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 35,001–35,100 of 51,399
SpikeGate-YOLO: Spiking Object Detection With Dynamic Gating and Multigranularity Fusion
Niu, Q., Zhao, C., Zhang, X., et al. (2026) · IEEE Internet of Things Journal · doi:10.1109/jiot.2026.3697141 · Cited by 1
“Object detection aims to identify and localize objects, generally categorized into two-stage detectors [27], which achieve high accuracy but incur slow inference, and one-stage detectors [19], [28], which are designed for real-time e ffi ciency.”
Shi, J., Luo, W., Wang, X. J., Guo, J., & Ren, H. (2026) · Sensors · doi:10.3390/s26113404 · Cited by 3
Stabilizing FOV Under the Microscope: Towards Eye-Hand Coordination in Motor-Control Tasks
Khalil, S., Franco-González, I. T., Fung, E., et al. (2026) · ACM Symposium on Eye Tracking Research and Applications (ETRA) · doi:10.1145/3797246.3805857 · Cited by 1
“To establish eye-hand coordination under the microscope, we used an Ultralytics YOLOv8n [Redmon et al. 2016] and a previously validated implementation [Vrzakova et al. 2026] trained on 622 manually annotated corrected frames [Tzutalin 2015].”
Comprehensive mutagenesis defines the functional landscape of human α-tubulin
Xu, K., Guo, Z., Chen, Z., Li, M., Chen, Z., Zhang, D., Wang, Y., Chai, Y., Zhang, J., Wang, H., et al. (2026) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2600822123 · Cited by 5
Che, Y., Ventikos, Y., & Arashpour, M. (2026) · Waste Management · doi:10.1016/j.wasman.2026.115623 · Cited by 1
Modeling and Control for Automated Sewing of Stretchable Fabrics of Different Shapes
Jin, B., Tang, K., Tien, N. C., et al. (2026) · IEEE/ASME Transactions on Mechatronics · doi:10.1109/tmech.2026.3693767 · Cited by 1
“VS [23] has recently benefited from advances in neural networks that broaden the toolkit for visual perception, such as YOLO [24], Segment-Anything [25], and UNet [26].”
Zhang, Q., Liu, D., Parmiggiani, A., et al. (2026) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2026.111852 · Cited by 1
Bias‐Tunable Two‐Terminal Organic Photodetector for Intelligent Imaging
Hahn, S., Park, S.-J., & Yoo, S. (2026) · Advanced Science · doi:10.1002/advs.75894 · Cited by 3
Robust SAR Ship Detection with Texture Perception Convolution and Region Balanced Sampler
Cao, H., & Chen, Z. (2026) · Remote Sensing · doi:10.3390/rs18111807 · Cited by 2
Wang, C., Bao, X., LI, Y., et al. (2026) · Pattern Analysis and Applications · doi:10.1007/s10044-026-01695-y · Cited by 1
“The one-stage You Only Look Once (YOLO) detector proposed by Redmon et al. [20] provides a favorable balance between detection accuracy and inference speed, making it widely used in real-time agricultural monitoring.”
Joshi, A. S., William, G. J., & Joshi, S. (2025) · International Conference on Smart Multimedia (ICSM) · doi:10.1109/icsm64417.2025.11541411 · Cited by 3
“A threshold of 0.5 is a commonly used practice in object detection frameworks such as YOLO [7] to filter low-confidence predictions.”
InfluentialTiboni, G., Camoriano, R., & Tommasi, T. (2026) · IEEE Transactions on Robotics · doi:10.1109/tro.2026.3699455 · Cited by 4
Subramanian, S., Prasheth, P., & Logapriyan, R. (2026) · doi:10.1109/iccsp68173.2026.11539593 · Cited by 1
“The YOLO family, pioneered by Redmon et al. [3], has become the dominant paradigm for real-time detection.”
Li, Q., Gao, M., Zhai, W., Wu, W., Wang, C., & Abdelmoniem, A. M. (2026) · Knowledge-Based Systems · doi:10.1016/j.knosys.2026.116300 · Cited by 6
A detailed review on license plate detection and recognition methods
Li, Z., & Ghaffar, M. A. (2026) · Journal of Traffic and Transportation Engineering (English Edition) · doi:10.1016/j.jtte.2024.10.007 · Cited by 3
Alhazmi, A. S., Hamza, A., & Moubayed, A. (2026) · Transportation research procedia · doi:10.1016/j.trpro.2026.03.008 · Cited by 1
Ma, T., Qu, Y., Guan, C., Yin, H., Yang, W., Chow, S. F., Tong, H. H. Y., Ouyang, D., & Ye, Z. (2026) · Aggregate · doi:10.1002/agt2.70372 · Cited by 1
“It contains two parts: the contracting path and the upsampling path, forming a distinctive U-shaped structure [ 80, 81 ].”
Lightweight Detection of Stone Inscriptions Based on an Improved YOLOv11n Model
Sun, Y., & Ma, S. (2026) · Applied Sciences · doi:10.3390/app16125762 · Cited by 1
GS-YOLO: A lightweight high-accuracy model for small target detection in drone aerial images
Jin, X., Zhu, X., Kang, D., Shen, W., Zhao, Y., Li, X., Yuan, B., & Zhao, Y. (2026) · PLoS ONE · doi:10.1371/journal.pone.0350840 · Cited by 1
Li, X., Yu, R., Qiu, Y., Luo, J., Lu, X., Huang, S., Wu, S., & Zhang, F. (2026) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2026.112005 · Cited by 1
Chakraborty, A., Gholap, A. D., Khuspe, P. R., Sundaram, G., Webster, T. J., Khalid, M., Haris, M. S., & Faiyazuddin, M. (2026) · International Journal of Nanomedicine · doi:10.2147/ijn.s600651 · Cited by 3
Rf-detr: advancing real-time transformer-based object detection model
Gadicha, A. B., Gadicha, V. B., Abdul, A., Reddy, D., V, Morampudi, M. K., & Kumar, R. (2026) · Signal Image and Video Processing · doi:10.1007/s11760-026-05441-z · Cited by 6
“The YOLO family redefines the standard for real-time object detection by treating detection as a direct regression problem, predicting bounding boxes and class probabilities in a single forward pass [26].”
Choroś, K., & Kazimov, F. (2026) · Communications in computer and information science · doi:10.1007/978-981-92-0068-9_31 · Cited by 1
Edge-Enhance YOLO for Steel Surface Defect Detection
Li, R., & Lin, M. (2026) · Journal of Imaging · doi:10.3390/jimaging12060259 · Cited by 2
A comprehensive review on image identification across varied lighting conditions
Samal, N., Barisal, S. K., & Gountia, D. (2026) · AIP conference proceedings · doi:10.1063/5.0319159 · Cited by 1
Vo, Q. L. K., Pitt, K. A., Stantić, B., et al. (2026) · Aquaculture Research · doi:10.1155/are/9899740 · Cited by 1
An Improved DeepSORT Algorithm for Multi-Target Posture Tracking of Firefighters
Li, H.-Y., Peng, X.-G., Li, W., Liu, Y., Cai, G., & Sun, H.-X. (2026) · Automation · doi:10.3390/automation7030093 · Cited by 1
Taşkın, S., Aksoy, S., Cesur, M. G., Demircioğlu, P., & Böğrekçi, İ. (2026) · Bioengineering · doi:10.3390/bioengineering13060687 · Cited by 1
“The single-stage architecture of YOLOv8 enables efficient localization of small anatomical structures and generation of bounding-box and keypoint outputs that can be used in subsequent analytical stages [12,17].”
A Lightweight and High-Precision Citrus Detection Model for Unstructured Orchard Environments
Yang, J., Wu, H., Lv, D., et al. (2026) · Horticulturae · doi:10.3390/horticulturae12060718 · Cited by 1
A Taxonomy of Machine Learning for UAV-Enabled Precision Agriculture: A Structured Survey
Bae, W. D., Alkobaisi, S., Safdar, M. F., & Chouhan, P. (2026) · AgriEngineering · doi:10.3390/agriengineering8060249 · Cited by 1
“…neural networks (CNNs) [18], residual networks (ResNet) [19], encoder–decoder architectures such as U-Net [20], region-based detectors including Faster region-CNN (Faster R-CNN) and Mask Region-CNN (Mask R-CNN) [21,22], and one-stage detectors such as you only look once (YOLO) variants [23,24].”
Budget-Aware Adaptive Adversarial Patches for Black-Box Object Detection
MohajerAnsari, P., Salarpour, A., Fernandez, D., & Pesé, M. D. (2026) · Proceedings - International Conference on Image Processing · doi:10.1109/icip61757.2026.11630525 · Cited by 1
Recognition of blast furnace top gas flow states based on deep learning of temporal images
X, W., Liang, H., Guo, H.-W., Li, J., Bing-ji, Y., & Huang, X.-Y. (2026) · Journal of Iron and Steel Research International · doi:10.1007/s42243-026-01814-3 · Cited by 1
Sangiovanni, G. M., Lasinio, G. J., Poggio, D., et al. (2026) · Remote Sensing in Ecology and Conservation · doi:10.1002/rse2.70051 · Cited by 1
“On the contrary, You Only Look Once (YOLO) (Redmon et al., 2016) adopts a more efficient methodology by tackling the regression challenge in a unified step, allowing image analysis to be significantly faster.”
Yao, J., Huang, N., Shi, W., et al. (2026) · Ocean Engineering · doi:10.1016/j.oceaneng.2026.126533 · Cited by 1
EDM-Net: A Multi-Scale Network for Object Detection in Remote Sensing Images
Liang, S., Wang, X. F., Sun, J. F., Liu, H., & Yang, H. (2026) · Sensors · doi:10.3390/s26123927 · Cited by 1
“Convolutional neural network (CNN)-based detectors, such as the R-CNN series [19–21], YOLO series [22–27], and SSD series [28,29], significantly improved detection accuracy.”
Wang, T., Jingyang, L., Kang, Z., 欧雨成, & Wang, X. (2026) · Buildings · doi:10.3390/buildings16122459 · Cited by 2
Guo, Y., Zhou, X., & Tang, S.-K. (2026) · Applied Sciences · doi:10.3390/app16136290 · Cited by 1
Amin, R., Boukabou, I., Abdelsalam, M., Devanga, A., Lei, T., & Kaabouch, N. (2026) · Integrated Communications, Navigation and Surveillance Conference (ICNS) · doi:10.1109/icns69853.2026.11570520 · Cited by 2
“Experiments were conducted using a publicly available dataset consisting of 209 autonomous UAV package-delivery flights performed with a DJI Matrice 100 quadcopter [21].”
Mitra, R., Sourav, M. A. A., Ceylan, H., et al. (2026) · ASCE International Airfield and Highway Pavements Conference · doi:10.1061/9780784487037.115 · Cited by 1
Zhan, Q., & Li, C.-H. G. (2026) · The International Journal of Advanced Manufacturing Technology · doi:10.1007/s00170-026-18573-w · Cited by 1
“…mapping Γ provided by CNN, such that the conditional probability of class membership is estimated via: State-of-the-art object detectors, including the YOLO (You Only Look Once) [6, 51] and R-CNN [52] families, operationalize CNN paradigms to localize and classify regions of interest.”
Ruan, J., Cheng, Z., & Zeng, M. (2026) · Journal of Real-Time Image Processing · doi:10.1007/s11554-026-01920-1 · Cited by 3
“Representative algorithms include SSD [13] and the YOLO series [14–18], which offer smaller model size, higher detection accuracy, and faster inference speed.”
AQS-IDETR: Adaptive Query Selection for Efficient Inference in Real-Time Detection Transformers
Minh, N. Q. N., Dang, N. H., Van, L. N., Sang, D. V., & Nguyễn, Đ. A. (2026) · Image and Vision Computing · doi:10.1016/j.imavis.2026.106097 · Cited by 3
Cho, J., Kong, D., Nam, J., & Cho, H. (2026) · Journal of Intelligent Manufacturing · doi:10.1007/s10845-026-02915-2 · Cited by 1
FFKD-Net: lightweight small-object detection based on feature fusion and knowledge distillation
Chen, N., Zhao, P., & Hou, S. (2026) · Journal of Real-Time Image Processing · doi:10.1007/s11554-026-01910-3 · Cited by 1
“With rapid advances in computer vision, research attention has progressively shifted toward deep learning-based detectors, including Faster R-CNN [7], YOLO [8], and Transformer-based architectures [9].”
Shen, L., Shi, Y., Lu, H., et al. (2026) · Buildings · doi:10.3390/buildings16132545 · Cited by 1
Spinal x-ray based scoliosis diagnosis using deep learning: a comparison of YOLOv11 and ResNet
Zhang, H., Qi, J., & Zhang, Z. (2026) · Biomedizinische Technik/Biomedical Engineering · doi:10.1515/bmt-2026-0192 · Cited by 1
Automated multi-class PPE detection in Egyptian construction worksites using YOLO
Elesawy, A., Osman, H., El-Anwar, O. H., & Abdelkader, E. M. (2026) · Discover Civil Engineering · doi:10.1007/s44290-026-00555-2 · Cited by 1
“(3) ([9, 37, 56]). where; L =total loss function, L cls =binary Cross-Entropy loss for class predictions, L obj =binary Cross-Entropy loss for objectness predictions, L CIoU =complete Intersection over Union loss for localization, and λ cls , λ obj , λ loc are weight coefficients for each loss…”
Zheng, Y., Yang, L., Zheng, H., Guo, Q., & Fang, H. (2026) · Comprehensive Reviews in Food Science and Food Safety · doi:10.1111/1541-4337.70551 · Cited by 3
Niaz, F., Utama, I. B. K. Y., & Jang, Y. M. (2026) · ICT Express · doi:10.1016/j.icte.2026.06.011 · Cited by 2
Dual-stream cross-modal networks for acoustic-visual detection of surface vessels on wave gliders
Wu, J., Sang, H., Jiang, J., et al. (2026) · Ocean Engineering · doi:10.1016/j.oceaneng.2026.126735 · Cited by 1
Real-Time Cellist Postural Evaluation With On-Device Computer Vision
Wang, P., Zhang, M., Perumal, S., et al. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-29839-3_6 · Cited by 1
LQ-YOLO11: a lightweight dual-gated network for real-time logistics visual quality inspection
Li, H., Liu, T., Dong, H., et al. (2026) · Journal of Real-Time Image Processing · doi:10.1007/s11554-026-01922-z · Cited by 1
Chen, Y., Xia, Z., & Xiao, S. (2026) · Journal of Intelligent Manufacturing · doi:10.1007/s10845-026-02920-5 · Cited by 1
Design and Experimental Validation of a Vision-Based Robotic Framework for Strawberry Harvesting
Campoamor, D., & Vega, J. (2026) · Electronics · doi:10.3390/electronics15142989 · Cited by 2
“One-stage object detectors such as YOLO [13–16] and SSD [17] provide an effective compromise between detection accuracy and computational efficiency, making them particularly suitable for real-time robotic applications.”
Bošnjak, A., Pejić, P., Cupec, R., et al. (2026) · MIPRO ICT and Electronics Convention (MIPRO) · doi:10.1109/mipro70003.2026.11591589 · Cited by 1
“General-purpose object detectors such as You Only Look Once (YOLO) [9] have demonstrated outstanding performance across a wide range of visual domains.”
Ganesan, M., Bharatiraja, C., Verma, R., Kandhasamy, S., & Mihet‐Popa, L. (2026) · IEEE Access · doi:10.1109/access.2026.3711217 · Cited by 1
FMCW LiDAR Range Imaging and Recognition System Utilizing FPGA‐Based Edge‐Aware Processing
Rong, S., Zhou, M., Ma, W., et al. (2026) · Microwave and Optical Technology Letters · doi:10.1002/mop.70701 · Cited by 1
“The optimized image data are transmitted to the host computer in real time via Gigabit Ethernet using the UDP protocol [11], where a pre‐trained YOLO (You Only Look Once: Unified, Real‐Time Object Detection) [12] deep learning model performs object detection and recognition.”
Zeinabadi, M. S., Math, S. Y., Ameli, N., Kocasaraç, H. D., & Pachêco‐Pereira, C. (2026) · Oral Surgery Oral Medicine Oral Pathology and Oral Radiology · doi:10.1016/j.oooo.2026.07.005 · Cited by 2
RepViT-Based UAV Small Object Detection on VisDrone and UAVDT
Jiva Bharathi, M., & Sathya, M. (2026) · Journal of Electronics and Informatics · doi:10.36548/jei.2026.3.004 · Cited by 1
“YOLO [1] represented object detection as a single regression problem providing real-time object detection capability.”
Enhanced multi-scale feature fusion for accurate steel surface defect detection
Liao, J., Wang, D., Liang, J., Yang, M. B., & Liang, C. (2026) · The Visual Computer · doi:10.1007/s00371-026-04575-y · Cited by 1
Miraki, M., Sohrabi, H., Bavaghar, M. P., et al. (2026) · Journal of Plant Diseases and Protection · doi:10.1007/s41348-026-01310-6 · Cited by 1
An Open MCU-Embedded Platform for Real-Time Onboard Vision on Resource-Constrained UAV Systems
Nedelcu, B., & Florea, A. M. (2026) · Drones · doi:10.3390/drones10070531 · Cited by 1
Li, L., Cheng, X., Yin, X., et al. (2026) · Mathematics · doi:10.3390/math14142634 · Cited by 1
Weld Seam Detection Using Human Hand Tracking
Kadam, P., Fang, G., Amirabdollahian, F., Zou, J. J., & Holthaus, P. (2025) · IEEE Conference on Engineering Informatics (ICEI) · doi:10.1109/icei68356.2025.11603741 · Cited by 1
“Using real-time detection methods like YOLO [16], a tracking-by-detection process [15] can be used to track fingertips.”
InfluentialYang, D., Wu, J., & Yu, Y. (2026) · Geomatics Natural Hazards and Risk · doi:10.1080/19475705.2026.2698968 · Cited by 1
Bayraktar, M., Zalluhoğlu, C., Aldemir, A., et al. (2026) · Journal of the Indian Society of Remote Sensing · doi:10.1007/s12524-026-02548-1 · Cited by 1
“The YOLO framework, introduced in 2016, redefined object detection as a single regression problem, performing classification and localization in one step (Redmon, 2016).”
Zhang, W., Guo, W. J., 谢伯祥, Lin, L., Zhang, J. Y., Yang, H., Meng, Y., Liu, Y., & Zhang, W. (2026) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2026.3716766 · Cited by 2
Surveillance Camera-Assisted Navigation for Mobile Robots Based on Human Costmap Layer
Park, J., Chea, J., Yang, B.-H., et al. (2026) · International Journal of Precision Engineering and Manufacturing · doi:10.1007/s12541-026-01590-w · Cited by 1
“The SCAN system employs the YOLOv3 model for human detection, the SORT algorithm for tracking, and homography transformation for estimating human positions and velocities on the 2D map [17–20].”
Zhang, A., Cao, H., Shan, N., Wang, J., Pu, M., & Song, Y. (2025) · Intelligent Opto-Electronics · doi:10.67704/ioe.2025.250007 · Cited by 7
Thakur, V., More, V. N., & Bhatt, A. (2026) · Journal of Systems Architecture · doi:10.1016/j.sysarc.2026.103940 · Cited by 1
Enhanced road infrastructure defect detection via attention-based visual inspection
Gao, N., Zhai, D., Shi, G., et al. (2026) · Journal of Real-Time Image Processing · doi:10.1007/s11554-026-01950-9 · Cited by 1
“Among these, object detection algorithms, particularly the YOLO (You Only Look Once) series models, have been widely adopted for road damage identification tasks due to their excellent balance between speed and accuracy [3].”
Bi, X., Wu, P., Teng, D., Wang, X., Chen, H., & Zeng, N. (2026) · IEEE Sensors Journal · doi:10.1109/jsen.2026.3715768 · Cited by 1
“When available, a fine-tuned detector such as YOLO [39] is used to prelocate defect regions; the detected patches are cropped, stitched with solid backgrounds, and segmented by SAM to obtain clean binary masks.”
Precise Localisation Technologies for the Industry
Berardinucci, F., Müürsepp, I., & Urgo, M. (2026) · Lecture notes on multidisciplinary industrial engineering · doi:10.1007/978-3-032-17967-8_10 · Cited by 3
Qu, T., Yang, S., Wang, H., Song, H., Guo, X., Hu, W., Liu, G., Chen, H., & Ou, Y. (2026) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3770855.3817449 · Cited by 3
“YOLO [30] family, such as YOLOv5 [12] and YOLOv8 [13], soon emerged as the mainstream solution, trading two-stage refinement for a lightweight, rapid-forward architecture that can be deployed on edge devices with minimal memory and latency.”
Zarrouk, Y., Bourhaleb, M., Rahmoun, M., Hamdaoui, H., & Hachami, K. (2026) · Array · doi:10.1016/j.array.2026.101069 · Cited by 1
Chen, J., He, J., Wang, Y., Lu, P., & Li, H. (2026) · Remote Sensing · doi:10.3390/rs18162680 · Cited by 1
Patel, V., Madane, A. R., Maiti, S., & Chakraborty, K. (2026) · SN Computer Science · doi:10.1007/s42979-026-05278-w · Cited by 1
“To address latency constraints, the industry transitioned toward single-stage detectors, notably the Single Shot MultiBox Detector (SSD) [10] and early iterations of the You Only Look Once (YOLO) framework [11].”
Chng, E., & Schneider, B. (2026) · Computers & Education · doi:10.1016/j.compedu.2026.105743 · Cited by 1
Zou, R., Guo, J., Liang, J., Che, K., Deng, Y., & Chen, B. (2026) · Remote Sensing · doi:10.3390/rs18162793 · Cited by 2
An efficient computer vision framework for RSU-based accident recognition and V2X communication
Ather, D., & Talipov, M. (2026) · Mathematical Models in Engineering · doi:10.21595/mme.2026.26075 · Cited by 1
“Convolutional neural networks have been widely adopted for object detection, classification, and event recognition, while modern visual models can capture richer scene semantics than classical handcrafted approaches [10], [13].”
Yun, B., Shen, J., Lin, Z., et al. (2026) · Fire · doi:10.3390/fire9080358 · Cited by 1
“…and classification into an end-to-end prediction process, providing a more direct trade-off between real-time performance and detection accuracy [30–32]. https://doi.org/10.3390/fire9080358 Therefore, lightweight one-stage detection frameworks are more suitable for forest-fire early-warning…”
InfluentialChenxuan, Z., Fan, P., Bu, S., & Wen, Y. (2026) · AI · doi:10.3390/ai7080324 · Cited by 2
“CNNs, object detection frameworks, and semantic segmentation models have been widely adopted for identifying insulator damage, conductor faults, corrosion, vegetation intrusion, and structural abnormalities in transmission infrastructure [66,67].”
DGQ-YOLO: Depth-Guided Quality-Aware detection with Pseudo-Depth for aerial imagery
Hou, X., & Liu, W. (2026) · Journal of King Saud University - Computer and Information Sciences · doi:10.1007/s44443-026-01167-7 · Cited by 1
“YOLO-style models provide a useful accuracy–efficiency balance (Redmon et al. 2016; Wang et al. 2024; Hua et al. 2025).”
A lightweight and multi-scale fire detection model using YOLOv11n
Fan, W., Hu, R., & Li, X. (2026) · Discover Applied Sciences · doi:10.1007/s42452-026-09455-7 · Cited by 1
Attention-Enhanced YOLOv11 for Early Detection of Fungal-Induced Forest Tree Decline
Akhmedov, F., Khasanov, D., Yusupov, S. S., et al. (2026) · Plants · doi:10.3390/plants15172609 · Cited by 1
DAAL: Dual Ambiguity in Active Learning for Object Detection with YOLOE
Phan, D. T., Nguyen, N., & Dang, D. N. M. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-36547-7_32 · Cited by 1
The Evolution of Image Segmentation from Classical Techniques to Deep Learning: A Survey
Shirzi, M. A., & Kermani, M. R. (2026) · Robotics · doi:10.3390/robotics15090169 · Cited by 1
“YOLO is a well-known and highly efficient framework initially developed for object detection by Joseph Redmon and colleagues in 2016 [78].”
Wen, Y., Kohnke, J., Parmar, V., Bojahr, C., Arzideh, K., Schmidt, C. S., Quinsten, A. S., Lindholz, M., Mancino, M., Schaarschmidt, B. M., et al. (2026) · European Radiology · doi:10.1007/s00330-026-12830-y · Cited by 1
AH-YOLOFlow: Vision-Based Pedestrian Flow Analytics for Smart Urban Crosswalk Performance Monitoring
Akhmedov, F., Khasanov, D., Yusupov, S. S., et al. (2026) · Sustainability · doi:10.3390/su18179040 · Cited by 1
Bi, Q., Sun, Y., Yang, Y., et al. (2026) · Applied Computing and Geosciences · doi:10.1016/j.acags.2026.100402 · Cited by 1
A Deep Learning Framework for Cetacean Detection: Integrating YOLOv11 With ADRIF Post‐Processing
Kuberan, G., Reshma, B., & KUMAR, S. (2026) · Marine Mammal Science · doi:10.1111/mms.70267
A Hierarchical Context-Fusion and Synergistic Alignment Network for small object detection
Zhang, B., Pan, W., Xu, B., & Dai, S. (2026) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2026.08.034 · Cited by 2
Kosanovic, N., Tran, A., Dave, A., & Vaz, J. C. (2026) · IEEE National Aerospace and Electronics Conference (NAECON) · doi:10.1109/naecon70028.2026.11674922 · Cited by 1
“Deep learning has quickly revolutionized the world, with complex neural network models outperforming humans on countless mental tasks ranging from rapid object detection [1] to protein folding [2].”
Supervised Local High-Order Differential Channel Feature Learning for Pedestrian Detection
Shen, J., Zuo, X., Liu, H., Wang, H., Yang, W., & Qian, C. (2016) · Neural Processing Letters · doi:10.1007/s11063-016-9561-7 · Cited by 1
Yuan, J., Cao, W., & Lv, F. (2017) · International Symposium on Advances in Electrical, Electronics and Computer Engineering (ISAEECE) · doi:10.2991/isaeece-17.2017.60 · Cited by 1
VISUAL TRACKING UTILIZING OBJECT CONCEPT FROM DEEP LEARNING NETWORK
Xiao, C., Yılmaz, A., & Lia, S. (2017) · ISPRS annals of the photogrammetry, remote sensing and spatial information sciences · doi:10.5194/isprs-annals-iv-1-w1-125-2017 · Cited by 1
Vehicle recognition using common appearance captured by 3D LIDAR and monocular camera
Shin, M.-O., & Seo, S. (2017) · IEEE Intelligent Vehicles Symposium · doi:10.1109/ivs.2017.7995751 · Cited by 1
Aircraft Detection in Remote Sensing Images via CNN Multi-scale Feature Representation
Wang, J., Niu, X., Zhang, P., et al. (2017) · DEStech Transactions on Computer Science and Engineering · doi:10.12783/dtcse/smce2017/12424 · Cited by 1
Detection of valuable left-behind items in vehicle cabins
Perrett, T., Mirmehdi, M., & Dias, E. (2017) · IEEE Intelligent Vehicles Symposium · doi:10.1109/ivs.2017.7995862 · Cited by 1
International Space Station Image Extraction from a Dynamic Environment using Deep Learning
Shi, J.-F., Ulrich, S., & Ruel, S. (2017) · Proceedings of the International Conference of Control, Dynamic systems, and Robotics · doi:10.11159/cdsr17.131 · Cited by 1
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.