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 34,701–34,800 of 51,399
AI-Driven Robotics in Agriculture: A Review
Singh, S. C. E., Flower, T. M. L., Benny, R., et al. (2026) · Premier journal of science. · doi:10.70389/pjs.100236 · Cited by 1
Monocular RGB 6D object pose estimation for augmented reality: a survey
Aguirrezabal, P., Aguinaga, I., & Álvarez-Gila, A. (2026) · Virtual Reality · doi:10.1007/s10055-026-01315-4 · Cited by 4
Real-Time Anomaly and Incident Detection Based on YOLO and Lucas–Kanade Optical Flow Tracking
Nitilappool, O., Singsom, J., Pongkao, N., Ketcham, M., & Ganokratanaa, T. (2026) · IEEE Access · doi:10.1109/access.2026.3662798 · Cited by 2
Noise-Robust Object Detection for Forward-Looking Sonar Imagery
Wang, Z., Guo, Q., & Luo, J. (2026) · IEEE Sensors Journal · doi:10.1109/jsen.2026.3661175 · Cited by 2
“CNN-based one-stage detectors, exemplified by YOLO [30] and SSD [31], eliminate the need for region proposal mechanisms by directly predicting both class probabilities and bounding box coordinates in a single inference step.”
Measuring Contextual Reliance of Object Detection Models: A Black Box Explainability Method
Vonderhaar, L., Elvira, T., & Ochoa, O. (2026) · International Journal of Artificial Intelligence Tools · doi:10.1142/s0218213026400051 · Cited by 1
A framework for evaluating predicted sperm trajectories in crowded microscopy videos
Hart, D., Cashwell, K. D., Bhandari, A., Premasinghe, J., & Schmidt, C. A. (2026) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1013955 · Cited by 2
Zong, L., Nan, S. J., Die, Z. F., & Peng, H. J. (2026) · Scientific Reports · doi:10.1038/s41598-026-37546-3 · Cited by 4
Expert-level probabilistic breathing event detector informs phenotyping of sleep apnea
Kjær, M. R., Hanif, U., Brink-Kjær, A., Olsen, M., Sum‐Ping, O., Carrillo, O., Sands, S. A., Redline, S. S., Stone, K. L., Jennum, P., et al. (2026) · Nature Communications · doi:10.1038/s41467-026-69163-z · Cited by 6
TASONet: A Spatial Enhancement and Temporal Modeling Framework for UAV Small Object Tracking
Ma, R., Lai, C., Sheng, Q., Tao, Z., & Li, X. (2026) · Remote Sensing · doi:10.3390/rs18040561 · Cited by 2
Zhang, Z., Feng, Z., Long, A., Wang, Z., Tian, X., Xiang, W., & Tu, Z. (2026) · IEEE Access · doi:10.1109/access.2026.3663875 · Cited by 1
Large language vision models for zero-shot handwriting recognition of historical herbarium labels
Körschens, M., Bucher, S. F., Ritz, C. M., Gebauer, S., Wesenberg, J., & Römermann, C. (2026) · Ecological Informatics · doi:10.1016/j.ecoinf.2026.103656 · Cited by 1
Optimized Hybrid Model Integrating CNN and Image Processing for Lung Cancer
Chintalapati, P. V., & Prasanth, A. (2025) · International Conference on Emerging Research in Electronics, Computer Science and Technology (ICERECT) · doi:10.1109/icerect65215.2025.11376159 · Cited by 1
Enhanced Underwater Object Detection Using Real-ESRGAN and YOLOv11
Rathi, M., Zuha, M., K.Sravankumar, et al. (2025) · International Conference on Emerging Research in Electronics, Computer Science and Technology (ICERECT) · doi:10.1109/icerect65215.2025.11377792 · Cited by 1
“YOLO-based architectures have evolved signifi-cantly since their inception [5], [6], with YOLOv11 offering improved performance in detecting small and occluded objects in real-time [7], [8].”
An Artificial Intelligence Framework for Crowd Surveillance and Risk Mitigation
Tomar, A., Kumar, P., Rishiwal, V., et al. (2026) · Transactions on Emerging Telecommunications Technologies · doi:10.1002/ett.70376 · Cited by 1
“…box region of interest, whereas the employment of a stage detector Efficient-Det [23], Retina Net [24], SSD [25], Yolo-V3 [26], and YOLOv1-v4 [27] is the second category, but their real-time accuracy is not on par for distance estimation [28] integrated the YOLOv3 and SWIN transformer models…”
Tao, J., Wang, P., Jiang, H., & Han, Y. (2026) · Process Safety and Environmental Protection · doi:10.1016/j.psep.2026.108597 · Cited by 2
Lei, 陆. L., Qian, 于. Y., & Hong, 张. Z. (2026) · Laser & Optoelectronics Progress · doi:10.3788/lop251216 · Cited by 1
Robust road damage detection via multi-expert collaboration and cross-scale attention
Zhao, J., Jia, M., Wang, S., Jiang, C., Niu, D., & Fang, X. (2026) · Advanced Engineering Informatics · doi:10.1016/j.aei.2026.104452 · Cited by 2
Intelligent Detection of Student Classroom Behavior Based on an Improved YOLOv8 Model
Zhou, M., Zhang, H., Peng, Y., et al. (2026) · Communications in computer and information science · doi:10.1007/978-981-95-6730-0_7 · Cited by 1
A YOLOv8-Based Network for Surface Defect Detection in Strip Steel
Jiang, J., Su, Y., & Song, J. (2026) · Journal of Computer and Communications · doi:10.4236/jcc.2026.142006 · Cited by 1
Stream-DINO: exploring DETR-based online object detection with streaming perception
Zhang, M., Zhang, Y., Tian, R., Zhang, Y., Zhang, Z., & Sun, J. (2026) · Applied Intelligence · doi:10.1007/s10489-026-07139-8 · Cited by 1
“To evaluate the performance of object detection models, both R-CNN [7], YOLO [14] and DETR [25] utilize mean average precision (mAP).”
Chan, S., Zheng, J., Li, S., Mu, P., & Bai, C. (2026) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2026.3664780 · Cited by 2
“Among them, YOLO [10], as an early one-stage detector, discards the region proposal network.”
Huang, S., Lin, C., Peng, J., & Pan, Y. (2026) · Advanced Engineering Informatics · doi:10.1016/j.aei.2026.104463 · Cited by 1
A Lightweight Adaptive Camera-Radar Fusion for Object Detection Under Fog–Haze Environment
Li, J., Xu, T., Wang, G. L., et al. (2026) · IEEE Sensors Journal · doi:10.1109/jsen.2026.3662443 · Cited by 1
“The YOLO series [3], [4] addresses speed and accuracy limitations through multiscale feature prediction, while DETR [5] introduces transformer-based detection at the cost of increased data and batch-size demands.”
Kovbasiuk, S., Romanchuk, M. P., Naumchak, O. M., & Naumchak, L. M. (2026) · Journal of Edge Computing · doi:10.55056/jec.749 · Cited by 1
“Compared to single-stage detectors [21, 27], they provide better optimisation and generate a larger number of high-level features.”
A Natural Language Guided Approach for Blind Face Restoration: Methodology and Dataset
An, W., Wang, C., Jiang, J., Jiang, K., Liu, X., & Nie, L. (2026) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2026.3665736 · Cited by 1
M., S. S., Archana, N., & Rishi Koushik, G. (2026) · IET Intelligent Transport Systems · doi:10.1049/itr2.70135 · Cited by 3
Distinguish Traffic Condition Based on YOLOv10 Model and Region of Interest (ROI)
Huu, P. N., Trung, K. H., & Minh, Q. T. (2026) · International Journal of Intelligent Systems · doi:10.1155/int/4252938 · Cited by 1
Diffusion Based Scalable Semantic Communication Framework For Image Compression And Transmission
Gamage, N. P., Fernando, T., & Fernando, A. (2025) · doi:10.1109/icipw68931.2025.11385841 · Cited by 1
“Object Recognition: The study utilizes the YOLO8X-SEG model [20] with default configuration to identify and where N is the total number of objects.”
A Robotic Grasping Framework for Railway Cargo Based on an Improved YOLOv8 Model
Xiong, S., Wu, H., & Lin, Y. (2025) · doi:10.1109/icrsa66467.2025.11383796 · Cited by 1
“In practical applications, after the robot captures an RGB image, object detection algorithms (e.g., Faster R-CNN [6], YOLO series [7]–[12]) are used to locate the object in the image.”
Sureban, N. B., Ajish, A. C., Abhinav, Y., Prusty, M. R., & Patra, S. R. (2026) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2026.109909 · Cited by 2
Carvalho, A., Miguéis, V., & Sá, M. M. E. (2026) · International Journal of Production Research · doi:10.1080/00207543.2026.2632695 · Cited by 4
“Conversely, YOLO networks (Redmon et al. 2016) enable the localisation of defects in a single-stage task.”
A Single-Shot Multi-Box Detector with MobileViT Backbone for Metallic Surface Defect Detection
Chee, A. L. T., Sivakumar, S., Lim, K. H., Chew, I. M., Lim, C. I., & Fui, S. E. (2025) · IEEE Region 10 Conference (TENCON) · doi:10.1109/tencon66050.2025.11375235 · Cited by 1
“Examples of single-stage detectors include You Only Look Once (YOLO) [9]–[12], Single-Shot Detector (SSD) [13], RetinaNet [14], EfficientDet [15], Center-Net [16], and etc. Single-stage detection models are regarded as a multi-task learning problem that generally have fast inference speed, thereby…”
Deep Learning-Based Phase Recovery and Image Analysis for Laser Interferometric Measurements
Song, Y., Wang, J., Fang, F., et al. (2026) · Procedia CIRP · doi:10.1016/j.procir.2025.09.013 · Cited by 1
Detection of Shielded Nuclear Materials Using Superheated Liquid Detectors
Rodrigues, L., & Felizardo, M. (2026) · Particles · doi:10.3390/particles9010020 · Cited by 1
“YOLO (You Only Look Once) reframes object detection as a regression task, allowing for high-speed, real-time detection critical for deployment in scenarios like border security and maritime inspections [25,26].”
Computer vision applications in vascular surgery: a systematic review and critical appraisal
Liyanage, A., Li, B., Yi, J., Mamdani, M. M., & Salata, K. (2026) · npj Digital Medicine · doi:10.1038/s41746-026-02427-6 · Cited by 2
“For this CNN category, some studies used common architectures, such as YOLO 29 , recurrent-CNNs 30 , ResNet 31 , Xception 32 and VGG 33 , while others createdtheirowncustommodels.”
Donnelly, S., Anderson, R., Economides, G., Broughton, J., Ball, P. R., Rast, A. D., & Bradley, A. (2026) · International Symposium on Communication Systems, Networks and Digital Signal Processing (CSNDSP) · doi:10.1109/csndsp68462.2026.11654478 · Cited by 1
“To detect and highlight road users in the imagery, the system utilises the YOLO computer vision model [22].”
Tizno, A., Abdar, A. K., Alimardani, A., et al. (2026) · Journal of Imaging Informatics in Medicine · doi:10.1007/s10278-026-01873-8 · Cited by 1
FPA: Football Performance Analysis Using YOLO-Based Object Detection System
Navaneetha, M., Jadhav, S. P., Jiddibgail, S., et al. (2025) · doi:10.1109/icancs65819.2025.11377386 · Cited by 1
“This research helps in exploring the application of You Only Look Once (YOLO)[4] object detection framework to address some of the key challenges in football performance analysis system.”
Traffic flow information detection under resource limitations based on framework optimization
Tian, Z., Wahab, M. N. A., Akbar, M. F., Misro, M. Y., & Ishak, M. K. (2026) · PeerJ Computer Science · doi:10.7717/peerj-cs.3522 · Cited by 1
Hong, S., Park, G., & Kim, J.-S. (2025) · International Conference on Information and Communication Technology Convergence (ICTC) · doi:10.1109/ictc66702.2025.11387904 · Cited by 1
Optimizing Object Detection with Multispectral RGB/IR Fusion
Chamizo, S. M. P., & Kim, D. (2025) · International Conference on Information and Communication Technology Convergence (ICTC) · doi:10.1109/ictc66702.2025.11388240 · Cited by 1
YOLO-RECAP: reassembly with channel attention for perception
Kim, H.-J., Park, S.-W., Sim, C.-B., et al. (2026) · Journal of King Saud University - Computer and Information Sciences · doi:10.1007/s44443-026-00525-9 · Cited by 1
“In contrast, a Two-Stage Detector first generates region proposals and then performs precise classification for each region, resulting in higher accuracy but difficulty in real-time processing (Redmon et al. 2016; Girshick et al. 2016).”
TOBITA, K., & Editorial Office (2026) · Journal of Robotics and Mechatronics · doi:10.20965/jrm.2026.p0035 · Cited by 1
A Multi-Sensor Fusion and Deep Learning Framework for Autonomous Underwater Mine Detection
Tiwari, B. K., Arul Elango., G., & Ahuja, N. (2025) · doi:10.1109/icec2nt65402.2025.11380080 · Cited by 1
“Redmon et al. [14] pioneered the YOLO (You Only Look Once) framework, offering real-time object detection with high accuracy across multiple domains.”
Unsupervised Domain Adaptive Object Detection via Semantic Consistency and Compactness Learning
Liu, Y., Zhang, Z., Su, Y., Hao, C., Liu, X., & Tian, J. (2026) · IEEE Transactions on Image Processing · doi:10.1109/tip.2026.3663935 · Cited by 1
Lml-yolo: Composite enhanced YOLO object detection model for underwater complex environments
Yang, D., Shen, C., Song, T., et al. (2026) · Journal of King Saud University - Computer and Information Sciences · doi:10.1007/s44443-026-00501-3 · Cited by 1
Design and Implementation of an AI-Based Automatic Plastic Waste Sorting System
Aissa, M. A. B., Kharroubi, H., Boukara, S., Aitigrine, I., & Moulai, H. (2025) · International Conference on Advances in Electronics, Control and Communication Systems (ICAECCS) · doi:10.1109/icaeccs68240.2025.11384741 · Cited by 2
“This end-to-end design reduces processing time and ensures robust performance under varying conditions [4].”
ESI-YOLOv11n: Efficient Multi-Scale Fusion Method for PCB Defect Detection
Liu, C., Liu, W., & Lian, L. (2026) · Machines · doi:10.3390/machines14020240 · Cited by 3
“In the current deep learning object detection algorithm system, two-stage algorithms are represented by Mask R-CNN [5] and Faster-RCNN [6], while one-stage algorithms are represented by SSD [7] (Single Shot MultiBox Detector) and YOLO [8–10] (You Only Look Once) series as typical examples.”
YoViNet: Remote Sensing Object Detection with Multi-Scale Attention and Vision Transformer
Yeqing, S. (2025) · IEEE Smart World Congress (SWC) · doi:10.1109/swc65939.2025.00163 · Cited by 1
“YOLOv1 [15] contrived the first single-stage object detection method, dividing images into grids and predicting object categories and bounding boxes in an end-to-end manner.”
Leiva, F., Rebeaud, S. G., & Christen, D. (2026) · Plant Methods · doi:10.1186/s13007-026-01508-7 · Cited by 8
“The most well-known example of qualitative resistance is Rvi6 (formerly Vf), widely used in apple breeding but increasingly overcome by virulent V. inaequalis races [21, 22].”
ECGyolo: An end-to-end model combining transformer and 1D YOLO for arrhythmia detection
Yan, C., Feng, G., Ma, M., Pan, J., Meng, Z., & Zhen, D. (2026) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2026.109943 · Cited by 1
Watchanupaporn, O., Jadejaroen, J., & Homsapaya, K. (2026) · Journal of Medical Primatology · doi:10.1111/jmp.70067 · Cited by 1
“When applying object detection techniques such as YOLO, this process typically includes resizing images to a consistent size (commonly 416 × 416 pixels) to meet the model's architectural requirements [30].”
CrossCompanion: An Empathetic Real-Time Assistant Supporting Street Crossing for Low-Vision Users
Liang, J., & Fang, Y. (2025) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw69036.2025.00259 · Cited by 2
“YOLO-v11 [23] was used to extract frames containing traffic lights as key indicators of crosswalk contexts.”
Enhancing object detection in complex lighting conditions via illumination-guided feature fusion
Xu, L., Zhu, L., Hu, J., & Guo, B. (2026) · Cluster Computing · doi:10.1007/s10586-026-05976-3 · Cited by 1
“Traditional models such as R-CNN [27], the YOLO series [6, 28], and others have demonstrated exceptional accuracy in identifying and localizing objects in images, leveraging innovative network architectures and large-scale training datasets.”
Explaining Object Detection Through Difference Map
Xia, S., Zhao, C., & Chan, A. (2025) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw69036.2025.00080 · Cited by 1
“Representative approaches include YOLO [24], RetinaNet [18], and FCOS [29].”
Stranded Human Detection in Flooded Environments From UAV Imagery
Monpara, M. A., Rahman, M. M., Alam, T., et al. (2025) · doi:10.1109/roboticcc68732.2025.00029 · Cited by 1
“…: Classification loss is formulated as the binary cross-entropy (BCE) between the predicted probability of person class and the ground truth label [22]: where y ∈ { 0 , 1 } denotes the ground-truth label ( 1 if a person is present, 0 otherwise), and p person ∈ [0 , 1] represents the predicted…”
Decoupling Localization and Semantics for Open-Set Object Detection
Zhang, G., Yang, C., Xia, L., & Zheng, Y. (2026) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2026.3667350 · Cited by 2
“Most existing detectors focus on closed set, where the final detection results only include categories present in the training set [1], [2], [3].”
S, S. B. V., & Raman, R. (2026) · Image and Vision Computing · doi:10.1016/j.imavis.2026.105942 · Cited by 2
Fan, Z., Guo, L., & Fan, L. (2026) · IEEE Access · doi:10.1109/access.2026.3667402 · Cited by 1
Machine Learning and Machine Vision For Airborne Intelligence in Congested Environments
Holosha, A. O., Kovbasa, S., & Lyshevski, S. E. (2025) · IEEE International Conference on Methods and Systems of Navigation and Motion Control (MSNMC) · doi:10.1109/msnmc61130.2025.11399697 · Cited by 1
“Performance metrics and benchmarks were evaluated for available variants and versions of YOLO and Real-Time Detection Transformer (RT-DETR) architectures in the x/l/m/s/n configurations [2]- [5].”
Scale aware dense dynamic SLAM for monocular, stereo and RGBD cameras
Cen, N., Xu, Y., Wong, T.-W., & Zheng, Y. (2026) · Scientific Reports · doi:10.1038/s41598-026-41208-9 · Cited by 1
“For handling dynamic objects efficiently, YOLO11s-seg is introduced.”
InfluentialEarly Vehicle Collision Detection in Road Traffic Using Deep Learning and Explainable AI
Thangavel, S. K., Abhina, K., Karthik, E. A., et al. (2025) · doi:10.1109/icoiics67115.2025.11390525 · Cited by 1
“[12] • Object Classes Detected: The model accurately detected multiple instances of vehicles (cars/SUVs) in the scene, which is critical for collision avoidance and path planning.”
Remote Sensing Image Detection Based on Improved RT-DETR
Chen, W., & Wu, Y. (2026) · International Conference on Consumer Electronics and Computer Engineering (ICCECE) · doi:10.1109/iccece69169.2026.11399845 · Cited by 1
“Predominant CNN-based methods are generally divided into two-stage detectors, which rely on region proposals (e.g., RCNN [3] , Fast-RCNN [4] , Faster-RCNN [5] ), and one-stage detectors, which use regression for direct prediction (e.g., the YOLO series [6–8] ).”
MCD-YOLO: An improved method for detecting mixed-class defects on steel plate surfaces
Li, J., Chu, M., Zong, P., & Ma, S. (2026) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2026.114282 · Cited by 3
Chen, Y., Yao, J., Gao, C., et al. (2026) · Sensors · doi:10.3390/s26051405 · Cited by 1
LEM-YOLO: Locality-Enhanced Mamba-YOLO Algorithm for Ship Detection in Remote Sensing Imagery
Yao, F., Sun, Q., Ding, Y., et al. (2025) · doi:10.1109/iccvit67848.2025.11391455 · Cited by 1
Research on Automatic Navigational Buoy Recognition Based on YOLOv11
Wei, Y., Lu, W., Chu, C., et al. (2026) · International Journal of Transportation Engineering and Technology · doi:10.11648/j.ijtet.20261201.13 · Cited by 1
Theoretical Perspectives of Precision Chemistry
Ma, H., Liu, J., Li, Z., & Yang, J. (2026) · Precision Chemistry · doi:10.1021/prechem.5c00382 · Cited by 1
Elkhadrawi, M., Ng, C. A., Bain, D. J., Gray, K. A., & Akçakaya, M. (2026) · Neural Computing and Applications · doi:10.1007/s00521-025-11732-2 · Cited by 3
“In deep learning approaches, bottleneck layers are used to learn abstract feature representations and reduce computational complexity, such as in ResNet [36], and YOLO [40] computer vision models, and low rank adaptation (LoRa) [41] used in fine tuning of large language models.”
Munir, J., Liu, X., Wang, W., Leng, S., Cao, X., Wang, X., & Wang, J. (2026) · Engineering Research Express · doi:10.1088/2631-8695/ae4a88 · Cited by 1
Chu, Z., Liu, X., Que, X., et al. (2026) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2026.3661009 · Cited by 1
“2) Basic performance comparative experiments: The proposed model is compared with YOLOv8n-Pose [28], [29] and PoseAnything [30], as well as variants using different back-bones, including ResNet18, ResNet50 [31], full HRNet, sim-plified HRNet (HRNet2s), and HRNet2s enhanced with the WASPv2 module…”
Aishwarya, K. V., Asuntha, A., & Murugan, J. (2026) · Multimedia Tools and Applications · doi:10.1007/s11042-026-21334-2 · Cited by 2
“However, it faces difficulties with small objects, overlapping instances, and demonstrates lower localization accuracy relative to region-based methodologies [ 23 ].”
WL-YOLOv11: enhanced YOLOv11 for wildlife detection and counting in complex environments
Elkholy, A., Sarhan, A. M., & Hassanien, A. E. (2026) · Neural Computing and Applications · doi:10.1007/s00521-026-11843-4 · Cited by 2
“One of the most prevalent AI models in the object detection field is YOLO (You Only Look Once) [16], which is widely recognized for its speed and accuracy.”
Zuo, G., Hu, S., Li, Y., Zhou, K., & Wang, Q. (2026) · IEEE Transactions on Consumer Electronics · doi:10.1109/tce.2026.3668368 · Cited by 1
“Single-stage detectors, such as the You Only Look Once (YOLO) series [19], [20], [21], [22], [23] and Single Shot MultiBox Detector (SSD) [24], model the target detection task as a regression problem.”
A Small Object Detection Model for UAV Aerial Images Based on an Improved YOLOv11s Approach
李, 云. (2026) · Computer Science and Application · doi:10.12677/csa.2026.162081 · Cited by 1
Ngon, N. V., Nhan, D. T., Long, C. H., & Phạm, T. Đ. (2026) · Journal of Military Science and Technology · doi:10.54939/1859-1043.j.mst.109.2026.154-163 · Cited by 2
PAS-YOLO: A Small Target Detection Model for UAV Aerial Photography Based on Improved YOLOv8
Luo, L., Li, W., & Zhang, Z. (2025) · International Conference on Computer Science, Electronic Information Engineering and Intelligent Control Technology (CEI) · doi:10.1109/cei66465.2025.11398572 · Cited by 1
“Traditional detectors, including two-stage (e.g., R-CNN series [1]–[3]) and one-stage (e.g., YOLO [4]–[9] and SSD [10]) frameworks, have achieved remarkable progress, while recent Transformer-based models such as DETR offer new insights.”
EA-HWP: An Efficient CNN/SNN Accelerator With Hybrid Weight Precision
Wang, Z., Ou, Z., Zhong, Y., et al. (2026) · IEEE Transactions on Circuits & Systems II Express Briefs · doi:10.1109/tcsii.2026.3668087 · Cited by 1
“O VER the past decade, artificial neural networks (ANNs) have played an important role in image classification [1], object detection [2] and signal processing [3].”
MECSA: a multi-scale enhanced channel and spatial attention module for robust pedestrian detection
Babu, V. S. S., & Raman, R. (2026) · Pattern Analysis and Applications · doi:10.1007/s10044-026-01634-x · Cited by 1
“The YOLO [11] family of detectors has become a popular choice for real-time object detection due to its unified architecture and speed.”
TFDF-YOLO: A Position Detection Model for Underwater Wireless Power Transfer Docking
Yin, H., Cheng, Y., & Shi, W. (2026) · Journal of Marine Science and Engineering · doi:10.3390/jmse14050429 · Cited by 1
Tsolia, M., Zygouris, N. C., Kamnis, S., Styliaras, S. K., Beazidou, E., & Stamouli, V. (2026) · Digital · doi:10.3390/digital6010015 · Cited by 1
Osagie, E. R., & Jeyavadhanam, B. R. (2026) · Journal of Experimental and Theoretical Analyses · doi:10.3390/jeta4010011 · Cited by 1
“To further address these issues, the YOLO (You Only Look Once) family has become particularly popular for PCB detection due to its speed and real-time applicability [31].”
Improved YOLOv10 with ScConv and FLA for Real-Time Cast Pipe Character Detection
Lin, H., Wang, Y., & Jiang, Y. (2025) · International Symposium on Computer Engineering and Intelligent Communications (ISCEIC) · doi:10.1109/isceic67854.2025.11405461 · Cited by 1
“The YOLO[1] series of detectors are well-known real-time frameworks.”
Progressive Query Pruning for Object Detection
Qian, Z., Cheng, H., Mao, S., & Ding, Y. (2025) · International Symposium on Computer Engineering and Intelligent Communications (ISCEIC) · doi:10.1109/isceic67854.2025.11405729 · Cited by 1
Accurate segmentation of high-density dislocations in micrographs with DeepCrack model
Shen, R., Zhai, Y., Chen, H., et al. (2026) · Materials Characterization · doi:10.1016/j.matchar.2026.116206 · Cited by 1
Evaluation of YOLOv11 and CNN Approaches for Lung Cancer Detection in CT Scan Data
Sharma, D. K., Pal, M. K., Shukla, D. K., Srivastava, S., Singh, G. N., Goel, P., & Dwivedi, V. K. (2025) · International Conference on Intelligent Systems and Embedded Design (ISED) · doi:10.1109/ised67359.2025.11405228 · Cited by 1
Robotic Arm Control Using a Q-Learning Reinforcement Algorithm
Timóteo, A. M., Barbosa, R. S., & Jesus, I. S. (2026) · Robotics · doi:10.3390/robotics15030050 · Cited by 1
“Table 3 lists the network hyperparameters used in the training process, while Figure 13 shows the corresponding performance results [54–56].”
ESO-Det: An Efficient Small Object Detector for Real-Time UAV Perception
Deng, H., Zhou, S., & Yang, W. (2026) · Sensors · doi:10.3390/s26051512 · Cited by 2
Sadeghnejad, S., Hasanloo, A., Moslemipour, A., & Schäfer, T. (2026) · Applied Computing and Geosciences · doi:10.1016/j.acags.2026.100335 · Cited by 1
An efficient deep learning method for pedestrian detection in high-density public places
Cao, S., Conghui, L., Ren, X., Yang, X., Zeng, Y., & Wang, P. (2026) · Expert Systems with Applications · doi:10.1016/j.eswa.2026.131878 · Cited by 1
Yu, J., & Qin, X. (2026) · Neural Processing Letters · doi:10.1007/s11063-026-11840-7 · Cited by 1
Text-Pass Filter: An Efficient Scene Text Detector
Yang, C., Ma, H., Han, X., Yuan, Y., & Wang, Q. (2026) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2026.3668365 · Cited by 2
“Researchers detect whole text regions and achieve superior performance initially [27] based on the detection framework [28], [29], [30], [31].”
Chen, Z., & Lu, S. (2026) · Scientific Reports · doi:10.1038/s41598-026-42286-5 · Cited by 1
“Here, our approach achieves a 2.6% increase in AP, reaching a high of 95.7%, compared to both the second-best performing model YOLOv12 (AP: 93.1”
InfluentialResearch on Tibetan Medicinal Materials Detection Model Based on Improved YOLOv10n
Liu, Y., & Liu, X. (2025) · International Conference on Communication Technology and Information Technology (ICCTIT) · doi:10.1109/icctit68197.2025.11406362 · Cited by 1
“Currently, the main real-time object detectors are the YOLO series [3]–[10].”
Jiang, Z., Yang, Y., Hu, J., & Yuan, C. (2026) · Scientific Reports · doi:10.1038/s41598-026-41557-5 · Cited by 2
DAS-YOLOv13: Dual-Axis Attention and Feature Fusion Model for Wafer Surface Defect Detection
Zhang, J., Sun, R., Li, B., Kong, D., Zhao, D., & Zhang, J. (2026) · Sensors · doi:10.3390/s26051574 · Cited by 3
“One-stage models such as FCOS [11], CenterNet [12], and the YOLO series [13] directly perform classification and localization inference on features, effectively reducing detection latency.”
Enhanced YOLO with Radar Attention and Multi-Scale Fusion for Maritime Target Detection
Cen, Z., Chen, H., Huang, X., et al. (2025) · doi:10.1109/ipmml68499.2025.11406982 · Cited by 1
“While deep learning-based object detection has achieved remarkable success in optical imagery [4], [5], direct application of state-of-the-art detectors like YOLO to radar imagery yields suboptimal performance due to the fundamental differences in signal characteristics— radar images exhibit lower…”
Scale and Occlusion Aware Object Detection for Autonomous Driving
Packiaraj, J. S., Ponraj, A. S., & Jeevakala, S. (2026) · International Journal of Computational Intelligence Systems · doi:10.1007/s44196-026-01160-y · Cited by 3
“1, Fully Convolutional One-Stage (FCOS), and Single Shot Multi-Box Detector (SSD) incorporate regression analysis directly to find out the target category probability and future coordinates without going through the requirement of forming early boxes [11 – 13 ].”
Lightweight Distracted Driving Behavior Detection Algorithm Based On WTL-Yolov10n
Bao, C., & Lin, J. (2025) · International Conference on Intelligent Control, Measurement and Signal Processing (ICMSP) · doi:10.1109/icmsp68723.2025.11407782 · Cited by 1
“As one-stage object detection algorithms, You-Only-Look-Once [7] series algorithms are widely used in the field of computer vision.”
Algebraic adversarial attacks on explainability models
Simpson, L., Costanza, F., Millar, K., Cheng, A., Lim, C., & Chew, H. G. (2026) · Machine Learning Engineering · doi:10.1088/3049-4761/ae375c · Cited by 1
Metadata
- Authors
- Redmon, J., Divvala, S., Girshick, R., & Farhadi, A.
- Affiliations
- University of Washington (US)
- Meta (United States) (US)
- Venue
- 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2016-06
- Pages
- 779-788
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W1483870316
- Cited by
- 53,803
- References
- 42
- Citations by year
- 2026: 5347 · 2025: 8912 · 2024: 8953 · 2023: 8264 · 2022: 6785 · 2021: 5741 · 2020: 4223 · 2019: 3286 · 2018: 1560 · 2017: 635 · 2016: 90
- FWCI
- 644.23
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Zenodo (CERN European Organization for Nuclear Research) (cc-by)
- Funders
- National Science Foundation (1338054)
- Office of Naval Research (N00014-13-1-0720, N00014)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image and Video Retrieval Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Visual Attention and Saliency Detection
- Keywords
- object detection, YOLO, real-time detection, bounding box regression, end-to-end learning, false positive reduction, domain generalization
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol and qwen3.8-omni-flash).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.