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 18,301–18,400 of 51,399
Guo, C., Ma, Z., Zhao, Y., Cao, C., Jiang, Z., & Zhang, H. (2025) · International Journal of Remote Sensing · doi:10.1080/01431161.2025.2479886 · Cited by 16
Wen, Z., Zhou, M., Mišković, S., & Zhou, C. (2025) · Flow Measurement and Instrumentation · doi:10.1016/j.flowmeasinst.2025.102892 · Cited by 9
TLD-READY: Traffic Light Detection ‐ Relevance Estimation and Deployment Analysis
Polley, N., Pavlitska, S., Boualili, Y., et al. (2024) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc58415.2024.10919699 · Cited by 8
Deep representation learning for license plate recognition in low quality video images
Zhao, K., Peng, L., Ding, N., Yao, G., Tang, P. C., & Wang, S. (2025) · Machine Vision and Applications · doi:10.1007/s00138-025-01678-9 · Cited by 8
WDS-YOLO: A Marine Benthos Detection Model Fusing Wavelet Convolution and Deformable Attention
Qian, J., & Chen, M. (2025) · Applied Sciences · doi:10.3390/app15073537 · Cited by 8
Hao, Y., Yan, S., Yang, G., Luo, Y., Liu, D., Han, C., Ren, X., & Du, D. (2025) · Scientific Reports · doi:10.1038/s41598-025-89952-8 · Cited by 13
Huang, Y., Ouyang, H., & Miao, X. (2025) · Applied Sciences · doi:10.3390/app15073961 · Cited by 8
YOLOv8n-DDSW: an efficient fish target detection network for dense underwater scenes
Yi, J., Han, W., & Lai, F. (2025) · PeerJ Computer Science · doi:10.7717/peerj-cs.2798 · Cited by 8
Dance any Beat: Blending Beats with Visuals in Dance Video Generation
Wang, X., Wang, H., Liu, D., & Cai, W. (2025) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61041.2025.00502 · Cited by 24
Huang, X., Teng, Q., Yang, H. W., He, X., Qing, L., Wang, P., & Chen, H. (2025) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2025.3559616 · Cited by 16
Li, L., Yin, Q., Wang, X., & Wang, H. (2025) · IEEE Access · doi:10.1109/access.2025.3559657 · Cited by 10
Peng, Y., Du, K., Yue, H., Li, H., Li, H., Liu, M., Shangguan, S., He, X., Li, X., & Chang, Y. (2025) · Journal of Advanced Research · doi:10.1016/j.jare.2025.04.011 · Cited by 14
Weerakkody, K. D., Balasundaram, R. J., Osagie, E. R., & Al-Ani, J. A. (2025) · Electronics · doi:10.3390/electronics14081542 · Cited by 10
“For reading annotation files, each annotation file A k corresponds to an image I k and contains structured data, including bounding box coordinates and class labels [33].”
Multi-Modality Sheep Face Recognition Based on Deep Learning
Liao, S., Shu, Y., Fang, T., Zhou, Y., Li, G., Zhang, C., Yao, C., Wang, Z., & Che, L. (2025) · Animals · doi:10.3390/ani15081111 · Cited by 8
High-Precision Multi-Source Fusion Navigation Solutions for Complex and Dynamic Urban Environments
Li, L., Nie, W., Zong, W., Xu, T., Li, M., Jiang, N., & Zhang, W. (2025) · Remote Sensing · doi:10.3390/rs17081371 · Cited by 10
Efficient crack segmentation with multi-decoder networks and enhanced feature fusion
Okran, A. M., Rashwan, H. A., Saleh, A., & Puig, D. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.110697 · Cited by 13
A dynamic weighted feature fusion lightweight algorithm for safety helmet detection based on YOLOv8
Ren, H., Fan, A., Zhao, J., Song, H., Wen, Z., & Lü, S. (2025) · Measurement · doi:10.1016/j.measurement.2025.117572 · Cited by 16
Hand Gesture Detection Using VGG-16
Madaan, V., Sharma, N., Gupta, D., et al. (2024) · International Conference on Information Science and Communications Technologies (ICISCT) · doi:10.1109/icisct64202.2024.10956830 · Cited by 8
Lu, J., Yu, R., Zhang, H., Wu, D., Zhang, R., Ren, W., Han, W., & Peng, Y. (2025) · Digital Signal Processing · doi:10.1016/j.dsp.2025.105238 · Cited by 20
PFW-YOLO Lightweight Helmet Detection Algorithm
Hong, Y., Wang, H., & Guo, S. (2025) · IEEE Access · doi:10.1109/access.2025.3561156 · Cited by 9
Photovoltaic panel defect detection algorithm based on infrared imaging and improved YOLOv8
Wang, J., & Cheng, Z. (2025) · PeerJ Computer Science · doi:10.7717/peerj-cs.2776 · Cited by 10
RDCRNet: RGB-T Object Detection Network Based on Cross-Modal Representation Model
Li, Y., Zhan, W., Jiang, Y., & Guo, J. (2025) · Entropy · doi:10.3390/e27040442 · Cited by 19
Dai, K., Zhu, J., Hou, H., Li, Q., Ma, X., & Yu, H. (2025) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2025.3558243 · Cited by 8
Wang, G., Xie, J., Zhang, T., Sun, Y., Chen, H., Zhuang, Y., & Li, J. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2025.3564332 · Cited by 21
Evaluation of Temporal Trends in Forest Health Status Using Precise Remote Sensing
Leidemer, T., Caceres, M. L. L., Díez, Y., Ferracini, C., Tsou, C., & Katahira, M. (2025) · Drones · doi:10.3390/drones9050337 · Cited by 10
“YOLO is an algorithm that revolutionized the field by framing detection as a single regression problem [42,43].”
Chen, S., Lu, Y., Qin, G., Hou, X., & Sun, Y. (2025) · Journal of Building Engineering · doi:10.1016/j.jobe.2025.112810 · Cited by 18
AOYOLO Algorithm Oriented Vehicle and Pedestrian Detection in Foggy Weather
Su, J. D., Mao, S., & Zhuang, W. (2025) · Chinese Journal of Electronics · doi:10.23919/cje.2023.00.280 · Cited by 13
Li, A., Li, D., & Wang, A. (2025) · Sensors · doi:10.3390/s25092903 · Cited by 17
“Moreover, its feature-extraction structure demonstrates strong perceptual capability for small-scale targets and surface damage [37].”
Hint-DETR: A Transfer Learning Model Based on DETR for Few-Shot Defect Detection
Liu, Y., Zhang, G., & Li, X. (2025) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2025.3568997 · Cited by 23
Microfluidic droplet detection using synthetic data generated by a Generative Adversarial Network
Karimzadeh, M., Meybodi, M. A., Shams, M., et al. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.111032 · Cited by 8
Spiking Trans-YOLO: A range-adaptive energy-efficient bridge between YOLO and Transformer
Huo, Y., Ge, H., Tang, G., Gao, S., & Xu, J. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.130407 · Cited by 8
Computer Vision-Based Obstacle Detection Mobile System for Visually Impaired Individuals
Guacho, G. K. B., Alvarado, M. A. P., Vallejo, P. X. M., et al. (2025) · Multimodal Technologies and Interaction · doi:10.3390/mti9050048 · Cited by 8
“Object detection models such as YOLO (You Only Look Once) [11] offer real-time processing capabilities that can be integrated into mobile applications, providing immediate assistance through auditory and haptic feedback to warn of obstacles in the environment.”
A lightweight steel surface defect detection network based on YOLOv9
Zheng, T., Yu, L. H., Shi, Y., & Niu, F. (2025) · AIP Advances · doi:10.1063/5.0273824 · Cited by 8
AI-enabled driver assistance: monitoring head and gaze movements for enhanced safety
Shah, S. M., Zengkang, G., Sun, Z., et al. (2025) · Complex & Intelligent Systems · doi:10.1007/s40747-025-01897-7 · Cited by 8
“YOLOv7 is chosen as the baseline network for this research [36].”
Chen, J., & Er, M. J. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.111067 · Cited by 10
A Precise Detection Method for Tomato Fruit Ripeness and Picking Points in Complex Environments
Wang, X., Wen, X., Li, Y., Du, C., Zhang, D., Sun, C., & Chen, B. (2025) · Horticulturae · doi:10.3390/horticulturae11060585 · Cited by 13
Kou, X., Qiu, R., Chen, P., Wang, Q., Chen, Y., & Guo, H. (2025) · Journal of Water Process Engineering · doi:10.1016/j.jwpe.2025.107988 · Cited by 10
Dual-Phase Severity Grading of Strawberry Angular Leaf Spot Based on Improved YOLOv11 and OpenCV
Xu, Y., Yu, X., Yi, Q., Zhang, Q.-Y., & Su, W. (2025) · Plants · doi:10.3390/plants14111656 · Cited by 11
“YOLO (You Only Look Once), introduced by Joseph Redmon and Ali Farhadi et al. in 2016 [34], is an object detection system that utilizes a single neural network.”
Karataş, E., Ünal, O., Çelik, Ö., & Bayrakdar, İ. Ş. (2025) · Australian Endodontic Journal · doi:10.1111/aej.12955 · Cited by 12
Xu, Y., Yang, X., Xiao, X., & Zhao, J. (2025) · IEEE Signal Processing Letters · doi:10.1109/lsp.2025.3575638 · Cited by 10
Dense small object detection via multi-scale fusion and context information enhancement
Zhou, H., Cao, X., Sun, K., Wu, T., & Deng, B. (2025) · The Journal of Supercomputing · doi:10.1007/s11227-025-07444-y · Cited by 12
“Representative algorithms include SSD [4], YOLO series [5–7], and RetinaNet [8].”
Xu, Y., Wu, H., Liu, Y., et al. (2025) · Sensors · doi:10.3390/s25113550 · Cited by 9
“The single-stage target detection algorithm is dominated by the YOLO algorithm [12], which does not need to produce pre-selected regions but directs the localization and classification of target objects.”
Su, X. W., Peng, X., Zhou, X., Cao, H., Shan, C., Li, S., Qiao, S., & Shi, F. (2025) · Photonics · doi:10.3390/photonics12060599 · Cited by 9
CGDU-DETR: An End-to-End Detection Model for Ship Detection in Day–Night Transition Environments
Wu, W., Fan, X., Hu, Z., & Zhao, Y. (2025) · Journal of Marine Science and Engineering · doi:10.3390/jmse13061155 · Cited by 11
Zhao, X., Yuan, Q., & Xu, J. (2025) · International Journal of Digital Earth · doi:10.1080/17538947.2025.2510568 · Cited by 7
“The development of deep convolutional neural networks (DCNN) provides a direction for underwater target detection (Redmon et al. 2016).”
Essien, E., & Frimpong, S. (2025) · Drones · doi:10.3390/drones9060433 · Cited by 18
Yin, Y., Yang, Z., Shi, H., Meng, F., & Li, W. (2025) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2025.3580747 · Cited by 11
A deep learning based approach for classifying the maturity of cashew apples
Winklmair, M., Sekulic, R., Kraus, J., Penava, P., & Buettner, R. (2025) · PLoS ONE · doi:10.1371/journal.pone.0326103 · Cited by 13
“Future research could explore approaches such as You Only Look Once for this purpose [97].”
Food Waste Detection in Canteen Plates Using YOLOv11
Ferreira, J., Cerqueira, P., & Ribeiro, J. (2025) · Applied Sciences · doi:10.3390/app15137137 · Cited by 11
Precision classification for anomaly detection in photovoltaic cells via optimal transport theory
Kang, N. B., Hu, W., Wang, D., & Xu, R. (2025) · Solar Energy · doi:10.1016/j.solener.2025.113704 · Cited by 9
Accurate segmentation of localized corrosion in structural alloys via deep learning
Zhao, L., Locke, J., Xu, F., Yao, T., & Guo, X. (2025) · npj Materials Degradation · doi:10.1038/s41529-025-00633-3 · Cited by 14
“Classical methods such as U-Net based architectures 17 , You Only Look Once (YOLO) series 18 , Mask Regional Convolutional Neural Network (Mask R-CNN) 19 , and the Detection TRansformer (DETR) 20 series are widely used, especially for segmentation tasks involving natural and medical objects.”
Dual-branch wavelet-CNN architecture for enhanced small ship detection
Zhou, W., Xu, B., & Wu, H. (2025) · Ocean Engineering · doi:10.1016/j.oceaneng.2025.121967 · Cited by 10
Artificial intelligence-enabled defect detection method and engineering application of ceramic mug
Mao, W., Wu, H., Xie, S., et al. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.111648 · Cited by 8
Low resolution remote sensing object detection with fine grained enhancement and swin transformer
Xu, Z., Wang, X., Huang, K., & Chen, R. (2025) · Scientific Reports · doi:10.1038/s41598-025-10286-6 · Cited by 12
Improved RT-DETR Framework for Railway Obstacle Detection
Li, P., Peng, Y., Wang, S.-M., & Zhong, C. M. (2025) · IEEE Access · doi:10.1109/access.2025.3589159 · Cited by 11
Can YOLO Detect Retinal Pathologies? A Step Towards Automated OCT Analysis
Ardelean, A.-I., Ardelean, E.-R., & Marginean, A. N. (2025) · Diagnostics · doi:10.3390/diagnostics15141823 · Cited by 11
“Among the vast expanse of approaches, the “You Only Look Once” (YOLO) [9] family of models has perhaps received the most attention, with many variations and versions having been developed in the last few years.”
YOLOv8-DBW: An Improved YOLOv8-Based Algorithm for Maize Leaf Diseases and Pests Detection
Gan, X., Cao, S., Wang, J., Wang, Y., & Hou, X. (2025) · Sensors · doi:10.3390/s25154529 · Cited by 10
“Another category is the single-stage detection algorithms represented by SSD [22] and the YOLO series [23], which do not require the generation of candidate regions and have a significant advantage in detection speed [24].”
Tian, B., Lu, Z., Zhang, C., Li, H., & Yu, P. (2025) · Infrared Physics & Technology · doi:10.1016/j.infrared.2025.106011 · Cited by 11
Sun, Y., & Lian, J. (2025) · Remote Sensing · doi:10.3390/rs17152643 · Cited by 16
LRFL-YOLO: A Large Receptive Field and Lightweight Model for Small Object Detection
Yan, Y., Wang, C., Zhou, X., Gao, X., & Qin, Z. (2025) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2025.3595197 · Cited by 13
Gao, K. D., Chen, L., Li, Z., & Wu, Z. (2025) · Buildings · doi:10.3390/buildings15152675 · Cited by 10
Su, B., Zhu, Y., & Lin, Y. (2025) · Journal of Plant Diseases and Protection · doi:10.1007/s41348-025-01134-w · Cited by 10
“The first YOLO (Redmon et al. 2016) paper, published in 2016, became the most advanced single-stage object detection technology at that time.”
Naouadir, I., Ogri, O. E., El-Mekkaoui, J., et al. (2025) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2025.108474 · Cited by 8
Balasubramanian, B., & Çetin, K. (2025) · Sensors · doi:10.3390/s25154824 · Cited by 13
FCMI-YOLO: An efficient deep learning-based algorithm for real-time fire detection on edge devices
Lu, J., Zheng, Y., Guan, L., Lin, B., Shi, W., Zhang, J., & Wu, Y. (2025) · PLoS ONE · doi:10.1371/journal.pone.0329555 · Cited by 15
“In contrast, one-stage detection algorithms, such as YOLO [29] and SSD [30], simplify the detection pipeline by performing target classification and bounding box regression directly on the image, bypassing redundant steps like region proposal generation and classification optimization.”
Vision-Guided Maritime UAV Rescue System with Optimized GPS Path Planning and Dual-Target Tracking
Wang, S., Zhao, Y., Zhou, C., et al. (2025) · Drones · doi:10.3390/drones9070502 · Cited by 8
Hou, F., Zhang, Y., Dong, J. L., et al. (2025) · Remote Sensing · doi:10.3390/rs17162791 · Cited by 8
Guo, T., Peng, Y., Han, L., Jia, T., Zhang, C., Liu, W., Yang, Q., Huang, H., & Hu, D. (2025) · Industrial Crops and Products · doi:10.1016/j.indcrop.2025.121716 · Cited by 10
Parekh, A., & Bauer, M. (2025) · Communications in computer and information science · doi:10.1007/978-3-031-94962-3_3 · Cited by 8
Chen, X., Fu, M., Shao, J., et al. (2025) · Petroleum Science · doi:10.1016/j.petsci.2025.08.013 · Cited by 8
DDR-YOLO: An Efficient Detection Model Based on YOLO11s for Steel Surface Defect
Ren, X., Liu, Z., Cheng, H., & Chen, L. (2025) · IEEE Access · doi:10.1109/access.2025.3599978 · Cited by 12
Lightweight SCL-YOLOv8: A High-Performance Model for Transmission Line Foreign Object Detection
Ji, H., Chen, X., Bai, J., & Gong, C. (2025) · Sensors · doi:10.3390/s25165147 · Cited by 12
“These include region-based CNN [20] and YOLO series algorithms [21].”
Ma, S., Wang, Y., Wei, Y. J., Zhang, E., Fan, J., Sun, X., & Chen, P. (2025) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2025.3600435 · Cited by 24
Madadum, H., Nasir, F. E., & Haruehansapong, K. (2025) · Smart Agricultural Technology · doi:10.1016/j.atech.2025.101326 · Cited by 15
Multimodal Sensing for Intelligent V2X: A Review of Recent Advances Toward Deployment
Tan, K., & Zhu, C. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3601236 · Cited by 22
“Building upon LSTM, Region-based CNN [110], and YOLO [111], their proposed Authorized licensed use limited to the terms of the applicable license agreement with IEEE.”
Sanatbyek, A., Rakhimzhanova, T., Nurmanova, B., Omarova, Z., Rakhmankulova, A. M., Orazbayev, R., Varol, H. A., & Chan, M. (2025) · IEEE Access · doi:10.1109/access.2025.3603287 · Cited by 13
Perez, J., & Fusco, G. M. (2025) · Geomatica · doi:10.1016/j.geomat.2025.100063 · Cited by 26
“These studies typically relied on convolutional neural networks (CNNs) and object detectors such as R-CNN [14] or YOLO [15], trained on extensive labeled corpora via supervised or semi-supervised learning.”
Visual Instruction Tuning towards General-Purpose Multimodal Large Language Model: A Survey
Huang, J., Zhang, J., Jiang, K. Y., Qiu, H., Zhang, X., Shao, L., Lu, S., & Tao, D. (2025) · International Journal of Computer Vision · doi:10.1007/s11263-025-02572-7 · Cited by 64
An Efficient Object Detection Model Based on NanoDet
Hoang, V.-T., Phuong, T. M., Nguyen, H.-P., et al. (2025) · International Workshop on Intelligent Systems (IWIS) · doi:10.1109/iwis66215.2025.11142424 · Cited by 8
“Anchor-based detectors such as Faster R-CNN [12], YOLO [11], and SSD [8] have traditionally dominated the field, using predefined anchor boxes to propose object regions for refinement and classification.”
Intelligent Parking Guidance System Using Computer Vision, IoT, and Edge Computing
Rajesh, P., Kallakuri, D., Chagarlamudi, S., Vissavajhula, S. M., Meng, J., & Zhao, J. (2025) · IEEE Open Journal of Intelligent Transportation Systems · doi:10.1109/ojits.2025.3605318 · Cited by 9
LSAR-Det: A Lightweight YOLOv11-Based Model for Ship Detection in SAR Images
Zhang, P., Jiang, Y. F., & Xinguo, Z. (2025) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2025.3605993 · Cited by 8
LCW-YOLO: An Explainable Computer Vision Model for Small Object Detection in Drone Images
Liao, D., Bi, R., Zheng, Y., Hua, C., Huang, L., Tian, X., & Liao, B. (2025) · Applied Sciences · doi:10.3390/app15179730 · Cited by 10
Li, H., Yin, Z., Zuo, Z., et al. (2025) · Frontiers in Plant Science · doi:10.3389/fpls.2025.1655093 · Cited by 8
Li, T., Bian, Z., Lei, H., Zuo, F., Yang, Y.-T. C., Zhu, Q., Li, Z., Chen, Z., & Özbay, K. M. A. (2025) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2025.3604569 · Cited by 28
“…service utilizes multiple Pan-Tilt Cameras (PTCs) positioned at various intersections to collect tra ffi c flow data, applying established video extraction technologies like multiple-object-detection (MOD) [18] and tracking [19], [20] to derive real-time tra ffi c metrics such as volume and speed.”
Dist-Tracker: A Small Object-Aware Detector and Tracker for UAV Tracking
Wang, W., Fu, J., Song, J., Li, K., Qiao, H., Jiang, L., Sun, H. S., & Cao, X. (2025) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw67362.2025.00657 · Cited by 15
“YOLOv1 [21] pioneered grid-based regression for unified localization and classification, achieving 45 FPS but struggling with small targets.”
Automated detection system of metro tunnel lining crack using dynamic snake convolution
Pan, Z., Zhang, X., Li, B., et al. (2025) · Computer-Aided Civil and Infrastructure Engineering · doi:10.1111/mice.70065 · Cited by 8
Industrial surface defect detection using hybrid attention mechanism and multiscale feature fusion
Zhou, S., Yang, Z., Ao, S., & Yan, X. (2025) · Measurement · doi:10.1016/j.measurement.2025.119040 · Cited by 14
Li, S., Lin, Z., Shi, Y., Lan, J., & Yu, Z. (2025) · Journal of Real-Time Image Processing · doi:10.1007/s11554-025-01766-z · Cited by 9
“The second type encompasses single-stage detectors, such as the YOLO family [13–15].”
Wang, Y., Zeng, W., Zhao, Z., Li, B., & Quan, Z. (2025) · Applied Soft Computing · doi:10.1016/j.asoc.2025.113849 · Cited by 9
Su, C., Zhu, L., Dai, W., Zhou, J., Wang, J., Mao, Y., & Sun, J. (2025) · ISPRS International Journal of Geo-Information · doi:10.3390/ijgi14090364 · Cited by 10
“In contrast, one-stage models, such as SSD [17] and YOLO [18], achieve comparable accuracy while significantly improving processing speed, thereby enhancing their suitability for real-time detection applications.”
Automated urban flood level detection based on flooded bus dataset using YOLOv8
Qiu, Y., Zhou, X., Wan, J., Yang, T., Zhang, L., Zhong, Y., Shen, L., & Ji, X. (2025) · Natural hazards and earth system sciences · doi:10.5194/nhess-25-3525-2025 · Cited by 13
“In previous studies, cars have commonly been used for flood detection (Puliti and Astrup, 2022; Redmon et al., 2016; Wan et al., 2024; Zhong et al., 2024) .”
Wang, Y., Sun, H., Luo, K., Zhu, Q., Li, H., Sun, Y., Wu, Z., & Wang, G. (2025) · Scientific Reports · doi:10.1038/s41598-025-16619-9 · Cited by 15
“The architecture consists of four primary components: the input module, the feature extraction network, the feature fusion neck, and the output layer 23 .”
Application of YOLO Algorithm for Intelligent Transportation Systems: A Survey and New Perspectives
Lv, X., Chen, T., Song, C., Yang, C., & Ping, T. (2025) · International Journal of Distributed Sensor Networks · doi:10.1155/dsn/2859040 · Cited by 18
Artificial intelligence-based method for detecting wrist fractures in children
Liu, D., Yang, Z., Bao, C., & Meng, Q. (2025) · Scientific Reports · doi:10.1038/s41598-025-22419-y · Cited by 11
Optimization of deep learning-based faster R-CNN network for vehicle detection
Deepak, G. D., & Bhat, S. K. (2025) · Scientific Reports · doi:10.1038/s41598-025-22828-z · Cited by 14
A real-time and efficient detector for small object in UAV aerial images
Tan, L., Zhang, C. G., Bai, H., Liu, Z., & Li, Y. (2025) · Scientific Reports · doi:10.1038/s41598-025-22855-w · Cited by 10
Yao, L., Liu, J., Hong, W., Kong, F., Fan, Z., Lei, L., & Li, X. (2025) · Veterinary Sciences · doi:10.3390/vetsci12111104 · Cited by 10
“Early studies concentrated on static tasks such as quantifying feed intake using RGB-D cameras [17] or detecting dairy cows via customized YOLO-based models like YOLOv5-ASFF, building upon foundational object detection frameworks [4,18–20].”
DLFE-YOLO: an enhanced framework for underwater object detection based on YOLOv8
Lin, Y., Zhang, Y., Yang, D., Zhou, Y., & Wang, L. (2025) · Intelligent Marine Technology and Systems · doi:10.1007/s44295-025-00088-x · Cited by 12
“Among these methods, the YOLO series has gained particular prominence for its balance of accuracy, efficiency, and lightweight design (Redmon et al. 2016).”
YOLO-depth: leveraging depth information for improved instance segmentation in construction scenes
Wang, Q., Yue, H., Li, Z., Huang, G., Liu, R., & Wang, J. (2025) · Advanced Engineering Informatics · doi:10.1016/j.aei.2025.104048 · Cited by 10
A systematic literature review of lightweight YOLO models for object detection
Wang, L., Wang, H., Letchmunan, S., Xiao, R., Ahmed, O. H., & Liu, Z. (2025) · PeerJ Computer Science · doi:10.7717/peerj-cs.3357 · Cited by 20
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.