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 45,701–45,800 of 51,399
Smart Data Annotation: Accelerating Data Labeling Processes through Deep Learning
Usta, Ş., Güneş, E., Deniz, Ü. İ., Yıldız, U., Küçük, K., & Akbulut, O. (2025) · International Conference on Computer Science and Engineering (UBMK) · doi:10.1109/ubmk67458.2025.11206861 · Cited by 1
Yasak, M. S., Keskin, G., & Gülem, E. Y. (2025) · doi:10.1109/ubmk67458.2025.11206948
“In this paper, that is proposed developed to detect fiducial marker points using the classification and detection model YOLOv11 [5] is one of the latest versions of the YOLO [6] model as a new approach.”
Kaya, U., Uluırmak, B. A., & Kurban, R. (2025) · International Conference on Computer Science and Engineering (UBMK) · doi:10.1109/ubmk67458.2025.11206954
“Initially proposed by Redmon et al. [1], YOLO introduced an end-to-end single-shot detection approach that significantly improved detection speeds.”
GenStream: Semantic Streaming Framework for Generative Reconstruction of Human-centric Media
Artioli, E., Lorenzi, D., Vats, S., Tashtarian, F., & Timmerer, C. (2025) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3746027.3758153 · Cited by 4
“Instance segmentation networks can further delineate objects from their surroundings, enabling region-specific treatment during encoding [39].”
DS-Det: Single-Query Paradigm and Attention Disentangled Learning for Flexible Object Detection
Cao, G., Lan, X., Huang, W., Zhang, J., Jiang, D., & Wang, Y. (2025) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3746027.3755045 · Cited by 5
“…transformer detectors like DETR [7] and DINO [51], have simplified the detection pipeline by providing end-to-end detection capabilities through query-based learning us-ing attention mechanisms, demonstrating promising performance compared to classical CNN-based detectors [13, 16, 29, 37, 38].”
Gao, N., Zhu, J., Zhang, Y., Liang, R., Sun, G., & Chen, P. (2025) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3746027.3755530 · Cited by 1
“Object detection[12, 28, 29, 35] in medical image analysis has made significantprogressindiseasediagnosisandtreatmentplanning[14].”
An Event-tailored State-Space Based Model for Pedestrian Detection
Liuyi, L., Shi, F., Wang, J., Zhu, J., & Shao, W. (2025) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3746027.3755380 · Cited by 1
Can I Trust You? Advancing GUI Task Automation with Action Trust Score
Mei, H., Gao, D., Wei, X., Yang, X., & Shou, M. Z. (2025) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3746027.3755618 · Cited by 1
“For the GUI Parser, we follow [5] to use Google OCR for extracting text, Yolo-v8 [19] to coarsely localize objects, and LangSAM [7, 11] to obtain the precise object contours; For the TrustModel’s training, parameters are initialized with the pre-trained DeBertv3 [6].”
Torrens, P. M. (2025) · Information Geography · doi:10.1016/j.infgeo.2025.100034 · Cited by 1
Uncertainty in AI Based Reservoir Modelling Workflows
Demyanov, V., Corlay, Q., Nathanail, A., et al. (2025) · Quantitative geology and geostatistics · doi:10.1007/978-3-031-92870-3_28
Integrating Local Learning Algorithms and Vision Transformers for Accurate Rice Yield Prediction
Ha, T.-V. T., & Do, T. (2025) · Lecture notes in networks and systems · doi:10.1007/978-3-032-08384-5_8
Real-Time Student Behavior Detection in Classroom Using YOLOv8 Model
Quang, T. N., Kim, T. D., Le, H. X., & Pham, A.-P. (2025) · Lecture notes in networks and systems · doi:10.1007/978-3-032-08384-5_20
PAMA-DETR: a lightweight attention and multi-kernel feature fusion detection model for UAV images
Wei, S., Li, W., Wei, F., & Wang, C. (2025) · The Journal of Supercomputing · doi:10.1007/s11227-025-07985-2 · Cited by 1
“Previous object detection methods predominantly employ CNN-based architectures, particularly the R-CNN [9–11] and YOLO series [12–14].”
Applications in Artificial Intelligence and Robotics
Sucar, L. E. (2025) · Computer science foundations and applied logic · doi:10.1007/978-3-031-98345-0_10
Tetris Image Detection: A Study on Convolutional Neural Networks for Game Piece Recognition
Vito, E., Narwandaru, N., & Suparwito, H. (2025) · Studies in computational intelligence · doi:10.1007/978-3-032-01133-6_21
Mobile crowd sensing for road anomaly detection using deep learning
Jana, S., Middya, A. I., & Roy, S. (2025) · Spatial Information Research · doi:10.1007/s41324-025-00651-y · Cited by 3
A Study of Why Weave Filters in CAPTCHA Prevent AI’s Object Detection
Hayashi, N., Miyazaki, T., Araki, S., et al. (2025) · IEEE International Conference on Consumer Electronics - Taiwan (ICCE-Taiwan) · doi:10.1109/icce-taiwan66881.2025.11208106
Automated Method for Alpha Track Recognition and Counting on CR-39 Detector by YOLO
Xu, H., Xie, Y., Feng, X., Yang, X., Zu, C., Mao, X., Luo, S., Liu, J., Liu, Y., Luo, C. X., et al. (2025) · IEEE Transactions on Nuclear Science · doi:10.1109/tns.2025.3626230
“With the rapid development of artificial intelligence, the You Only Look Once (YOLO) series of object detection algorithms has been continuously optimized and upgraded since its open-source release [18].”
A YOLOv5-Based Printed Circuit Board Defect Detection System
Lin, J., & Chong, L. W. (2025) · IEEE International Conference on Consumer Electronics - Taiwan (ICCE-Taiwan) · doi:10.1109/icce-taiwan66881.2025.11207944 · Cited by 1
“YOLOv5, developed in Python, integrates modules such as Focus, CSPNet, SPP, and PANet, enhancing feature extraction efficiency and inference accuracy [4]-[6].”
Semantic-Guided Video Retrieval Framework
Wang, C.-H., Siang, Y.-S., & Yang, X. S. (2025) · IEEE International Conference on Consumer Electronics - Taiwan (ICCE-Taiwan) · doi:10.1109/icce-taiwan66881.2025.11207878
“But, they need extensive annotations and only handle predefined categories [1,2,3].”
AndroGen: Open-source synthetic data generation for automated sperm analysis
Hernández, D. L., Pantrigo, J. J., Montalvo, S., & Cabido, R. (2025) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2025.109132
A small object detection method based on CSF-YOLO for UAV images
Li, J., Guo, X., Lv, S., Su, J., & Tang, F. (2025) · Neural Computing and Applications · doi:10.1007/s00521-025-11687-4
Adversarial image detection based on spatial and frequency information
Li, Y., Wang, S., Li, G., Shi, J., Wang, W., Han, X., & Lu, P. (2025) · Displays · doi:10.1016/j.displa.2025.103262 · Cited by 2
Amplifying Robotics Capacities with a Human Touch: An Immersive Human-Machine Interaction System
Li, J., Li, K., Han, D., Xu, J., & Ma, Z. (2025) · Lecture notes in networks and systems · doi:10.1007/978-3-032-07986-2_23
26312 Artificial intelligence in bacterial culture plate images
Jain, P., Jeevan Kumar, M., Ravi, L., & Kar, D. (2025) · De Gruyter eBooks · doi:10.1515/9783111548777-012
Wu, X., & Ablameyko, S. (2025) · «System analysis and applied information science» · doi:10.21122/2309-4923-2025-3-4-10
A YOLOv5 Model with Hybrid Attention Mechanism for Transparent Product Detection in E-Commerce
张, 伟. (2025) · E-Commerce Letters · doi:10.12677/ecl.2025.14103364
Real-time human detection in thermal images: Challenges and solutions with thermosense
Tripathi, V., Mishra, C., Verma, N., Dey, U., & Sharma, N. (2025) · AIP conference proceedings · doi:10.1063/5.0288121
Cancer vision: Harnessing advanced computer vision for empowered cancer diagnosis
Shukla, S., Goel, V., Pandey, S., et al. (2025) · AIP conference proceedings · doi:10.1063/5.0287287
Dahane, A., Walha, R., & Drira, F. (2025) · International Forum on Research and Technologies for Society and Industry Leveraging a better tomorrow · doi:10.1109/rtsi64020.2025.11212582
“YOLO : Originally introduced by Redmon et al. [23], YOLO (You Only Look Once) revolutionized computer vision by framing complex visual tasks as single-stage regression problems.”
A VLM Based Zero-Shot Weight Estimation Approach For Efficient Waste Management
Viti, M., Napoli, V. D., Degiacomo, V., et al. (2025) · doi:10.1109/rtsi64020.2025.11212297
“YOLO (You Only Look Once) [5] introduced a single-stage detection paradigm, directly predicting bounding boxes and class probabilities in a single pass, prioritizing speed.”
SVR-YOLO11: Real-Time Animal Detection for Situational Awareness in SAR Operations
He, Z., Liu, Y., Yang, H., Sun, P., & Chen, B. (2025) · International Symposium on Distributed Simulation and Real Time Applications (DS-RT) · doi:10.1109/ds-rt68115.2025.11185992
“The single neural network of YOLO can process the input image through a single, deep convolutional neural network in a single forward pass, and can be optimized end-to-end directly on the prediction performance [28].”
A Study on Target Detection of Site Helmet Wearing Based on Improved YOLO 11n
Chen, Y., Liu, Y., Peng, J., et al. (2025) · International Conference on Mobile Internet, Cloud Computing and Information Security (MICCIS) · doi:10.1109/miccis66057.2025.00029
“The main algorithms are YOLO (You Only Look Once) series [6] [7] , SSD (Single Shot MultiBox Detector) [8] , RetinaNet [9] .”
A Fast Rivet Detection Algorithm Based on VanillaNet Network and Computer Vision
Zheng, J., & Yuan, P. (2025) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-032-03215-7_11
He, Y., Feng, Z., & Liu, W. (2025) · Electronics · doi:10.3390/electronics14214200 · Cited by 1
Yang, X., Peng, Z., & Xie, X. (2025) · Sensors · doi:10.3390/s25216628 · Cited by 2
Plant Pest and Disease Detection Based on Improved YOLOv10
Hou, H., Wang, S., Hou, C., et al. (2025) · International Conference on Internet of Things, Automation and Artificial Intelligence (IoTAAI) · doi:10.1109/iotaai66837.2025.11213173
“The YOLO (You Only Look Once) object detection algorithm based on deep learning is a one-stage detection algorithm proposed by Redmon et al. in 2016 [3] .”
FireNet: A GAN-Augmented Cross-Modality Network for Robust Flame Detection
Mo, J., Huang, W., Yin, Y., et al. (2025) · International Conference on Internet of Things, Automation and Artificial Intelligence (IoTAAI) · doi:10.1109/iotaai66837.2025.11213199
YOLOv8-Based Watermelon Seed Visual Quality Inspection with Multi-Scale Feature Enhancement
Chen, J., Gao, B., & Cai, X. (2025) · International Conference on Internet of Things, Automation and Artificial Intelligence (IoTAAI) · doi:10.1109/iotaai66837.2025.11212986
Steel Surface Defect Detection Based on GAE-YOLO Algorithm
Gan, Z., Dong, H., Wang, R., Wu, H., Tan, Z., & Zhao, X. (2025) · International Conference on Internet of Things, Automation and Artificial Intelligence (IoTAAI) · doi:10.1109/iotaai66837.2025.11213317 · Cited by 1
“In contrast, single-stage detection algorithms (represented by the YOLO [14]series) have become the preferred solution for industrial scenarios due to their end-to-end architecture advantages.”
Real-time Obstacle Perception and Distance Estimation Based on Binocular Vision
Dong, Y., & Jin, H. (2025) · International Conference on Internet of Things, Automation and Artificial Intelligence (IoTAAI) · doi:10.1109/iotaai66837.2025.11213326
“As a typical single-stage detection algorithm, YOLO effectively balances accuracy and real-time requirements by converting the object detection task into a single regression problem [5] .”
YOLO-FIS: Enhancing Infrared Traffic Object Detection from UAV Perspectives
Gu, H., Huang, J., Shen, Y., & Wang, S. (2025) · International Conference on Internet of Things, Automation and Artificial Intelligence (IoTAAI) · doi:10.1109/iotaai66837.2025.11212867
“YOLOv11 represents a recent advancement in the YOLO family, building upon iterative improvements across the series— from the original YOLOv1 [8] to more recent versions such as YOLOv3 [9] , YOLOv4 [10] , and YOLOv7 [11] .”
Design and Optimization of an Edge Intelligence Object Detection System
Guo, C., Xu, Y., Wang, Z., et al. (2025) · International Conference on Internet of Things, Automation and Artificial Intelligence (IoTAAI) · doi:10.1109/iotaai66837.2025.11212901
“While traditional cloud computing offers substantial computational power, it struggles with transmission delays, bandwidth limitations, and privacy concerns in demanding applications like smart security, autonomous driving, and industrial inspection [2].”
A Unified Approach to Cross-Domain Object Detection in Electro-Optical and Infrared Aerial Imagery
Prajapati, V. M., & Dave, H. J. (2025) · International Conference on Emerging Technology in Autonomous Aerial Vehicles (ETAAV) · doi:10.1109/etaav66793.2025.11213424 · Cited by 1
“The introduction of deep convolutional neural networks (CNNs), particularly one-stage detectors such as YOLO (8), SSD (9), and RetinaNet (10), significantly improved both accuracy and inference speed, enabling practical real-time detection applications.”
UAV-Imagery Based Remote Sensing For Building Crack Detection Using Mask R-CNN
Mekala, V. A. R., Kumar, J., Kandath, H., Sarvadevabhatla, R. K., & Ramancharla, P. K. (2025) · International Conference on Emerging Technology in Autonomous Aerial Vehicles (ETAAV) · doi:10.1109/etaav66793.2025.11213018
“While conventional object detection methods utilize classifiers to identify objects, YOLO [8] addressed object detection as a regression task to estimate bounding boxes and class probabilities.”
Enhancing Visual-Inertial SLAM with ORB-SLAM3
Prasad, M. B., & Omkar, S. N. (2025) · International Conference on Emerging Technology in Autonomous Aerial Vehicles (ETAAV) · doi:10.1109/etaav66793.2025.11213296 · Cited by 1
“Early YOLO models supported real-time detection [23], while recent versions like YOLOv11 improve accuracy and speed [13].”
PromptPilot: Controlling UAVs Using Multimodal AI
Balaji, T., Vineet, S. S., & Kanhangad, V. (2025) · doi:10.1109/etaav66793.2025.11213101
“The method uses the GPT-4 language model aided with a You Only Look Once (YOLO)[3] based perception algorithm, to plan feasible motions within the specified environment.”
RGB-IR Object Detection in Aerial Imagery via Spectral-Aware Augmentation Techniques
Gautam, V., Sinha, S., & Prasad, S. (2025) · International Conference on Emerging Technology in Autonomous Aerial Vehicles (ETAAV) · doi:10.1109/etaav66793.2025.11213242
“CNN-based detectors are generally categorized into two types: (i) single-stage detectors such as YOLO [11] and SSD [12], and (ii) two-stage detectors including R-CNN [13], Fast R-CNN [14], and Faster R-CNN [15].”
Kentsel Trafik Analizinde 3D/2D Hibrit CNN Mimarisi ve Dikkat Mekanizmalarının İncelenmesi
Arı, A., & Acar, S. Y. (2025) · Journal of Polytechnic · doi:10.2339/politeknik.1752555
KI-Training durch Simulation statt Annotation
May, C. M., Fuchs, S., Franke, J. E., et al. (2025) · Zeitschrift für wirtschaftlichen Fabrikbetrieb · doi:10.1515/zwf-2025-1114
UNDERSTANDING HABITAT DISTRIBUTION OVER A WIDE AREA OF MULTIPLE TIDAL FLATS USING MACHINE LEARNING
NAKAMURA, T., OOHARA, T., Hirokazu, S. U. M. I., et al. (2025) · Japanese Journal of JSCE · doi:10.2208/jscejj.25-18039
Panachakel, J. T., Anusha, S. P., Sabu, A., et al. (2025) · Lecture notes in civil engineering · doi:10.1007/978-981-96-8118-1_4
Cheng, Q., Du, H., Xuan, Z., et al. (2025) · doi:10.1145/3767624.3767633
“State-of-the-art target detection algorithms, including the YOLO (You Only Look Once) series (Redmon, 2016; Redmon and Farhadi, 2017; Farhadi and Redmon, 2018; Bochkovskiy et al., 2020; Li et al., 2022; Wang et al., 2023, 2024, 2025) [6–13], demonstrate remarkable efficacy in real-time object…”
Adaptation of Object Detection Models Using Transfer Learning for Navigation in Urban Environments
Flores, A. Y. H., Trujillo, J. A. V., Sánchez-Ruiz, D., et al. (2025) · Communications in computer and information science · doi:10.1007/978-3-032-08704-1_21
Sankaye, R., Bhad, P., Mirajkar, P., et al. (2025) · International Journal of Advanced Research in Science Communication and Technology · doi:10.48175/ijarsct-29378
Zhu, L., Ren, S., Lu, B., & Chen, Z. (2025) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2025.3627247 · Cited by 1
An Effective Interval Normalization Weighting Method for Accurate Object Detection
Wu, S., Tian, C., Liu, R., Wei, H., & Xu, Y. D. (2025) · IEEE Transactions on Systems Man and Cybernetics Systems · doi:10.1109/tsmc.2025.3624473 · Cited by 2
“To increase the detection efficiency, YOLO [21] and SSD [22] are designed with a one-stage framework that can perform classification and bounding box regression directly on hundreds of manually defined anchors.”
WSGS: A Speech-Driven Zero-Shot System for 6D Robotic Arm Grasping
Ge, Y., Zhang, L., Chen, Y., et al. (2025) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme59968.2025.11210090
“Methods like YOLO [9], [10] and Faster R-CNN [11] are widely used for their accuracy and efficiency.”
Relational Enhancement Network for Industrial Defect Detection
Linghu, H., Liu, M., & Zhang, S. (2025) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme59968.2025.11209168
Detection and Classification of Multiple Power Quality Disturbances using a Deep Learning Framework
Savaridass, M. P., Esakkirajan, S., & Angamuthu, A. (2025) · International Conference on Electronics and Sustainable Communication Systems (ICESC) · doi:10.1109/icesc65114.2025.11212471
“In 2015, Redmon et al. [40] introduces the YOLO algorithm, which revolutionizes the object detection by offering a single-stage approach that processes an entire image in a single pass-through CNN. YOLO is a faster and highly accurate with simultaneous object location prediction and classification.”
CAPAA: Classifier-Agnostic Projector-Based Adversarial Attack
Li, Z., Zhao, M., Dong, X. L., Ling, H., & Huang, B. (2025) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme59968.2025.11209575 · Cited by 1
“9 or the perturbation size is below a threshold d thr (2 ≤ d thr ≤ 5 ).”
Chaganti, V. R., Mann, M., Badoni, R. P., et al. (2025) · doi:10.1109/icaiet65052.2025.11211437
“[1]–[3] Object Detection (YOLO, SSD) No team segmentation Ref.”
Data-Driven Visual Defect Detection and Analysis in Manufacturing
Srija, S., Vijithaa, K. J., Priscilla, R., et al. (2025) · International Conference on Electronics and Sustainable Communication Systems (ICESC) · doi:10.1109/icesc65114.2025.11212454
Real Time Object Detection for Visually Impaired People
Sharma, K., Langote, V. B., Rambhia, K., et al. (2025) · Lecture notes in networks and systems · doi:10.1007/978-3-032-06691-6_38
Smart Packaging, Smarter Inspection: A Deep Learning Approach
Verma, D., Gupta, H. S., Verma, V. K., Varun, & Verma, A. (2025) · Materials horizons · doi:10.1007/978-981-95-0677-4_9
MFD ‐ YOLO : A Small Traffic Sign Detection Algorithm Applied to the Field of Automated Driving
Kong, W., Qu, Z., Liu, H., et al. (2025) · IEEJ Transactions on Electrical and Electronic Engineering · doi:10.1002/tee.70209
“Major representative algorithms of this type are the YOLO [11] series and SSD [12] series, which are widely used in autonomous driving systems for vehicles.”
Nianpeng, 潘. P., Guangcheng, 戴. D., Li, Z., Kun, 王. W., & Minhao, 刘. L. (2025) · Laser & Optoelectronics Progress · doi:10.3788/lop250486
Li, Z., & Yin, J. (2025) · Discover Artificial Intelligence · doi:10.1007/s44163-025-00541-0
“The representative models mainly include SSD [10–12], YOLO [13–16] (You Only Look Once), etc.”
Assessment of Freezing and Unfreezing Approach in VGG Model for Breast Cancer Detection
Arifunnisa, S., Bhuyan, H. K., & Brahma, B. (2025) · Advances in intelligent systems and computing · doi:10.1007/978-981-96-8563-9_32
Wavelet-Based Distillation with Structured Frequency Alignment
Lu, P., Yi, J., Mao, J., Yu, J., Xiao, S., He, Z., & Wang, Y. H. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-3393-0_27
A Deep Learning-Based Model for Auxiliary Diagnosis of Pediatric Pneumonia Detection
Du, L., Fan, Z., & He, G. (2025) · Journal of Public Health and Preventive Medicine · doi:10.64904/fpm25013
An Optional 2D Feature Scene Text Recognition Network Based on Transformer
Ibrayim, M., Kang, J., & Bao, Z. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-3729-7_14
Insulator Fault Detection Method Based on Improved YOLOv11n
Li, Z., Wang, S., & Chen, E. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-3729-7_20
Greenhouse Tomato Seedling Detection Algorithm Based on OMB-YOLO
Li, B., & Liu, D. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-3729-7_11
Lightweight Object Tracking and Localization for Assembly Guidance on AR Helmet
Ma, Z., Liu, Y., & Wan, R. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-3729-7_45
Graph-Based Multi-Target Association for AIS and Video Data in Complex Waterways
Lu, Y., Weng, J., Yang, D., & Zhao, C. (2025) · International Conference on Transportation Information and Safety · doi:10.1109/ictis68762.2025.11214797
“Learning methods further enhance this process, such as deep learning models (e.g., YOLO [7], [8], Faster R-CNN [9]) for target detection, combined with multi-target tracking algorithms (e.g., DeepSORT [10]) to improve the identification and tracking of ship targets in video.”
Vehicle Trajectory Extraction from UAV-Captured Traffic Surveillance Videos
Ma, F., Wang, X., Niu, L., et al. (2025) · International Conference on Transportation Information and Safety · doi:10.1109/ictis68762.2025.11214804
“The YOLO series of detection algorithms, first introduced by Redmon et al. [15] in 2016, has emerged as a dominant force in the field of object detection due to its exceptional performance.”
MLRT-DETR: An Efficient and Lightweight Multi-Scale Object Detection Model for Intelligent Driving
Nan, K., Wang, M., Cao, X., & Zheng, W. (2025) · IEEE International Conference on Software Quality, Reliability and Security Companion (QRS-C) · doi:10.1109/qrs-c65679.2025.00064
“The single-stage method such as YOLO has improved the detection speed through structural simplification[3][4][5].”
Fire Detection in Marine Cargo Holds for New Energy Vehicles Based on Improved YOLOv8
Dai, Z., Xie, L., Geng, X., Niu, L., & Mao, Z. (2025) · International Conference on Transportation Information and Safety · doi:10.1109/ictis68762.2025.11214965
“In contrast, one-stage algorithms exemplified by YOLO (You Only Look Once) [6] and SSD (Single Shot Multibox Detector) [7] employ end-to-end architectures that eliminate region proposal generation, substantially improving inference speed while maintaining detection accuracy, thus gaining widespread…”
YOLOv8-Based Lung Nodule Detection and Stage-Aware Multi-Class Classification
Özen, S., Dengizek, M. Y., Hancı, N. B., et al. (2025) · Signal Processing: Algorithms, Architectures, Arrangements, and Applications · doi:10.23919/spa65537.2025.11215140
“The YOLO model was first introduced in 2015 by Joseph Redmon and his colleagues [9].”
Uncertainty-Driven YOLO for Object Detection in Adverse Weather
Gong, Z., Qian, C., & Chen, Z. (2025) · International Conference on Transportation Information and Safety · doi:10.1109/ictis68762.2025.11214987
“The YOLO (You Only Look Once) family of detectors [6-10] has become a dominant approach in object detection due to its speed and competitive accuracy.”
Research on Optimization of Traffic Cone Object Detection Algorithm Based on YOLOv5
Liao, J., Gu, J., Wang, X., et al. (2025) · International Conference on Transportation Information and Safety · doi:10.1109/ictis68762.2025.11214901
“The YOLO (You Only Look Once) algorithm [10] uses only one neural network to complete object detection processes such as classification and localization, with a simple and lightweight structure and a detection speed of up to 155 frames per second.”
Detection or Classification? Towards a Mobile Application for PLN Coin Recognition
Judt, M., Kamiński, K., & Świetlicka, A. (2025) · Signal Processing: Algorithms, Architectures, Arrangements, and Applications · doi:10.23919/spa65537.2025.11215143
“To address this issue, we propose and compare two approaches: one based on linear regression combined with YOLO neural network detection [9], and another that uses a reference token approach supported by a pre-trained ResNet model [10].”
AdaptiVision: Dynamic Confidence Thresholding for Enhanced Object Detection
Rai, A., & Athya, D. (2025) · doi:10.1109/icoeit63558.2025.11211709
“In this paper, we present AdaptiVision, a system which overcomes these shortcomings by: Related work Major advances in object detection were fueled by advances in deep architectures like R-CNN [3], Fast R-CNN [4], Faster R-CNN [5], SSD [6], YOLOv3 [7] and YOLO [8].”
Wei, C., Peng, Z., Yang, L., et al. (2025) · IEEE International Conference on High Performance Computing and Communications (HPCC) · doi:10.1109/hpcc67675.2025.00237
“One-stage object detection models include YOLO [12] series, RetinaNet [13], SSD [14], and other models, which directly output the predicted target positions and categories through a single forward propagation.”
Artificial Intelligence Implementation on Unmanned Aerial Vehicle for Real-Time Detection
Mahmudlu, F., Heybatov, D., & Samadov, S. (2025) · Sustainable aviation · doi:10.1007/978-3-032-07678-6_30
Jia, S., Li, N., Gong, G., et al. (2025) · Communications in computer and information science · doi:10.1007/978-981-95-2751-9_24
Methods of Objects Recognition System Enhancement in Computer Vision
Kokoulin, A. N., & Kokoulin, A. N. (2025) · Communications in computer and information science · doi:10.1007/978-3-032-04764-9_7
Nagarajan, S., Tilahun, L., & Bechera, Y. (2025) · AIP conference proceedings · doi:10.1063/5.0292502
A systematic review of moving object tracking and identification techniques
Devgan, M. S., Singh, K., Dhiman, P., et al. (2025) · AIP conference proceedings · doi:10.1063/5.0293186
Sulaiman, M. A., Farmanbar, M., Belbachir, A. N., & Rong, C. (2025) · Frontiers of artificial intelligence, ethics and multidisciplinary applications. · doi:10.1007/978-981-96-7945-4_32
ProtoP-OD: Explainable Object Detection with Prototypical Parts
Rath-Manakidis, P., Strothmann, F., Glasmachers, T., & Wiskott, L. (2025) · Frontiers of artificial intelligence, ethics and multidisciplinary applications. · doi:10.1007/978-981-96-7945-4_31 · Cited by 6
Fruit Recognition and Calorie Estimation Using YOLO
Pravalika, G. L., Vardhan, G. H., & Kumar, M. A. (2025) · Lecture notes in electrical engineering · doi:10.1007/978-981-96-7253-0_8
Visual Recognition System with Artificial Intelligence and PID Control for an Autonomous Vehicle
Benitez, E. L. G., Martínez, A., Morales, B. A. L., et al. (2025) · Communications in computer and information science · doi:10.1007/978-3-032-09738-5_20
Martínez, S. R., Ruiz, R. B. J., Talamantes, J. F. S., et al. (2025) · Communications in computer and information science · doi:10.1007/978-3-032-09738-5_22
Distant Water Surface Garbage Recognition Method in Complex Scenarios
Lu, C., & Sun, X. (2025) · Journal of Computer Science and Artificial Intelligence · doi:10.54097/w29n3w46
“Network models such as Faster R-CNN [1] and YOLO [2] can rapidly obtain target categories and bounding boxes, achieving good progress in water surface debris object detection.”
HierDETR: Hierarchical Multi-Head Attention-based Pulmonary Nodule Detection in Medical Imaging
Tong, Z. (2025) · Journal of Computer Science and Artificial Intelligence · doi:10.54097/aktcae20
“Compared with the baseline models Yolo [9], DETR [10], and Lung-DETR [11], HierDETR improved the F1 Score by 5.5%, 3.9%, and 1.3%, respectively; the Average Precision by 6.7%, 4.3%, and 2.2%; and the Average Recall by 5.0%, 3.3%, and 1.9%, respectively.”
InfluentialFlying Steel Detection in Wire Rod Production Based on Improved You Only Look Once v8
Lu, Y., Zhang, F., Li, X., Zhang, J., Xiao, X., Wang, L., & Xiang, X. (2025) · Processes · doi:10.3390/pr13072297 · Cited by 1
Multimodal AI-Driven Framework for Real-Time Compliance Monitoring
Srivastava, D. N., Dhakal, A., Choudhary, N., Shrivastava, K., Sridhar, G., Bhatt, B., Qu, G., & Samuel, P. (2025) · Abu Dhabi International Petroleum Exhibition & Conference (ADIPEC) · doi:10.2118/229197-ms · Cited by 1
Omobolanle, O. C., & Ikiensikimama, S. S. (2025) · doi:10.2118/229339-ms
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.