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 34,601–34,700 of 51,399
Tan, H. P., Li, R., Zhang, J., Zhang, H., Qian, Y., Liu, J., & Gu, Z. (2026) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2025.3646216 · Cited by 2
“D detection model, which normally includes class loss, object confidence loss, and regression loss [24]. f t denotes the target object including bbox [ x 1 , y 1 , x 2 , y 2 ] and class cls .”
Efficient adaptive rotated object detection for 1D and QR barcodes
Luo, P., Ma, Z., Wu, Q., Zhao, T., & Shen, X. (2026) · Scientific Reports · doi:10.1038/s41598-025-34854-y · Cited by 1
“To address this issue, Joseph Redmon et al. introduced YOLOv1 11 , which excels in speed but struggles with small object detection, crowd detection, and has limited generalization capability.”
AI-Based Detection of Fire and Smoke in Healthcare Facilities
Rhayem, A., Rizk, M., Chaaya, J. A., & Nasser, A. (2025) · IEEE International Conference on Emerging Trends in Engineering and Computing (ETECOM) · doi:10.1109/etecom66111.2025.11319009 · Cited by 3
“Among various CNN-based models, You Only Look Once (YOLO) models have been introduced as a prominent method for real-time detection, effectively balancing computation speed and detection performance [8].”
Jiang, Z., Shi, D., Pan, D., Yu, H., & Wang, Y. (2026) · IEEE Sensors Journal · doi:10.1109/jsen.2026.3651494 · Cited by 2
“…of location prediction and category prediction through a network, and its representative methods include SSD [31], RetinaNet [32], YOLO series [33], [34], [35], [36], [37], [38], [39], [40], [41] and other algorithms, and the second-level detection network divides the location prediction and…”
Multi-scale object detection with feature enhancement for traffic scenes
Chuai, Q., Zhu, T., Wang, X., Wang, Z., & Fu, X. (2026) · International Journal of Multimedia Information Retrieval · doi:10.1007/s13735-025-00396-2 · Cited by 1
“Popular one-stage approaches include SSD [7] and YOLO [6, 29–32] and their variants.”
Power Transmission Fault Detection Using Hyperparameter-Tuned YOLOv11 with XAI
Islam, M. K., Nirob, A. A., Khan, M. R. K., et al. (2025) · doi:10.1109/etecom66111.2025.11318992 · Cited by 1
“Conversely, one-stage networks such as YOLO [3] and SSD [4] eliminate these additional steps, enabling faster, real-time detection.”
SFCFNet: A Spatial–Frequency Cross-Attention Fusion Network for Hyperspectral Image Classification
Huang, W., Li, J., Chen, Q., Yin, J., Niu, J., & Sun, L. (2026) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2026.3651577 · Cited by 1
Aravind, J. V., & Prince, S. (2026) · IEEE Sensors Letters · doi:10.1109/lsens.2026.3652605 · Cited by 1
Tang, W., Yang, X., Zhou, H., et al. (2026) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2026.3653619 · Cited by 1
Yu, N., Huang, C., Li, T., et al. (2026) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2026.3653005 · Cited by 1
Chen, J., & Cao, Y. (2026) · Engineering Construction & Architectural Management · doi:10.1108/ecam-07-2025-1095 · Cited by 1
López, H. D. L. (2026) · Salduie · doi:10.26754/ojs_salduie/sald.2025212652 · Cited by 1
EinsPT: Efficient Instance-Aware Pre-Training of Vision Foundation Models
Wang, Z., Tian, Y., Xie, L., Wang, Y., & Ye, Q. (2026) · IEEE Transactions on Image Processing · doi:10.1109/tip.2026.3652371 · Cited by 2
Zhang, J., & Peng, X. L. (2026) · Signal Image and Video Processing · doi:10.1007/s11760-025-05097-1 · Cited by 1
“Deep learning-based object detection models, particularly the “You Only Look Once” (YOLO) series, have demonstrated remarkable success in various medical imaging applications, owing to their real-time processing and robust feature extraction capabilities [4, 5].”
Zhu, Z., Yang, Y., Qi, G., Li, S., Li, H., & Liu, Y. (2026) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2026.3651289 · Cited by 4
“In recent years, deep learning has significantly propelled the advancement of object detection, from region-based detectors such as Faster R-CNN [35] to end-to-end models like YOLO [36] and SSD [37].”
Zou, D., Hu, Q., Bai, Z., Zhang, M. F., Liu, T., Zhou, A., & Li, Y. (2026) · Journal of Building Engineering · doi:10.1016/j.jobe.2026.115269 · Cited by 1
Deepfake detection using a distinctive eye signature and the entropy heat map of the image texture
Tchaptchet, E., Tagne, E. F., Djimeli-Tsajio, A., Acosta, J. C., Rawat, D. B., & Kamhoua, C. (2026) · Multimedia Tools and Applications · doi:10.1007/s11042-026-21276-9 · Cited by 1
“Unlike traditional methods such as Faster R-CNN [63], YOLO [64], Zoom Text Detector [65], and CM-Net [66], which rely on geometric and textual approaches, our method leverages physiological inconsistencies in the eyes and skin texture to detect deepfakes.”
DAH-YOLO: An Accurate and Efficient Model for Crack Detection in Complex Scenarios
Fan, Y., Li, Q., Chen, Y., Yao, Z., Sun, Y., & Zhang, W. (2026) · Applied Sciences · doi:10.3390/app16020900 · Cited by 4
Okumuş, H. (2026) · Ömer Halisdemir Üniversitesi Mühendislik Bilimleri Dergisi · doi:10.28948/ngumuh.1666320 · Cited by 1
Yamauchi, T. (2026) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2026.104658 · Cited by 9
Jie, 徐. X., Yuang, 贾. J., & Zhifeng, 汪. W. (2026) · Laser & Optoelectronics Progress · doi:10.3788/lop251315 · Cited by 1
Computer Vision-Based Corrosion Detection and Feature Extraction for Rock Bolts
Lu, S., Wu, S., Ma, X., et al. (2026) · Materials · doi:10.3390/ma19020392 · Cited by 1
“Electromagnetic detection is susceptible to electromagnetic interference from geological bodies, resulting in limited accuracy [26,27].”
Baziyad, M. S., Arain, B., Rabie, T. F., & Kamel, I. (2026) · Intelligent Service Robotics · doi:10.1007/s11370-025-00683-1 · Cited by 1
“The YOLO family of object detectors [9, 44] has gained popularity due to their real-time performance and reason-ableaccuracy.”
Energy-Efficient Automated Detection of OPGW Features for Sustainable UAV-Based Inspection
Yan, X., Mao, W., Li, X., Huang, R., Ye, C., Li, F., & Fan, Z. (2026) · Sensors · doi:10.3390/s26020658 · Cited by 1
Human Automatic Trespassing Detection System
Thakur, D., Sharma, S., & Kaur, K. (2025) · IEEE International Conference on Computing, Communication and Automation (ICCCA) · doi:10.1109/iccca66364.2025.11325689 · Cited by 1
“Building upon the success of previous research works on object detection and human activity recognition, we propose enhancements of YOLOv3 to address the unique challenges of trespassing detection in security surveillance context [4].”
Qin, Z., Xie, Q., & Li, Z. (2026) · Wood Material Science and Engineering · doi:10.1080/17480272.2026.2615040 · Cited by 1
Unleashing the Power of Deep Learning: Revolutionizing Crime Detection with CCTV Technology
Yaqoob, M. M., Chaudary, M. A., Naseem, M. U., Khalid, A. R., Khattak, U. F., & Khan, M. A. (2025) · IEEE Symposium on Wireless Technology & Applications (ISWTA) · doi:10.1109/iswta68114.2025.11330036 · Cited by 1
“YOLO, which stands for ”You Only Look Once,” is a well-known algorithm for object detection in deep learning [9].”
A Road Crack Detection Method for UAV Based on Improved YOLOv8n
Gong, D. (2025) · International Conference on Image Processing, Computer Vision and Machine Learning (ICICML) · doi:10.1109/icicml67980.2025.11333524 · Cited by 1
“Single-stage algorithms (e.g., SSD[9] (Single Shot Multibox Detector), YOLO[10] (You Only Look Once) series (e.g., YOLOv5, YOLOv8).) balance speed and accuracy, yet still have shortcomings in small-target crack detection, cross-scale feature fusion, and shallow information retention.”
A Lightweight Multi-Scale Attention Model for Small Object Detection in UAV Imagery
Nguyen, D., Hoang, V.-D., & Le, V.-T.-L. (2026) · IEEE Access · doi:10.1109/access.2026.3656179 · Cited by 3
FSD-DETR: A Lightweight Fire and Smoke Detection Model Based on Improved RT-DETR
Zhang, J., Yan, P., Zhang, Y., et al. (2025) · doi:10.1109/icftic68075.2025.11324987 · Cited by 1
“CNN-based detection algorithms are broadly categorized into single-stage detectors (SSD, YOLO family [3–7]) that prioritize inference efficiency but sacrifice accuracy, and two-stage detectors (Faster This work was supported by the Key Research Project of Natural Science in Anhui Province under…”
Adaptive Edge-Aware Detection with Lightweight Multi-Scale Fusion
Pan, X., Xiong, K., & Li, J. (2026) · Electronics · doi:10.3390/electronics15020449 · Cited by 2
“The YOLO series has consistently served as the cornerstone of real-time object detection, evolving from the single-stage YOLOv1 [18] to the optimized YOLOv11 [19].”
Fast Helmet Detection in Low-Resolution Surveillance via Super-Resolution and ROI-Guided Inference
He, T., Wang, Z., & Yang, L. (2026) · Applied Sciences · doi:10.3390/app16020967 · Cited by 1
VLMs-in-the-Wild: Bridging the Gap Between Academic Benchmarks and Enterprise Reality
Bandraupalli, S., Gajera, M., Saifee, A. A., & Parwar, A. (2025) · International Conference on AI-ML Systems (AIMLSystems) · doi:10.1109/aimlsystems67835.2025.11330553 · Cited by 4
“Traditional computer vision models rely on pixel-level bounding boxes for evaluating localization performance [19].”
Fault Detection and Recognition of Wind Turbine Blades Based on YOLOv8
Jiang, H., Hu, P., Wang, C., et al. (2025) · International Conference on Cloud Computing, Big Data Application and Software Engineering (CBASE) · doi:10.1109/cbase67452.2025.11335477 · Cited by 1
Malecha, Z. M., Ożarowski, K., Siemasz, R., Chorowski, M., Tomczuk, K., Strochalska, B., & Wondołowska-Grabowska, A. (2026) · Applied Sciences · doi:10.3390/app16021075 · Cited by 1
Vessel-guided joint detection and classification of retinal vascular junctions
Long, J., Xie, Y., Zhang, Y., et al. (2026) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2026.109636 · Cited by 1
Intelligent and autonomous pipeline deposit tracking based on a multi-object tracking framework
Wong, L. N. Y., Yu, S., & Wong, K. Y. P. (2026) · Tunnelling and Underground Space Technology · doi:10.1016/j.tust.2026.107463 · Cited by 1
Saliency-Guided Selection Driven Multi-scale Network for Breast Tumor Detection
Gu, X., Liu, C., Luo, X., et al. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-5634-2_15 · Cited by 1
A Real-Time Computer Vision System for Liquid Monitoring in Transparent Containers
Torres, N. (2025) · Asia Service Sciences and Software Engineering Conference (ASSE) · doi:10.1145/3775030.3775041 · Cited by 1
“• Real-time performance: Safety applications demand minimal latency, requiring optimized algorithms capable of processing video streams efficiently without compromising accuracy [5, 18, 23].”
Li, J., Ju, G., Chen, H., et al. (2026) · Nondestructive Testing And Evaluation · doi:10.1080/10589759.2026.2619577 · Cited by 1
An Improved RT-DETR Model for High-Performance Steel Surface Defect Detection
Hy, W., Wu, S., Chen, X., et al. (2025) · International Conference on Electronic Information Engineering and Computer Technology (EIECT) · doi:10.1109/eiect68017.2025.11331980 · Cited by 1
“Single-stage YOLO [4]–[9] treats detection as regression, enabling faster inference.”
A Label-Free Lightweight Prompt-Driven Cross-Modal Fire Detection on Robotic Edge Platforms
Lee, H., & Nadeem, M. (2025) · International Conference on Robotics and Computer Vision (ICRCV) · doi:10.1109/icrcv67407.2025.11349293 · Cited by 1
“Object detection models such as YOLO [9] and SSD [10] have been applied successfully to fire detection under complex environmental conditions [11].”
FlowDet: Overcoming Perspective and Scale Challenges in Real-Time End-to-End Traffic Detection
Wang, Z., & Zhao, Y. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-5764-6_1 · Cited by 1
Printed Circuit Board (PCB) Defect Detection using YOLOv5
Nitish, K., Koduru, U. C. R., Gurucharan, J., et al. (2025) · doi:10.1109/iceamst67459.2025.11335829 · Cited by 1
Vijay, M., Sundareswaran, N., Janakiram, M., et al. (2025) · doi:10.1109/iceamst67459.2025.11335774 · Cited by 1
Lin, Y., Gao, Y., Fang, C., Lyu, Z., & Cheng, X. (2026) · Structural Health Monitoring · doi:10.1177/14759217251403370 · Cited by 2
Dynamic global tracker for online multi camera multi vehicle tracking
Chen, X., Chan, S., Guo, B., Yao, Y., Hong, F., Mao, J., & Zhou, X. (2026) · Scientific Reports · doi:10.1038/s41598-026-35768-z · Cited by 1
Jian, Z., Liu, S., Liu, J., Hu, J., Huang, J., & Liang, Y. (2026) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2025.3650258 · Cited by 1
“The loss of structural details . a) Defect detection experiment: YOLO [24] is predominantly employed in defect detection tasks, with numerous state-of-the-art models being built upon its framework.”
Deep Learning-Based Vision System for Banknote Recognition: A Neurocomputational Approach
Levano, M. A., Tori, M., & Peralta, B. (2025) · International Conference on Systems and Informatics (ICSAI) · doi:10.1109/icsai68704.2025.11345859 · Cited by 1
“In individuals with visual impairment, cortical visual areas can be activated by auditory or haptic stimuli, a phenomenon known as multisensory reorganization [6].”
Mousavirad, S. J., Shallari, I., & O'Nils, M. (2026) · Measurement · doi:10.1016/j.measurement.2026.120584 · Cited by 1
“Then, nine conventional machine learning algorithms and two deep learning models are compared with two object detection methods, namely You Only Look Once version 3 (YOLOv3) [10] and Region-based Convolutional Network (Faster R-CNN) [11].”
YOLO-IRUAV: An Efficient Multi-Scale Feature Remote Sensing Infrared Small Target Detector
Song, Y., Zhang, Y., Ma, W., et al. (2025) · International Conference on Electronic Engineering and Informatics (EEI) · doi:10.1109/eei67650.2025.11335027 · Cited by 1
“With the evolution of the YOLO (You Only Look Once) model [4][5][6][7][8], its application in infrared small target detection has grown rapidly, particularly in remote sensing object detection (OD).”
A Robust Forward Collision Warning System Using Single Camera
Nosher, N., Muazzam, H., Khawaja, M. E., Rehman, A., & Amjad, A. (2026) · IEEE Access · doi:10.1109/access.2026.3657052 · Cited by 1
Enhancing Military Object Detection with YOLOv8: A Deep Learning Approach
Kaushal, A., Sharma, A., & Sehgal, V. K. (2025) · International Conference on Image Information Processing (ICIIP) · doi:10.1109/iciip68302.2025.11346270 · Cited by 1
“Redmon et al. (2016) [6].”
Deep learning for object detection: state of the art, challenges, and future directions
Gupta, N., & Rohil, M. K. (2026) · International Journal of Data Science and Analysis · doi:10.1007/s41060-026-01030-y · Cited by 3
“…(better scale and aspect ratio predictions) Multiscale detections Included batch normalization in the network to handle higher resolution YOLOv3[145] Increased number of anchor boxes per grid cell Implemented skip connections, which were routes in the neural network architecture that allows a…”
InfluentialFan, W., Liu, Y., Wang, X., et al. (2026) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2026.3657206 · Cited by 1
Enhancing road infrastructure management efficiency using Yolov8 model for pavement damage detection
Pham, S. V. H., Nguyen, K. V. T., Le, H. L., & Nguyen, H. N. (2026) · Innovative Infrastructure Solutions · doi:10.1007/s41062-026-02500-9 · Cited by 1
“The methodology of this study is highly inter-disciplinary, integrating information technology, artificial intelligence, and transportation infrastructure management to address practical challenges in a comprehensive and feasible manner.”
Anisha, N. K., Mohandas, P., Bhavana, P., et al. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-14041-8_25 · Cited by 1
How Scale Breaks “Normalized Stress” and KL Divergence: Rethinking Quality Metrics
Smelser, K., Gunaratne, K., Miller, J. A., & Kobourov, S. (2026) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2026.3657654 · Cited by 3
“For instance, a technique designed for visualization might prefer to output the units as pixel coordinates [33], which will be a large region compared to another technique designed for ML, which outputs coordinates between 0 and 1 [59].”
SABR-YOLO: A Lightweight Detector for Power Transmission Tower Detection in Remote Sensing Image
Qin, Z., Qu, K., Yan, Z., Li, Y., Zhang, Z., Zhang, W., & Zhang, Q. (2026) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2026.3658532 · Cited by 1
RCD-DETR: A Lightweight Real-Time Detection Transformer for Conveyor Belt Egg Detection
Shen, Y., Dai, M., Cai, Y., et al. (2025) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc58881.2025.11343239 · Cited by 1
“These algorithms can be primarily categorized into two types: (1) single-stage detectors, such as SSD [5] and the YOLO series [6]–[8], which are renowned for their efficient detection speed; (2) two-stage detectors, including R-CNN [9] and Fast R-CNN [10], which typically offer superior detection…”
OngoingWork: A Runtime Assurance Framework for Low-flying Autonomous UAS Medical Operations
Kandula, A., Shu, K., Wright, G., Slagel, T., Lehman, S. M., & Fody, J. M. (2026) · AIAA SciTech Forum · doi:10.2514/6.2026-1293 · Cited by 1
HapticVLM: VLM-Driven Texture Recognition Aimed at Intelligent Haptic Interaction
Khan, M. H., Cabrera, M. A., Iarchuk, D., Mahmoud, Y., Trinitatova, D., Tokmurziyev, I., & Tsetserukou, D. (2025) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc58881.2025.11343053 · Cited by 3
“While recent advances in Computer Vision and Machine Learning have significantly improved the object detection [2] and classification [3], the replication of fine-grained tactile perception remains an open challenge.”
Yuan, Q., Kwon, H., Raza, M., Lee, S., Alqahtani, A., Hussain, J., Salem, S., Gu, Y. H., & Al–antari, M. A. (2026) · IEEE Access · doi:10.1109/access.2026.3657829 · Cited by 3
Visual-based spatial audio generation system for multi-speaker environments *
Liu, X., Gurelli, O., Wang, Y., & Reiss, J. D. (2025) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc58881.2025.11343015 · Cited by 4
Zhang, R., Cai, S., He, Z., & Zhao, Y. (2026) · Scientific Reports · doi:10.1038/s41598-026-37293-5 · Cited by 1
Song, W., He, T., Zhang, H., Zheng, S., Chen, H., Shangguan, C., & Hao, C. (2026) · Journal of King Saud University - Computer and Information Sciences · doi:10.1007/s44443-026-00489-w · Cited by 3
Wang, X., Yu, C., & Wei, C. (2026) · Engineering Research Express · doi:10.1088/2631-8695/ae3f88 · Cited by 1
Comparative Evaluation of YOLO and RT-DETR Machine Learning Models for Coral Bleaching Detection
McKendry, L., Piyathilaka, L., & Sul, J.-H. (2025) · International Conference on Advancements in Computing (ICAC) · doi:10.1109/icac69156.2025.11361420 · Cited by 1
A Template-Based Approach for Industrial Title Block Compliance Check
Laurendin, O., Ninpan, K., Robcis, Q., Lehaut, R., Danlos, H., Bureau, N., & Plana, R. (2026) · Algorithms · doi:10.3390/a19020105 · Cited by 1
MedMamba-YOLO: A Vision State Space Model for Medical Image Detection
Guo, J., & Wu, X. (2025) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm66473.2025.11357013 · Cited by 1
“Among mainstream object detection frameworks, the YOLO series [1]-[10] has been widely adopted in various real-time perception applications due to its end-to-end architecture and superior speed-accuracy trade-off.”
BIOFED: A Biomedical Federated and Explainable Framework for Object Detection
Mercaldo, F., Giammarco, M. D., Niro, F., Renzo, M. D., Cesarelli, M., Martinelli, F., Agnello, P., Petyx, M., & Santone, A. (2025) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm66473.2025.11357121 · Cited by 4
“Among them, the You Only Look Once (YOLO) family of detectors [14] and vision trans-former approaches like YOLOS have proven to be effective solutions for real-time analysis [4].”
An, X., Wang, Z., Wei, D., Gu, J., Futao, L. I., Zhang, C., & Xia, G. (2026) · Machines · doi:10.3390/machines14020150 · Cited by 2
Enhanced Fruit and Vegetable Image Recognition with CNN and MobileNetV2
Reddy, P. V., Kandukuri, P., Kiran, M. A., & Kativarapu, P. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-14531-4_28 · Cited by 1
Ni, J., Gao, B., Zhu, H., Zhao, M., & Liu, X. (2026) · ISPRS International Journal of Geo-Information · doi:10.3390/ijgi15020060 · Cited by 3
Luo, S. K., Chen, X., Zheng, S., & Zhao, Y. (2026) · Alexandria Engineering Journal · doi:10.1016/j.aej.2026.01.035 · Cited by 1
Cross domain object detection with multi-level domain feature refinement
Li, J., Ren, F., Liang, M., Yi, J., & Cao, F. (2026) · Computing · doi:10.1007/s00607-026-01621-4 · Cited by 1
“The classic work is the YOLO [ 15 ] (You Only Look Once) algorithm.”
Multi-Perceptual Framework for Anomaly Detection
Li, C., Li, H., & Zhang, G. (2026) · IEEE Transactions on Emerging Topics in Computational Intelligence · doi:10.1109/tetci.2026.3657946 · Cited by 1
“Given video sequence I 1 , . . . , I M , each object with its class attribute can be obtained through object detection, e.g., Yolo [50] that also outputs the confidence thresholds.”
Lightweight target detection based on improved YOLOv5n for unmanned aerial vehicle infrared imagery
Xue, W., Zhang, X., Yan, J., Chen, D., & Wang, Y. (2026) · Engineering Research Express · doi:10.1088/2631-8695/ae408c · Cited by 1
Zhong, S., Wei, X., Jiang, J., Li, J., & Wang, G. (2026) · Applied Optics · doi:10.1364/ao.579973 · Cited by 2
Zhu, Z., Ruan, X., Tian, K., Jiang, Z., & Liu, D. (2026) · Structural Health Monitoring · doi:10.1177/14759217251411321 · Cited by 1
Impact of purple nutsedge ( Cyperus rotundus ) density on detection accuracy of a YOLOv8 model
Rodriguez, A. G., Furlanetto, R. H., Peres, J., Schumann, A. W., & Boyd, N. S. (2026) · Weed Science · doi:10.1017/wsc.2026.10086 · Cited by 1
“YOLO streamlines the detection process by integrating feature extraction and bounding-box prediction into a single network pass (Redmon et al. 2016), enabling fast and accurate identification and localization of weeds in agricultural settings.”
Detection Models for Concrete Crack Using Deep Learning Approaches: A Review
Aydın, Y., Orman, Z., & Bekdaş, G. (2026) · Structural Engineering International · doi:10.1080/10168664.2025.2576470 · Cited by 1
UAV-Based Computer Vision Approach for Melon Fruit Detection and Yield Estimation
Aldakn, H., Dragonetti, G., Khadra, R., et al. (2026) · AgriEngineering · doi:10.3390/agriengineering8020053 · Cited by 1
“The advent of one-stage detectors, exemplified by the YOLO algorithm, has signified a substantial advancement in this domain [15].”
X2P-Net: Context-Aware 2D/3D Vertebra Localization
Tao, R., Ye, K., Zhang, W., Sun, W., Yu, D., Hang, D., & Zheng, G. (2026) · Bioengineering · doi:10.3390/bioengineering13020178 · Cited by 2
“Recently, object detection models like the You Only Look Once (YOLO) series [40–42] and Faster R-CNN [43] have gained increasing adoption for vertebra localization tasks owing to their speed and efficiency.”
Development and Testing for Perception-Based Autonomous Landing of a Long-Range QuadPlane
Rasul, A. E., Tasnim, H., Kim, J. Y., et al. (2026) · AIAA SciTech Forum · doi:10.2514/6.2026-2172 · Cited by 1
Li, J., Xu, L., Jiao, J., Huang, Q., Yang, S., Wang, P., & Jiao, A. (2026) · Multimedia Systems · doi:10.1007/s00530-025-02209-2 · Cited by 2
“Since the advent of the first you only look once (YOLO) model [9 ] in 2016, the YOLO series has undergone con - tinuous evolution, progressively enhancing both detec - tion accuracy and computational efficiency.”
Pati, N., Sharma, A., Gourisaria, M. K., Jena, J. J., Jha, A. V., Appasani, B., & Bizon, N. (2026) · Scientific Reports · doi:10.1038/s41598-026-37869-1 · Cited by 3
“Redmon (2016) 7 introduced the YOLO architecture, ground-braking, performing the bounding box object detection directly-a unified approach to real-time object detection problems.”
Baydilli, Y. Y. (2026) · The Journal of Supercomputing · doi:10.1007/s11227-026-08244-8 · Cited by 1
Extracting Player Speed from Football Videos
Rustebakke, O. K., Sarkhoosh, M. H., Midoglu, C., & Halvorsen, P. (2025) · International Symposium on Multimedia · doi:10.1109/ism66958.2025.00058 · Cited by 2
“1) Player Detection and Tracking: YOLOv8 [10] builds on the YOLO [11] framework, and introduces a neck to refine and fuse features through an optimized Path Aggregation Network (PANet) [12], improving detection of objects at different scales.”
Design and Implementation of a YOLO-Based Screen Time Monitoring System Using PyQt and MySQL
Arun Krishna, B., V, Gowtham, S., & Sivakumar, J. (2026) · ITM Web of Conferences · doi:10.1051/itmconf/20268203012 · Cited by 1
An Explainable AI Approach for Weed and Crop Localization Via Image-Level Classification
Gundampati, K. S., & Udgata, S. K. (2025) · IEEE International Conference on Computational Intelligence and Communication Networks (CICN) · doi:10.1109/cicn67655.2025.11367978 · Cited by 1
“Powered by deep learning models like YOLO, R-CNN, Masked R-CNN, and others, these systems can identify and draw precise bounding boxes around each instance of a weed or crop in an image [6], [7].”
A cloud robotics architecture for greenhouse strawberry harvesting with single-pass data collection
Baig, M. A., Han, L., Yang, D., & Danaish (2026) · Industrial Robot the international journal of robotics research and application · doi:10.1108/ir-09-2025-0306 · Cited by 2
Pugh, N. A., Young, A., Nesbitt, M., & Hayes, C. M. (2026) · Plant Phenomics · doi:10.1016/j.plaphe.2026.100179 · Cited by 1
Liang, Y., Xia, Y., Merzouk, M., et al. (2026) · Developments in the Built Environment · doi:10.1016/j.dibe.2026.100869 · Cited by 1
Wang, D., Wang, Y., & Zhu, Y. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-6960-1_8 · Cited by 1
Cross-stage edge information fusion network for small object detection in aerial images
Xiao, J., Li, C., Chen, H., et al. (2026) · Scientific Reports · doi:10.1038/s41598-026-36251-5 · Cited by 1
Localized Background-Aware Generative Distillation for Enhanced Remote Sensing Object Detection
Wang, C., Sun, Y., Yang, J. J., & Luo, L. (2026) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2026.3661231 · Cited by 4
“The YOLO series [25], [26], [27] has achieved remarkable success by balancing detection accuracy and inference speed, making it well-suited for real-time aerial and satellite applications.”
PROTheft: A Projector-Based Model Extraction Attack in the Physical World
Liu, X., Yang, Y., Liu, T., Yang, H. J., Zhang, L. Y., Zhang, Y., Liu, Y., & Ma, Z. (2026) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2026.3661794 · Cited by 1
OpenEar: an ultra-affordable, high-throughput, and accurate maize ear phenotyping system
Fan, S.-Q., Li, G., Bahitwa, R., Jia, Z., Zhang, H., Shao, J., Yu, Q., Chen, X.-R., Qian, Y., Xu, M.-C., et al. (2026) · Plant Methods · doi:10.1186/s13007-026-01504-x · Cited by 5
“Among these, the You Only Look Once (YOLO) architecture [41] stands out for its real-time object detection capabilities.”
Single-Shot Object Detection Framework for Low-Light Condition Scenarios
Soumya, A., Abdulla, A. A. M., Mohan, C. K., & Cenkeramaddi, L. R. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-07623-6_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.