You Only Look Once: Unified, Real-Time Object Detection
Open accessThe DOI matches its Crossref record; 53 of the 53 references it cites were found in a registry or an index; 8 of the 25 sources its claims cite were checked for support.
Abstract
We present YOLO, a new approach to object detection. Prior work on object detection repurposes classifiers to perform detection. Instead, we frame object detection as a regression problem to spatially separated bounding boxes and associated class probabilities. A single neural network predicts bounding boxes and class probabilities directly from full images in one evaluation. Since the whole detection pipeline is a single network, it can be optimized end-to-end directly on detection performance. Our unified architecture is extremely fast. Our base YOLO model processes images in real-time at 45 frames per second. A smaller version of the network, Fast YOLO, processes an astounding 155 frames per second while still achieving double the mAP of other real-time detectors. Compared to state-of-the-art detection systems, YOLO makes more localization errors but is less likely to predict false positives on background. Finally, YOLO learns very general representations of objects. It outperforms other detection methods, including DPM and R-CNN, when generalizing from natural images to other domains like artwork.
Overview
CoChat Summary
TL;DR
YOLO reframes object detection as a single regression problem, using one convolutional network to predict bounding boxes and class probabilities directly from full images. It achieves real-time detection speeds while remaining competitive with, and complementary to, slower region-based detectors.
Key findings
- YOLO runs at 45 FPS on a Titan X GPU, and Fast YOLO runs at 155 FPS; Fast YOLO reaches 52.7% mAP on PASCAL VOC 2007, more than double prior real-time detectors, while YOLO reaches 63.4% mAP.
- On PASCAL VOC 2012, YOLO scores 57.9% mAP; combining Fast R-CNN with YOLO raises Fast R-CNN from 71.8% to 75.0% mAP on VOC 2007, a 3.2% gain.
- YOLO makes fewer background false positives than Fast R-CNN: Fast R-CNN has 13.6% background false positives among top detections and is almost 3× more likely to predict background detections than YOLO.
- YOLO generalizes better to artwork: on Picasso, YOLO gets 53.3 AP versus R-CNN’s 10.4 AP and DPM’s 37.8 AP; on People-Art, YOLO gets 45 AP versus R-CNN’s 26 AP and DPM’s 32 AP.
Methods
- Detection is modeled as a single CNN regression: the image is divided into an S×S grid; for PASCAL VOC, S=7, B=2, C=20, producing a 7×7×30 tensor of bounding boxes, confidence scores, and class probabilities.
- The base network has 24 convolutional layers followed by 2 fully connected layers; Fast YOLO uses 9 convolutional layers. Convolutional layers are pretrained on ImageNet at 224×224, then detection training uses 448×448 input.
- Training uses PASCAL VOC 2007 and 2012 for about 135 epochs, batch size 64, momentum 0.9, decay 0.0005, sum-squared error with λ_coord=5 and λ_noobj=0.5, dropout, and data augmentation.
Limitations
- The paper states YOLO imposes strong spatial constraints because each grid cell predicts only two boxes and one class, limiting nearby objects and struggling with small objects in groups such as flocks of birds.
- The paper states YOLO struggles to generalize to objects in new or unusual aspect ratios or configurations, uses relatively coarse features due to downsampling, and its loss treats small and large box errors equally; its main error source is incorrect localization.
- The paper states YOLO still lags state-of-the-art detection accuracy and struggles to precisely localize some objects, especially small ones.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Figures





Verification
Claims the paper makes
6 Valid · 8 Not valid · 15 Not checked · 92 Own results and interpretations
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“While it is much faster than R-CNN, it still falls short of real-time and takes a significant accuracy hit from not having good proposals.”
What the sources say
- Could not verifycites [20] [20] K. Lenc and A. Vedaldi. R-cnn minus r. arXiv preprint arXiv:1506.06981 , 2015. 5, 6 - sourceExperimental — accuracy not yet measured
The ConvNet-based Object Detection section identifies R-CNN minus R as a method that uses predefined regions instead of region proposals. It gives no runtime measurement or assessment of whether the method achieves real-time detection; searches for real-time performance and speed did not establish that claim. (LLM, conf=0.76)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Could not verify
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“To avoid overfitting we use dropout and extensive data augmentation.”
What the sources say
- Partly supportedcites [18] [18] G. E. Hinton, N. Srivastava, A. Krizhevsky, I. Sutskever, and R. R. Salakhutdinov. Improving neural networks by preventing co-adaptation of feature detectors. arXiv preprint arXiv:1207.0580 , 2012. 4 - sourceExperimental — accuracy not yet measured
The paper states that dropout reduces overfitting (p. 1) and describes using dropout with data augmentation for its ImageNet model (H Models for ImageNet, p. 18). It does not establish that YOLO uses either technique or describe YOLO’s augmentation as extensive. (LLM, conf=0.88)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“However, only 30Hz DPM [31] actually runs in real-time.”
What the sources say
- Supportedcites [31] [31] M. A. Sadeghi and D. Forsyth. 30hz object detection with dpm v5. In Computer Vision-ECCV 2014 , pages 65-79. Springer, 2014. 5, 6 - source
The Introduction (p.1) states that 'except for certain objects including face, pedestrians and certain rigid objects, detectors do not currently run at video rate' and that the presented architecture detects the 20 PASCAL VOC categories simultaneously at 30Hz, i.e. at video/real-time rate. The Abstract (p.1) and Table 2 (Method) bound the comparison to other DPM speed-up efforts: reference DPM at 0.07Hz, the fastest GPU 'Vanilla DPM' at ~1Hz, FTVQ at 0.53s, and 'over an order of magnitude faster than the previous fastest DPM implementation', so none of the listed variants reaches real-time. Thus our copy supports both parts of the attribution: that this 30Hz DPM runs in real-time and that it is the only such DPM among the speed-up efforts compared. (LLM, conf=0.82)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“While it is much faster than R-CNN, it still falls short of real-time and takes a significant accuracy hit from not having good proposals.”
What the sources say
- Could not verifycites [20] [20] K. Lenc and A. Vedaldi. R-cnn minus r. arXiv preprint arXiv:1506.06981 , 2015. 5, 6 - sourceExperimental — accuracy not yet measured
The ConvNet-based Object Detection section identifies R-CNN minus R and says it uses predefined regions in an SPPnet system, but gives no speed comparison with R-CNN. A search for R-CNN minus R and speed found no passage in our copy establishing that it is much faster. (LLM, conf=0.73)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Could not verify
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“While it is much faster than R-CNN, it still falls short of real-time and takes a significant accuracy hit from not having good proposals.”
What the sources say
- Partly supportedcites [20] [20] K. Lenc and A. Vedaldi. R-cnn minus r. arXiv preprint arXiv:1506.06981 , 2015. 5, 6 - sourceExperimental — accuracy not yet measured
The “ConvNet-based Object Detection” section (page unavailable) says R-CNN minus R uses predefined regions instead of region proposals. It does not say that this causes a significant accuracy loss; the paper’s discussion of low accuracy concerns a different system, naïve Faster R-CNN. (LLM, conf=0.83)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
84 more claims
Create a free account to see all 121 claims and to verify the 2 references still open.
- Probably not a substantial claim. 17
- It may state two separate claims as one. 15
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“which was not thoroughly investigated in prevIoUs work such as YOLOv1 [20] and YOLOv2 [51] employing MSE/L2 loss (Mean Squared Error).”
From Object Detection in 20 Years: A Survey (2023) · cites this paper as [20]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“the YOLO series models v2-v5 [144-147] are some of the most advanced object detection methods based on DNN, which have good performance in terms of speed and precision.”
From A survey of model compression strategies for object detection (2023) · cites this paper as [144]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“As a typical and more widely used new form of applications [9], various deep learning-based intelligent services and applications have changed many aspects of people's lives due to the great advantages of Deep Learning (DL) in the fields of Computer Vision (CV) and Natural Language Processing (NLP) [10].”
From Convergence of Edge Computing and Deep Learning: A Comprehensive Survey (2020) · cites this paper as [9]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“A convolutional neural network predicts the bounding boxes as well as class probabilities for all the objects depicted in an image.”
From Object detection using YOLO: challenges, architectural successors, datasets and applications (2023) · cites this paper as [56]
The cited source says what the claim attributes to it.
In the citing paper
“Authors of YOLO [56] have reframed the problem of object detection as a regression problem instead of classification problem.”
From Object detection using YOLO: challenges, architectural successors, datasets and applications (2023) · cites this paper as [56]
6 more claims about this paper
Create a free account to see every claim other papers make about this one.
Citations
Cites
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2577031 · Cited by 73,472
Self-citationFaster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2015) · arXiv · doi:10.48550/arxiv.1506.01497 · Cited by 70,812
Self-citationGoing deeper with convolutions
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298594 · Cited by 48,562
ImageNet Large Scale Visual Recognition Challenge
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-015-0816-y · Cited by 39,380 · cited 1×
“We pretrain our convolutional layers on the ImageNet 1000-class competition dataset [29].”
MethodHistograms of Oriented Gradients for Human Detection
Dalal, N., & Triggs, B. (2005) · 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) · doi:10.1109/cvpr.2005.177 · Cited by 33,584 · cited 2×
“Detection pipelines generally start by extracting a set of robust features from input images (Haar [25], SIFT [23], HOG [4], convolutional features [6]).”
MethodRich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
Girshick, R., Donahue, J., Darrell, T., & Malik, J. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.81 · Cited by 32,684 · cited 2×
“Then, classifiers [35, 21, 13, 10] or localizers [1, 31] are used to identify objects in the feature space.”
MethodSelf-citationGirshick, R. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.169 · Cited by 28,105
Self-citationDelving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
He, K., Zhang, X., Ren, S., & Sun, J. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.123 · Cited by 19,741 · cited 1×
“Convolutional neural networks (CNNs) achieve impressive performance on classification tasks at real-time speeds [13].”
Object recognition from local scale-invariant features
Lowe, D. G. (1999) · Proceedings of the Seventh IEEE International Conference on Computer Vision · doi:10.1109/iccv.1999.790410 · Cited by 16,472 · cited 1×
“Detection pipelines generally start by extracting a set of robust features from input images (Haar [25], SIFT [23], HOG [4], convolutional features [6]).”
MethodRobust Real-Time Face Detection
Viola, P., & Jones, M. J. (2004) · International Journal of Computer Vision · doi:10.1023/b:visi.0000013087.49260.fb · Cited by 14,097 · cited 1×
“Detectors for single classes like faces or people can be highly optimized since they have to deal with much less variation [36].”
Background
Cited by
Items 34,501–34,600 of 51,399
YOLOv8-SwinT: a Real Time Object Detector via Fusion of YOLOv8 and Swin Transformer
Liu, K.-H., Wang, M., Liu, T.-J., & Tai, W.-S. (2025) · IEEE International Conference on Consumer Electronics - Taiwan (ICCE-Taiwan) · doi:10.1109/icce-taiwan66881.2025.11208080 · Cited by 1
“Among various object detection methods, the YOLO series [1] stands out for its speed and efficiency.”
Taming neural radiance fields for underwater object detection in sonar images
Zhang, X., Chen, X., & Yu, J. (2025) · Ocean Engineering · doi:10.1016/j.oceaneng.2025.123281 · Cited by 1
UWDET: IoT-Enabled Training Enhancement for Resource-Limited Underwater Object Detection
Zhu, Y., Han, G., Zhu, H., & Wang, Z. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3630828 · Cited by 2
“One-stage detectors, such as single shot multibox detector [25] and the You Only Look Once (YOLO) series [26], [27], [28], [29], [30], treat object detection as a unified regression problem.”
SAILDet: Wavelet-Preserved Lightweight One-Stage Detector for Tiny Objects in Remote Sensing
Ma, J., Wang, H., Wang, T., et al. (2025) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2025.3631843 · Cited by 1
Xingfei, 朱. Z., Zhaofei, 孙. S., Qimeng, 王. W., et al. (2025) · Laser & Optoelectronics Progress · doi:10.3788/lop250821 · Cited by 1
Ghelmani, A., & Hammad, A. (2025) · Journal of Computing in Civil Engineering · doi:10.1061/jccee5.cpeng-6670 · Cited by 1
Hybrid Sensor Fusion Beamforming for UAV mmWave Communication
Sugimoto, Y., & Tran, G. K. (2025) · Future Internet · doi:10.3390/fi17110521 · Cited by 1
“We employ a YOLO-based (You Only Look Once) model [26] for real-time 2D object detection due to its high speed, which is essential for tracking a fast-moving UAV (Figure 3).”
Application of machine learning tools in road bridge weigh-in-motion systems
Mróz, A., Kamiński, T., & Bień, J. (2024) · Studia Geotechnica et Mechanica · doi:10.2478/sgem-2025-0020 · Cited by 1
UnfoldDet: Advancing Surface Defect Detection With Dual Feature Separation and Relation Reasoning
Hou, X., Liu, M., & Du, S. (2025) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2025.3634684 · Cited by 1
“However, existing defect detectors [11], [12], [13] commonly employ a parallel Region of Interest (RoI) inference strategy.”
Chauhan, H. N., & Thacker, C. B. (2025) · Cybernetics and Information Technologies · doi:10.2478/cait-2025-0036 · Cited by 1
Abiam, R. G., Meriem, C., Timon, B. R., Raúl, T. C., Marina, M. S., Lorenzo-Felipe, Á., Hyun-Suk, S., María-Jesús, Z. S., Ricardo, T., Juan-Antonio, C. P., et al. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.113493 · Cited by 2
Automated quality evaluation of Cervical Cytopathology Whole Slide Images based on content analysis
Kang, L., Wang, J., Qin, J., Liang, Y., & He, Y. (2025) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2025.109419 · Cited by 1
Wang, T., Wang, Y., Zong, P., Xu, S., Wei, W., & Liu, H. (2025) · IET Image Processing · doi:10.1049/ipr2.70261 · Cited by 1
MFDGNet: multi-domain fusion and dynamic gating network for infrared gas leak detection
Li, D., Wang, S., & Gao, S. (2025) · Measurement Science and Technology · doi:10.1088/1361-6501/ae2cb4 · Cited by 1
“CNNs employ multiple convolutional and pooling layers to extract local features [11, 12], which are subsequently fused by fully connected layers into high-dimensional representations for object detection and loss computation.”
Brief review on deep learning-based tomato ripeness detection techniques for smart agriculture
Zhang, X., Adli, H. K., Abdullah, N., Ridzuan, F., & Wu, P. (2025) · AIP conference proceedings · doi:10.1063/5.0294916 · Cited by 1
Suga, S., Ishii, H., Takahashi, T., Suzuki, M., Tsuzuki, K., Mae, Y., & Aoyagi, S. (2025) · Journal of Robotics and Mechatronics · doi:10.20965/jrm.2025.p1283 · Cited by 2
Wang, L., Ouyang, L., Weng, H., Chen, X., Wang, A., & Zhang, K. (2025) · Mathematics · doi:10.3390/math14010004 · Cited by 1
Kurdthongmee, W., Sukkuea, A., Alahi, M. E. E., et al. (2025) · Journal of Imaging · doi:10.3390/jimaging12010001 · Cited by 1
“Using YOLO family provides real-time detection ability with high accuracy [29–32], and more recent segmentation architectures such as the Mask R-CNN, YOLACT, Mask2Former, and SAM provide pixel-wise details of thick fruit boundaries [33–36].”
Hidayattuloh, C., Ferdinand, R., Darmawan, S. C., et al. (2025) · International Conference on Cybernetics and Intelligent System (ICORIS) · doi:10.1109/icoris67789.2025.11296071 · Cited by 1
“Object detection-based methods such as You Only Look Once (YOLO) are increasingly popular due to their ability to perform real-time detection, with high accuracy and speed [7],[8].”
Gao, Y., Zheng, Z., & Dongdong, L. (2025) · Complexity · doi:10.1155/cplx/6666447 · Cited by 1
Li, Z., Jia, D., He, Z., & Du, D. (2025) · Journal of Real-Time Image Processing · doi:10.1007/s11554-025-01826-4 · Cited by 1
“Object detection models are generally categorized into two main types: single-stage models, exemplified by the YOLO series [3, 15, 20–22, 24–26, 28], and two-stage models, represented by the Fast-RCNN [7] family.”
BFS-YOLO: a lightweight vehicle detection algorithm with a cross-layer feature fusion structure
Yang, X., Qiang, S., He, L., Gao, J., Zhu, G., Gui, C., & Ren, N. (2025) · Journal of Real-Time Image Processing · doi:10.1007/s11554-025-01835-3 · Cited by 2
“Redmon et al. [13] designed the YOLO (You Only Look Once) target detection algorithm after a lot of research, which was an end-to-end one-stage detection algorithm.”
DCAS-EMAdp: Small Space Object Detection with Lightweight DCAS and Directional-Pooling Enhanced EMA
Nuamnoi, P., Thammasudjarit, R., Khonthapagdee, S., et al. (2025) · International Computer Science and Engineering Conference · doi:10.1109/icsec67360.2025.11298118 · Cited by 1
“Moreover, SSA missions require real-time processing to avoid collision risks, thereby necessitating the application of AI-based object detection models to enhance the detection of space objects from imagery [6]–[16].”
Srithongtae, K., Kitrattana, B., Tanirat, P., et al. (2025) · International Joint Conference on Computer Science and Software Engineering · doi:10.1109/jcsse67377.2025.11297919 · Cited by 1
“It was developed by J. Redmon, S. Divvala, R. Girshick, and A. Farhadi (2016) [3] and is based on the concept of dividing an image into a grid and simultaneously predicting the locations and classes of objects.”
Automated Information Extraction From Medical Prescriptions
Bourahla, A., Kadi, A. K., & Malki, A. (2025) · International Conference on Networking and Advanced Systems (ICNAS) · doi:10.1109/icnas68168.2025.11298003 · Cited by 1
Muthaiyah, S., Zaw, T. O. K., Chuah, T. K., et al. (2025) · International Conference on Emerging Trends in Networks and Computer Communications (ETNCC) · doi:10.1109/etncc66224.2025.11299687 · Cited by 1
“Machine learning helps in disease detection at an early stage and efficient allocation of resources for hospitals, whereas AI-based surveillance systems help public security with expedited threat detection and emergency response [3].”
Li, Y., Lu, L., Guo, G., Na, L., Liang, X., Su, P., An, Q., & Wang, P. (2025) · ISPRS International Journal of Geo-Information · doi:10.3390/ijgi15010007 · Cited by 1
Vision-Based Autonomous Underwater Cleaning System Using Multi-Scale A* Path Planning
Chen, E., Lin, Z., Chen, J., Shen, Z., Chen, P., & Fu, X. (2025) · Technologies · doi:10.3390/technologies14010007 · Cited by 1
Confidence-Guided Multi-Exit Models for Energy-Optimized Object Detection in Road Environments
Dofitas, C. S., Kim, Y.-W., & Byun, Y.-C. (2025) · IEEE Access · doi:10.1109/access.2025.3648049 · Cited by 1
Fu, X., Wu, D., & Xu, S. (2025) · Remote Sensing · doi:10.3390/rs18010044 · Cited by 1
AI-Based Digitization of Product Inspection Forms with LLMs and Document Intelligence
Taşyürek, E. Y., Omurca, S. İ., Damar, T. P., et al. (2025) · International Conference on Communications, Information, Electronic and Energy Systems (CIEES) · doi:10.1109/ciees66347.2025.11300243 · Cited by 1
“The YOLO (You Only Look Once) architecture [8] was designed for real-time object detection in images and videos.”
Cracking location prediction of UHPFRC based on deep learning of fiber distribution
Luo, X., & Matsumoto, T. (2025) · Engineering Failure Analysis · doi:10.1016/j.engfailanal.2025.110488 · Cited by 1
Han, S., Zhang, Z., Liu, J., Han, X., Wang, T., & Che, H. (2025) · IEEE Access · doi:10.1109/access.2025.3648771 · Cited by 1
Liu, H., Qin, J., ZHANG, Z. Z., Liang, H., Deng, H., Xiao, S., & Yu, M. (2025) · Scientific Reports · doi:10.1038/s41598-025-32425-9 · Cited by 4
KGNAS: Prior-Knowledge-Guided NAS for Real-Time Object Detection on Edge Devices
Mo, Y., Tu, X., Chen, Y., & Liu, H. (2025) · IEEE Transactions on Computers · doi:10.1109/tc.2025.3646160 · Cited by 1
“One-stage object detection models [15], [28], [29] aiming to achieve a balance between speed and accuracy are evolving rapidly.”
Tan, S., Tan, J., Man, J., Ma, J., & Ding, X. (2025) · Journal of Real-Time Image Processing · doi:10.1007/s11554-025-01838-0 · Cited by 3
“Well-known algorithms such as the YOLO series [22, 30, 33] and Faster RCNN [10, 23] have contributed to quality inspection in various industries.”
Chen, X., Chen, X., Xie, Q., et al. (2025) · International Journal of Mass Spectrometry · doi:10.1016/j.ijms.2025.117567 · Cited by 1
Wang, H., Qu, Y., Dang, Z., Wu, D., Cui, M., Shi, H., & Zhao, J. (2025) · Sensors · doi:10.3390/s26010205 · Cited by 2
Deep Learning for Post-earthquake Road Blockage and Debris Detection in Resource-Limited Contexts
Bayat, Z., Dindar, S., & Erkal, B. G. (2025) · Journal of the Indian Society of Remote Sensing · doi:10.1007/s12524-025-02394-7 · Cited by 1
Multi-Person Automatic Attendance System Based on YOLOv11-Pose and Facenet
Choi, Y., Ryu, T., Jung, I., et al. (2025) · International Conference on Control, Automation and Systems (ICCAS) · doi:10.23919/iccas66577.2025.11301228 · Cited by 1
MCB-RT-DETR: A Real-Time Vessel Detection Method for UAV Maritime Operations
Liu, F., Wei, Y., Yan, A., Cao, T., & Xie, X. (2025) · Drones · doi:10.3390/drones10010013 · Cited by 1
A Visual-Based Target Tracking Framework for UAV Using Model Predictive Contouring Control
Du, Y., Li, H., Huang, X., Wang, Z., & Bu, L. (2025) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2025.3642419 · Cited by 2
“In particular, the work [30] applied a method that combines a monocular camera with you only look once (YOLO) [31] to localize ground vehicles and achieve servo tracking.”
Research and Application of Tomato Leaf Disease Recognition Method Based on Improved YOLOv12
Meng, X., Bu, F., Wu, J., He, Z., Li, Y., & Wang, X. (2025) · International Conference on Trustworthy Big Data and Artificial Intelligence (ICTBAI) · doi:10.1109/ictbai68361.2025.00018 · Cited by 3
“Since YOLOv1, the YOLO series has adopted multiple downsampling, which makes small targets almost invisible in the deep feature map, seriously affecting the model's perception of their spatial and texture information[5].”
MLOps Challenges in Deploying High-Performance Vision Models: An Empirical Analysis
Hakkeem, P. A. A., Ottakandathil, A., Jose, B. A., et al. (2025) · IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT) · doi:10.1109/conecct65861.2025.11306401 · Cited by 1
“The YOLO framework introduced a real-time, single-stage object detection paradigm, revolutionizing the field with high-speed inference and end-to-end optimization [1].”
Cho, Y. M., Lee, W., Shin, H., et al. (2025) · International Conference on Control, Automation and Systems (ICCAS) · doi:10.23919/iccas66577.2025.11301236 · Cited by 1
“In recent years, deep learning approaches – especially those based on Convolutional Neural Networks (CNNs) – have achieved superior performance in general object detection and segmentation tasks [7], [8].”
Real-Time Machine Vision Intelligence: Object Recognition and Dynamic Tracking
Lyshevski, S. E., Kovbasa, S., & Holosha, A. O. (2025) · IEEE International Symposium on Computational Intelligence and Informatics (CINTI) · doi:10.1109/cinti67731.2025.11311820 · Cited by 1
Li, Z., Zhen, Z., chen, S., Zhang, L., & Cao, L. (2025) · Remote Sensing · doi:10.3390/rs18010107 · Cited by 2
Zhang, H., Gao, J., Wang, X., et al. (2025) · CAAI Artificial Intelligence Research · doi:10.26599/air.2025.9150053 · Cited by 1
Traffic Light Surveillance Management using YOLOv12
Yaswanth, M. S., Rao, L. S., Kutumbam, K. H. N., et al. (2025) · International Conference on Sustainable Communication Networks and Application (ICSCNA) · doi:10.1109/icscn67106.2025.11308577 · Cited by 1
“[1] Redmon et al. (2016) have suggested YOLO, a real-time object detection system, it features the unbiased prediction of both bounding boxes and class probabilities in a single scan.”
Lightweight express package detection with GYOLO feature fusion
Zhang, J., & Wang, M. (2025) · IEEE China International Youth Conference on Electrical Engineering (CIYCEE) · doi:10.1109/ciycee67631.2025.11308924 · Cited by 1
“Another popular target detection algorithm is the YOLO (You Only Look Once) series, encompassing YOLOv1[2], YOLOv2[3], among others.”
Zeng, T., Hu, J., Galindo, G. L., Ali, S., Sarıkaya, D., Valdastri, P., & Jones, D. (2025) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2025.3648299 · Cited by 1
“We employ well-established and widely-used models in the respective domains: YOLOv5 [37] for object detection and U-Net [38] for semantic segmentation.”
Shi, Z. (2025) · IEEE International Conference on Information Systems and Computer Aided Education (ICISCAE) · doi:10.1109/iciscae66104.2025.11307293 · Cited by 1
“In the same year, Joseph et al. [9] proposed YOLO, which created a new paradigm for single-stage detection by transforming the detection task into a single grid regression problem, enabling real-time detection (45 fps) while maintaining high accuracy.”
Cheng, L., & Lai, Y. (2025) · Journal of Field Robotics · doi:10.1002/rob.70147 · Cited by 1
“YOLO series are rapid and robust object detection methods applied to various subjects (Redmon et al. 2016; Diwan et al. 2023; Yang et al. 2022; Xing et al. 2023).”
Benchmarking YOLO Variants for Underwater Pollution Detection
Tawfik, M. K., Shabaka, S. H., & Badawy, W. M. (2025) · International Conference on Intelligent Computing and Information Systems (ICICIS) · doi:10.1109/icicis66182.2025.11313110 · Cited by 1
“As a result, researchers have increasingly turned toward intelligent vision-based systems powered by deep learning to automate underwater object detection and analysis [1], [2].”
Performance Evaluation of YOLO Models for Sign Language Detection: A Comparative Study
Tawfik, M. K., & Badawy, W. M. (2025) · International Conference on Intelligent Computing and Information Systems (ICICIS) · doi:10.1109/icicis66182.2025.11313192 · Cited by 1
“One of the earliest and most influential developments in real-time object detection was the introduction of the YOLO (You Only Look Once) family of models by Redmon et al. [3].”
Hybrid MoViNet + YOLO Framework for Accurate and Efficient Violence Detection in Videos
Yadav, Y., Shourya, & Lamba, T. (2025) · doi:10.1109/ic366947.2025.11290583 · Cited by 1
Chen, Z., Fan, W., & Guo, B. Q. (2025) · IEEE Access · doi:10.1109/access.2025.3649757 · Cited by 1
Dynamic SLAM by Combining Rigid Feature Point Set Modeling and YOLO
Ding, P., Wang, W., Wu, X., Xu, K., Wu, D., & Du, Z. (2025) · Sensors · doi:10.3390/s26010235 · Cited by 2
“With the rapid development of deep learning methods, scholars have also started to consider combining the deep learning algorithms emerging in the fields of object recognition [9–11] and segmentation [12,13].”
Hardware Design and Side-Channel Security Analysis on the Key Computational Block for YOLOv11
Shao, R., Wu, L., Hu, J., et al. (2025) · International Conference on Integrated Circuits and Microsystems (ICICM) · doi:10.1109/icicm66614.2025.11316014 · Cited by 1
“Then several promising approaches have been proposed for object detection and image classification with deep learning such as R-CNN [3], EfficientDet [4] and YOLO [5] which performs extremely fast and high accuracy for these tasks.”
Mizutani, A., Tanaka, Y., Tamukoh, H., Nomura, O., Tateno, K., & Morie, T. (2025) · Nonlinear Theory and Its Applications IEICE · doi:10.1587/nolta.17.108 · Cited by 2
Knee Osteoarthritis Detection and Categorization with Deep Learning Models
Roy, G., Pal, A. K., Raj, M., et al. (2026) · Lecture notes in networks and systems · doi:10.1007/978-981-96-9239-2_9 · Cited by 1
UI Component Detection in Graphical Interfaces: A YOLO-Based Comparative Analysis
Dicu, M. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-12478-4_9 · Cited by 1
Potato Leaf Diseases Detection Model for Precision Agriculture Using an Enhanced YOLO
Elghamrawy, S. M., & Mohamed, Z. (2026) · Studies in systems, decision and control · doi:10.1007/978-3-032-05701-3_5 · Cited by 1
MIE-YOLO: A Multi-Scale Information-Enhanced Weed Detection Algorithm for Precision Agriculture
Heng, Z., Xie, Y., & Du, D. (2026) · AgriEngineering · doi:10.3390/agriengineering8010016 · Cited by 4
“One-stage algorithms include YOLO (You Only Look Once) [10], SSD (Single Shot MultiBox Detector) [11], RetinaNet [12], CornerNet [13], CenterNet [14] and DETR (Detection Transformer) [15].”
Comparative Analysis of Lightweight Vision Models on Embedded Accelerator Devices
Corti, G., Veronesi, C., Bartoli, P., et al. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-10185-3_18 · Cited by 1
Rapid Seismic Inspection of Structures
Charalambidi, B. G., Schetakis, N. A., Papoutsakis, N., et al. (2025) · Springer Proceedings in Materials · doi:10.1007/978-3-032-13156-0_24 · Cited by 1
A YOLO Model for Car License Plates Detection and Recognition
Nguyen, N., Tuba, E., & Tuba, M. (2026) · Smart innovation, systems and technologies · doi:10.1007/978-981-95-1361-1_50 · Cited by 1
Towards Field-Ready AI-Based Malaria Diagnosis: A Continual Learning Approach
Guillon, L., Biga, S., Kantchire, Y. E., et al. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-09569-5_17 · Cited by 1
Cavadini, R., Sedghani, H., Filippini, F., et al. (2026) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-032-06818-7_14 · Cited by 1
PALM-LAY: A Multi-script Cross-Regional Dataset for Layout Analysis of Palm Leaf Manuscripts
Thuon, N., Du, J., Theang, P., & Thuon, R. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-09371-4_15 · Cited by 4
Yousif, H. A., & Al‐Milaji, Z. (2026) · Results in Control and Optimization · doi:10.1016/j.rico.2026.100654 · Cited by 2
Towards Robust Object Detection Against Adversarial Patches: A GAN-Based Approach for YOLO Models
Zimoń, M. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-14163-7_16 · Cited by 1
A lightweight deep learning model for detection of Huanglongbing disease
Zheng, Y., Hu, Y., Gao, Z., et al. (2026) · Smart Agricultural Technology · doi:10.1016/j.atech.2026.101778 · Cited by 1
Visual SLAM Based on Line Feature Extraction and Dynamic Object Removal in Dynamic Environments
Gao, R., Han, Q., Li, G., Zhao, Z., Wang, B., & Zhang, G. (2026) · Arabian Journal for Science and Engineering · doi:10.1007/s13369-025-11027-7 · Cited by 1
“The YOLO series of neural network-based object detection techniques [24] is an end-to-end approach capable of detecting multiple targets in an image and providing their locations and categories.”
Practical guidance on automated sorting of underwater images in plankton ecology research
Sorochan, K. A., Vaswani, A. R., Howard, A., Rühl, S., O’Grady, E., Möller, K. O., & Johnson, C. L. (2025) · ICES Journal of Marine Science · doi:10.1093/icesjms/fsaf212 · Cited by 2
Salt Deposit Detection on Offshore Photovoltaic Modules Using an Enhanced YOLOv8 Framework
Li, G., Wang, S., Liu, B., Xu, M., Liu, Z., & Wang, H. (2026) · Energies · doi:10.3390/en19020294 · Cited by 1
ESS-DETR: A Lightweight and High-Accuracy UAV-Deployable Model for Surface Defect Detection
Wang, Y., Yao, Y., Zheng, H., & Han, Y. (2026) · Drones · doi:10.3390/drones10010043 · Cited by 3
Hoseinzadeh, Z., Eskandarnejad, M., & Ghaderzadeh, M. (2026) · International Journal of Intelligent Computing and Cybernetics · doi:10.1108/ijicc-07-2025-0411 · Cited by 3
Distributed quantum model learning for traffic density estimation
Wang, K., Wang, B., Zhai, W., & Cheng, J.-A. (2026) · Image and Vision Computing · doi:10.1016/j.imavis.2026.105900 · Cited by 2
Attention–Diffusion–Fusion Paradigm for Fine-Grained Lentinula edodes Maturity Detection
Xu, X., Wang, J., Wei, Z., Wei, S., & Li, J. (2026) · Horticulturae · doi:10.3390/horticulturae12010076 · Cited by 1
Zhu, W. B., Gong, W., Wang, Y., et al. (2026) · Sensors · doi:10.3390/s26020407 · Cited by 1
“Single-stage detectors (e.g.SSD [18], YOLO series [19–24]) have become the main-stream solution for real-time inference and have been applied in drone imagery [25], infrared detection [26], satellite-component detection [27], landslide monitoring [28], and fruit classification [29].”
A lightweight CBBox-KiwiYOLO network for kiwifruit detection in open orchard conditions
Zhiwei, T., Yang, X., Jiachen, H., et al. (2026) · Information Processing in Agriculture · doi:10.1016/j.inpa.2026.01.004 · Cited by 1
Advancing Indian Vehicle Detection Using YOLO11 and YOLO12 with SAHI Optimization
Guleria, A., Varshney, K., Garima, & Jindal, S. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-08638-9_3 · Cited by 1
Teodoro, R., de Lima, F. V., Popa, M., Sampaio, G. S., Kochi, C., Longui, C., & da Silva, L. A. (2026) · Scientific Reports · doi:10.1038/s41598-025-34651-7 · Cited by 1
Physical Parameters Estimation Using Roadside Monocular Vision
Zhang, N., Lu, M.-F., Yuan, S., Liu, C., Wang, Y., Yang, Z., Zhu, C., Chen, Z., Zhang, S., Zhang, F., et al. (2026) · IET Intelligent Transport Systems · doi:10.1049/itr2.70138 · Cited by 1
Guo, H., & Liu, S. (2026) · Image and Vision Computing · doi:10.1016/j.imavis.2026.105897 · Cited by 2
Efficient Transformer-Based SAR Ship Detection with Hybrid Cross-Fusion Modules
Zhao, X. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-4445-5_1 · Cited by 1
DPN-YOLO: an enhanced algorithm for small target detection in UAV imagery
Li, Z., Liu, M., Lv, B., Xu, B., Zhang, J., & Zhang, L. (2026) · The Journal of Supercomputing · doi:10.1007/s11227-025-08198-3 · Cited by 1
HawkEye: a lightweight edge-aware detector for classroom behavior recognition
Xie, M., Ran, Z., Chen, D., Chen, R., Liu, Z., He, Z., Guan, Q., & Cai, Z. (2026) · Journal of Real-Time Image Processing · doi:10.1007/s11554-025-01845-1 · Cited by 1
Yuan, H., Shi, Y., Guan, X., et al. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-4445-5_30 · Cited by 1
Guo, R., Gui, Y., Zhang, J., & Li, F. Y. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-4445-5_27 · Cited by 1
Dataset of Solar Active Regions in the Solar Full-disk Magnetograms
Pan, J., Liu, J., & Rui, L. I. U. (2025) · Chinese Journal of Space Science · doi:10.11728/cjss2025.06.2025-0086 · Cited by 1
Categorization and Content Extraction in Medical Prescription Using YOLOv8
Rekha, G. R., & Siddesha, S. (2026) · Lecture notes in electrical engineering · doi:10.1007/978-981-96-9554-6_33 · Cited by 1
Refining small object detection in aerial images with PF-DETR: a progressive fusion approach
Liu, J., Cao, Y., Dong, C., Zhang, X., Liang, Y., & Liang, Y. (2026) · PeerJ Computer Science · doi:10.7717/peerj-cs.3470 · Cited by 5
M2S-YOLOv8: Multi-Scale and Asymmetry-Aware Ship Detection for Marine Environments
Li, P., Qiao, D., Mu, J., et al. (2026) · Sensors · doi:10.3390/s26020502 · Cited by 1
“The YOLO series [25] became dominant for its accuracy–speed balance: Li et al. [26] optimized it for thermal infrared images, Hu et al. [27] designed a lightweight variant for small ships, and Chen et al. [28] integrated attention for distant targets.”
Park, J.-C., Kim, M., Choi, S., & Kim, G.-W. (2026) · Applied Sciences · doi:10.3390/app16020778 · Cited by 4
Capuozzo, S., & Marassi, L. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-11381-8_34 · Cited by 1
Vehicle Identification and Classification Using YOLO Algorithm
Huyen, C. L. T., Quyet, C. P., & Nguyen, Q. T. (2026) · IIUM Engineering Journal · doi:10.31436/iiumej.v27i1.3694 · Cited by 2
“Currently, the most widely used methods for object detection are R-CNN chains [6,7], SSD chains [8,9], and YOLO chains [10,11].”
Yang, H., Zhang, S., & Shin, I. (2026) · IEEE Access · doi:10.1109/access.2026.3651330 · Cited by 1
Ji, Y., Li, J., Ren, L., et al. (2026) · IEEE Sensors Journal · doi:10.1109/jsen.2025.3650681 · Cited by 1
“Early generations (YOLOv1–v3) established a foundation that balanced accuracy and real-time capability through the introduction of anchor boxes, multiscale feature extraction, and residual connections [24], [25], [26].”
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.