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 19,401–19,500 of 51,400
Ghai, D., Saxena, S., Dhingra, G., & Tripathi, S. L. (2024) · Multimedia Tools and Applications · doi:10.1007/s11042-024-20257-0 · Cited by 37
A unified object and keypoint detection framework for Personal Protective Equipment use
Yang, B., Xiao, H., & Zhang, B. (2024) · Developments in the Built Environment · doi:10.1016/j.dibe.2024.100559 · Cited by 17
Fadja, A. N., Rigobert, S., & Atemkeng, M. (2024) · Information · doi:10.3390/info15100635 · Cited by 7
Setiawan, F. A., Rohmah, Z. A., & Laxmi, G. F. (2024) · International Conference on Computer, Control, Informatics and its Applications · doi:10.1109/ic3ina64086.2024.10732209 · Cited by 7
Automatic raster engineering drawing digitisation for legacy parts towards advanced manufacturing
Maupou, C., Yin, Y., Fodop, G., Qie, Y., Migliorini, C., Mehdi-Souzani, C., & Anwer, N. (2024) · Procedia CIRP · doi:10.1016/j.procir.2024.10.041 · Cited by 7
High-Precision and Lightweight Model for Rapid Safety Helmet Detection
Jia, X., Zhou, X., Su, C., Shi, Z., Lv, X., Lu, C., & Zhang, G. (2024) · Sensors · doi:10.3390/s24216985 · Cited by 11
Cai, C., Yang, G., Liu, T., et al. (2024) · Remote Sensing · doi:10.3390/rs16214095 · Cited by 7
Hamza, A., Alzalabny, S., Buduru, P., Bhagwat, S., Usama, A., Prabhulingaiah, S. K., Song, Q., Kluck, S., Jaworek, G., Pezeshkpour, P., et al. (2024) · Advanced Materials & Technologies · doi:10.1002/admt.202401029 · Cited by 8
Hoehner, F., Langenohl, V., Akyol, S., el Moctar, O., & Schellin, T. E. (2024) · Journal of Marine Science and Engineering · doi:10.3390/jmse12112038 · Cited by 10
An Enhanced Feature-Fusion Network for Small-Scale Pedestrian Detection on Edge Devices
Hu, M., Zhang, Y., Jiao, T., Xue, H., Wu, X., Luo, J., Han, S., & Lv, H. (2024) · Sensors · doi:10.3390/s24227308 · Cited by 12
Smart Monitoring Method for Land-Based Sources of Marine Outfalls Based on an Improved YOLOv8 Model
Zhao, S., Zhou, H., & Yang, H. (2024) · Water · doi:10.3390/w16223285 · Cited by 8
Transformer based 3D tooth segmentation via point cloud region partition
Wu, Y., Yan, H., & Ding, K. (2024) · Scientific Reports · doi:10.1038/s41598-024-79485-x · Cited by 13
Streaming Quanta Sensors for Online, High-Performance Imaging and Vision
Zhang, T., Dutson, M., Boominathan, V., Gupta, M., & Veeraraghavan, A. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3501154 · Cited by 12
Tanimoto, Y., Zhang, Z., & Yoshida, S. (2024) · AgriEngineering · doi:10.3390/agriengineering6040243 · Cited by 7
Cross Teaching-Enhanced Multispectral Remote Sensing Object Detection With Transformer
Zhu, J., Zhang, H., Li, S., Wang, S., & Ma, H. (2024) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2024.3504549 · Cited by 15
Development of plant phenotyping system using Pan Tilt Zoom camera and verification of its validity
Pham, D. T., Amin, N. A., Yasutake, D., Hirai, Y., Ozaki, T., Koga, M., Hidaka, K., Kitano, M., Vo, H. B., & Okayasu, T. (2024) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2024.109579 · Cited by 7
Defect Detection of Photovoltaic Panels to Suppress Endogenous Shift Phenomenon
Chen, H., Zhang, Y., Zhang, Y., Yan, X., Zhang, X., & Zou, K. (2024) · IEEE Transactions on Semiconductor Manufacturing · doi:10.1109/tsm.2024.3510358 · Cited by 7
Packaging Defect Detection in Lean Manufacturing: A Comparative Study of YOLOv8, YOLOv9, and YOLOv10
Chomklin, A., Jaiyen, S., Wattanakitrungroj, N., Mongkolnam, P., & Chaikhan, S. (2024) · International Computer Science and Engineering Conference · doi:10.1109/icsec62781.2024.10770712 · Cited by 8
Kirana, N. L., Kurnianingtyas, D., & Indriati, I. (2024) · Engineering Technology & Applied Science Research · doi:10.48084/etasr.8592 · Cited by 14
Ciulla, F., Santos, A., Jordan, P. D., Kneafsey, T. J., Biraud, S. C., & Varadharajan, C. (2024) · Environmental Science & Technology · doi:10.1021/acs.est.4c04413 · Cited by 6
Automatic detection and classification of beluga whale calls in the St. Lawrence estuary
Cotillard, T., Sécheresse, X., Aubin, J. A., et al. (2024) · The Journal of the Acoustical Society of America · doi:10.1121/10.0030472 · Cited by 7
Liu, R., Shao, Z., Yu, Z., & Li, R. (2024) · Signal Image and Video Processing · doi:10.1007/s11760-024-03584-5 · Cited by 7
García-Pérez, A., Gómez-Silva, M. J., & de la Escalera, A. (2024) · NDT & E International · doi:10.1016/j.ndteint.2024.103303 · Cited by 8
Through-Wall Multi-Person Action Recognition Using Enhanced YOLOv5 and IR-UWB Radar
Li, X., Zhang, S., Chen, S., & Xiao, Z. (2024) · IEEE Sensors Journal · doi:10.1109/jsen.2024.3513983 · Cited by 9
Relation-Guided Adversarial Learning for Data-Free Knowledge Transfer
Liang, Y., & Fu, Y. (2024) · International Journal of Computer Vision · doi:10.1007/s11263-024-02303-4 · Cited by 12
Lightweight Detection Counting Method for Pill Boxes Based on Improved YOLOv8n
Sun, W., Niu, X., Wu, Z., & Guo, Z. (2024) · Electronics · doi:10.3390/electronics13244953 · Cited by 7
Malaria parasite detection in Red Blood Cells with rouleaux formation morphology using YOLOv9
Muhammad, F. A., Sudirman, R., & Zakaria, N. A. (2024) · Tissue and Cell · doi:10.1016/j.tice.2024.102677 · Cited by 7
A Survey of Industrial Surface Defect Detection Based on Deep Learning
Haobo, Y. (2024) · International Conference on Cyber-Physical Social Intelligence (ICCSI) · doi:10.1109/iccsi62669.2024.10799405 · Cited by 10
Li, J., Li, H., Xu, H., Song, R., Li, Y., & Du, Q. (2024) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2024.3520299 · Cited by 15
Ahn, S. H., Baek, S., Park, J., Kim, J., Rhee, H., Chung, Y. E., Kim, H., & Lee, Y. H. (2024) · Journal of Imaging Informatics in Medicine · doi:10.1007/s10278-024-01369-3 · Cited by 11
PCAF: UAV scenarios detector via pyramid converge-and-assign fusion network
Li, Z., He, Q., Ren, L., Yao, W., & Yang, W. (2024) · Multimedia Systems · doi:10.1007/s00530-024-01595-3 · Cited by 7
EP-YOLO: A Pipeline Leak Detection Algorithm Based on Improved YOLOv7
Zhang, J., Lan, X., Wang, S., et al. (2024) · IEEE Access · doi:10.1109/access.2024.3521295 · Cited by 7
Machine learning assisted fast optical identification of 2D materials
He, J., Zhou, Y., Zhang, P., & Zhai, H. (2024) · Applied Surface Science · doi:10.1016/j.apsusc.2024.162110 · Cited by 8
A novel dataset and a two-stage deep learning method for breast cancer mitosis nuclei identification
Wang, H., Liu, Z., Pan, X., Kang, Y., Lan, R., Guan, J., & Li, B. (2024) · Digital Signal Processing · doi:10.1016/j.dsp.2024.104978 · Cited by 8
Song, Y., Zhang, P., Huang, W., Zha, Y., & Zhang, Y. (2025) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2024.3525051 · Cited by 11
“For the dense object detectors [32], [33], [34] with faster inference, such as SSD [35] and YOLO series [36], [37], [38], the dense proposal made them extremely difficult to distinguish the positive and negative samples during training, which limits the accuracy to be further improved.”
RDynaSLAM: Fusing 4D Radar Point Clouds to Visual SLAM in Dynamic Environments
Zhu, D., & Yang, G. (2025) · Journal of Intelligent & Robotic Systems · doi:10.1007/s10846-024-02204-1 · Cited by 7
Li, C., He, Z., Lü, K., & Fang, C. (2025) · Sensors · doi:10.3390/s25010291 · Cited by 11
Chen, Y., Jiang, W., & Wang, Y. (2025) · Remote Sensing · doi:10.3390/rs17020205 · Cited by 11
Wang, H., Zhang, S., Zhang, C., Liu, Z., Huang, Q., Ma, X., & Jiang, Y. (2025) · Scientific Reports · doi:10.1038/s41598-024-84328-w · Cited by 8
Sun, H., Tan, S., Luo, Z., Yin, Y., Cao, C., Zhou, K., & Zhu, L. (2025) · Agriculture · doi:10.3390/agriculture15020122 · Cited by 9
HangCon: Benchmark Data Set for Enhanced Detection of Hanging Objects in Construction Sites
Jeong, G., Park, S.-E., Lee, J., Park, M., & Ahn, C. R. (2025) · Journal of Computing in Civil Engineering · doi:10.1061/jccee5.cpeng-6283 · Cited by 9
A novel deep learning-based pipeline architecture for pulp stone detection on panoramic radiographs
Gürhan, C., Yiğit, H., Yılmaz, S., & Çetinkaya, C. (2025) · Oral Radiology · doi:10.1007/s11282-025-00804-7 · Cited by 10
Kapetas, D., Kalogeropoulou, E., Christakakis, P., Klaridopoulos, C., & Pechlivani, E. M. (2025) · Agriculture · doi:10.3390/agriculture15020164 · Cited by 15
MSA-YOLOv5: An Improved Light-Weight YOLOv5 Model for Small Object Detection
Park, J.-C., Kim, M., & Kim, G.-W. (2024) · International Conference on Information and Communication Technology Convergence (ICTC) · doi:10.1109/ictc62082.2024.10827062 · Cited by 9
Sun, C., Ming, D., Xu, L. T., Xie, S.-Z., Liu, R., & Ling, X. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2025.3530934 · Cited by 8
Kozhekin, M. V., Александрович, Г. М., Komyshev, E. G., Zavyalov, Z. A., & Afonnikov, D. A. (2025) · Journal of Imaging · doi:10.3390/jimaging11010028 · Cited by 8
SVDD: SAR Vehicle Dataset Construction and Detection
Gao, D., Wu, X., Wen, Z., Xu, Y., & Chen, Z. (2025) · IEEE Access · doi:10.1109/access.2025.3532294 · Cited by 10
Improved YOLOv5: Efficient Object Detection for Fire Images
Yu, D., Li, S., Zhang, Z., Liu, X., Ding, W., & Zhao, X. (2025) · Fire · doi:10.3390/fire8020038 · Cited by 8
A two-stage fast stereo matching algorithm for real-time 3D coordinate computation
Liu, H., Shen, B., Zhang, J., Huang, Z., & Huang, M. (2025) · Measurement · doi:10.1016/j.measurement.2025.116672 · Cited by 7
Human Robot Interaction for Blind and Low Vision People: A Systematic Literature Review
Wei, Y., Rocher, N., Gupta, C., Nguyen, M. H., Zimmermann, R., Ooi, W. T., Jouffrais, C., & Nanayakkara, S. C. (2025) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3706598.3713438 · Cited by 20
“For example, the original paper on YOLO (You Only Look Once), a popular object detection algorithm, was published in 2016 [110].”
Use of artificial intelligence in soybean breeding and production
Singh, A. K., Jones, S. E., der Laan, L. V., Ayanlade, T. T., Raigne, J., Saleem, N., Joshi, S., Arshad, M., Zaremehrjerdi, H., Rairdin, A. M., et al. (2025) · Advances in agronomy · doi:10.1016/bs.agron.2024.11.003 · Cited by 12
Deutch, F., Weiss, M. G., Wagner, S., Hansen, L. S., Larsen, F., Figueiredo, C., Moers, C., & Keller, A. K. (2025) · Sensors · doi:10.3390/s25030785 · Cited by 9
Rapid and Automatic UAV Detection of River Embankment Piping
Duan, Q., Chen, B., & Luo, L. (2025) · Water Resources Research · doi:10.1029/2024wr038931 · Cited by 9
R-SABMNet: A YOLOv8-Based Model for Oriented SAR Ship Detection with Spatial Adaptive Aggregation
Li, X., Duan, W., Fu, X., & Lv, X. (2025) · Remote Sensing · doi:10.3390/rs17030551 · Cited by 7
Railway Side Slope Hazard Detection System Based on Generative Models
Zheng, X., He, Y., Luo, Y., Zhang, L., Wang, J., Shi, T., & Bai, Y. (2025) · IEEE Sensors Journal · doi:10.1109/jsen.2025.3538529 · Cited by 18
“Among the various AI models employed for image analysis, You Only Look Once (YOLO) [1] has been widely recognized for its efficiency and effectiveness in real-time object detection.”
LW-PV DETR: lightweight model for photovoltaic panel surface defect detection
Han, T., Bao, M., He, T., Zhang, R., Feng, X., & Huang, Y. (2025) · Engineering Research Express · doi:10.1088/2631-8695/adb4be · Cited by 10
An unsupervised learning method based on U-Net + + for low-light image enhancement
Wang, X., Wang, Y., Zhou, J., et al. (2025) · Signal Image and Video Processing · doi:10.1007/s11760-024-03621-3 · Cited by 7
Sun, W., Xu, Z., Xu, K., Lin, R., Yang, R., Wang, R., & Xing, J. (2025) · Frontiers in Plant Science · doi:10.3389/fpls.2024.1491593 · Cited by 10
SSD-based innovations for improved construction management
Lung, L.-W., & Wang, Y. R. (2025) · Journal of Engineering Research · doi:10.1016/j.jer.2025.02.004 · Cited by 8
Dynamic relevance learning for few-shot object detection
Liu, W., Cai, X., Wang, C., Li, H., & Yu, S. (2025) · Signal Image and Video Processing · doi:10.1007/s11760-024-03774-1 · Cited by 27
Chen, R., Jiang, J., Maheshwary, P., Cochran, B. R., & Zhao, Y. (2025) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3706598.3713847 · Cited by 21
SCR-YOLOv8: an enhanced algorithm for target detection in sonar images
Weng, Y., Xiang, X., & Ma, L. (2025) · Journal of Real-Time Image Processing · doi:10.1007/s11554-025-01637-7 · Cited by 10
Animal Detection and Classification to Prevent Human-Animal Conflict Using YOLOv8
Gomathi, V., Harini, I. S., Badmabharathi, S., Kaarthiga, K., & Dhanushkumar, M. (2024) · International Conference on System Modeling & Advancement in Research Trends (SMART) · doi:10.1109/smart63812.2024.10882585 · Cited by 7
Diverse Visible-to-Thermal Image Translation via Controllable Temperature Encoding
Zhao, L., Li, M., Li, B., & Wei, X. (2025) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2025.3543053 · Cited by 13
Hu, Z., Zhang, Z., Liu, S., Zhao, D., Zheng, L., & Tang, L. (2025) · The Journal of Supercomputing · doi:10.1007/s11227-025-07045-9 · Cited by 7
SPAFPN: Wear a multi-scale feature fusion scarf around neck for real-time object detector
Bian, Z., Yao, B., & Li, Q. (2025) · Information Fusion · doi:10.1016/j.inffus.2025.103034 · Cited by 11
SAM-YOLO: An Improved Small Object Detection Model for Vehicle Detection
Liao, J., Jiang, S., Chen, M., & Sun, C. (2025) · The European Journal on Artificial Intelligence · doi:10.1177/30504554251319452 · Cited by 14
FuseGrasp: Radar-Camera Fusion for Robotic Grasping of Transparent Objects
Deng, H., Xue, T., & Chen, H. H. (2025) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2025.3547371 · Cited by 10
Detecting Small Damage on Wind Turbine Surfaces Using an Improved YOLO in Drone-Captured Scenes
Cao, J., Peng, B., Gao, M., Hao, H., Guo, J., Liu, X., & Liu, W. (2025) · Journal of Failure Analysis and Prevention · doi:10.1007/s11668-025-02130-w · Cited by 7
IMRMB-Net: A lightweight student behavior recognition model for complex classroom scenarios
Feng, C., Luo, Z., Kong, D., Ding, Y., & Liu, J. (2025) · PLoS ONE · doi:10.1371/journal.pone.0318817 · Cited by 9
A lightweight distance estimation method using pinhole camera geometry model
Han, T. T., Duc, M. T., & Tan, H. D. (2025) · Measurement Science and Technology · doi:10.1088/1361-6501/adbf3b · Cited by 8
Omni-Deblurring: Capturing Omni-Range Context for Image Deblurring
Li, Y., An, H., Zhang, T., Chen, X., Jiang, B., & Pan, J. (2025) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2025.3549853 · Cited by 15
Weakly Semi-Supervised Infrared Small Target Detection Guided by Point Labels
Cui, X., Li, X., Wu, P., et al. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2025.3550548 · Cited by 7
An enhanced discovery of multiple natural disasters using machine learning model
Thirukrishna, J. T. (2025) · Earth Science Informatics · doi:10.1007/s12145-025-01793-1 · Cited by 7
Lu, Z., Sun, L., Lv, P., Hao, J., Tang, B., & Chen, X. (2025) · IET Computer Vision · doi:10.1049/cvi2.70007 · Cited by 11
Li, K., Li, Y., Wen, X., Shi, J., Yang, L., Xiao, Y., Lu, X., & Mu, J. (2025) · Agronomy · doi:10.3390/agronomy15030693 · Cited by 8
Hosseini-Begtary, S. S., Gurabi, A., Hegedus, P., & Marton, N. (2025) · Imaging · doi:10.1556/1647.2025.00277 · Cited by 12
FDFuse: Infrared and Visible Image Fusion Based on Feature Decomposition
Cheng, M., Huang, H., Liu, X., Mo, H., Wu, S., & Zhao, X. (2025) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2025.3551460 · Cited by 21
Li, R., Katsigiannis, S., Kim, T., & Shum, H. P. H. (2025) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2025.3545268 · Cited by 21
Yang, Z., Lu, X., Zhao, J., Wang, W., Zhang, C., Zhao, J., Yu, J., Liu, S., & Dong, F. (2025) · IEEE Access · doi:10.1109/access.2025.3553264 · Cited by 7
Safari, K., Rodríguez-Vila, B., & Pierce, D. M. (2025) · Journal of Orthopaedic Research® · doi:10.1002/jor.26071 · Cited by 7
Road manhole cover defect detection via multi-scale edge enhancement and feature aggregation pyramid
Liu, J., Zhao, J., Cao, Y., Wang, Y., Dong, C., & Guo, C. (2025) · Scientific Reports · doi:10.1038/s41598-025-95450-8 · Cited by 9
Nabiullina, R., Николаевич, Г. С., Kirichenko, E. Y., Petrushan, M. V., Logvinov, A. K., Kaplya, M., Андреевна, С. Д., & Rodkin, S. (2025) · Frontiers in Bioscience-Landmark · doi:10.31083/fbl36266 · Cited by 10
SCASNet: Spatial Context-Aware Selection Network for Small Object Detection in Aerial Imagery
Wang, Z., Dong, X., & Xu, Y. (2025) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2025.3555627 · Cited by 8
Defect recognition network for optical fiber cables based on feature information compensation
Zheng, S., Ni, S.-S., Yan, P., et al. (2025) · Applied Soft Computing · doi:10.1016/j.asoc.2025.113139 · Cited by 7
Advanced lightweight deep learning vision framework for efficient pavement damage identification
Dong, S., Wang, Y., Cao, J., Ma, J., Chen, Y., & Kang, X. (2025) · Scientific Reports · doi:10.1038/s41598-025-97132-x · Cited by 14
“…the region-based two-stage detection algorithms, including R-CNN 22 , Fast R-CNN 23 , Faster R-CNN 24 , and U-Net 25 , as well as the regression-based single-stage detection algorithms, such as Single Shot MultiBox Detector(SSD) 26 , RetinaNet 27 , and You Only Look Once(YOLO) 28–32 series.”
Action Recognition via Multi-View Perception Feature Tracking for Human–Robot Interaction
Bandi, C., & Thomas, U. (2025) · Robotics · doi:10.3390/robotics14040053 · Cited by 11
“Recent works have leveraged deep-learning-based approaches, such as YOLO [5] and Faster R-CNN [6], to achieve real-time object detection with high accuracy.”
A TBD-YOLO-Based Surface Defect Detection Method for Hot Rolled Steel Strips
Kong, S., Kong, Y., Chi, X., Feng, X., & Ma, L. (2025) · Russian Journal of Nondestructive Testing · doi:10.1134/s1061830924603192 · Cited by 9
Real-time rainfall estimation using deep learning: Influence of background and rainfall intensity
Qin, X., Zhu, Q., Shen, J., Chen, H., & Gao, X. (2025) · Environmental Modelling & Software · doi:10.1016/j.envsoft.2025.106496 · Cited by 7
Cui, M., Yan, Y., Feng, D., Wu, G., & Zhu, Z. (2025) · Structural Control and Health Monitoring · doi:10.1155/stc/3621939 · Cited by 8
Mo, Y., Li, C., Ren, W., & Wang, W. (2025) · IEEE Journal of Oceanic Engineering · doi:10.1109/joe.2025.3545289 · Cited by 9
“YOLO [28] partitions input images into grid cells, predicting multiple bounding boxes relative to each cell’s center.”
Research on Enhanced Dynamic Pig Counting Based on YOLOv8n and Deep SORT
Shen, P., Mei, K., Xue, H., Li, T., Zhang, G., Zhao, Y., Luo, W., & Mao, L. (2025) · Sensors · doi:10.3390/s25092680 · Cited by 8
“The YOLO [30] (You Only Look Once) series represents a landmark family of classic single-stage object identification algorithm, excelling in both accuracy and speed of detection.”
YOLOv5-Based Object Detection for Emergency Response in Aerial Imagery
Boddu, S., Mukherjee, A., & Agarwal, M. (2025) · Proceedings of IEEE Southeastcon · doi:10.1109/southeastcon56624.2025.10971604 · Cited by 7
Multi-scale feature enhanced detection of foreign object intrusions on railways
Gao, J., Zhu, L., Guo, B., & Wang, Y. (2025) · The Journal of Supercomputing · doi:10.1007/s11227-025-07254-2 · Cited by 8
Zheng, B., Zhou, J. L., Hong, Z., Tang, J., & Huang, X. (2025) · Sensors · doi:10.3390/s25092788 · Cited by 8
“Finally, the of Unlike traditional methods that reuse detection problem into a regression problem, and outputs the results with only a single forward inference, i.e., “one-stage method”, hence its name, “You Only Look Once” [39].”
InfluentialA lightweight approach for accurate detection of pipeline weld defects
Wang, G., Luo, R., Zeng, X., & Ni, P. (2025) · Nondestructive Testing And Evaluation · doi:10.1080/10589759.2025.2499031 · Cited by 7
“Compared to the widely used Bottleneck structure in the YOLO series [39], the RGE module adopts a more streamlined architectural design to alleviate the model’s computational burden.”
An AI-Based Open-Source Software for Varroa Mite Fall Analysis in Honeybee Colonies
Yániz, J. L., Casalongue, M., Martínez-de-Pisón, F. J., Silvestre, M. A., Santolaria, P., & Divasón, J. (2025) · Agriculture · doi:10.3390/agriculture15090969 · Cited by 11
Detection of Welding Defects Using the YOLOv8-ELA Algorithm
Chen, Y., He, Y., & Wu, L. (2025) · Applied Sciences · doi:10.3390/app15095204 · Cited by 8
“In 2016, Redmon and his team introduced the single-stage detection model You Only Look Once (YOLOv1) [6], and in the same year, the Single Shot MultiBox Detector (SSD) algorithm was proposed [7].”
Gong, H., Li, M., Wang, L., Huang, S., & Li, M. (2025) · Applied Sciences · doi:10.3390/app15105518 · Cited by 7
HMS-Net: A Hierarchical Multilabel Fine-Grained Ship Detection Network in Remote Sensing Images
Yang, Y., Zhang, Z., Feng, P., Yan, Y., He, G., Liu, S., Zhang, P., & Gao, H. (2025) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2025.3570872 · Cited by 10
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.