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 29,601–29,700 of 51,399
Toward Efficient Test Time Adaptation With Hierarchical Distribution Alignment
Liu, Y., Huang, C., Xu, Y. D., et al. (2025) · IEEE Transactions on Image Processing · doi:10.1109/tip.2025.3622340 · Cited by 2
“Many works have achieved success on visual tasks, such as recognition [1], [2], [3], [4], image clustering [5], [6], [7], [8], [9], anomaly detection [10], [11], [12], image segmentation [13], [14], [15], [16], and object detection [17], [18], [19], [20], [21], [22].”
Real-time AI-guided ultrasound localization method for breast tumor rotational resection
Sun, H., Zhu, H., Zhang, M., et al. (2025) · Frontiers in Oncology · doi:10.3389/fonc.2025.1675180 · Cited by 2
Video coding for machines using region-of-interest-based retargeting
Różek, S., Stankiewicz, O., Maćkowiak, S., Grajek, T., Stankowski, J., Wawrzyniak, M., Lorkiewicz, M., Ding, D., Liu, S., & Domański, M. (2025) · EURASIP Journal on Image and Video Processing · doi:10.1186/s13640-025-00682-3 · Cited by 2
“For the default configuration of RoI detection, we have used the same neural networks as in the reference technique [52], i.e., YOLO [54] for object tracking, and Detectron2 (Faster R-CNN) [55] for object tracking.”
An, T. T. V., You, S., Long, L. N. B., Tan, N. D., & Kim, H. (2025) · Alexandria Engineering Journal · doi:10.1016/j.aej.2025.10.023 · Cited by 2
ESOD: Event-Based Small Object Detection
Liang, Q., Lu, J., Li, Q., Liu, S., Zhao, Z., Zhao, Y., Zhang, W., Huang, K., & Tian, Y. (2025) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3746027.3755486 · Cited by 3
“Currently, image-based detection methods can be broadly categorized into three main types: the two-stage RCNN series [22, 24, 47], the one-stage YOLO series [2, 28, 30, 46, 50], and the end-to-end DETR series [5, 9, 60, 61, 67].”
A Deep Learning Model for Automated Quantification of DNA Repair Foci in Somatic Mammalian Cells
Shadmehri, S., Bezhanyan, T., Bondarev, M., Streltsova, O., Zuev, M. I., Chigasova, A. K., Osipov, A., Vorobyeva, N. Y., & Osipov, A. N. (2025) · Physics of Particles and Nuclei · doi:10.1134/s1063779625700984 · Cited by 2
“In 2016, Joseph Redmon and his colleagues introduced a powerful object detection model called YOLO (You Only Look Once) [20].”
UAVs detect hazards with multi-directional Mamba on overhead transmission lines
Xu, C., Zheng, C.-H., & Zhang, J. (2025) · Scientific Reports · doi:10.1038/s41598-025-21243-8 · Cited by 2
Hou, Z., Zhao, J., Li, X., Ma, S., Yang, X., & Pu, L. (2025) · Infrared Physics & Technology · doi:10.1016/j.infrared.2025.106232 · Cited by 4
Hazediff: A training-free diffusion-based image dehazing method with pixel-level feature injection
Lin, X., Li, Z., Huang, D., Feng, W., An, X., Sun, L., Yu, N., Li, Y., & Leng, C. (2025) · PLoS ONE · doi:10.1371/journal.pone.0329759 · Cited by 3
“In 4.3.3, to further verify the effectiveness and applicability of the proposed method in the real world, we compare the mean Average Precision (mAP) obtained from YOLO [34] detection on the dehazed RTTS hazy dataset with other related works in hazy weather object detection.”
InfluentialShah, V., & Patel, H. J. (2025) · Augmented Human Research · doi:10.1007/s41133-025-00086-y · Cited by 3
“Recent critiques have pointed out that the lack of such a unifying perspective frequently causes literature evaluations to appear fragmented [63, 65].”
InfluentialRaza, N., Razzaq, A., Noman, W., et al. (2025) · International Conference on Communication, Computing and Digital Systems (C-CODE) · doi:10.1109/c-code67372.2025.11204143 · Cited by 2
“Because YOLO’s detection happens all at once, it can be used immediately for [5] applications that require fast reactions, including self-driving cars and watching busy roads [7].”
Antonya, C., Țârulescu, R., Țârulescu, S., & Butnariu, S. (2025) · Vehicles · doi:10.3390/vehicles7040125 · Cited by 2
Wang, Q., Geng, X., Li, P., Zhang, L., Niu, B., Wang, F., Zhou, G., & Hu, Y. (2025) · Remote Sensing · doi:10.3390/rs17213577 · Cited by 3
Zhang, Y., Liu, F., Lyu, J., et al. (2025) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme59968.2025.11210086 · Cited by 2
“…through a region proposal network; SSD [12] enhances multi-object detection capabilities using a multi-scale feature pyramid; the YOLO series [13]–[17] significantly improves detection speed with its single-stage framework; and RT-DETR [18], leveraging a self-attention mechanism, captures…”
Deep learning for extraneous material detection in a rice processing factory
Chuang, P., Cheng, M.-H., Chi, C.-H., & Ku, H. (2025) · Food Control · doi:10.1016/j.foodcont.2025.111804 · Cited by 6
Slitless Spectroscopy Source Detection Using YOLO Deep Neural Network
Chen, X., Lam, M. I., Zhou, Y., Gu, H., Lai, J., Fan, Z., Li, J., Zhang, X., & Tian, H. (2025) · Publications of the Astronomical Society of the Pacific · doi:10.1088/1538-3873/ae1256 · Cited by 2
Wang, X., Lin, C., Pan, Y., & Wang, R. (2025) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2025.3628010 · Cited by 7
“The YOLO [3] series, a representative of single-stage algorithms, has evolved to version 11, performing end-to-end training for object classification and bounding box regression.”
Wang, D.-L., Huang, Z., Peng, L., et al. (2026) · IEEE Journal of Photovoltaics · doi:10.1109/jphotov.2025.3619980 · Cited by 1
“At the same time, the development of lightweight models, such as the YOLO series [29], DETR [30], and RTDETR [31], meets the demands for real-time detection and resource-constrained environments.”
Smart IoT and AI-Driven Physical Harassment Detection System for Enhanced Personal Safety
Murali, S., Anchitaalagammai, J. V., Kavitha, S., et al. (2025) · doi:10.1109/iccds64403.2025.11209686 · Cited by 2
Cheating recognition in examination halls based on improved YOLOv8
Xu, E., Lu, J., Xu, S., & Wang, J. (2025) · Discover Computing · doi:10.1007/s10791-025-09747-3 · Cited by 7
“Our proposed solution integrates an optimized version of the YOLOv8 [8] object detection algorithm with multilayer perceptron (MLP) [9] enhancements and a deep learning framework based on ResNet.”
DCSDNet: A Dual-Stream Cooperative Sensing Detection Network for Infrared Small Targets
Zhou, L., Xie, Y., Zhang, G., Yang, J., Liu, C., & Liu, Y. (2025) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2025.3628933 · Cited by 2
Performance Analysis of Filter Pruning Methods for Edge Classification Tasks
Stefanidou, A., Kontopoulos, I., Tserpes, K., et al. (2025) · doi:10.1109/mobilecloud66020.2025.00012 · Cited by 2
“Deeper architectures have led to significant improvements in automated diagnostics [2], dynamic object detection [3], and real-time facial recognition [4].”
Deep blueprint: A literature review and guide to automated image classification for ecologists
Game, C. A., Piechaud, N., & Howell, K. L. (2026) · Journal of Animal Ecology · doi:10.1111/1365-2656.70271 · Cited by 3
“This performs an important function in object detec - tion (Redmon et al., 2016 ), which, in one step (1) localises, ideally all, individuals of your target species (or class) by regressing a box around the boundary of each individual (i.e. predicting the box cen - tre ( x , y ) , width, and…”
InfluentialZhang, Z., Wang, Y., Chai, S., & Tian, Y. (2025) · Plants · doi:10.3390/plants14213378 · Cited by 5
Research on automatic detection and segmentation of prostate zones based on YOLO-D
Wang, X., Feng, R., Chen, X., Wang, C. C., Wang, W., Gao, C., & Tan, Y. (2025) · Technology and Health Care · doi:10.1177/09287329251392399 · Cited by 2
Rotiferometer: An automated system for quantification of rotifer cultures
Diouf, A., Bereziat, L., Nodier, D., et al. (2025) · Aquacultural Engineering · doi:10.1016/j.aquaeng.2025.102662 · Cited by 2
Wang, H., Wang, Y., & Chen, T. (2025) · Applied Sciences · doi:10.3390/app152111838 · Cited by 3
“The YOLO [5] is particularly well-suited for such tasks due to its compact architecture and computational efficiency, which align with the essential requirements for real-time object counting [6].”
mmTracking: A DL-Based mmWave RADAR Data Processing Algorithm for Indoor People Tracking
Raimondi, M., Ciattaglia, G., Nocera, A., Gardano, M., Senigagliesi, L., Spinsante, S., & Gambi, E. (2025) · IEEE Sensors Journal · doi:10.1109/jsen.2025.3628185 · Cited by 2
“YOLO is a NN that performs object detection in a single image pass [47], [48], [49].”
Privacy-Preserving Approaches in Smart Surveillance Systems Using the YOLO Algorithm
Srivastava, Y. Y. (2025) · Journal of Interdisciplinary Knowledge · doi:10.37497/jik.v8iknowledge.1633 · Cited by 2
Huang, W., Dong, C., Liu, X., Li, Y., Zhai, Y., Ou, K., & Quan, H. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.113016 · Cited by 2
Blueberry regional ripeness detection based on an improved YOLOv7tiny model
Li, J., He, J., Wang, C., Tan, S., & Zhao, J. (2025) · Journal of Food Measurement & Characterization · doi:10.1007/s11694-025-03734-4 · Cited by 2
Sha, P., Lu, S., Xu, Z., Yu, J., Li, L., Zou, Y., & Zhao, L. (2025) · Journal of Marine Science and Engineering · doi:10.3390/jmse13112124 · Cited by 3
“Building upon these design principles, YOLOv1 [22] was introduced, achieving the fastest inference speed of its time.”
Corner Sparse R-CNN for Pedestrian Detection in Dense Scenes
Wang, J., Wu, C., Wan, L., Zhang, X., & Liu, S. (2025) · Applied Intelligence · doi:10.1007/s10489-025-06984-3 · Cited by 2
Smith, E., Wagman, J., Barnes, C. M., Rees, P. C. T., & Johnson, G. E. (2025) · Mutagenesis · doi:10.1093/mutage/geaf026 · Cited by 2
“…region proposals and then classifying them, which, while more computationally demanding, can offer higher accuracy in object localization [31], while YOLO is renowned for its real-time processing abilities, treating detection as a single regression problem allowing for instant analysis [32].”
The Drone-vs-Bird Detection Grand Challenge at IJCNN 2025
Coluccia, A., Fascista, A., Dimou, A., et al. (2025) · doi:10.1109/ijcnn64981.2025.11228314 · Cited by 2
Miglionico, G. C., Di Rienzo, F., Ducange, P., Marcelloni, F., & Vallati, C. (2025) · 2025 International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11227764 · Cited by 2
“YOLOv1[9] was the first Convolutional Neural Network (CNN)-based system for real-time object detection.”
Artificial Intelligence for Critical Infrastructure Systems: Past, Present and Future
Pillay, N., Nyathi, T., & Venayagamoorthy, G. K. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11229347 · Cited by 4
“CNNs also form the foundation of the You Only Look Once (YOLO) architecture [26], optimised for object detection.”
Šoberl, D., Kalin, J., Anžlin, A., Kreslin, M., Pucihar, K. Č., Kljun, M., Hekič, D., & Žnidarič, A. (2025) · Computer-Aided Civil and Infrastructure Engineering · doi:10.1111/mice.70144 · Cited by 4
“This can be accomplished using the YOLO (You Only Look Once) object detection and segmentation model (Redmon et al., 2016).”
An Enhanced DETR Network for Sonar Image Object Detection
Yang, S., Zhang, X., Tan, P., Liu, Y., & Du, X. (2025) · IEEE Journal of Oceanic Engineering · doi:10.1109/joe.2025.3573793 · Cited by 2
“CNN-based detectors can also be divided into one-stage detectors, represented by SSD, RetinaNet, and the YOLO series [9], [10], [20], [21], [22], [23], and two-stage detectors, represented bytheR-CNNseries[12],[24],[25],[26],[27].”
Defenses Against Adversarial Attacks on Object Detection: Methods and Future Directions
Thunuguntla, A., Tadepalli, P. V., & Raffa, G. (2025) · Information · doi:10.3390/info16111003 · Cited by 7
Zhang, X., Yu, X., Feng, J., Chen, W., & Li, Y. (2025) · Science Progress · doi:10.1177/00368504251395116 · Cited by 4
“One-stage detectors, notably the You Only Look Once (YOLO) series 10 – 12 and Single-Shot MultiBox Detector (SSD), 13 offer faster inference by directly regressing object coordinates and classes from dense prediction maps.”
Li, J., Long, H., Liu, M., Huang, Y., & Bao, N. (2025) · Scientific Reports · doi:10.1038/s41598-025-24225-y · Cited by 5
“The YOLO series 10–21 has gained attention for its real-time performance and efficiency.”
Zhang, H., Ai, H., Liu, D., Mei, C., Wang, H., & Zhang, W. (2025) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2025.3634774 · Cited by 4
Bird detection method for transmission line based on improved YOLOv8 algorithm
Fu, S., Liu, S., An, B., Hu, C., Zhang, Z., She, Y., & Wang, A. (2025) · International Conference on Energy and Electrical Power Systems (ICEEPS) · doi:10.1109/iceeps66790.2025.11239665 · Cited by 2
“…with other similar YOLO series algorithms as well as Fully Convolutional One Stage (FCOS) target detection algorithm [17], Faster Region Convolutional Neural Network ( Faster Region Convolutional Neural Network, Faster RCNN) [18] for training and the results of the test are shown in Table 2.”
Wang, C., Yi, Q., Ye, J., Xu, X., Ashraf, F., Ashraf, S. Q., Dearn, K. D., & Hajiyavand, A. M. (2025) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2025.109158 · Cited by 4
IE‐YOLO: An Information‐Enhanced Small Target Detection Model for Remote Sensing Images
Yun, H., Han, Z., Du, Q., Li, M., Yang, L., Liu, X., Wang, C., & Ma, W. (2025) · IET Image Processing · doi:10.1049/ipr2.70250 · Cited by 2
Rahi, A., Wasfy, H. M., Wasfy, T. M., & Anwar, S. (2025) · Automation · doi:10.3390/automation6040077 · Cited by 3
“Around the same time, YOLO (You Only Look Once) [2] was proposed as a fast and accurate single-stage method for object detection.”
Marine Obstacles Multi-Modal Detection, Classification and Tracking via Camera-LiDAR Late Fusion
Ponzini, F., & Martelli, M. (2025) · IEEE International Workshop on Metrology for the Sea; Learning to Measure Sea Health Parameters (MetroSea) · doi:10.1109/metrosea66681.2025.11245686 · Cited by 2
“To perform one-shot detection and classification on the RGB image, a CNN-based detector YOLOv8 [14] is employed.”
Synthetic Dataset and Enhanced YOLOv11 for Robust Financial Document Layout Analysis
Qiao, M., Li, L., Chu, X., Shang, Z., Zhang, W., & Luo, Z. (2025) · International Conference on Artificial Intelligence and Digital Finance (AIDF) · doi:10.1145/3764727.3764745 · Cited by 2
“On the other hand, detection methods [19-21] are highly recommended due to their advantages in model inference speed.”
Visual SLAM algorithm based on dynamic attribute recognition in dynamic scenes
Xiong, J., Fan, L., Yang, D., Xiong, P., Lu, J., & Zhong, W. (2025) · Mechatronics · doi:10.1016/j.mechatronics.2025.103427 · Cited by 3
Research on an industrial liquid level detection method based on an improved SSD
Qi, X., & Jia, L. (2025) · Scientific Reports · doi:10.1038/s41598-025-29277-8 · Cited by 2
A feature cascade and recursive fusion architecture for traffic sign detection in vehicle perception
Liu, X., Wang, X., Li, F., Duan, X., Yin, S., & Tang, R. (2025) · Scientific Reports · doi:10.1038/s41598-025-25945-x · Cited by 5
Zhang, R., Song, Y., Zhang, R., Yang, L., Cheng, H., & Zhong, J. (2025) · Electronics · doi:10.3390/electronics14234620 · Cited by 2
Bonković, M., Uvodić, O., Cecić, M., & Skelin, A. K. (2025) · International Conference on Software, Telecommunications and Computer Networks (SoftCOM) · doi:10.23919/softcom66362.2025.11197339 · Cited by 3
“Among available models, the YOLO (You Only Look Once) family stands out for its balance of speed and accuracy, particularly in real-time and resource-constrained agricultural settings [1, 2].”
DA-RTDETR: domain-adaptive RT-DETR with feature fusion and category-level constraints
Geng, H., Wang, Y. J., Liu, Z., Fang, L., & Fan, Z. (2025) · Complex & Intelligent Systems · doi:10.1007/s40747-025-02134-x · Cited by 3
“The one-stage detector, such as YOLO [5], directly predicts an object’s category and bounding box by sliding a fixed-size window across the image, eliminating the need for ROI pooling.”
Saeheaw, T. (2025) · Buildings · doi:10.3390/buildings15234274 · Cited by 5
Zade, F. A., & Ebrahimkhanlou, A. (2025) · Journal of Computing in Civil Engineering · doi:10.1061/jccee5.cpeng-7001 · Cited by 13
Inoue, S., Kawaharazuka, K., Yoneda, K., et al. (2025) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros60139.2025.11247141 · Cited by 2
“First, YOLO [12] (YOLO11) is used to obtain bounding boxes for potential wire attachment locations from the RGB image captured by CubiX’s camera (Fig.”
VaLID: Verification as Late Integration of Detections for LiDAR-Camera Fusion
Vats, V., Nizam, M. B., & Davis, J. (2025) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros60139.2025.11246472 · Cited by 6
Real-Time PCB Defect Detection Using YOLOv8
Bind, S. K., & Nishant (2025) · International Conference on Reliability, Infocom Technologies and Optimization (Trends and Future Directions) (ICRITO) · doi:10.1109/icrito66076.2025.11241378 · Cited by 2
“While region-based CNN frameworks [5] attained 88% mean accuracy on standardized datasets and Yang’s R-CNN adaptation [8] demonstrated exceptional performance on trace defects, these systems demanded GPU workstations exceeding the computational resources of many small-to-medium manufacturers.”
InfluentialMulti-object sperm detection and tracking based on enhanced YOLOv4 and improved DeepSORT
Pei, J., Yang, Z., Zhao, Y., Tian, M., Zeng, N., Kang, X., Wu, J., & Yang, X. (2025) · Scientific Reports · doi:10.1038/s41598-025-26465-4 · Cited by 3
“The You Only Look Once (YOLO) algorithms has gained popularity due to its real-time performance and efficiency 8,9 .”
Li, Z., Guo, B., & Mu, D. (2025) · Electronics · doi:10.3390/electronics14234689 · Cited by 2
Wu, Z., Ge, X., Zhang, Z., et al. (2025) · Mobile Networks and Applications · doi:10.1007/s11036-025-02488-z · Cited by 2
ACS-YOLO: a lightweight bearing surface defect detection algorithm
Ding, L., Xu, H. M., Du, P., et al. (2025) · Journal of Engineering and Applied Science · doi:10.1186/s44147-025-00818-2 · Cited by 2
Chen, J., Mei, S., Ren, Z., Tang, L., Xu, B., Fu, G., Du, X., & Ivanov, S. (2025) · Journal of King Saud University - Computer and Information Sciences · doi:10.1007/s44443-025-00376-w · Cited by 8
“…two categories: (1) Two-Stage Detector: Represented by the R-CNN family (including R-CNN, Fast R-CNN (Girshick 2015), and Faster R-CNN (Ren et al. 2016 (Liu et al. 2016) and You Only Look Once (YOLO) algorithm series (Jegham et al. 2024), this approach directly fore-casts the category and…”
MODNet: A Monocular Object-Based Depth Estimation Network for AI Robotic Chemists
Fu, X., Cheng, X., Chen, Y., Wang, H., Dong, L., Ge, X., Wang, Y., Wei, Y., & Xie, L. (2025) · Precision Chemistry · doi:10.1021/prechem.5c00088 · Cited by 2
Research on coal gangue detect method based on multi-feature fusion of AHM-YOLO model
Ge, Y., Zhao, W., Xie, X., et al. (2025) · International Journal of Coal Preparation and Utilization · doi:10.1080/19392699.2025.2596808 · Cited by 2
Zhong, Y., Wan, J., Cao, M., et al. (2025) · Scientific Reports · doi:10.1038/s41598-025-31043-9 · Cited by 2
“Among detection architectures, single-stage models like YOLO (You Only Look Once) 25 series are ideal for the task.”
Real-Time Chinese Sign Language Recognition Based on Convolutional Neural Network
Tian, Y., Dong, Y., Ahmed, M., Shah, S. O., & Alabdulkreem, E. A. (2025) · International Journal of Humanoid Robotics · doi:10.1142/s0219843625400225 · Cited by 2
Le, V. T., Song, H., Narman, H. S., Zhu, P., Alzarrad, A., Cisko, A. R., & Beasley, J. (2025) · IEEE Access · doi:10.1109/access.2025.3641797 · Cited by 2
Research methods for digitalization of transport systems using artificial intelligence
Podberezkin, A. A., Ostroukh, A. V., Borzenkov, A. M., Shmonin, A. M., & Pronin, C. B. (2025) · Transportation and Information Technologies in Russia · doi:10.12731/3033-5965-2025-15-3-396 · Cited by 2
MRA-YOLOv8: A Transmission Line Fault Detection Algorithm Integrating Multi-Scale Feature Fusion
Hao, S., Li, J., & Ma, X. (2025) · Sensors · doi:10.3390/s25247508 · Cited by 3
Infrared target detection model based on global edge feature extraction
Da, M., Shen, Y., Jiang, L., Hu, J., & Zhang, Z. (2025) · Infrared Physics & Technology · doi:10.1016/j.infrared.2025.106313 · Cited by 3
SFDN: A Novel Semantic Feature Decouple Network for Fine-Grained Remote Sensing Object Detection
Yang, X., Zhou, Z., & Yang, D. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2025.3642640 · Cited by 3
Jingnan, 赵. Z., Yang, 刘. L., Xueqiong, 白. B., & Yong, 吕. L. (2025) · Infrared and Laser Engineering · doi:10.3788/irla20250312 · Cited by 2
LIST-DETR:复杂背景下红外小目标检测的高效轻量级检测网络
Shang, 张. Z., Yujie, 崔. C., Guoqiang, 龚. G., et al. (2025) · Infrared and Laser Engineering · doi:10.3788/irla20250271 · Cited by 2
Application of an artificial intelligence-based airway identification system in tracheal intubation
Liu, H., Yang, X., Duan, L., Liu, K., Wu, P., Wang, X., Tang, H., & Wang, Z. (2025) · BMC Anesthesiology · doi:10.1186/s12871-025-03504-1 · Cited by 2
“This allocation strategy optimizes model learning capacity while maintaining evaluation reliability, consistent with established machine learning practices [34].”
Yaseen, A., Poggi, G., Vascon, S., et al. (2025) · Remote Sensing · doi:10.3390/rs17244014 · Cited by 2
Deep learning for sorghum yield forecasting using uncrewed aerial systems and lab-derived imagery
Bari, M. A. A., Bakshi, A., Choton, J. C., Pramanik, S., Witt, T. D., Caragea, D., Bean, S. R., Jagadish, S. V. K., & Felderhoff, T. J. (2025) · Plant Phenomics · doi:10.1016/j.plaphe.2025.100133 · Cited by 2
“Also, Non-Maximum Suppression (NMS) was applied to refine predictions to eliminate redundant bounding boxes, ensuring the most probable detections [34].”
Offline Proctoring Using YOLOv8 and VGG-16
Benny, A. R., George, J., Johny, J., et al. (2025) · doi:10.1109/aicdmb64359.2025.11277919 · Cited by 2
Monkam, P., Wang, X., Liu, S., Qian, W., Yao, Y., Shi, X., & Qi, S. (2025) · Annals of Biomedical Engineering · doi:10.1007/s10439-025-03944-3 · Cited by 6
Deng, Z., Mei, X., Qiu, Z., Huang, X., & Qiu, Z. (2025) · Applied Sciences · doi:10.3390/app152413239 · Cited by 5
“First proposed by Joseph Redmon et al. [24], YOLO was a groundbreaking contribution to object detection, introducing a real-time, end-to-end detection model.”
$\ell _{0}$ℓ0-Regularized Sparse Coding-Based Interpretable Network for Multi-Modal Image Fusion
Panda, G., Kundu, S., Bhattacharya, S., & Routray, A. (2025) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2025.3643898 · Cited by 8
Kim, J., Gong, Y., Chi, S., Kim, J. I., & Seo, J. (2025) · Advanced Engineering Informatics · doi:10.1016/j.aei.2025.104245 · Cited by 6
Enhancing vehicle-mountable multiple object tracking systems with embeddable Ising machines
Tatsumura, K., Hamakawa, Y., Yamasaki, M., Oya, K., & Fujimoto, H. (2025) · Nature Communications · doi:10.1038/s41467-025-67282-7 · Cited by 6
Fu, J., Zhang, Z., Peng, T., Hu, X., & Zhang, J. (2025) · Sensors · doi:10.3390/s26010023 · Cited by 2
“Due to the fast and efficient characteristics of the YOLO [24] series detectors, many studies [25–27] have explored their application in the field of defect detection.”
Placitelli, A. P., Hochscheid, S., Maffucci, F., Rees, A. F., Treglia, G., & Staiano, A. (2025) · Ecological Informatics · doi:10.1016/j.ecoinf.2025.103569 · Cited by 3
Multi-Directional Shifted Patch Encoding With Transformers for Non-Invasive Cattle Identification
Kumar, N., & Singh, S. K. (2025) · IEEE Transactions on Biometrics Behavior and Identity Science · doi:10.1109/tbiom.2025.3599374 · Cited by 2
“Accurately identifying and extracting the muzzle region plays a vital role in verifying cattle identity, a task well-suited to modern object detection techniques such as the YOLO family of algorithms [43], [44].”
Harnessing Temporal Awareness: Dual-CNN Model for Non-Intrusive Load Monitoring
Wu, H., 業春, 阮., & Huang, Q. (2025) · IEEE Transactions on Green Communications and Networking · doi:10.1109/tgcn.2025.3609569 · Cited by 2
STC-Net: Combining a Swin Transformer With a CNN for Micro-Doppler Curve Separation
Chang, W., Chen, D., Han, J., et al. (2025) · IEEE Transactions on Aerospace and Electronic Systems · doi:10.1109/taes.2025.3617026 · Cited by 2
“CNN-based architectures, such as the mask region-based CNN [30] and you only look once (YOLO) [31], have achieved notable successes in terms of handling complex scenarios.”
Legend-Informed Symbol Recognition in Engineering Diagrams with Self-supervised Learning
Hain, A., Gölzhäuser, S., Réhault, N., et al. (2025) · Lecture notes in computer science · doi:10.1007/978-3-662-72243-5_23 · Cited by 2
NarAdv: Natural-Style Physical Adversarial Attack on Traffic Sign Detection for Autonomous Vehicles
Xu, Y., Xie, F., Lyu, C., Liu, J., Ji, Y., & Shiratori, N. (2025) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2025.3626196 · Cited by 3
“2) Dataset Setup: To train the ODS based on YOLOv5 [41], [42], we utilize the TT100 K dataset [43], published by the TsinghuaUniversity-Tencent Joint Laboratory.”
SDWS-YOLO: A Lightweight Small Object Detection Model for Aerial Remote Sensing Images
Bi, J., Zheng, X., Li, K., Zhang, H., Zhang, G., & Leí, T. (2025) · IEEE Signal Processing Letters · doi:10.1109/lsp.2025.3628795 · Cited by 4
Zhao, P., Wu, L., Yue, T., Zhao, X., Zhou, J., Xue, D., Huang, J., Yang, Z., & Chang, L. (2025) · IEEE Transactions on Circuits and Systems I Regular Papers · doi:10.1109/tcsi.2025.3635899 · Cited by 3
“Therefore, conventional neural networks for image processing, e.g., the Yolo series [1], [2], do not apply to point clouds.”
Franco-Alucano, I., Tortorella, G. L., Aguilar-Duque, J., Flores, D., Limón-Romero, J., Báez-López, Y., & Tlapa, D. (2025) · IEEE Access · doi:10.1109/access.2025.3640970 · Cited by 5
Li, L., Rashidi, M., Yu, Y., Bozorg, B., & Kalhori, H. (2025) · Structural Control and Health Monitoring · doi:10.1155/stc/9952459 · Cited by 5
Moreira, R. S., Moita, S., Torres, J. M., Gouveia, F., Dinis, M. A. P., Ferreira, D., Araújo, M., & Guerreiro, M. J. (2025) · IET Smart Cities · doi:10.1049/smc2.70020 · Cited by 2
Hu, F., Li, Y., Zhao, J., & Min, C. (2025) · Symmetry · doi:10.3390/sym17122158 · Cited by 2
“Although the design of lightweight detectors (e.g., YOLO [19,20], RetinaNet [21], RefineDet [22], HSD [23], FCOS [24]) can accelerate inference, applying these models directly to ultra–high–resolution images incurs prohibitive computational costs.”
Improved YOLO for fabric defect detection algorithm deployment based on FPGA
Xiang, H., Zhen, W., Huang, Z., Li, B., & Li, C. (2025) · Journal of Real-Time Image Processing · doi:10.1007/s11554-025-01820-w · Cited by 2
“Two-stage algorithms include R-CNN [2], Fast R-CNN [3] and Faster R-CNN [4], whereas single-stage algorithms are represented by the YOLO [5] series and the SSD [6] network model.”
Huang, X., Zhang, D., & He, Y. (2025) · Royal Society Open Science · doi:10.1098/rsos.242239 · Cited by 2
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.