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 25,201–25,300 of 51,401
Bearing defect detection algorithm and experiment based on YOLO-BDD
Ma, K., Zhong, X., & Wei, J. (2025) · Engineering Research Express · doi:10.1088/2631-8695/adcdc3 · Cited by 4
E2CL: An Efficient and Effective Classification Learning for Pneumonia Detection in Chest X-rays
Bao, Y., Wang, W., Zhao, L., Zheng, Z., Wu, H. Y., Yu, G., & Lv, L. (2024) · International Conference on Computers and Artificial Intelligence Technology (CAIT) · doi:10.1109/cait64506.2024.10962855 · Cited by 6
Pedestrian and vehicle detection in foggy weather using dehazeformer
Gao, J., Dai, L., Zhang, W., et al. (2025) · The Visual Computer · doi:10.1007/s00371-025-03882-0 · Cited by 4
“This type of algorithm is represented by YOLOv1 proposed by Redmon et al. [20] in 2015.”
Chen, J., Yue, J., Chen, Y., Zhou, H., & Hu, Z. (2025) · IEEE Sensors Journal · doi:10.1109/jsen.2025.3560461 · Cited by 4
“…learning has greatly promoted the advancement of intelligent fault diagnosis techniques, among which convolutional neural networks (CNNs) have been widely used in several fields such as computer vision (CV) because of their ability to automatically extract discriminative features [11], [12], [13].”
Co-training encoder-based transformer method for steel surface defect detection
Wang, Y., Cheng, H., Shi, J., Du, X., & Wang, P. (2025) · Journal of Electronic Imaging · doi:10.1117/1.jei.34.2.023058 · Cited by 4
GCF-DeepLabv3+: An Improved Segmentation Network for Maize Straw Plot Classification
Liu, Y. Y., Zhang, J., Wang, Y., Luo, Y., Sui, P., Ying, R., Liu, X., & Wang, J. (2025) · Agronomy · doi:10.3390/agronomy15051011 · Cited by 5
Defect Detection Method of Carbon Fiber Unidirectional Band Prepreg Based on Enhanced YOLOv8s
Su, W. K., Sang, M., Liu, Y., et al. (2025) · Sensors · doi:10.3390/s25092665 · Cited by 4
“Although YOLO [14–22] (You Only Look Once) is an efficient object detection framework with high speed and accuracy, existing implementations show deficiencies in detecting small targets and defects with large aspect ratios in carbon fiber unidirectional band prepreg surface inspection scenarios.”
Research on underwater disease target detection method of inland waterway based on deep learning
Yu, T., Xie, Y., Luo, J., et al. (2025) · Scientific Reports · doi:10.1038/s41598-025-98570-3 · Cited by 4
“The one-stage object detection methods, such as the YOLO and SSD series, directly return the category probability and position coordinates of objects 16,17 , making them faster than two-stage methods.”
Lightweight Deep Learning Model for Airborne Object Classification
Puduru, V. K., Pardhasaradhi, B., Koorapati, S., et al. (2025) · IEEE International Conference on Communication Systems and Network Technologies (CSNT) · doi:10.1109/csnt64827.2025.10968603 · Cited by 4
PatrolVision: Automated License Plate Recognition in the Wild
Singhal, A., & Singhal, N. (2025) · IEEE SoutheastCon · doi:10.1109/southeastcon56624.2025.10971696 · Cited by 6
Training-free fish species population monitoring in unconstrained underwater videos
Kavasidis, I., Sorrenti, A., Tomarchio, O., et al. (2025) · Procedia Computer Science · doi:10.1016/j.procs.2025.03.104 · Cited by 4
YOLOv8-SP: ship object detection in optical remote sensing imagery
Tian, P., & Li, Z. (2025) · Marine Geodesy · doi:10.1080/01490419.2025.2493860 · Cited by 5
“…offer faster speeds, with representative models including Single Shot MultiBox Detector (SSD) (Liu et al. 2016), You Only Look Once (YOLO) series (Redmon 2016; Redmon and Farhadi 2017; Farhadi and Redmon 2018; Bochkovskiy, Wang, and Liao 2020; Li et al. 2022; Wang, Bochkovskiy, and Liao 2023)…”
Deep sky object detection in astronomical imagery using YOLO models: a comparative assessment
Ramos, L., & Rivas, F. (2025) · Neural Computing and Applications · doi:10.1007/s00521-025-11223-4 · Cited by 7
“Originally introduced by Redmon et al. [21], YOLO is designed for real-time detection, predicting bounding boxes and class probabilities directly from full images in a single pass [22, 23].”
Kathait, S. S., Kumar, A., Sawal, S., et al. (2025) · International Journal of Computer Applications · doi:10.5120/ijca2025924714 · Cited by 4
Simulated Adversarial Attacks on Traffic Sign Recognition of Autonomous Vehicles
Lin, C., Yu, C.-T., Chen, Y., et al. (2025) · IEEE Eurasia Conference on IOT, Communication and Engineering (ECICE) · doi:10.3390/engproc2025092015 · Cited by 4
UEVAVD: A Dataset for Developing UAV's Eye View Active Object Detection
Jiang, X., Liu, T., Liu, L., Liu, Z., & Liu, Y. (2025) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2025.3566604 · Cited by 7
Automated PPE Detection Using YOLOv8 for Real-Time Workplace Safety Monitoring
Gupta, V. K., Rathore, P., Prajapati, P., et al. (2025) · doi:10.38124/ijisrt/25apr1699 · Cited by 4
RSD-YOLO: A Defect Detection Model for Wind Turbine Blade Images
Wang, J., Liu, N., Liu, G., Liu, Y., Zhuang, X., Zhang, L., Wang, Y., & Yu, G. (2025) · Lecture notes in electrical engineering · doi:10.1007/978-981-96-4229-8_39 · Cited by 5
Study on an Improved YOLOv7-Based Algorithm for Human Head Detection
Wu, D. Q., Yan, W., & Wang, J. (2025) · Electronics · doi:10.3390/electronics14091889 · Cited by 5
“Current main-stream deep learning object-detection algorithms are mainly divided into three categories: two-stage algorithms (such as RCNN [8], Faster-RCNN [9], Mask-RCNN [10]), single-stage algorithms (such as the SSD series [11] and YOLO series [12]), and end-to-end detection approaches [13].”
Deep Mix: AI in Littoral Sonar Operations
Vasankari, L., Borzyszkowski, A., Zelioli, L., & Heikkonen, J. (2025) · Journal of Marine Science and Application · doi:10.1007/s11804-025-00695-4 · Cited by 6
“More recent papers have investigated the use of, e.g., Con ‐ volutional Neural Network (CNN)s and novel algorithms such as You Only Look Once (YOLO) (Redmon et al., 2016) to detect mines floating on the surface or in the water column (Munteanu et al., 2022).”
IoT based Speed Control Monitoring and Accident Avoidance using AI Traffic Sign Detection
Rathanasabhapathy, G., Dharaneesh, M., Harivignesh, K. S. M., & Manikandan, M. (2025) · International Conference Trends Material Science and Inventive Materials · doi:10.1109/ictmim65579.2025.10988174 · Cited by 4
Raj, R., Sreemathy, R., Turuk, M., Jagdale, J., & Anish, M. (2025) · Procedia Computer Science · doi:10.1016/j.procs.2025.04.053 · Cited by 10
A Sea-Surface Radar Target-Detection Method Based on an Improved U-Net and Its FPGA Implementation
Zhai, G., Zhou, J., Yang, H., et al. (2025) · Electronics · doi:10.3390/electronics14101944 · Cited by 4
PPDD: Egocentric Crack Segmentation in the Port Pavement with Deep Learning-Based Methods
Yoon, H., Kim, H. K., & Kim, S. (2025) · Applied Sciences · doi:10.3390/app15105446 · Cited by 4
Zheng, W., & Yang, Y. (2025) · IEEE Access · doi:10.1109/access.2025.3569658 · Cited by 4
Alikhani, A., Nguyen, V. D., Inagaki, S., Busam, B., Faridpooya, K., Maier, M. M., Gehlbach, P. L., Iordachita, I. I., Navab, N., Nasseri, M. A., et al. (2025) · IEEE Access · doi:10.1109/access.2025.3564944 · Cited by 6
Hou, F., Meng, Q., Fan, X., & Wang, Y. (2025) · Scientific Reports · doi:10.1038/s41598-025-98203-9 · Cited by 5
Automatic damage detection and localization of ancient city walls—a case study of the Great Wall
Ma, S., Chun, Q., Zhang, C., Li, D., Zhai, F., & Yuan, Y. (2025) · npj Heritage Science · doi:10.1038/s40494-025-01749-0 · Cited by 7
“Notable examples include the YOLO (You only look once) v1 11 -v8 、 SSD (Single Shot Multibox Detector) 12 .”
Air‐to‐Ground Target Detection and Tracking Based on Dual‐Stream Fusion of Unmanned Aerial Vehicle
Wang, C., Yang, J., Sun, D., Gao, Q., Liu, Q., Wang, T., Hu, A., & Wang, L. (2025) · Journal of Field Robotics · doi:10.1002/rob.22592 · Cited by 7
“…UAV reconnaissance usually relies on single ‐ spectral imaging, which is still challenging for target detection and identification in complex environments. et al. 2016] is widely used in the field of computer vision as an advanced target detection algorithm with fast and efficient characteristics.”
Ahmar, W. E., Kolhatkar, D., Nowruzi, F. E., & Laganière, R. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-91575-8_7 · Cited by 6
Jiang, T., Shao, M., Zhang, T., Li, X., & Yu, Q. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-91835-3_2 · Cited by 5
Towards Safer Aging: A Comprehensive Edge Computing Approach to Unconsciousness and Fall Detection
Jim, E. M., Utsha, M. A. H., Aurna, F. N., Choudhury, A., & Hoque, M. A. (2025) · International Conference on Electrical, Computer and Communication Engineering · doi:10.1109/ecce64574.2025.11013783 · Cited by 4
Persimmon fruit detection in complex scenes based on PerD-YOLOv8
Liu, H., Gu, W., Wang, W., Zou, Y., Yang, H., & Li, T. (2025) · Journal of Food Measurement & Characterization · doi:10.1007/s11694-025-03268-9 · Cited by 6
“(b) one-stage algorithms in which target localisation and classification are performed directly and simultaneously, typical network include SSD [14] and YOLO [15].”
A global object-oriented dynamic network for low-altitude remote sensing object detection
Tang, D., Tang, S., Wang, Y., Guan, S., & Jin, Y. (2025) · Scientific Reports · doi:10.1038/s41598-025-02194-6 · Cited by 4
Khang, N. P. H., Triet, N. M., Tuan, H. V., et al. (2025) · IEEJ Transactions on Electrical and Electronic Engineering · doi:10.1002/tee.70067 · Cited by 4
“The YOLO series is a deep learning architecture that has been continuously developed since 2015 [7] for object detection purposes.”
EER-DETR: An Improved Method for Detecting Defects on the Surface of Solar Panels Based on RT-DETR
Dun, J., Yang, H. R., Yuan, S., & Tang, Y. (2025) · Applied Sciences · doi:10.3390/app15116217 · Cited by 7
Ma, C., Liu, C. K., Deng, L., & Xu, P. (2025) · Sensors · doi:10.3390/s25113511 · Cited by 8
“With the rapid development of deep learning technology, deep learning-based object detection algorithms, such as Faster R-CNN [4], SSD [5], and YOLO [6], have become the mainstream choice for optimizing traffic sign detection problems due to their powerful feature extraction capabilities.”
Wu, D., Li, Y., Yang, Z., et al. (2025) · Journal of Medical Internet Research · doi:10.2196/74402 · Cited by 4
Flatfish lesion detection based on part segmentation approach and lesion image generation
Hwang, S., Kim, H., Heo, C., Jeong, H., Jung, S., & Cho, Y. (2025) · Journal of the World Aquaculture Society · doi:10.1111/jwas.70031 · Cited by 6
Real-Time Monitoring of Mobile Construction Resources Based on Multiple Object Tracking
Deng, R., Wang, K., & Mao, Y. (2025) · Journal of Computing in Civil Engineering · doi:10.1061/jccee5.cpeng-6587 · Cited by 8
Pan, T., Hui, M., Huang, J., Fu, Z., Hai, T., & Yao, J. (2025) · Journal of Electronic Imaging · doi:10.1117/1.jei.34.3.033043 · Cited by 5
RL-Net: a rapid and lightweight network for detecting tiny vehicle targets in remote sensing images
Du, Y., Chen, L., & Hao, X. (2025) · Complex & Intelligent Systems · doi:10.1007/s40747-025-01956-z · Cited by 5
“Recently, scholars have begun to explore the practical applications of the You Only Look Once (YOLO) [29] one-stage algorithm in remote sensing images.”
DS-YOLO: A SAR Ship Detection Model for Dense Small Targets
Shen, Y., & Gao, Q. (2025) · Radioengineering · doi:10.13164/re.2025.0407 · Cited by 7
Shan, Z., Dou, H., Wu, F., & Yu, Z. (2025) · Smart Materials and Structures · doi:10.1088/1361-665x/ade6b5 · Cited by 4
Rehman, Z. U., Fauzi, M. F. A., Ahmad, W. S. H. M. W., Abas, F. S., Cheah, P., Chiew, S.-F., & Looi, L. (2025) · Diagnostics · doi:10.3390/diagnostics15131584 · Cited by 8
Streamlining tuberculosis detection with foundation model-based weakly supervised transformer
Bedőházi, Z., Biricz, A., Foster, N., Lin, Y. E., & Csabai, I. (2025) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2025.110554 · Cited by 6
NICE: Improving Panoptic Narrative Detection and Segmentation With Cascading Collaborative Learning
Wang, H., Ji, J., Guo, T., Yang, Y., Sun, X., & Ji, R. (2025) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2025.3583795 · Cited by 11
MSHF-YOLO: Cotton growth detection algorithm integrated multi-semantic and high-frequency features
Luo, J., Wu, Q., Wang, Y., Zhou, Z., Zhuo, Z., & Guo, H. (2025) · Digital Signal Processing · doi:10.1016/j.dsp.2025.105423 · Cited by 5
Sway: efficient pedestrian detection using SAM-based walkable area segmentation and YOLO
Gupta, J., & Sharma, S. (2025) · International Journal of Information Technology · doi:10.1007/s41870-025-02596-9 · Cited by 4
“The initial YOLO model [47], often referred to as a one shot detector, was the first object detection network to integrate the tasks of class label identification and bounding box drawing into a single end-to-end differentiable network.”
Application and identification of aluminum alloy inclusions microstructures based on deep learning
Wang, T., Li, Y., Ding, Y., Liu, Z., Hao, Y., Zhuang, C., & Zhang, W. (2025) · Materials Today Communications · doi:10.1016/j.mtcomm.2025.113184 · Cited by 5
Diverse prey capture strategies in teleost larvae
Mearns, D. S., Hunt, S. A., Schneider, M., Parker, A. V., Stemmer, M., & Baier, H. (2025) · eLife · doi:10.1101/2023.10.03.560453 · Cited by 11
Remoscope: a label-free imaging cytometer for malaria diagnostics
Lebel, P. M., Jeyakumar, I., Khoo, M. W. L., Emorut, J., Charlton, C., Saxena, A., Jacobsen, A., Huynh, E., Wu, W., Courville, G., et al. (2025) · Transactions of the Royal Society of Tropical Medicine and Hygiene · doi:10.1093/trstmh/traf070 · Cited by 6
Do, N.-T., Nguyen, N. N.-Y., Nguyen, D.-P., & Do, T.-H. (2024) · International Conference on Knowledge and Systems Engineering/Proceedings · doi:10.1109/kse63888.2024.11063545 · Cited by 5
YOLO-MFD: Object Detection for Multi-Scenario Fires
Mo, F., Liu, S., Wu, S., Chen, R., & Song, T. (2025) · Information · doi:10.3390/info16070620 · Cited by 6
Cheng, H., Li, Y., Zhang, R., & Zhang, W. (2025) · Sensors · doi:10.3390/s25154565 · Cited by 5
Improving Small Object Detection with Area-Scaled and Dynamic Focal Loss
Raina, S., Challagundla, J., Acharya, S., et al. (2025) · IEEE Annual Computing and Communication Workshop and Conference (CCWC) · doi:10.1109/ccwc62904.2025.10903720 · Cited by 4
A lightweight RKM-YOLO algorithm for transmission line fault inspection
Li, H., Wu, Z., Sun, Y., Wu, X., Luo, K., Zhu, Q., & Wang, G. (2025) · Energy Reports · doi:10.1016/j.egyr.2025.06.052 · Cited by 6
Automated Railway Crack Detection Using Machine Learning: Analysis of Deep Learning Approaches
D'Arms, A., Song, H., Narman, H. S., et al. (2024) · IEEE Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON) · doi:10.1109/iemcon62851.2024.11093324 · Cited by 4
Flapping-Wings Drones for Pests and Diseases Detection in Horticulture
Awesta, O., Hollink, V., & Gallo, M. (2025) · IEEE Transactions on AgriFood Electronics · doi:10.1109/tafe.2025.3589762 · Cited by 7
“YOLO, introduced by Redmon et al. [26], is a prominent one-stage neural network renowned for its real-time performance, achieved by simultaneously predicting bounding boxes and class probabilities.”
Chen, Y., Gu, Q., Wang, X., Shi, X., Xu, L., & Zhang, C. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2025.3597159 · Cited by 8
Tang, J., Xu, B., Li, J., Zhang, M., Huang, C. H., & Feng, L. (2025) · Eng—Advances in Engineering · doi:10.3390/eng6080196 · Cited by 6
“Redmon et al. [14] highlighted that YOLO revolutionized traditional object detection by framing the task as a regression problem.”
MWD-YOLO11n: A Tomato Leaf Disease Detection Method
Yang, Z., Xiao, Y., Zhang, G., et al. (2025) · International Conference on Computer Engineering and Application (ICCEA) · doi:10.1109/iccea65460.2025.11102361 · Cited by 4
“Faster Region-based Convolutional Neural Networks (R-CNN) [6] represent two-stage detection networks, while Single Shot Multibox Detector (SSD) [7] and You Only Look Once (YOLO) [8] represent single-stage detection networks.”
An Efficient Model for Real-Time Traffic Density Analysis and Management Using Visual Graph Networks
Nigam, N., Singh, D. P., Choudhary, J., & Solanki, S. (2025) · IEEE Access · doi:10.1109/access.2025.3593136 · Cited by 4
Optimal Flight Speed and Height Parameters for Computer Vision Detection in UAV Search
Lanča, L., Mališa, M., Jakac, K., & Ivić, S. (2025) · Drones · doi:10.3390/drones9090595 · Cited by 9
Kayadibi, İ., Köse, U., Güraksın, G. E., & Çeti̇n, B. (2025) · The Journal of Supercomputing · doi:10.1007/s11227-025-07775-w · Cited by 5
“The You-Only-Look-Once (YOLO) architecture, proposed by Redmon et al. [40], has emerged as one of the most popular, efficient, and user-friendly open-source object detection algorithms in recent years, owing to its high accuracy and fast inference capabilities.”
Kong, C., Qiu, A., Wibowo, I., Ren, M., Dhori, A., Ling, K., Hu, A.-P., & Kousik, S. (2025) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra55743.2025.11127933 · Cited by 4
Sharma, U., Khan, O. S., Rudinac, S., & Jónsson, B. Þ. (2025) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw67362.2025.00359 · Cited by 5
“…require human judgment and user studies [37], as well as the advent of supervised learning techniques for computer vision and multimedia, especially since the breakthrough of deep learning [7, 18, 19, 31, 41], over the time the focus of research community has shifted towards automatic solutions.”
FCTFANet: A Fused CNN-Transformer Feature Aggregator Network for Image Restoration
Monga, A., Nehete, H., Kaushik, P., Reddy, T. K., Raman, B., & Gaurav Sharma, A. (2025) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw67362.2025.00092 · Cited by 4
“Advances in deep learning approaches for tasks like image classification [20], detection [33] and segmentation [3] have significantly improved the performance and generalization of these methods.”
PineSORT: A Simple Online Real-Time Tracking Framework for Drone Videos in Agriculture
Xie-Li, D., & Fallas-Moya, F. (2025) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw67362.2025.00012 · Cited by 4
CDNet: Efficient Real-Time Chip Defect Detection for Consumer Electronics
Han, T., Wang, X., Dong, Q., et al. (2025) · IEEE Transactions on Consumer Electronics · doi:10.1109/tce.2025.3608075 · Cited by 4
“In contrast, end-to-end methods like YOLO [19], [20], [21] and SSD [22] directly output class probabilities and bounding box coordinates, balancing efficiency and accuracy, and are more suitable for real-time applications, though they may sacrifice some precision for speed.”
Constraint-Driven Auto-Tuning of GEMM-like Operators for MT-3000 Many-core Processor
Qi, X., Fang, J., Zhang, P., Che, Y., & Ren, J. (2025) · International Conference for High Performance Computing, Networking, Storage and Analysis (SC) · doi:10.1145/3712285.3759898 · Cited by 4
“Deep neural networks (DNNs) have made remarkable advancements in areas such as image recognition, object detection, speech recognition, and natural language processing, becoming central to both academic research and industrial applications [2, 9, 10, 16, 22, 26, 29, 31, 32].”
Kyem, B. A., Denteh, E., Asamoah, J. K., Tutu, K. A., & Aboah, A. (2025) · Advances in Data Science and Adaptive Analysis · doi:10.1142/s2424922x26500026 · Cited by 22
Integrating planning perception and action for informed object search
Manso, L. J., Gutierrez, M. A., Bustos, P., & Bachiller, P. (2017) · Cognitive Processing · doi:10.1007/s10339-017-0828-3 · Cited by 4
A segment-wise prediction based on genetic algorithm for object recognition
Tang, X., & Wei, H. (2017) · Neural Computing and Applications · doi:10.1007/s00521-017-3189-z · Cited by 4
Corner points localization in electronic topographic maps with deep neural networks
Dong, L., Zheng, F., Chang, H., & Qin, Y. (2017) · Earth Science Informatics · doi:10.1007/s12145-017-0317-3 · Cited by 4
Reading Text in the Wild from Compressed Images
Galteri, L., Bazazian, D., Seidenari, L., Bertini, M., Bagdanov, A. D., Nicolaou, A., Karatzas, D., & Bimbo, A. D. (2017) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2017.283 · Cited by 5
Deep affordance learning for single- and multiple-instance object detection
Wang, J.-G., Mahendran, P. S., & Teoh, E. K. (2017) · IEEE Region 10 Conference (TENCON) · doi:10.1109/tencon.2017.8227883 · Cited by 4
Target recognition in large scene SAR images based on region proposal regression
Wang, S., Cui, Z., & Cao, Z. (2017) · IEEE International Geoscience and Remote Sensing Symposium (IGARSS) · doi:10.1109/igarss.2017.8127702 · Cited by 4
People detection in crowded scenes using hierarchical features
Zeng, Q., Yuan, Y., Fu, C., & Zhao, Y. H. (2017) · IEEE International Conference on Imaging Systems and Techniques (IST) · doi:10.1109/ist.2017.8261462 · Cited by 4
Map-scan node accelerator for big-data
Maliţa, M., & Gheorghe, Ș. (2017) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata.2017.8258342 · Cited by 4
FasterMDNet: Learning model adaptation by RNN in tracking-by-detection based visual tracking
Hsu, H.-W., & Ding, J. (2017) · Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) · doi:10.1109/apsipa.2017.8282115 · Cited by 5
Precision Security: Integrating Video Surveillance with Surrounding Environment Changes
Wang, W., Chen, X., Zhang, G., Qian, J., Peng, W., Wu, B., & Zheng, H. (2018) · Complexity · doi:10.1155/2018/2959030 · Cited by 4
Temporal Semantic Motion Segmentation Using Spatio Temporal Optimization
Haque, N., Reddy, N. D., & Krishna, K. M. (2018) · Lecture notes in computer science · doi:10.1007/978-3-319-78199-0_7 · Cited by 4
Depth image-based object segmentation scheme for improving human action recognition
Park, S., Park, U., & Kim, D. (2018) · International Conference on Electronics, Information, and Communication (ICEIC) · doi:10.23919/elinfocom.2018.8330654 · Cited by 4
A Hardware Accelerated Robot Middleware Package for Intelligent Processing on Robots
Ishida, Y., Morie, T., & Tamukoh, H. (2018) · IEEE International Symposium on Circuits and Systems proceedings · doi:10.1109/iscas.2018.8351722 · Cited by 4
A Multi-Oriented Scene Text Detector with Position-Sensitive Segmentation
Cheng, P., & Wang, W. (2018) · International Conference on Multimedia Retrieval · doi:10.1145/3206025.3206043 · Cited by 5
A Visual Cortex-Inspired Imaging-Sensor Architecture and Its Application in Real-Time Processing
Wei, H., & Wang, L. (2018) · Sensors · doi:10.3390/s18072116 · Cited by 4
Object Detection Based on Multiscale Merged Feature Map
Luo, Z., Zhang, H., Zhang, Z., Yang, Y. F., & Li, J. (2018) · Communications in computer and information science · doi:10.1007/978-981-13-1702-6_8 · Cited by 4
MFDCNN: A Multimodal Fusion DCNN Framework for Object Detection and Segmentation
Zhou, F., Hu, Y., & Shen, X. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-00764-5_1 · Cited by 3
Research on Multitask Deep Learning Network for Semantic Segmentation and Object Detection
Rui, T., Xiao, F., Tang, J., Zhang, F., Yang, C., & Liu, M. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-00764-5_65 · Cited by 4
3-D People Counting with a Stereo Camera on GPU Embedded Board
Lee, G.-C., Lee, S.-H., & Yoo, J. (2018) · Applied Sciences · doi:10.3390/app8112017 · Cited by 4
EFFICIENT CYCLIC LEARNING RATE SCHEDULES AND THEIR EVALUATIONS FOR NEURAL NETWORK ENSEMBLE
Mori, M., & Nakano, M. (2018) · Machine learning for signal processing ... · doi:10.1109/mlsp.2018.8517060 · Cited by 4
Detecting Knowledge Artifacts in Scientific Document Images - Comparing Deep Learning Architectures
Kerwat, M., George, R., & Shujaee, K. A. (2018) · International Conference on Social Networks Analysis, Management and Security (SNAMS) · doi:10.1109/snams.2018.8554818 · Cited by 4
Fire Area Detection based on Convolutional Neural Network and Improved A* Path Planning
Yu, J., Heo, S. N., Shin, J.-S., & Lee, H. (2018) · International Conference on Information and Communication Technology Robotics (ICT-ROBOT) · doi:10.1109/ict-robot.2018.8549908 · Cited by 4
Computer Vision for Supporting Fashion Creative Processes
Donati, L., Iotti, E., & Prati, A. (2018) · Studies in computational intelligence · doi:10.1007/978-3-030-03000-1_1 · Cited by 4
Multi-mode Study of Deep Learning Applications in Acoustic Signal Processing
Guan, S. U., He, W., Gu, W., Hou, Y., Chen, Y., & Zeng, X. (2018) · SiPS ... design and implementation - IEEE Workshop on Signal Processing Systems · doi:10.1109/sips.2018.8598422 · Cited by 4
Neural Network as an Alternative to the Jacobian for Iterative Solution to Inverse Kinematics
Montenegro, F. J. C., Grando, R. B., Librelotto, G. R., et al. (2018) · doi:10.1109/lars/sbr/wre.2018.00067 · Cited by 4
Evaluating Extended Pruning on Object Detection Neural Networks
O’Keeffe, S., & Villing, R. C. (2018) · Irish Signals and Systems Conference · doi:10.1109/issc.2018.8585345 · Cited by 4
Detection Accuracy of Soccer Players in Aerial Images Captured from Several Viewpoints
Oki, T., Miyamoto, R., Yomo, H., & Hara, S. (2019) · Journal of Functional Morphology and Kinesiology · doi:10.3390/jfmk4010009 · Cited by 6
Omura, K., Yahata, S., Ozawa, S., Ohkawa, T., Chonan, Y., Tsuji, H., & Murakami, N. (2018) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc.2018.00293 · Cited by 4
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.