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 26,601–26,700 of 51,401
An Enhanced YOLOv5 Algorithm with Coordinate Attention for Efficient Tuberculosis Bacteria Detection
Yi, J., Zhang, X., & Ye, Y. (2025) · Asia-Pacific Conference on Communications Technology and Computer Science (ACCTCS) · doi:10.1109/acctcs66275.2025.00022 · Cited by 3
“YOLO[11] is an object detection approach that processes object category and bounding box predictions in one step, enabling rapid and immediate detection.”
Dongliang, 李. L., Hongxing, 蔡. C., Tingting, 王. W., Junxia, 赵. Z., Yangyang, 花. H., Jianguo, 李. L., Siyuan, 刘. S., & Siyuan, 宋. S. (2025) · Acta Optica Sinica · doi:10.3788/aos251247 · Cited by 3
Multi-Dataset Training Strategy for Robust Polyp Detection With Clinical Validation Insights
Mert, A., Büyüklü, A. H., Bayram, B., & Taşabat, S. E. (2025) · IEEE Access · doi:10.1109/access.2025.3608668 · Cited by 4
Liu, S. H., Li, K., Ding, Y., et al. (2025) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2025.110944 · Cited by 3
Explainable AI to unveil cellular autophagy dynamics
Presacan, O., Mesa, M. H., Aldea, A. C., Andresen, S., Outa, A. A., Johannessen, J. A., Ionescu, B. E., Knævelsrud, H., & Riegler, M. A. (2025) · PLoS ONE · doi:10.1371/journal.pone.0331045 · Cited by 3
“For the detection task, we used the well-established You Only Look Once (YOLO) model [14].”
Exploring hand wrist feature as biometric identifier: A deep learning perspective using Yolov11
Elumalai, G., & Malathi, G. (2025) · Results in Engineering · doi:10.1016/j.rineng.2025.107107 · Cited by 3
EEM-YOLO: Real-Time Fire and Smoke Detection in Power Substation Environments
Zhou, J., Dong, X., Zhou, Z., et al. (2025) · IEEE Conference on Industrial Electronics and Applications (ICIEA) · doi:10.1109/iciea65512.2025.11148713 · Cited by 3
“…and models for flames and smoke, scholars at home and abroad have conducted extensive research on various methods including the fast region-based convolutional neural network [3] ( Faster R-CNN), the YOLO (you only look once) algorithm [4], and the single-shot multi-box detector (SSD) model [5].”
Wang, Y., Wu, R., Li, X., & Kutscher, D. (2025) · ACM/IEEE Design Automation Conference (DAC) · doi:10.1109/dac63849.2025.11133419 · Cited by 6
“These DL models exhibit excellent performance in various computer vision (CV) and neutral language processing (NLP) tasks [4]–[7].”
MCEM: Multi-Cue Fusion with Clutter Invariant Learning for Real-Time SAR Ship Detection
Chen, H., He, M., Yang, Z., et al. (2025) · Sensors · doi:10.3390/s25185736 · Cited by 3
“These advances are inseparable from the continuous evolution of technical approaches: early traditional methods based on sea clutter statistics (such as CFAR) laid the foundation [9,11,13], while current mainstream deep learning methods demonstrate stronger feature learning capabilities [14–18].”
Deep Learning-driven DAA System for UAVs With Frenet Trajectory Optimization
Ywet, N. L., Maw, A. A., & Lee, J.-W. (2025) · International Journal of Control Automation and Systems · doi:10.1007/s12555-025-0180-9 · Cited by 3
“[18] introduced YOLO, a real-time object detection system that frames detection as a single regression problem, moving directly from image pixels to bounding box coordinates and class probabilities.”
Thainimit, S., Kitiwouranon, K., Buaphuan, A., & Sanposh, P. (2025) · IEEE Access · doi:10.1109/access.2025.3607955 · Cited by 4
Liu, H., Cheng, X., & Wang, C. (2025) · IEEE Sensors Journal · doi:10.1109/jsen.2025.3608212 · Cited by 3
“Subsequently, single-stage detectors represented by YOLO [8], [9], [10], [11], [12] and SSD [13] significantly improved detection speed, but accuracy under adverse weather conditions still needs improvement.”
Mohy, A. A., Bassioni, H., Elgendi, E. O., et al. (2025) · Journal of Information Technology in Construction · doi:10.36680/j.itcon.2025.057 · Cited by 3
Lightweight Multi-Frame Integration for Robust YOLO Object Detection in Videos
Quan, Y., Kiefer, B., Messmer, M., & Zell, A. (2025) · European Conference on Mobile Robots · doi:10.1109/ecmr65884.2025.11162972 · Cited by 6
“Architectures like Faster R-CNN [8], YOLO [9], [1], and RetinaNet [10] have demonstrated strong performance on still images.”
Chen, M., Li, Q., Nie, W., Liu, J., Geng, J., Ma, Y., & Guan, X. (2025) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2025.3613161 · Cited by 5
Advancements in Obstacle Intrusion Detection Methods for Rail Transit: A Comprehensive Review
Xu, X.-Y., Wang, S.-M., Liu, W., & Ni, Y. (2025) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2025.3612624 · Cited by 20
Lian, X., Sun, X. J., Liu, H., Tan, L., & Li, J. (2025) · Signal Image and Video Processing · doi:10.1007/s11760-025-04574-x · Cited by 6
“Among the many deep learning methods, the YOLO [5] series of algorithms has attracted widespread attention since its inception.”
YOLO-GSD: a real-time pedestrian detection algorithm based on YOLOv8 in dense environments
Zhang, Z., Li, W., & Luo, L. (2025) · Journal of Real-Time Image Processing · doi:10.1007/s11554-025-01771-2 · Cited by 4
“Representative methods include the Single Shot Multi-Box Detector (SSD) [15], proposed by Liu et al., and the You Only Look Once (YOLO) series [16–21], introduced by Redmon.”
Image-based phenotypic sorting of synthetic cells
van den Brink, M., Stam, M., Claassens, N. J., & Danelon, C. (2026) · Science Advances · doi:10.1126/sciadv.aed0860 · Cited by 2
Deng, S., Chen, T., & Qiao, Q. (2025) · Image and Vision Computing · doi:10.1016/j.imavis.2025.105744 · Cited by 3
Punia, D., & Kumar, R. (2025) · Applied Soft Computing · doi:10.1016/j.asoc.2025.113981 · Cited by 5
Jiang, Y., Atwa, E. M., He, P., Zhang, J., Di, M., Pan, J., & Lin, H. (2025) · Agriculture · doi:10.3390/agriculture15192035 · Cited by 9
Zhu, W., Hu, F., He, X., et al. (2025) · Applied Sciences · doi:10.3390/app151910625 · Cited by 3
Dynamic Collaborative Inference for Multi-Type DNN Tasks in Space-Ground Networks: A DRL Approach
Tian, S., Wang, R., Hao, J., Wu, Q., & Niyato, D. T. (2025) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2025.3616114 · Cited by 5
Monzón-Verona, J. M., García–Alonso, S., & Santana-Martín, F. J. (2025) · Electronics · doi:10.3390/electronics14193916 · Cited by 3
Jnaini, A., & Koulali, M.-A. (2025) · Computers · doi:10.3390/computers14100414 · Cited by 3
Li, K., Qian, Y., Cheng, S. Z. D., Yang, Z., & Lu, Z. (2025) · Composites Communications · doi:10.1016/j.coco.2025.102603 · Cited by 5
Zhuang, X., Wang, B., Xie, Z., Qiao, Z., Feng, J., Behm, J. E., Schneider, C., Shi, B., Zheng, J., Gu, Y., et al. (2025) · Soil Ecology Letters · doi:10.1007/s42832-025-0352-9 · Cited by 6
“You Only Look Once (YOLO) is one of the most widely used one-stage detectors (Redmon et al., 2016).”
Mask-Guided Teacher–Student Learning for Open-Vocabulary Object Detection in Remote Sensing Images
Wang, S., Song, Y. C., Xiang, J., Chen, Y., Zhong, P., & Fu, R. (2025) · Remote Sensing · doi:10.3390/rs17193385 · Cited by 4
Sang, H., Lu, Q., Sun, X., Zhang, S., & Liu, F. (2025) · Measurement · doi:10.1016/j.measurement.2025.119280 · Cited by 5
YOLO-IMS: an improved method for infrared damaged ship detection
Wang, J., Han, S., Chen, J., et al. (2025) · Journal of Real-Time Image Processing · doi:10.1007/s11554-025-01783-y · Cited by 3
“Single-stage detectors, such as SSD [9, 10], RetinaNet [11], and the YOLO series [12, 13], perform classification and bounding box regression in one step.”
Yu, S., Peng, J., Wang, S., Wu, D., & Ma, C. (2025) · Smart Cities · doi:10.3390/smartcities8050171 · Cited by 6
“Traditional 2D detectors, such as R-CNN [17], Faster R-CNN [18], SSD [19], and YOLO [20], achieve high accuracy for planar localization but do not recover depth.”
Zhang, B., & Zhang, Y. (2025) · IEEE Access · doi:10.1109/access.2025.3620956 · Cited by 6
Shen, C., Sun, S., Zhang, H., & Jiang, M. (2025) · Journal of Real-Time Image Processing · doi:10.1007/s11554-025-01777-w · Cited by 6
“With the arrival of the deep learning era, CNN-based detectors, being categorized into two-stage models(Faster R-CNN) [5, 6] and one-stage models(YOLO series) [7–10], has emerged.”
Apple estimation and recognition in complex scenes using YOLO v8
Geng, H., Pan, J., Cao, Y.-C., Yin, Z.-B., Wang, J., Shi, M., Si, C., & Qi, L.-M. (2025) · PeerJ Computer Science · doi:10.7717/peerj-cs.3116 · Cited by 4
Lu, S., Zhao, H., Zhang, E., et al. (2025) · International Journal of Intelligent Computing and Cybernetics · doi:10.1108/ijicc-06-2025-0370 · Cited by 3
Bakhshi, E. A., Yazdanpanah, O., & Dolatshahi, K. M. (2025) · Automation in Construction · doi:10.1016/j.autcon.2025.106587 · Cited by 4
Insulator Defect Detection Algorithm Based on Improved YOLO11s in Snowy Weather Environment
Ding, Z., Deng, S., & Liu, Q. (2025) · Symmetry · doi:10.3390/sym17101763 · Cited by 3
A Systematic Review of AI-Driven Wearable Plant Disease Recognition Systems
Mohamed, A., Abdin, F. A., Hamdallah, M. R., Mohammed, M. A., Khawaja, S. G., Yousaf, J., Ghazal, M., & Hassan, T. (2025) · International Conference on Future Internet of Things and Cloud (FiCloud) · doi:10.1109/ficloud66139.2025.00065 · Cited by 4
“IoT-integrated approaches, such as YOLO[38] paired with environmental sensors, demonstrate moderate classification accuracy but offer significant advantages in multi-modal disease monitoring (e.g., fusing imagery with humidity or soil data).”
Explainable AI (XAI) for Object Detection and Application to Satellite Imagery
Roy, A., Gaikwad, K. D., Hude, A. J., Shinde, J. S., Parekh, J. J., & Nagrani, H. R. (2025) · IEEE Access · doi:10.1109/access.2025.3624198 · Cited by 10
Wang, S., Feng, Y., Tao, H., et al. (2025) · Photonics · doi:10.3390/photonics12111044 · Cited by 3
“Among their early representatives, YOLOv1 pioneered real-time object detection; however, it exhibited insufficient accuracy under thermal signals with low contrast [12].”
Efficient bridge damage detection using a lightweight attention‐based modeling framework
Huang, J., Zhu, Y., Xiong, M., Ser, J. D., Alotaibi, A., Papa, J. P., & Muhammad, K. (2025) · Computer-Aided Civil and Infrastructure Engineering · doi:10.1111/mice.70098 · Cited by 5
“Specifically, it achieves a processing speed at an inference of 45 FPS, which is close to real-time for typical frame rates achieved by IoT vision sensors (Redmon et al., 2016).”
Donizette, A. C., & Rocco, C. D. (2025) · Applied Artificial Intelligence · doi:10.1080/08839514.2025.2576891 · Cited by 4
“This study aims to enhance the precision of sorting in the tomato industry by leveraging machine learning models, specifically object detection techniques like the YOLO algorithm (Redmon et al. 2016), to improve both reliability and efficiency.”
Liu, Y., Zou, Y., Li, X., Zhu, X., Han, K., Jiang, Z., Ma, L., & Liu, J. (2025) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3746027.3755087 · Cited by 14
Miao, W., Shen, J., Xu, H., Kärkkäinen, T., Xu, Q., Xu, Y., & Cong, F. (2025) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3746027.3754854 · Cited by 9
“Over the past decade, the You Only Look Once (YOLO) series [16, 29] employ a single convolutional neural network (CNN) to predict bounding boxes and class probabilities simultaneously, offering an efficient and real-time object detection framework.”
Su, P.-J., Chen, T.-M., & Su, J. (2025) · Agriculture · doi:10.3390/agriculture15212227 · Cited by 3
“In image deep learning, three main algorithms are commonly used: R-CNN series (R-CNN, Fast R-CNN, Faster R-CNN), Single Shot Detector (SSD), and YOLO (You Only Look Once) [10].”
AI-DRIVEN GEOSPATIAL ANALYSIS IN ECOSYSTEM MANAGEMENT: INTEGRATION OF MACHINE LEARNING METHODS
Saygıner, C., & Nurlu, E. (2025) · TURKISH JOURNAL OF FOREST SCIENCE · doi:10.32328/turkjforsci.1704059 · Cited by 6
Bing, J., Lu, Z., He, L., & Yu, P. (2025) · The Journal of Supercomputing · doi:10.1007/s11227-025-07947-8 · Cited by 4
“Representative two-stage algorithms include R-CNN [11], Fast R-CNN [12], and Faster R-CNN [13], while one-stage detectors are exemplified by SSD [14] and YOLO [15].”
Han, Y., Wang, L., Jiang, W., & Wang, H. (2025) · Agriculture · doi:10.3390/agriculture15212249 · Cited by 3
Real-time detection method for Litchi diseases and pests based on improved YOLOv5s
Ma, X.-Z., Huang, T.-Y., Zhao, G., et al. (2025) · Frontiers in Plant Science · doi:10.3389/fpls.2025.1686997 · Cited by 4
Deep Learning Approach for Damage Detection on Composite Structures
Merola, S., Guida, M., & Marulo, F. (2025) · Journal of Materials Engineering and Performance · doi:10.1007/s11665-025-12483-w · Cited by 4
A lightweight infrared target detection network suitable for land and water surfaces
Yang, F., Yu, Y., Xu, P., Lu, Y., Hua, W., & Li, Y. (2025) · Scientific Reports · doi:10.1038/s41598-025-21550-0 · Cited by 3
Bingol, E. C., & Al-Raweshidy, H. S. (2025) · Applied Sciences · doi:10.3390/app152111582 · Cited by 6
PGLD-YOLO: a lightweight algorithm for pomegranate fruit localisation and recognition
Lǚ, J., Zhao, Y., & Yu, M. (2025) · PeerJ Computer Science · doi:10.7717/peerj-cs.3307 · Cited by 3
Patiño-Ortiz, J., CARREÑO-AGUILERA, R., Vázquez, S. J., Patiño-Ortiz, M., & BENÍTEZ, M. A. C. (2025) · Fractals · doi:10.1142/s0218348x26500040 · Cited by 5
HADF: A hybrid attention and dual-branch feature fusion method for infrared and visible image fusion
Li, Q., Shen, Y., Wu, P., & Wu, J. (2025) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2025.104557 · Cited by 3
Real-Time Detection of Airport Vertical Signs Using YOLOv8 and Enhanced Data Augmentation Strategies
Suder, J., Stankiewicz, T., & Szczerbowski, K. (2025) · Signal Processing: Algorithms, Architectures, Arrangements, and Applications · doi:10.23919/spa65537.2025.11215127 · Cited by 3
“The You Only Look Once (YOLO) [6] family of object detection algorithms, particularly the most recent YOLOv8, offers real-time performance with high accuracy.”
JUHCCR-v1: a database for hand-drawn electrical and electronics circuit component recognition
Roy, A., Pani, S., Malakar, S., et al. (2025) · Scientific Reports · doi:10.1038/s41598-025-22404-5 · Cited by 3
“In these works, the researchers mostly relied on different incremental versions of you only look once (YOLO) models 34 , fast region based convolutional neural network (Fast R-CNN) 35 , and faster region based convolutional neural network (Faster R-CNN) 36 .”
Yamaguchi, T., & Mizutani, T. (2025) · Computer-Aided Civil and Infrastructure Engineering · doi:10.1111/mice.70125 · Cited by 3
“YOLO and SSD are two major RPNs (W. Liu et al., 2016; Redmon et al., 2016).”
Hsu, F.-C., Tsai, M., & Hsieh, S. (2025) · The Journal of Supercomputing · doi:10.1007/s11227-025-07855-x · Cited by 3
“Xu et al. proposed a BAA framework [23], utilizing a YOLO object-detection model [24] to identify and segment 13 different bone regions in a hand.”
Yang, Y., Yan, L., Wang, J., Liu, J. B., & Tang, X. (2025) · Sensors · doi:10.3390/s25226856 · Cited by 5
“In contrast, SSDs [11] pioneered single-stage detection, followed by methods such as RetinaNet [12] and YOLO [13].”
Rapid Detection of Corrosion on Steel Bridges Using a Deep Learning Method
Hacıefendioğlu, K., Özgan, K., Mostofi, S., & Altunışık, A. C. (2025) · Applied Sciences · doi:10.3390/app152211929 · Cited by 4
Rate-Accuracy Bounds in Visual Coding for Machines
Bajić, I. V. (2025) · IEEE International Conference on Multimedia Information Processing and Retrieval (MIPR) · doi:10.1109/mipr67560.2025.00038 · Cited by 7
“2 shows rate-accuracy plot for YOLO-like object detection [28] on the COCO dataset [29].”
Self-Prompting Hybrid YOLOv12-SAM 2 Model for MRI Brain Tumour Segmentation in Real Time
Pasunoori, K. C., Prasad, C. R., & Raj Kumar, K. (2025) · The Open Public Health Journal · doi:10.2174/0118749445421967251007105043 · Cited by 4
YOLO-MT: real-time and efficient surface defect detection method for magnetic sheet
Fan, D., Ge, H., Li, J., et al. (2025) · Nondestructive Testing And Evaluation · doi:10.1080/10589759.2025.2589470 · Cited by 3
Lin, L., Zeng, Z., Tang, C., Xie, Y., & Liang, Q. (2025) · Hydrology · doi:10.3390/hydrology12110307 · Cited by 6
“Other methods for extracting reference targets include R-CNN [39], YOLO [40], and similar techniques.”
Hwang, C., Yang, S., Kim, Y., Park, S., & Choi, H. (2025) · Computer-Aided Civil and Infrastructure Engineering · doi:10.1111/mice.70142 · Cited by 6
“YOLO framework, a unified one-stage approach for object detection, was first introduced in 2016 (Redmon et al., 2016).”
Khan, A., Hussain, S., Jawad, M., Ahmad, W., & Jahanzaib, M. (2025) · The International Journal of Advanced Manufacturing Technology · doi:10.1007/s00170-025-16731-0 · Cited by 6
“In another study, single-stage detectors such as YOLOv1 [35] and Single Shot MultiBox Detector (SSD) [36] were introduced to prioritize real-time performance.”
Real-Time Parking Space Management System Based on a Low-Power Embedded Platform
Kim, K., Lee, J., Jeong, I., Jung, J., & Cho, J. (2025) · Sensors · doi:10.3390/s25227009 · Cited by 5
“The growing need for real-time object recognition has led to the development of the YOLO algorithm [22].”
DG-DETR: Toward domain generalized detection transformer
Hwang, S., Han, D., & Jeon, M. (2025) · Pattern Recognition Letters · doi:10.1016/j.patrec.2025.11.023 · Cited by 7
“Furthermore, existing S-DG studies have largely focused on CNN-based detectors [1, 2, 3], although Vision Transformers (ViTs) have demonstrated strong generalization capabilities attributed to their superior shape bias, which stems from their ability to capture global dependencies among tokens [23,…”
InfluentialChicken freshness detection method based on integrated intelligent indicator film and improved CNN
He, J., Ouyang, Z., Zhang, C., et al. (2025) · Food Control · doi:10.1016/j.foodcont.2025.111860 · Cited by 3
MSFC-Net: Multi-scale feature and contextual fusion network for high-precision UAV detection
Li, H., Xiao, L., Cao, L., Liu, Y., & Li, Y. (2025) · Alexandria Engineering Journal · doi:10.1016/j.aej.2025.11.033 · Cited by 5
Crop leaf disease detection with additive gated convolution and hierarchical attention fusion
Liu, J., Liu, X., Tao, J., Cao, Y., Zhou, X., Guo, C., & Dong, C. (2025) · Scientific Reports · doi:10.1038/s41598-025-25751-5 · Cited by 8
Lightweight DETR algorithm for X-ray weld defect detection
Zhang, X., Chen, H., Liu, Z., & Anli, S. (2025) · Scientific Reports · doi:10.1038/s41598-025-25916-2 · Cited by 13
Automatic Reconstruction of 3D Building Models from ALS Point Clouds Based on Façade Geometry
Zhao, T., Xiong, T., Li, M., & Li, Z. (2025) · ISPRS International Journal of Geo-Information · doi:10.3390/ijgi14120462 · Cited by 3
“The YOLO family of models [39] represents a typical learning-driven approach.”
Gunawardhana, M., Kulathilaka, A., & Zhao, J. (2025) · Discover Artificial Intelligence · doi:10.1007/s44163-025-00324-7 · Cited by 10
Enhancing Weakly Supervised Video Anomaly Detection with Object-Centric Features
Wang, Y.-W., Chen, Y., & Yeo, C. K. (2025) · Information · doi:10.3390/info16121042 · Cited by 3
Multimodal learning on RGB-D image for precise litchi phenotyping and weight estimation
Yang, M., Chen, R., Chen, D., Wang, H., Wang, X., & Hu, F. (2025) · Plant Methods · doi:10.1186/s13007-025-01472-8 · Cited by 3
“With the rapid advancement of computer vision and deep learning technologies, high-performing instance segmentation models such as YOLO [29] and Mask R-CNN [30] have been widely developed and applied.”
Multiple Large AI Models’ Consensus for Object Detection—A Survey
Iwanowski, M., & Gahbler, M. (2025) · Applied Sciences · doi:10.3390/app152412961 · Cited by 9
Real Time Child Abduction and Detection System
Yashwanth, T. S., Royal, Y. S., Kashyap, M., et al. (2025) · International Conference on Intelligent Systems: Theories and Applications · doi:10.1109/sita67914.2025.11273371 · Cited by 3
“Redmon et al. [11] introduced the YOLO (You Only Look Once) family of detectors, reframing detection as a single end-to-end regression task instead of a multi-stage pipeline.”
Dong, Z., Yang, Q., Chen, H., & Gao, D. (2025) · Multimedia Systems · doi:10.1007/s00530-025-02116-6 · Cited by 4
“Prominent examples of one-stage detectors encompass the SSD framework and the YOLO series [ 6– 8 ].”
Capsicum Counting Algorithm Using Infrared Imaging and YOLO11
Méndez, E., Cabello, J. A. E., Gómez-Espinosa, A., Cantoral-Ceballos, J. A., & Ochoa, O. (2025) · Agriculture · doi:10.3390/agriculture15242574 · Cited by 5
Ke, S., Yang, K., Zhan, C., Liao, S., Ma, Y., Shang, H., Shen, E., Li, Z., Zhao, Z., & Chen, Z. (2025) · Geocarto International · doi:10.1080/10106049.2025.2600779 · Cited by 7
“Combined with deep learning-based object detection algorithms (such as YOLO and Faster R-CNN), they significantly enhance the automatic identification and tracking capabilities for enemy equipment, vehicles, and personnel (Redmon et al. 2016).”
Deep learning accurately identifies fjord benthic foraminifera
Plavetić, M., Hsiang, A. Y., Josefson, M., Hulthe, G., & Asteman, I. P. (2025) · Journal of Micropalaeontology · doi:10.5194/jm-44-693-2025 · Cited by 5
Spectral-spatial feature fusion for real-time facial expression recognition
Ma, J., Lin, Y., Qian, L., You, H., & Gao, T. (2025) · Scientific Reports · doi:10.1038/s41598-025-27666-7 · Cited by 3
“YOLO 12 (You Only Look Once), as an efficient single-stage object detection framework, achieves a favorable balance between computational efficiency and detection accuracy.”
Distributed Deep Learning in IoT Sensor Network for the Diagnosis of Plant Diseases
Papanikolaou, A., Tziouvaras, A., Floros, G., Xenakis, A., & Bonsignorio, F. (2025) · Sensors · doi:10.3390/s25247646 · Cited by 6
“Additionally, experimental results showed that YOLOv5 [16] achieved the highest accuracy for object detection, while ResNet50 [17] and MobileNetV2 [18] offered the best balance between accuracy and computational efficiency.”
Dong, R.-Z., Fan, Y., Na, B.-W., & Yang, J. (2025) · Composites Communications · doi:10.1016/j.coco.2025.102687 · Cited by 6
A Lightweight Feature Enhancement Model for UAV Detection in Real-World Scenarios
Han, Y.-N., Yan, X., Li, Y., Li, D., Liu, X., Huang, H., & Bie, D. (2025) · Drones · doi:10.3390/drones9120874 · Cited by 3
“YOLOv5 [15]: YOLOv5 consists of four main components: input, backbone network, neck network, and output.”
InfluentialMFA-YOLO: a multi-feature aggregation approach for small-object detection method in drone imagery
Li, S., & Chen, C. (2025) · Scientific Reports · doi:10.1038/s41598-025-32247-9 · Cited by 8
“YOLOv10 29 incorporated programmable gradients and non-maximum suppression-free training for streamlined end-to-end processing.”
InfluentialHou, C., Tang, X., Ji, L., Wang, Y., Yin, Z., & Li, R. (2025) · Scientific Reports · doi:10.1038/s41598-025-30735-6 · Cited by 5
Modeling anesthetic-drug label detection for low-resource operating rooms
Nsumba, S., Ninsiima, F. D., Nampawu, M. J., Nabende, P., & Nabende, J. N. (2025) · BMC Medical Informatics and Decision Making · doi:10.1186/s12911-025-03316-w · Cited by 3
Wang, X., Pang, C. C., & Hui, P. (2025) · ACM Symposium on User Interface Software and Technology (UIST) · doi:10.1145/3746059.3747617 · Cited by 8
Adaptive Grid Selection Training Strategy for Tiny Object Detection
Yim, S., Cho, M., Kang, D., & Lee, S. (2025) · IEEE Access · doi:10.1109/access.2025.3613741 · Cited by 4
Star-YOLO: A lightweight detection algorithm for UAV landing markers
Yu, D., Qu, R., Li, C., & Liu, X. (2025) · The Journal of Supercomputing · doi:10.1007/s11227-025-07938-9 · Cited by 3
“The second category comprises one-stage detectors such as SSD [14] and YOLO [15], which directly predict object classes and bounding boxes in a single forward pass.”
Lin, X., Li, T., Hua, B., Li, L., & Zhao, C. (2025) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2025.3633611 · Cited by 4
Deep‑learning‑based detection of open‑apex teeth on panoramic radiographs using YOLO models
Edik, M., Çelebi, F., & Cukurluoglu, A. (2025) · Oral Radiology · doi:10.1007/s11282-025-00884-5 · Cited by 3
“YOLO performs both object localization (detection) and object type prediction (classification) simul - taneously, within the same network [14].”
Wang, C. C., & Tang, J. (2025) · Remote Sensing · doi:10.3390/rs18010051 · Cited by 3
Artificial intelligence in sustainable horticultural production: a systematic review
Chaudhary, V., Kumar, M., Chaudhary, V., Kumar, R. R., & Chauhan, C. (2025) · Discover Plants. · doi:10.1007/s44372-025-00455-2 · Cited by 10
“…classification of images such as AlexNet [61, 62] VGGNet [63], GoogLeNet [64], Incep-tionNet [65], ResNet50 [66, 67] DenseNet [68], XceptionNet [69], EfficientNet [70] and NASNet [71], CIFAR-10 dataset [72], U-Net [73], Mask R-CNN, and YOLO [74], YOLOv5 and AlexNet [75], NIR and RGB images [76].”
DOMino-YOLO: A Deformable Occlusion-Aware Framework for Vehicle Detection in Aerial Imagery
Fu, T., Dong, H., Yang, B., & Deng, B. (2025) · Remote Sensing · doi:10.3390/rs18010066 · Cited by 4
Visual intelligence framework for track division and obstruction risk estimation in rail transport
Gorane, Y. M., & Joshi, R. D. (2025) · Discover Computing · doi:10.1007/s10791-025-09872-z · Cited by 3
“This study addresses these gaps by contributing a specialized dataset, conducting a comprehensive comparative evaluation of state-of-the-art YOLO models, and proposing a dynamic ROI-based framework for threat assessment [16–26].”
Influential
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.