Studies in computational intelligence · doi:10.1007/978-3-031-85614-3_18
Machine Learning and Artificial Intelligence for Cell Biology Imaging
Maddalena, L., Antonelli, L., Polverino, F., Asteriti, I. A., Degrassi, F., Guarguaglini, G., Albu, A., Hada, A., & Guarracino, M. R. (2025) · Springer eBooks · doi:10.1007/978-3-031-97461-8_11
Effectiveness Investigation into Lightweight Models for 2D Object Detection
Nguyen, T. A., & Pham, H.-A. (2025) · Lecture notes in networks and systems · doi:10.1007/978-981-96-4142-0_24
Computer Vision Technologies for Cost-Effective Asset Condition Inspections
Ramos, E. O. (2025) · Sustainable civil infrastructures · doi:10.1007/978-3-032-03154-9_20
YOLOV5, YOLOV7, and YOLOV8: Architectures Benchmark for 5G Pipeline Inspection Drones
Aromoye, I. A., Hiung, L. H., Sebastian, P., et al. (2025) · Lecture notes in electrical engineering · doi:10.1007/978-981-96-8093-1_3
Part Coupled Transformer Network for Vehicle Re-Identification
Sun, W., Hu, Y., Dai, G., et al. (2023) · Journal of Computer-Aided Design & Computer Graphics · doi:10.3724/sp.j.1089.2023.19641
Improving Imbalanced Tuberculosis Diagnosis Using GoogleNet with Image-Based SMOTified-GAN
Singh, D., & Sharma, A. (2025) · Lecture notes in networks and systems · doi:10.1007/978-981-96-5370-6_33
Robot system for accurate nail recognition, localization and retrieval
Wang, H., Hu, Z., & Zhao, X. (2025) · Intelligent Service Robotics · doi:10.1007/s11370-025-00645-7
“The initial iterations of the YOLO family—specifically, YOLOv1 [9], YOLOv2 [10], and YOLOv3 [11]—incorporated prior frames, residual networks, feature fusion and multi-scale training techniques and outperform other object detection algorithms of the same period.”
Strawberry Inflorescence Detection Using Improved YOLOv5
Feng, J., Gong, G., & Tang, J. (2025) · International Symposium on Intelligent Robotics and Systems (ISoIRS) · doi:10.1109/isoirs65690.2025.11167979
“Detection algorithms can be divided into two-stage (e.g., R-CNN[11]) and single-stage (e.g., SSD[12-13], YOLO[14-18]) detectors.”
Factory Safety Helmet Detection Algorithm Based on Improved YOLOv8
Chen, K., Tian, X., Liu, W., & Liang, J. (2025) · International Symposium on Intelligent Robotics and Systems (ISoIRS) · doi:10.1109/isoirs65690.2025.11168043
“…achieve higher accuracy but suffer from computational complexity and poor real-time performance, while single-stage methods (e.g., SSD [9], YOLO [10], RetinaNet [11], etc.) adopt end-to-end architectures that better balance efficiency and accuracy, making them suitable for real-time monitoring…”
A Plug-and-Play Module for Enhancing Fault-Tolerant Distributed Inference Based on Gaussian Dropout
Hou, Z., & Ohtsuki, T. O. (2025) · International Conference on Communications · doi:10.1109/icc52391.2025.11161290 · Cited by 1
“The cloud server obtains pre-trained DNN models from public repositories suitable for inference tasks generated on IoT devices, such as ResNet [18] for image recognition tasks, YOLO [19] for target detection tasks, and BERT [20] for neurolinguistic tasks.”
Research on the Application of YOLO8 Model in Driver Fatigue Monitoring
Wu, X., Jin, Y., & Jiang, X. C. (2025) · International Symposium on Intelligent Robotics and Systems (ISoIRS) · doi:10.1109/isoirs65690.2025.11168072
“Single-stage approaches, such as OverFeat[2], SqueezeDet [3], and the YOLO [4] series, directly predict target categories and locations through a single network, offering faster processing speeds.”
A Hybrid YOLO-ViT Approach for Real-Time Accident Monitoring through Automated CCTV Surveillance
Vats, T., Chakraborty, D., Rudrapal, D., et al. (2025) · IEEE Guwahati Subsection Conference (GCON) · doi:10.1109/gcon65540.2025.11173324
“The YOLO (You Only Look Once) algorithm [22] is used to analyzeall the frames and filter out the frames without any cars.”
Djellouli, A., Merzoug, M., Hadjila, M., M’hamedi, M., Etchiali, A., & Bekkouche, A. (2025) · Journal of Cardiac Critical Care TSS · doi:10.25259/jccc_45_2025
Nken, A. T. A., McKeever, S., Corcoran, P., & Ullah, I. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-06096-9_20
One-Shot Person Re-identification Using YOLO11-Based FaceNet Architecture
Fernandes, F., Hanchinamani, A., Bagewadi, T. S., et al. (2025) · Lecture notes in networks and systems · doi:10.1007/978-981-96-5723-0_31
Heterogeneous Multi-Chiplets Neural Network Accelerator
Guoyi, Z., Ma, S., Zhang, C., & Wang, B. (2023) · Journal of Computer-Aided Design & Computer Graphics · doi:10.3724/sp.j.1089.2023.19451
Ghosh, A., Bhattacharya, S., Roy, S., Ray, S., Upadhyay, R., & Chakraborty, S. (2025) · Lecture notes in networks and systems · doi:10.1007/978-981-96-4008-9_43
Mayadunna, M. D. N., Senanayake, W. G. N. S., & Senara, N. B. A. (2025) · Proceedings in Technology Transfer · doi:10.1007/978-981-96-9551-5_18
Design and Implementation of AI Algorithms in Home-Cleaning Robot
Ananda, R., Liu, H., Zhang, J., et al. (2023) · Journal of Computer-Aided Design & Computer Graphics · doi:10.3724/sp.j.1089.2023.20048
Identification of Dangerous Driving Patterns Through Computer Vision and Deep Learning
Landa-Buendía, A., Aguilar, J. A. H., Ortiz-Hernández, J., et al. (2025) · Communications in computer and information science · doi:10.1007/978-3-031-97910-1_1
Lightweight Target Detection Algorithm Based on Split Inverted Residual
Zhou, H., Hou, J., Yang, Z., Zeng, L., & Kang, P. (2023) · Journal of Computer-Aided Design & Computer Graphics · doi:10.3724/sp.j.1089.2023.19248
Fei, J. (2025) · Smart innovation, systems and technologies · doi:10.1007/978-3-032-06372-4_23
Machine Learning Algorithms for Computer Vision in Robotics
Kumbhar, M. F., Ghosh, S., & Attaullah, H. M. (2025) · Information systems engineering and management · doi:10.1007/978-3-031-95302-6_9
Guclu, E., Halstead, M., Denman, S., & McCool, C. (2025) · The International Journal of Robotics Research · doi:10.1177/02783649251379093 · Cited by 6
“Early CNN-based object detection approaches such as Faster R-CNN (Ren et al., 2015) and YOLO (Redmon et al., 2016) revolutionized performance.”
Real-time detection of multi-growth-stage strawberry in complex orchard environments via smartphone
Xu, D., Li, Z., Zhang, C., et al. (2025) · Smart Agricultural Technology · doi:10.1016/j.atech.2025.101468
Vehicle detection on roads based on Yolov5 with multi-scale feature fusion
Xu, L., Li, P., Peng, Q., Zhao, Y., Zhu, L., & Yuan, S. (2025) · Array · doi:10.1016/j.array.2025.100522 · Cited by 1
MambaOVD: a Mamba-based open-vocabulary object detection method
Liu, K., Ma, L., & Lu, T. (2025) · Scientific Reports · doi:10.1038/s41598-025-18769-2
Real-Time Object Detection and Motion Estimation on UAVs With Onboard Edge Computing
Wang, L., Yang, M., Lian, S., & Zhang, F. (2025) · IEEE/ASME International Conference on Advanced Intelligent Mechatronics · doi:10.1109/aim64088.2025.11175707
“To overcome these challenges, researchers have proposed several network models based on single-stage object detection algorithms, such as SSD [16], and YOLO [17].”
Zhu, P., Yang, Q., & Wang, F. (2025) · International Conference on Geoinformatics · doi:10.1109/geoinformatics67279.2025.11173545
“Take pavement map cracking and block cracking as examples [11] .”
AI-Enhanced Application for Incentivizing Waste Recycling: A Step Towards Sustainable Environment
Esam, A. M., Khan, S., Chowdhury, O. F., et al. (2025) · doi:10.1109/qpain66474.2025.11171843
“In the first module, a YOLO (You Only Look Once) [14] based object recognition model was trained and deployed for waste category classification.”
InfluentialDeep Learning-Driven Vision-Based Crosswalk Navigation with History-Based and Cascaded Control
Zhuang, H., & Li, C.-H. G. (2025) · IEEE/ASME International Conference on Advanced Intelligent Mechatronics · doi:10.1109/aim64088.2025.11175876
“Pure vision-based navigation, employing deep learning models such as YOLO[7], enables object recognition, obstacle avoidance, and path planning in complex urban landscapes.”
Li, Y., Jiang, M., Zhang, Z., et al. (2025) · International Conference on Electronic Communication and Artificial Intelligence (ICECAI) · doi:10.1109/icecai66283.2025.11170929
“The objective function of YOLO algorithm is the weighted sum of multiple loss functions, which is used to optimize model training [4] .”
Aerial image object detection algorithm based on the improved YOLOv11n
Peng, H., Pang, L., & Wang, J. (2025) · International Conference on Electronic Communication and Artificial Intelligence (ICECAI) · doi:10.1109/icecai66283.2025.11170538
“With the latest progress in deep learning, detection ability is significantly enhanced, especially the YOLO (YOU ONLY LOOK ONCE) [3] series.”
Chen, W. (2025) · International Conference on Electronic Communication and Artificial Intelligence (ICECAI) · doi:10.1109/icecai66283.2025.11170888
“We also include comparisons with other well-known supervised object detection methods, such as SSD [14] and YOLOv3 [15].”
SATSN: A Spatial-Adaptive Two-Stream Network for Automatic Detection of Giraffe Daily Behaviors
Gan, H., Wu, X., Chen, J., Wang, J., Fang, Y., Xue, Y., Jiang, T., Chen, H., Zhang, P., Dong, G., et al. (2025) · Animals · doi:10.3390/ani15192833 · Cited by 1
“The first is a YOLO [21] format dataset for giraffe detection, used to train and evaluate the detection and localization of giraffes.”
Improving Image Classification Performance with Balanced Synthetic Data
Coelho, L. P., & Reis, S. S. (2025) · Lecture notes in mechanical engineering · doi:10.1007/978-3-032-07144-6_15
AS400-DET: Detection using Deep Learning Model for IBM i (AS/400)
Tran, T., Luu, S. T., Bui, Q., & Nomura, S. (2025) · International Conference on Image, Video and Signal Processing (IVSP) · doi:10.1145/3749859.3749866
Weld Detection and Segmentation Using Improved Deep Learning Approach
Nguyen, D. T., Le, V. P., To, T. T., & Nguyen, H. D. (2025) · EAI/Springer Innovations in Communication and Computing · doi:10.1007/978-3-031-90629-9_39 · Cited by 1
YOLO-GNN: An Improved GNN Based YOLOv4 Algorithm for Street Pedestrian Detection
Peng, F., & Chen, Y. (2025) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-032-00218-1_25
Multimodal Anomaly Detection in Medical Imaging: A Text and Image Feature-Based Approach
Jain, R. K., Sato, T., Ruan, X., et al. (2025) · Intelligent systems reference library · doi:10.1007/978-3-031-98149-4_10
Ye, H., Yu, M., & Tang, Q. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-0985-0_19
Healthcare Applications of Object Detection for Tumor Detection Across Diverse Medical Imaging
Jain, R. K., Satô, T., Xiang, R., et al. (2025) · Intelligent systems reference library · doi:10.1007/978-3-031-98149-4_5
Generative Method-Based Traffic Sign Detection and Recognition in Occluded Conditions
Choudhary, P., & Dey, S. (2025) · IEEE Vehicular Technology Conference · doi:10.1109/vtc2025-spring65109.2025.11174525
A Survey on Deep Learning-Based Approaches for Tomato Ripeness Detection
Lestari, D., Aradea, A., Rianto, R., & Mardiati, R. (2025) · International Conference on Wireless and Telematics (ICWT) · doi:10.1109/icwt66752.2025.11181847
“In 2016, [35] introduced an object detection algorithm to the public called YOLO (You Only Look Once).”
Initial Pose Estimation of an Autonomous Mobile Robot via Feature Object Learning and Recognition
Oh, J. S., Park, J., Lee, D. Y., et al. (2025) · doi:10.1109/icufn65838.2025.11170056
“In this paper, we propose an automatic initial localization system that utilizes an RGB-D camera and YOLOv5 to detect real-world objects that humans intuitively recognize, and uses them as semantic landmarks [3].”
Safer and Trustworthier Navigation of Automated Vehicles
Aleksandrov, M. D., Yordanova, K., Borges, E., et al. (2025) · International Conference on Control Systems and Computer Science · doi:10.1109/cscs66924.2025.00035
“Its capabilities extend beyond simple classification, enabling systems to understand spatial relationships, detect anomalies, and facilitate real-time decision making [1].”
Deep Learning-Based Wideband Signal Detection via Time-Frequency Analysis for LPD Communication
Jeon, S., Lee, J.-H., & Jeong, E.-R. (2025) · doi:10.1109/icufn65838.2025.11170066
“The YOLO model is based on the latest one-stage detection architecture, YOLOv8, and employs the x variant (YOLOv8x), which offers the highest accuracy and has the largest number of parameters among the models [5].”
Deep Learning-Based Object Detection System for Vocal Cords in Laryngoscopy Images
Wu, Y.-C., Liang, S., Hsu, C., & Cheng, M.-C. (2025) · IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB) · doi:10.1109/cibcb66090.2025.11177055
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.