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 20,901–21,000 of 51,401
Nondestructive Inspection of Steel Cables Based on YOLOv9 with Magnetic Flux Leakage Images
Zhao, M., Ding, N., Fang, Z., Jiang, B., Zhong, J., & Deng, F. (2025) · Journal of Sensor and Actuator Networks · doi:10.3390/jsan14040080 · Cited by 6
“The initial YOLO proposed by Redmon et al. [26] presented a unified approach, which requires precise manual annotation for bounding boxes and integrates all object detection components within a single neural network.”
Surface Defect Detection of Magnetic Tiles Based on YOLOv8-AHF
Ma, C., Pan, Y., & Chen, J. (2025) · Electronics · doi:10.3390/electronics14142857 · Cited by 6
Shi, Y., Ma, Y., Geng, L., Chu, L., Li, B., & Li, W. (2025) · Sensors · doi:10.3390/s25154871 · Cited by 7
“One-stage detectors, exemplified by SSD [5] and the YOLO family [6], accelerate inference by predicting classes and boxes in a single pass, yet their reliance on high-contrast edges causes recall to collapse when back-lighting or deep shade blurs contours.”
A Classification Method for the Severity of Aloe Anthracnose Based on the Improved YOLOv11-seg
Zhong, W., Li, X., Yue, X., Feng, W., Yu, Q. P., Chen, J., Chen, B., Zhang, L., Cai, X., & Wen, J. (2025) · Agronomy · doi:10.3390/agronomy15081896 · Cited by 7
DSV-LFS: Unifying LLM-Driven Semantic Cues with Visual Features for Robust Few-Shot Segmentation
Karimi, A., & Poullis, C. (2025) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52734.2025.00432 · Cited by 10
Wang, Y., Wang, X., Wang, K., et al. (2025) · Journal of Applied Geophysics · doi:10.1016/j.jappgeo.2025.105905 · Cited by 6
Landslide detection using deep learning on remotely sensed images
Song, Y., Hao, L., & Li, W. (2025) · Applied Computing and Geosciences · doi:10.1016/j.acags.2025.100278 · Cited by 7
Liu, K.-H., Wang, M., & Liu, T.-J. (2025) · Proceedings - International Conference on Image Processing · doi:10.1109/icip55913.2025.11084535 · Cited by 6
Wang, Y., Sun, H., Jiang, T., Shi, J., Wang, Q., Yang, H., & Qiao, Y. (2025) · Frontiers in Medicine · doi:10.3389/fmed.2025.1635016 · Cited by 7
“Firstly, the medical images used for ulnar radius fracture typing definition are mainly CT 3D Recent advances in deep learning (20), particularly with the YOLO (You Only Look Once) (21, 22) family of models, have demonstrated promising results for medical imaging applications.”
Hussain, S. S., Xu, D., Shah, P. M., Khan, H., & Zeb, A. (2025) · Computerized Medical Imaging and Graphics · doi:10.1016/j.compmedimag.2025.102638 · Cited by 10
Ren, Z., Liang, K., Zhang, Y., Song, J., Wu, X., Zhang, C., Mei, X., Zhang, Y., & Liu, X. (2025) · Plant Methods · doi:10.1186/s13007-025-01436-y · Cited by 9
“…we verified the effectiveness of the improved YOLOv5s algorithm in terms of spore detection through a comparison with nine detection algorithms: SSD [47], YOLOv5s [48], CenterNet [49], the Faster R-CNN [50], the, TPH-YOLO [51], MG-YOLO [52], SPD-YOLO [53], YOLO-ECA-ASFF [26], and YOLO-CG-HS [37].”
Majumdar, A., Bhattacharyya, R., & Yadav, V. S. (2025) · Archives of Computational Methods in Engineering · doi:10.1007/s11831-025-10366-w · Cited by 8
Quan, B. H., Anh, N. D., Phi, H. V., et al. (2025) · Sensors · doi:10.3390/s25175411 · Cited by 6
“Advances in artificial intelligence (AI) are rapidly improving machines’ ability to process and understand visual data [1].”
TRS-YOLO: a lightweight insulator defect detection method based on enhanced YOLOv12
Wang, J., & Li, B. (2025) · Journal of Real-Time Image Processing · doi:10.1007/s11554-025-01754-3 · Cited by 10
“Single-stage algorithms, renowned for superior detection speed, are exemplified by the YOLO series models [15–18], along with several excellent lightweight convolutional neural network algorithms published in recent years [19–21].”
Integrating Computer Vision and Deep Learning for Automated Object Diagnosis and Repair
Nanthini, I., Manivannan, K., Vishnu, T. S., Thirumalaivasan, S., Yugith, M., & Titus Raj, R. (2025) · International Conference for Emerging Technology (INCET) · doi:10.1109/incet64471.2025.11140111 · Cited by 11
“Redmon et al. [1] YOLO presented a single, real-time object detection framework that was much faster without compromising on accuracy.”
A top-down deep neural network for multi-dairy cows pose estimation and lameness detection
Wu, S., Han, S., Mo, X., Wei, Y., Qin, Y., Chen, H., Wu, J., & Zeng, Z. (2025) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2025.110911 · Cited by 11
Garibaldi-Márquez, F., Valentín-Coronado, L. M., Díaz-Ponce, A., Servín‐Palestina, M., García-Hernández, R. V., & Ramos-Cantú, L. (2025) · Smart Agricultural Technology · doi:10.1016/j.atech.2025.101405 · Cited by 10
Nom, V., Keo, S., Bakkali, S., Luqman, M. M., Coustaty, M., Rusiñol, M., & Ogier, J.-M. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-04630-7_20 · Cited by 6
Zfusion: an Effective Fuser of Camera and 4D Radar for 3D Object Perception in Autonomous Driving
Yang, S., Zhan, T., Qiao, S., Gong, J., Yang, Q. X., Wang, J., & Lu, Y. (2025) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw67362.2025.00362 · Cited by 17
A Deep Learning-Based Plantar Pressure Measurement System for Accurate Foot Arch Index Estimation
Liao, H.-R., Yu, H., & Li, S.-J. (2025) · Applied Sciences · doi:10.3390/app151810156 · Cited by 7
Li, L., Hu, S., Hou, Y., Ke, Y., & Chen, Z. (2025) · Measurement Science and Technology · doi:10.1088/1361-6501/ae08dc · Cited by 7
“Modern CNN-based detection architectures are generally classified into two categories depending on whether the network generates candidate regions: two-stage algorithms, represented by Fast R-CNN [11] and Faster R-CNN [12], and one-stage algorithms, represented by the YOLO series [13] and SSD [14].”
SOOD++: Leveraging Unlabeled Data to Boost Oriented Object Detection
Liang, D., Hua, W., Shi, C., Zou, Z., Ye, X., & Bai, X. (2025) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2025.3611519 · Cited by 25
Ye, Z., Peng, X., Li, D., & Shi, F. (2025) · Journal of Marine Science and Engineering · doi:10.3390/jmse13101843 · Cited by 12
An explainable AI-based approach for identifying interior design style principles
Seo, J.-H., Jin, S., Choi, K., Hyun, K. H., & Joung, J. (2025) · Advanced Engineering Informatics · doi:10.1016/j.aei.2025.103879 · Cited by 8
Steel surface defect detection algorithm based on improved YOLOv10
Zhang, L., Wang, Z., Ma, Y., & Li, G. (2025) · Scientific Reports · doi:10.1038/s41598-025-16725-8 · Cited by 15
Li, X., Chen, Y., Liu, X., Qin, Z., Wan, J., & Yan, Q. (2025) · Remote Sensing · doi:10.3390/rs17193288 · Cited by 9
Online exam cheating detection and blockchain trusted deposit based on YOLOv12
Wang, H., Shukur, Z., Ariffin, K. A. Z., Xiao, R., & Wang, L. (2025) · Scientific Reports · doi:10.1038/s41598-025-18412-0 · Cited by 12
“The core idea of YOLO is to treat the target detection task as a regression problem by predicting the bounding box and category probabilities directly from the whole image through a single neural network 22 .”
GLDS-YOLO: An Improved Lightweight Model for Small Object Detection in UAV Aerial Imagery
Ju, Z., Shui, J., & Huang, J. (2025) · Electronics · doi:10.3390/electronics14193831 · Cited by 6
Kim, M., Yoo, J., Kwon, S., Kim, B. J., Pak, C. J., Won, C. H., Moon, S., Song, W. J., Cha, H. G., & Park, K. H. (2025) · PLoS ONE · doi:10.1371/journal.pone.0331404 · Cited by 11
“Additionally, in [48] addressing object detection and multi-organ localization problems in CT images, CycleGAN [53] was used for data augmentation and combined with the YOLO [54] model to improve detection efficiency.”
Shteriyanov, V., Джусупова, Р., Bosch, J., & Olsson, H. H. (2025) · Computers & Chemical Engineering · doi:10.1016/j.compchemeng.2025.109436 · Cited by 6
Optimizing surface defect detection with YOLOv9: the role of advanced backbone models
Zeng, Z., Wang, H., Yao, C., Dong, Z., & Cai, S. (2025) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2025.1675154 · Cited by 7
He, Q., Xu, A., Ỹe, Z., Sheng, S., Wen, Z., & Lai, X. (2025) · Geo-spatial Information Science · doi:10.1080/10095020.2025.2555616 · Cited by 7
“To address this issue, we have developed a lightweight remote sensing object detection framework, RS-YOLO, which is based on the single-stage YOLO detector (Redmon and Farhadi 2018; Redmon et al. 2016; Wang, Bochkovskiy, and Liao 2023).”
Zai, K., Mukti, A. P., Notty, G. S., Niswah, S. U., Refliandi, & Oktivendra, F. (2025) · International Journal of Pharmaceutics · doi:10.1016/j.ijpharm.2025.126266 · Cited by 8
Arthur, L., Mahnan, S., He, L., et al. (2025) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2025.111071 · Cited by 6
Multimodal prediction of situation awareness during automated driving: a gaze and EEG-based approach
Lim, C., Liang, N., Villarreal, R. T., Prakah-Asante, K. O., Pitts, B. J., & Yu, D. (2025) · Ergonomics · doi:10.1080/00140139.2025.2571792 · Cited by 11
“…must be directed both towards the sign itself and its surrounding area (peripheral area) (costa et al. 2018; Garvey and Kuhn 2004). as a result, traffic sign area and peripheral area of the traffic sign were extracted from the data using the You-Only-look-Once (YOlO) algorithm (Redmon et al. 2016).”
Dual-domain attentions for unmanned aerial vehicle small object detection
Wang, C., Chang, Y., Xie, S. J., Yang, X., Tian, Y., Sun, W. M., & Hu, J. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.112849 · Cited by 9
Super Mamba feature enhancement framework for small object detection
Shi, N., Yang, Z., Yang, G., et al. (2025) · Scientific Reports · doi:10.1038/s41598-025-21837-2 · Cited by 6
Paul, S., Venu, E., Sarkar, M., Das, S., Roy, A., & Sinha, P. (2025) · Plant Methods · doi:10.1186/s13007-025-01453-x · Cited by 11
Automated C. elegans behavior analysis via deep learning-based detection and tracking
Liu, X., Liu, J., Teng, W., Peng, Y., Li, B., Han, X., & Huo, J. (2025) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1013707 · Cited by 7
“Notable examples of these advanced algorithms include the YOLO series (YOLOv1 [25] through YOLOv8 [26]) and SSD [27] architectures.”
Bai, Y., & Liu, Y. (2025) · Applied Sciences · doi:10.3390/app152211966 · Cited by 5
Evaluation of VITA shade–based tooth color categories using deep learning
Jeong, J.-S., Kim, K.-S., Gu, Y., Yang, L. Y., Yoon, D.-H., Wang, L., Zhang, M., & Kim, J. (2025) · Scientific Reports · doi:10.1038/s41598-025-23954-4 · Cited by 9
“The tooth ROI utilized a Feature Pyramid Network (FPN) 26 architecture composed of a convolutional neural network 27 and YOLO 28 from an object detection model, while tooth segmentation employed U-Net 29 .”
Nguyen, H., & Pham, T. V. (2025) · Cluster Computing · doi:10.1007/s10586-025-05848-2 · Cited by 9
“In contrast, single-stage detectors such as YOLO [ 16–18] and SSD [ 19 ] enhance inference efficiency by eliminating the proposal generation stage.”
Global and Local Context-Aware Detection for Infrared Small UAV Targets
Zhao, L., Zhang, Y., Li, Y., & Han, Z. (2025) · Drones · doi:10.3390/drones9110804 · Cited by 6
“These detection frameworks primarily exist in two architectural paradigms: dual-phase detectors exemplified by Faster R-CNN [10] and its subsequent variants [11,12], and unified detection systems including YOLO [13] and SSD [14].”
Dang, L., Zhang, G., Mu, H., & Xie, Y. (2025) · Journal of Real-Time Image Processing · doi:10.1007/s11554-025-01803-x · Cited by 6
“The YOLO (You Only Look Once) series of object detection algorithms [28–33] have attracted considerable interest due to their high speed and accuracy.”
Explainable AI for Diabetic Retinopathy: Utilizing YOLO Model on a Novel Dataset
Mutawa, A. M., Sabti, K. A., Raizada, S., & Sruthi, S. (2025) · AI · doi:10.3390/ai6120301 · Cited by 9
“Joseph Redmon et al. released YOLOv1, the initial version of the YOLO object identification algorithm, in 2015 [16].”
Xie, H., Wang, M., Cao, R., Wang, J., Jiang, Y., Qiang, H., & Jiang, L. (2025) · Remote Sensing · doi:10.3390/rs17233823 · Cited by 13
Woźniak, Z. Z., Trybuszewski, K., Nowobilski, T., Stolarz, M., & Šmalec, F. (2025) · Sustainability · doi:10.3390/su172310584 · Cited by 6
Research on eggplant pest and disease detection in complex environments based on improved RT-DETR
Sun, H. Z., Fu, R., Zhang, Z., Sun, H., Jeong, Y.-K., & Lyu, J. (2025) · BMC Plant Biology · doi:10.1186/s12870-025-07518-2 · Cited by 8
Environmental acoustic intelligence through sound event localization and detection: a review
Yeow, J.-W., Tan, E.-L., Peksi, S., & Gan, W. (2025) · npj Acoustics · doi:10.1038/s44384-025-00036-3 · Cited by 14
“For instance, Kim et al. 117 proposed AD-YOLO,inspiredbythe “ YouOnlyLookOnce ” objectdetectionalgorithm 118 .”
IFD-YOLO: A Lightweight Infrared Sensor-Based Detector for Small UAV Targets
Li, F., Lv, X., Zhao, M., & Wu, W. (2025) · Sensors · doi:10.3390/s25247449 · Cited by 11
“In contrast, one-stage methods, represented by YOLO (You Only Look Once) [24] series, perform dense predictions directly over the entire image.”
Liu, Q., Yu, H., Zhang, P., Geng, T., Yuan, X., Ji, B., Zhu, S., & Ma, R. (2025) · Remote Sensing · doi:10.3390/rs17243996 · Cited by 9
Xu, Z., & Wang, N. (2025) · Electronics · doi:10.3390/electronics14244968 · Cited by 6
“Single-stage algorithms, such as the YOLO (You Only Look Once) [5] series and SSD (Single Shot MultiBox Detector) [6], generally offer better efficiency.”
RT-DETRv4: Painlessly Furthering Real-Time Object Detection with Vision Foundation Models
Liao, Z., Zhao, Y., Shan, X., Yan, Y., Liu, C., Lu, L., Ji, X., & Chen, J. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37029-7_7 · Cited by 73
Traffic Monitoring Using Optical Fiber Distributed Acoustic Sensing for Metropolitan Environments
Li, Y., Zhang, J., Yan, Y., & Lau, A. P. T. (2025) · Journal of Lightwave Technology · doi:10.1109/jlt.2025.3642924 · Cited by 9
Multispecies weed mapping using deep learning on UAV imagery for SSWM in maize and tomato
Mesías-Ruiz, G. A., Borra‐Serrano, I., Dorado, J., de Castro, A. I., & Peña, J. M. (2025) · Precision Agriculture · doi:10.1007/s11119-025-10309-2 · Cited by 7
“…the field area into three categories, according to a customized grid size (e.g. 1 × 1 m 2 ) and adaptive economic weed thresholds (EWTs), as follows: (1) weed-free, so no treatment is needed (zone 1), (2) infested with weed density (#weeds/m 2 ) below EWT, so no treatment is economically…”
CCAI-YOLO: A High-Precision Synthetic Aperture Radar Ship Detection Model Based on YOLOv8n Algorithm
Liu, H., Dong, H., Shi, H., & Li, F. (2026) · Remote Sensing · doi:10.3390/rs18010145 · Cited by 7
SOO-YOLO: an efficient small object detection model for UAV images
Chen, R., Sun, H., Fan, H., Wu, P., Zhang, Z., & Yang, C. (2026) · Cluster Computing · doi:10.1007/s10586-025-05821-z · Cited by 7
“Single-stage algorithms like SSD [9] and the YOLO series [10] produce prediction frames straight from the input image, eliminating the need for candidate region formation, hence considerably decreasing computing time and enhancing practical applicability.”
SARLANG-1M: A Benchmark for Vision–Language Modeling in SAR Image Understanding
Wei, Y., Xiao, A., Ren, Y., Zhu, Y., Chen, H., Xia, J., & Yokoya, N. (2026) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2026.3652099 · Cited by 35
YOLO11-WLBS: an efficient model for pavement defect detection
Lin, J., Wang, P., Ruan, Y., & Sun, Y. (2026) · Scientific Reports · doi:10.1038/s41598-026-35743-8 · Cited by 11
“As a general-purpose object detection model, YOLO11 is designed to balance high-and low-frequency information, which is effective for typical object detections 17 .”
Huang, D., Chen, Z., Zhuang, J., Song, G., Huang, H., Li, F., Huang, G., & Liu, C. (2026) · Agriculture · doi:10.3390/agriculture16020234 · Cited by 10
Review of space robotics technology for on-orbit construction of ultra-large optical systems
Wei, Y., Liu, X., Zhan, B., Wen, H., & Chen, T. (2026) · Acta Astronautica · doi:10.1016/j.actaastro.2026.01.048 · Cited by 6
Bai, Y., Song, C., Wang, Y., & Li, P. (2026) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2026.3660762 · Cited by 7
Adaptive image zoom-in with bounding box transformation for UAV object detection
Wang, T., Lin, C.-Y., Tang, C., Zhou, J., Xiong, D., Li, J., Zhao, J., & Lv, J. (2026) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2026.01.036 · Cited by 14
“The representative one-stage models are mainly the YOLO series [25, 26, 27, 28, 29, 30, 19, 31, 32] models and SSD series [33, 34, 35, 36] models.”
Towards Secure Low-Altitude Airspace: MLLM-Enabled UAV Intent Recognition
Lei, G., Liang, T., Ping, Y., et al. (2026) · IEEE Internet of Things Magazine · doi:10.1109/miot.2025.3646875 · Cited by 6
“The YOLO series [6] is a classic algorithm capable of regressing target positions and classes at hundreds of frames per second, while emerging methods can further improve detection accuracy.”
Med-VLM: Enhancing Medical Image Segmentation Accuracy Through Vision-Language Model
Zhao, Y., Zhong, E., Yuan, C., Li, Y., Zhao, M., Li, C., Hu, J., Liu, W., & Liu, C. (2025) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw69036.2025.00756 · Cited by 13
Drone Detection with Event Cameras
Magrini, G., Berlincioni, L., Becattini, F., Cultrera, L., & Pala, P. (2025) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw69036.2025.00494 · Cited by 21
“In Zundel et al. [78], event frames are fed into a YOLO-based detector [50], and DBSCAN [18] is used for post-processing to identify and track drone clusters.”
Integrated Radio Sensing Capabilities for 6G Networks: AI/ML Perspective
Shatov, V., Schieler, S., Muth, C., Mateos-Ramos, J. M., de Almeida, I. B. F., Euchner, F., Semper, S., ten Brink, S., Fettweis, G. P., Häger, C., et al. (2026) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2026.3668458 · Cited by 15
“With CFAR the noise power for the decision threshold is estimated using training cells patterned around the cell under test, often accompanied by guard cells.”
Video-based cattle behaviour detection for digital twin development in precision dairy systems
Rao, S., Garcia, E. R. M., & Neethirajan, S. R. (2026) · npj Veterinary Sciences · doi:10.1038/s44433-026-00004-x · Cited by 10
“Cows were localized in each frame using a YOLOv11 based object detection model 16 ,whichwastrainedonacustomdatasetof2308images,eachlabeled with bounding boxes around individual Holstein cows.”
Adapting Vision–Language Models for Few-Shot Industrial Defect Detection
Sub-r-pa, C., & Chen, R.-C. (2026) · Algorithms · doi:10.3390/a19040259 · Cited by 9
LWU-YOLO: A lightweight algorithm for small object detection in UAV applications
Li, Y., Wang, T., Li, T., & Yang, X. (2026) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2026.104791 · Cited by 6
CFPR-YOLO: chili flower pose estimation for robotic pollination in unstructured environments
Kuang, M., Wang, Y., Li, X., et al. (2026) · Frontiers in Plant Science · doi:10.3389/fpls.2026.1861155 · Cited by 6
The Use of Vision Foundation Models Combined with Temporal Context for Vehicle Detection
Gorskiy, M., & Moseva, M. (2026) · 2026 Wave Electronics and its Application in Information and Telecommunication Systems (WECONF) · doi:10.1109/weconf69969.2026.11553770 · Cited by 6
“Convolutional neural networks remain relevant, including two-stage detectors such as RCNN [3], Faster-RCNN [4], and one-stage detectors like YOLO [5].”
A Comparative Analysis of Shape Descriptors in Deep Learning-Based Real-Time Object Detection
Gupta, S., Kaur, M., & Singh, T. (2026) · International Conference on Connected Intelligence for Industrial Applications (CI2A) · doi:10.1109/ci2a69097.2026.11576872 · Cited by 6
BAOD: Budget-Aware Object Detection
Pardo, A., Xu, M., Thabet, A., Arbeláez, P., & Ghanem, B. (2021) · LatinX in AI at Computer Vision and Pattern Recognition Conference (LXAI) · doi:10.1109/cvprw53098.2021.00137 · Cited by 19
A review of the prevalent ICT techniques used for COVID-19 SOP violation detection
Ikram, T., Saeed, A., Ayn, N., Tahir, M. A., & Mumtaz, R. (2020) · IEEE International Conference on Smart Communities: Improving Quality of Life using AI, Robotics and IoT (HONET) · doi:10.1109/honet50430.2020.9322821 · Cited by 7
Automatically Generating Websites from Hand-drawn Mockups
Ferreira, J., Restivo, A., & Ferreira, H. S. (2021) · International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP) · doi:10.5220/0010193600480058 · Cited by 8
Englund, C., Aksoy, E. E., Alonso‐Fernandez, F., Cooney, M. D., Pashami, S., & Åstrand, B. (2021) · Smart Cities · doi:10.3390/smartcities4020040 · Cited by 91
YOLO as a Region Proposal Network for Diagnosing Breast Cancer
Bal, A., Das, M., & Satapathy, S. M. (2021) · Grace Hopper Celebration India (GHCI) · doi:10.1109/ghci50508.2021.9513988 · Cited by 9
Logic Rules Meet Deep Learning: A Novel Approach for Ship Type Classification
Pitsikalis, M., Do, T.-T., Lisitsa, A., & Luo, S. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-91167-6_14 · Cited by 9
3D Vehicle Trajectory Extraction Using DCNN in an Overlapping Multi-Camera Crossroad Scene
Heo, J., & Kwon, Y. J. (2021) · Sensors · doi:10.3390/s21237879 · Cited by 6
Sailboat Detection Based on Automated Search Attention Mechanism and Deep Learning Models
Luo, Z., Nguyen, M., & Yan, W. Q. (2021) · International Conference on Image and Vision Computing New Zealand (IVCNZ) · doi:10.1109/ivcnz54163.2021.9653237 · Cited by 14
Hybrid FPGA–CPU-Based Architecture for Object Recognition in Visual Servoing of Arm Prosthesis
Fejér, A., Nagy, Z., Benois‐Pineau, J., Szolgay, P., de Rugy, A., & Domenger, J. (2022) · Journal of Imaging · doi:10.3390/jimaging8020044 · Cited by 10
Cooperative Forward Collision Avoidance System Based on Deep Learning
Farhat, W., Rhaiem, O. B., Faiedh, H., & Souani, C. (2021) · International Conference on Developments in eSystems Engineering (DeSE) · doi:10.1109/dese54285.2021.9719448 · Cited by 8
An Implementation of Face Mask Detection System Based on YOLOv4 Architecture
Qin, Z., Guo, Z., & Lin, Y. (2022) · International Conference on Computer Research and Development · doi:10.1109/iccrd54409.2022.9730470 · Cited by 6
Object detectors involving a NAS-gate convolutional module and capsule attention module
Viriyasaranon, T., & Choi, J. (2022) · Scientific Reports · doi:10.1038/s41598-022-07898-7 · Cited by 8
A Framework for Pothole Detection via the AI-Blockchain Integration
Mubarak, A. S., Ameen, Z. S., Tonga, P., Altrjman, C., & Al-Turjman, F. M. (2022) · Lecture notes on data engineering and communications technologies · doi:10.1007/978-3-030-99616-1_53 · Cited by 7
Shruti, S., Shravya, M., Mohan, S., et al. (2022) · International Conference on Intelligent Computing and Control Systems (ICICCS) · doi:10.1109/iciccs53718.2022.9788361 · Cited by 6
Santos, L. G. R. O., Marcato, J., Zamboni, P., et al. (2022) · Sensors · doi:10.3390/s22114116 · Cited by 6
Resource- and Power-Efficient High-Performance Object Detection Inference Acceleration Using FPGA
Tesema, S. N., & Bourennane, E. (2022) · Electronics · doi:10.3390/electronics11121827 · Cited by 7
DY-RetinaNet Based Identification of Common Species at Beehive Nest Gates
Hu, X., Liu, C., & Lin, S. (2022) · Symmetry · doi:10.3390/sym14061157 · Cited by 7
FGSR: A Fine‐Grained Ship Retrieval Dataset and Method in Smart Cities
Xian, Y., Jin, X., Lu, L., & Tang, J. (2022) · Wireless Communications and Mobile Computing · doi:10.1155/2022/2807139 · Cited by 8
Patibandla, S., Archana, M., & Tanguturi, R. C. (2022) · Indian Journal of Computer Science and Engineering · doi:10.21817/indjcse/2022/v13i3/221303049 · Cited by 6
Multiple structural defect detection for reinforced concrete buildings using YOLOv5s
Li, C., Pan, W., Yuen, P. C., & Su, R. K. L. (2022) · HKIE Transactions · doi:10.33430/v29n2thie-2021-0033 · Cited by 6
HRM: An Intelligent Helmet Recognition Model in Complex Scenes
He, P., Wu, C., Yared, R., et al. (2022) · Advances in Mathematical Physics · doi:10.1155/2022/1352775 · Cited by 6
MemFRCN: Few Shot Object Detection with Memorable Faster-RCNN
Lu, T., Jia, S., & Zhang, H. (2022) · IEICE Transactions on Fundamentals of Electronics Communications and Computer Sciences · doi:10.1587/transfun.2022eal2010 · Cited by 7
ScriptPainter: Vision-based, On-device Test Script Generation for Mobile Systems
Choi, Y., Seo, A., & Kim, H. (2022) · ACM/IEEE International Conference on Information Processing in Sensor Networks (IPSN) · doi:10.1109/ipsn54338.2022.00045 · Cited by 10
Zhao, L., Sun, X., Liu, F., Wang, P., & Chang, L. (2022) · Energies · doi:10.3390/en15155367 · Cited by 7
Research on Urban Traffic Incident Detection Based on Vehicle Cameras
Xia, Z., Gong, J., Yu, H., et al. (2022) · Future Internet · doi:10.3390/fi14080227 · Cited by 6
Lee, S., & Yeh, C.-H. (2022) · Journal of Ambient Intelligence and Smart Environments · doi:10.3233/ais-210129 · Cited by 6
Mao, J., Cheng, L., Ji, C., Jing, M., Duan, Z., Li, N., Gesang, Z., & Li, M. (2022) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2022.3199249 · Cited by 8
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.