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 45,101–45,200 of 51,399
Evolution of Object Detection: From Classical to Modern AI Approaches
Verma, P., Verma, G., Charan, C., & Ramola, J. (2025) · Springer eBooks · doi:10.1007/978-981-96-7445-9_3
Unlocking the Secrets of Deep Space: AI Techniques for Object Detection in Astronomical Imagery
Panda, M., & Chandra, Y. (2025) · Springer eBooks · doi:10.1007/978-981-96-7445-9_4
Zhang, Q., Xu, R., Zhang, Z., et al. (2025) · Communications in computer and information science · doi:10.1007/978-981-95-0880-8_31
A Comparative Study on Distal Radius Fracture Detection: YOLOv8 and YOLOv11 Versus Faster R-CNN
Selçuk, B., Serif, S., & Şerif, T. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-02060-4_16
Pace, A., Domínguez-Cid, S., Larios, D. F., et al. (2025) · Springer Proceedings in Materials · doi:10.1007/978-3-031-99987-1_26
Strategic Construction of Initial Datasets for Active Learning: Leveraging Self-Supervised LearningPreprint
Hwang, S., Choi, J., & Choi, J. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5385953
Qin, X., Wu, B., Zhang, M., et al. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5385751
SCSP-YOLO: a method for detecting surface defects on strip steel
Jiang, S., Xu, Y., Lu, H., & Wang, S. (2025) · Pattern Analysis and Applications · doi:10.1007/s10044-025-01530-w
Lane-Based Vehicle Recognition Using Deep Learning Models
Mien, D. P., & Vu, T. T. (2025) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-032-01497-9_26
Building an Automatic Traffic Monitoring System Based on WEBGIS 3D
Hoang, H. M., & Khoi, N. T. (2025) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-032-01497-9_21
A Comparison of Deep Learning Models for White Blood Cell Detection
Le, H. V., & Huynh, H. T. (2025) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-032-01472-6_1
Xue, Y., Dong, C., Wei, Z., et al. (2025) · doi:10.1109/aaiee64965.2025.11100851
“Single-stage mainstream algorithms, such as YOLO [5], SSD [6], and RetinaNet [7], utilize end-to-end architectures to directly predict object locations and categories, offering real-time advantages but struggling with precision in small object detection.”
Yang, I., & Park, D. (2025) · doi:10.3390/engproc2025103010 · Cited by 2
Yang, J., Bao, Y., Xie, Z., Zhang, H., Li, Z., & Li, Y. (2025) · Applied Sciences · doi:10.3390/app15158662 · Cited by 1
Wang, J., Su, J., & Sun, Y. (2025) · Proceedings - International Conference on Image Processing · doi:10.1109/icip55913.2025.11084583
Chang, H., Li, M., Huang, S., & Li, M. (2025) · IEEE Access · doi:10.1109/access.2025.3599213
Towards All-Time, All-Weather Fod Detection Through Generative AI
Qin, X., Song, S., Brengman, J., Bartone, C. G., & Liu, J. (2025) · Proceedings - International Conference on Image Processing · doi:10.1109/icip55913.2025.11084735
Towards Effective and Robust Unlearnable Examples Against Object Detection
Yi, C., Meng, R., Peng, H., Shen, B., & Kot, A. C. (2025) · Proceedings - International Conference on Image Processing · doi:10.1109/icip55913.2025.11084567 · Cited by 1
Frozen Network Few-Shot Object Detection
Nagano, K., Sato, F., Hachiuma, R., Tsutsukawa, K., & Sekii, T. (2025) · Proceedings - International Conference on Image Processing · doi:10.1109/icip55913.2025.11084624
SF-VQA: Saliency Fragments No-Reference Video Quality Assessment
Kim, N.-U., Hahm, C.-H., Kim, W., Cho, I., & Park, S. (2025) · Proceedings - International Conference on Image Processing · doi:10.1109/icip55913.2025.11084380 · Cited by 2
Xue, R., Zeng, G., Tan, Q., Feng, L., Gong, D., Fen, L., Xiao, F., Liu, M., & Peng, Y. (2025) · IEEE International Conference on Pattern Recognition, Machine Vision and Artificial Intelligence (PRMVAI) · doi:10.1109/prmvai65741.2025.11108523 · Cited by 1
“In 2015, Joseph Redmon et al. proposed the yolov1[8] algorithm, which not only marked the birth of yolo detection algorithms but also ushered in a new era of object detection algorithms.”
Implicit Object Recognition via Reinforcement Learning in Out-Of-Domain Scenarios
Koga, K., & Kawakami, R. (2025) · Proceedings - International Conference on Image Processing · doi:10.1109/icip55913.2025.11084495
Savathrakis, G., & Argyros, A. (2025) · Proceedings - International Conference on Image Processing · doi:10.1109/icip55913.2025.11084680
Abdullah, K., Zhang, S., & Nasr, H. (2025) · doi:10.1109/prmvai65741.2025.11108564
“Conversely, single-stage algorithms like YOLO (You Only Look Once) [5] directly predict bounding boxes and class probabilities in one pass, and thus can be utilized quickly and efficiently.”
Face Mask-Wearing Detection Network Based on MSCA-YOLO
Li, D., Zhang, D., Xu, R., et al. (2025) · doi:10.1109/prmvai65741.2025.11108469
ACAM-EfficientDet: a robust deep learning framework for detecting small lesions on plant leaves
Aissaoui, A., Aloui, I., Boudibi, S., Khomri, Z.-E., & Foughalia, A. (2025) · Journal of Ambient Intelligence and Humanized Computing · doi:10.1007/s12652-025-04995-z
“YOLO (Redmon et al. 2016) and (Liu et al. 2016) apply a CNN across the whole image and directly predict bounding boxes and class scores per grid cell.”
Thakur, S. (2025) · Lecture notes in networks and systems · doi:10.1007/978-981-96-6066-7_13
A High-Performance Model for Landslide Geological Hazard Detection, CDCS-YOLO
Ye, Z., Ainiwaer, F., Han, D., et al. (2026) · Applied Sciences · doi:10.3390/app16104804
Moradi, Z., Jahedazad, S., Hosseinian, E., Minaei, T., & Sadighi, A. (2025) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2025.08.11.668339
Real-Time Polyp Detection in Colonoscopy Using YOLOv8: A Fast and Accurate Deep Learning Approach
Redjimi, K., Redjimi, M., & Talaa, A. (2025) · International Journal of Online and Biomedical Engineering (iJOE) · doi:10.3991/ijoe.v21i10.55797
An Improved YOLOv8 Object Detection Method for Images Recognition for Wearable AR Smart Maintenance
Wang, Y., Wang, J., Ye, C., et al. (2025) · Communications in computer and information science · doi:10.1007/978-981-95-1334-5_12
Edge Computing-Enhanced UAV Target Recognition for Real-Time Applications on Terminal Devices
Wang, W., Wu, Y., & Li, H. (2025) · Communications in computer and information science · doi:10.1007/978-981-95-1331-4_33
Automatic Electric Tricycles Trajectory Tracking and Multi-Violation Detection
Guo, L., Yu, B., Xie, B., et al. (2025) · Sensors · doi:10.3390/s25165135
“Single-stage object detection algorithms can be categorized into four types: the entire YOLO (You Only Look Once) series [31], SSD [32], RetinaNet [33], and EfficientDet [34].”
Gurve, M. K., Behera, S., Prasad, Y., & Nitin, N. (2025) · Cluster Computing · doi:10.1007/s10586-025-05181-8
“Consequently, the one-stage detector YOLO [33] has emerged as a preferred choice in the agricultural domain due to its capability to deliver real-time inference, maintain high precision, and ensure compatibility with computationally constrained devices.”
InfluentialA Compact YOLOv5-GhostNet-Based Weapon Detection System for Smart City Applications
Nayak, R., Sahoo, G. K., Pati, U. C., Das, S. K., & Singh, P. (2025) · Lecture notes in networks and systems · doi:10.1007/978-981-96-4741-5_24
Amsa-Yolo: Real-Time Object Detection with Adaptive Multi-Scale Attention MechanismPreprint
Wang, R., wang, C., Sun, P. J., et al. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5396172
Yu, R., Zou, C., Li, J., Gao, B., Tang, J., Qian, H., & Wu, H. (2025) · IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems · doi:10.1109/tcad.2025.3600366
Intelligent Detection of Sports Fields Based on Very High-Resolution Stereo Satellite Imagery
Shang, D., Zhang, Y., Dai, C., & Zhang, L. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2025.3600107 · Cited by 2
Image-based Pedestrian Detection and LiDAR Data Integrated Path Planning for Mobile Robots
Chen, S.-R., & Chen, S.-H. (2025) · IEEE International Conference on Advanced Robotics and its Social Impacts (ARSO) · doi:10.1109/arso64737.2025.11124995
“Among various deep learning models, the You Only Look Once (YOLO) series has been widely adopted due to its high detection efficiency and accuracy [12-13].”
LynX: An Event-Based Gesture Dataset for Egocentric Interaction in Extended Reality
Bartoli, P., Jayaprakash, V., Moosmann, J., Mayer, P., Zappa, F., & Magno, M. (2025) · International Workshop on Advances in Sensors and Interfaces (IWASI) · doi:10.1109/iwasi66786.2025.11122013 · Cited by 2
“The presented dataset provides per-frame hand bounding boxes in the YOLO format ( class , x center , y center , width , height ) [24], together with temporal segmentation for each gesture repetition via start-and end-frame indices, enabling both spatial and temporal analyses.”
Building Resilient AI: Strengthening Data, Security, and Robustness in Neural Networks
Ravikumar, D., Gammell, J., & Roy, K. (2025) · IEEE International On-Line Testing Symposium (IOLTS) · doi:10.1109/iolts65288.2025.11117107
“Machine learning systems have become foundational in numerous applications, from traditional domains such as object localization [20, 3] and classification [13, 23] to healthcare [15] and finance [2, 14], to name a few.”
Red Light Running Detection Using AI-Powered Object Tracking on Embedded Systems
Silva, T., Dias, T. M., & Jorge, P. A. S. (2025) · International Young Engineers Forum on Electrical and Computer Engineering (YEF-ECE) · doi:10.1109/yef-ece66503.2025.11117531
Cao, L., Liang, S., Yang, H., & Tian, X. (2025) · doi:10.1109/icnlp65360.2025.11108402
Modeling of Sleep-Onset Contact Pressure Interaction for Childcare Support Systems
Li, Y., Zhang, B., Shen, H., et al. (2025) · International Conference on Robotics and Automation Sciences (ICRAS) · doi:10.1109/icras65818.2025.11108801
“This model enables real-time human pose estimation and achieves high-precision localization of joint positions [6].”
Measurement of Secondary Dendrite Arm Spacing Using Deep LearningPreprint
Fujiwara, S., Ode, M., Kojima, Y., & Muramatsu, M. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5396650
Sadiq, T., & Omlin, C. W. P. (2025) · Lecture notes in networks and systems · doi:10.1007/978-3-031-99965-9_40
Cloud Particle Detection in 2D-S Imaging Data via an Adaptive Anchor SSD Model
Liu, S., Yang, D., & Fan, L. (2025) · Atmosphere · doi:10.3390/atmos16080985
“Improved methods, such as Faster R-CNN and YOLO, have achieved notable advancements in detection accuracy and efficiency [19–22].”
Pan, H., Yu-jin, Z., Song, J., & Xu, H. (2025) · Electronics · doi:10.3390/electronics14163302
Computer Vision Image Processing and Intelligent Transportation from the Perspective of UAVs
Lin, T., Li, Y., Wu, Z., et al. (2024) · International Conference on Mechatronics and Computer Technology Engineering (MCTE) · doi:10.1109/mcte62870.2024.11117233
A Novel Deep Learning-Based Network for Weld Defect Detection on Steel SurfacesPreprint
Zhong, Z., Shen, F., Xiao, W., Xu, X., Dong, Q., & Deng, J. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5398760
Detection of Brain Tumors Using YOLOv8 Cascaded with Spatial Attention Module
Kumar, S., Jena, P., & Pati, U. C. (2025) · Lecture notes in networks and systems · doi:10.1007/978-981-96-2329-7_31
Rusydi, A. T., Fauzi, R., & Suakanto, S. (2024) · International Conference on Digital Business and Technology Management (ICONDBTM) · doi:10.1109/icondbtm64135.2024.11122721
PCB defect detection method based on improved Yolov8
Zhang, Z., & Zhang, Y. (2024) · International Conference on Mechatronics and Computer Technology Engineering (MCTE) · doi:10.1109/mcte62870.2024.11118155
Study on the Object Identification Method for Improved YOLOv8 in Complex Scenarios
Zhao, J., Song, X., Wang, Y., et al. (2024) · International Conference on Mechatronics and Computer Technology Engineering (MCTE) · doi:10.1109/mcte62870.2024.11117756
Automated Detection and Segmentation of Astrocytes in GFAP-labeled Micrographs using YOLOv8Preprint
Syed, S., Rahman, M. R., Papadakis, M., & Labate, D. (2025) · Research Square · doi:10.21203/rs.3.rs-7330566/v1
A Deep Neural Network for Insulator Defect Detection in Aerial Images
Chen, A., He, X., Zhang, C., et al. (2025) · Journal of Electrical Engineering and Technology · doi:10.1007/s42835-025-02408-x
“The other class is the single-stage target detection algorithm that directly performs positional regression, mainly including SSD [20] and YOLO series [21–24] algorithms.”
Alenizi, F. A., Karim, F. K., Al-shamasneh, A. R. M., et al. (2025) · Computer Modeling in Engineering & Sciences · doi:10.32604/cmes.2025.066023
LAP-Net: a lightweight PCB defect detection network combined with attention mechanisms
Li, Z., Ai, Q., Peng, E., Mao, S., & Han, T. (2025) · Journal of Real-Time Image Processing · doi:10.1007/s11554-025-01749-0
“First are the single-stage methods, with typical algorithms including You Only Look Once (YOLO) [7–11] and Single Shot MultiBox Detection (SSD) [12].”
A Benchmark for Pedestrian Detection in Rain and Fog
张, 伟. (2025) · Computer Science and Application · doi:10.12677/csa.2025.158207
Multi-scale count-task guided feature enhancement face detection
Wu, Z., Lin, Y., Huang, Q., Zhou, W., & Li, H. (2025) · Multimedia Systems · doi:10.1007/s00530-025-01901-7
“With the development of deep learning technology, neural network-based approaches to general object detection, such as SSD [5], YOLO [6], and RetinaNet [7], have markedly advanced the capabilities and performance in the domain of face detection.”
OASIS: Optimized Adaptive System for Intelligent SLAM
Rebel, A., Dutt, N. D., & Donyanavard, B. (2025) · ACM Transactions on Embedded Computing Systems · doi:10.1145/3761808
“However, these accelerators are often shared among multiple processes such as object detection, labeling, and other tasks within the perception pipeline [17], which can lead to contention in memory bandwidth or computational resources.”
Xue, F., Zhang, W., Chen, H., & Song, F. (2025) · Measurement Science and Technology · doi:10.1088/1361-6501/adfe04 · Cited by 2
“Two main strategies have emerged: object detection [13, 14] and semantic segmentation [15, 16].”
Pedestrian Accident Prevention: Intensifying ADAS Framework with YOLO
Shakila, T., & Baalaji, K. (2025) · International Conference on Computing for Sustainable Global Development · doi:10.23919/indiacom66777.2025.11115786
A Wavelet Convolution-Based Improved YOLOv11 Model for Metallic Surface Defect Detection
Li, J., Xu, H., Xie, Z., Wang, S., Wei, S., & Qian, L. (2025) · International Symposium on Big Data and Applied Statistics (ISBDAS) · doi:10.1109/isbdas64762.2025.11117100
Head-Adaptive Knowledge Distillation for Dense Object Detection
Wu, K.-F., Wang, L., & Duan, S. (2025) · International Symposium on Big Data and Applied Statistics (ISBDAS) · doi:10.1109/isbdas64762.2025.11116857
ACL-YOLO: A Novel Real-Time Network for UAV-Based Infrared Object Detection
Gao, F., Xu, H., Zhang, Y., & Cheng, L. (2025) · International Conference on Automation, Control and Robotics Engineering (CACRE) · doi:10.1109/cacre66141.2025.11119553
“Within the domain of real-time object detection, the main-stream YOLO [2] algorithm, compared with traditional real-time object detection algorithms such as SSD and DETR.”
YOLO-CLA: An Efficient and Lightweight Dense Target Detection Model Based on YOLOv5
Liu, J., Zeng, S., Li, X., et al. (2024) · International Academic Exchange Conference on Science and Technology Innovation (IAECST) · doi:10.1109/iaecst64597.2024.11117296
AWBN-YOLO: a surface defect detection method for aero-engine blades in sample-limited scenarios
Gao, W., Lv, N., & Du, F. (2025) · Multimedia Systems · doi:10.1007/s00530-025-01967-3 · Cited by 5
DeblurGAN-v2-Based Landslide Recognition Method for Blurred Images
Song, Z., & Fang, D. (2025) · Highlights in Science Engineering and Technology · doi:10.54097/dtwpmb68
SW-YOLO: Wildlife Object Detection Based on Segment Anything and YOLO Models
Yang, Q., Liu, G., Zhao, X., Ma, B., & Mou, C. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-1233-1_20
A Lightweight Method Based on YOLOv8 for Metal Surface Defect Detection in Industrial Manufacturing
Huang, Y., & Zheng, D. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-1233-1_47
FFYOLO: A Lightweight Small Target Detection Algorithm for UAVs
Su, G., Lu, F., & Yan, S. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-1233-1_51
Ded-YOLOv5: An Efficient Defect Detection Network Based on HR Imaging
Chen, Y., Wang, X., Hao, Y., et al. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-1233-1_49
DHPE-DETR: A Dynamic Hybrid Position Encoding-Based Multi-Scale Traffic Sign Detection Algorithm
Ren, Y., Zhang, J., Liu, B., & Ren, B. (2025) · IEEE Access · doi:10.1109/access.2025.3598815
Lightweight Detection Network for Small Target Defects in Shaft Lining Crack
Hu, R. B., Jia, X., Han, X., et al. (2025) · IET Image Processing · doi:10.1049/ipr2.70170
A Lightweight YOLOv7‐Based Algorithm for Detecting Foreign Objects on Coal Conveyors
Zhang, M., Zilong, S., & Zhang, Y. (2025) · Energy Science & Engineering · doi:10.1002/ese3.70255
“Currently, mainstream target detection algorithms are generally classified into two categories: two ‐ stage algorithms and one ‐ stage algorithms, exemplified by RCNN and the YOLO series, respectively [8, 9].”
Life history induces markedly divergent insect responses to habitat loss
Colares, L. F., Peres, C. A., & Dambros, C. D. S. (2025) · Journal of Animal Ecology · doi:10.1111/1365-2656.70117
“We trained and performed fivefold cross-validation using the extra-large variant of the YOLO object detection model (YOLOv8; Redmon et al., 2016) for 250 epochs, with a batch size of 50 and an input image size of 640 × 640 pixels.”
Adaptive Attention Mechanism Based on Dynamic Event Priority for Highway Surveillance
Liu, T., Qi, Z., Kong, D., Zhang, Y., Tian, Y., & Lv, C. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-9582-9_6
A Comparative Study of a Real-Time Multi-Person Tracking System in an Urban Square Dataset
Jafarzadeh, P., Zelioli, L., Farahnakian, F., Nevalainen, P., & Heikkonen, J. (2025) · International Conference on Activity and Behavior Computing (ABC) · doi:10.1109/abc64332.2025.11118548
“YOLO models [7], [8], [9] split the input image into a grid and predict bounding boxes and class probabilities directly for each cell.”
Sajja, B., Qiu, W., Yoo, J., et al. (2025) · IEEE International Conference on Data Engineering Workshops (ICDEW) · doi:10.1109/icdew67478.2025.00013
“Another prominent CNN-based object detection framework is YOLO (You Only Look Once) [13].”
Closing the Gap Between Real and Anonymized Data for Training Face Detection Models
Leibl, A., Gomez‐Barrero, M., & Mayer, H. (2025) · International Workshop on Biometrics and Forensics (IWBF) · doi:10.1109/iwbf63717.2025.11113394
“Here, we adopt the same evaluation approach, but replace DSFD with YOLOv8 [30], [31].”
Kirindearachchi, Y., & Liyanage, L. H. (2025) · International Conference on Activity and Behavior Computing (ABC) · doi:10.1109/abc64332.2025.11118553 · Cited by 1
“To address these challenges, this study applies State of The Art (SoTA) computer vision and machine learning techniques, specifically YOLO [5] models, to detect small animals on roadsides in real-time.”
Small, Mobile, and Autonomous Agricultural Robots
Muelaner, J. E. (2025) · doi:10.4271/epr2025012
Optimizing Fire and Smoke Detection in CCTV Systems using Real-Time Detection Transformers
Imran, M. M., & Razzaq, F. A. (2024) · International Conference on Innovative Computing (ICIC) · doi:10.1109/icic63915.2024.11116389
Balancing Model Inference Speed and Accuracy in the Satellite Object Detection Task
Affek, M., & Szymański, J. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-02406-0_19
Automated Segmentation and Quantification of Histology Fragments for Enhanced Macroscopic Reporting
Chaiani, M., Selouani, S., & Mailhot, S. (2025) · Applied Sciences · doi:10.3390/app15179276 · Cited by 1
Fernandez-de-Osso, A. I., & Sánchez-Trigo, H. (2025) · International Journal of Sports Science & Coaching · doi:10.1177/17479541251370192 · Cited by 1
“4 Following this milestone, numerous CNN-based models have been developed for various image-processing tasks, 5,6 many of which have been adapted for sports performance analysis.”
InfluentialSafety Support Network System Using Overhead Sensing by a UAV Equipped with 3D LiDAR
Miyaji, H., Shudo, T., & Yamamoto, H. (2025) · IEEE Consumer Electronics Magazine · doi:10.1109/mce.2025.3601303 · Cited by 1
“11 Furthermore, by mounting the camera on the UAV, the system can acquire broader data compared with ground-based observations and can move the observation node in parallel with the target’s movement.”
Navarro, A., de Quinto, C., Hernández, J. A., et al. (2025) · International Conference on Transparent Optical Networks · doi:10.1109/icton67126.2025.11125075
Tian, P., Ma, Q., Yu, H., & Lü, J. (2025) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2025.3598594 · Cited by 1
“I N RECENT years, deep learning models have emerged as fundamental components across various domains, such as computer vision, natural language processing, and data mining [1], [2], [3].”
Ye, Z., Li, F., Ding, Y., Cai, J., Wang, L., & Huang, L. (2025) · IEEE International Conference on Electrical Materials and Power Equipment (ICEMPE) · doi:10.1109/icempe66159.2025.11123039
SmartClassVue: Video-Based Automated Student Behavior Monitoring in Offline Classrooms
Pandey, S. K., Pabba, C., & Kumar, P. (2025) · Lecture notes in educational technology · doi:10.1007/978-981-96-5761-2_8 · Cited by 1
Real-Time Littering Detection: A Computer Vision Approach Using OpenCV2 and YOLO V3
Haritas, H. K., Bankapure, D., Kulkarni, P. S., et al. (2025) · Lecture notes in electrical engineering · doi:10.1007/978-981-96-1587-2_38
VisLint: An Automated Static Analysis Approach for Visual Programming
Chai, X., & Sun, Y. (2025) · Tsinghua Science & Technology · doi:10.26599/tst.2024.9010108
A LIGHTWEIGHT WEED IDENTIFICATION METHOD FOR CHINESE CABBAGE FIELDS BASED ON THE IMPROVED YOLOv11
Ji, S., Sun, J., & Zhang, C. (2025) · INMATEH Agricultural Engineering · doi:10.35633/inmateh-76-73
Yapay Zeka Kullanarak Yüzdeki Duygu Tanıma
Tuzcu, S. K., & KASAPBAŞI, M. C. (2025) · İstanbul Ticaret Üniversitesi Teknoloji ve Uygulamalı Bilimler Dergisi · doi:10.56809/icujtas.1518225
A-CLAPS: Automatic Correction of Language and Pronunciation Errors in Slide-based Presentations
Li, Y., Liu, Y., & Zhao, Y. (2025) · IEEE Annual Computers, Software, and Applications Conference (COMPSAC) · doi:10.1109/compsac65507.2025.00189
“Advances in computer vision, from early SIFT and HOG techniques to modern CNN-based models like YOLO [4] and Faster R-CNN [5], enable real-time accuracy.”
YOLO-ALS: Dynamic Convolution With Adaptive Local Context for Remote Sensing Target Detection
Feng, R., Zhao, Z., Zhao, T., et al. (2025) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2025.3602896
Detecção de Ninhos de Cupins em Pastagens com Técnicas de Visão Computacional
Pereira, P. L. M., Tomaz, L. B. P., & Orbolato, D. R. S. (2025) · doi:10.5753/encompif.2025.8990
HLM-YOLO: A Lightweight Instance Segmentation Model for Road Potholes
Cheng, J., & Cheng, Y. (2025) · Communications in computer and information science · doi:10.1007/978-981-95-0848-8_15
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.