You Only Look Once: Unified, Real-Time Object Detection
Open accessThe DOI matches its Crossref record; 53 of the 53 references it cites were found in a registry or an index; 8 of the 25 sources its claims cite were checked for support.
Abstract
We present YOLO, a new approach to object detection. Prior work on object detection repurposes classifiers to perform detection. Instead, we frame object detection as a regression problem to spatially separated bounding boxes and associated class probabilities. A single neural network predicts bounding boxes and class probabilities directly from full images in one evaluation. Since the whole detection pipeline is a single network, it can be optimized end-to-end directly on detection performance. Our unified architecture is extremely fast. Our base YOLO model processes images in real-time at 45 frames per second. A smaller version of the network, Fast YOLO, processes an astounding 155 frames per second while still achieving double the mAP of other real-time detectors. Compared to state-of-the-art detection systems, YOLO makes more localization errors but is less likely to predict false positives on background. Finally, YOLO learns very general representations of objects. It outperforms other detection methods, including DPM and R-CNN, when generalizing from natural images to other domains like artwork.
Overview
CoChat Summary
TL;DR
YOLO reframes object detection as a single regression problem, using one convolutional network to predict bounding boxes and class probabilities directly from full images. It achieves real-time detection speeds while remaining competitive with, and complementary to, slower region-based detectors.
Key findings
- YOLO runs at 45 FPS on a Titan X GPU, and Fast YOLO runs at 155 FPS; Fast YOLO reaches 52.7% mAP on PASCAL VOC 2007, more than double prior real-time detectors, while YOLO reaches 63.4% mAP.
- On PASCAL VOC 2012, YOLO scores 57.9% mAP; combining Fast R-CNN with YOLO raises Fast R-CNN from 71.8% to 75.0% mAP on VOC 2007, a 3.2% gain.
- YOLO makes fewer background false positives than Fast R-CNN: Fast R-CNN has 13.6% background false positives among top detections and is almost 3× more likely to predict background detections than YOLO.
- YOLO generalizes better to artwork: on Picasso, YOLO gets 53.3 AP versus R-CNN’s 10.4 AP and DPM’s 37.8 AP; on People-Art, YOLO gets 45 AP versus R-CNN’s 26 AP and DPM’s 32 AP.
Methods
- Detection is modeled as a single CNN regression: the image is divided into an S×S grid; for PASCAL VOC, S=7, B=2, C=20, producing a 7×7×30 tensor of bounding boxes, confidence scores, and class probabilities.
- The base network has 24 convolutional layers followed by 2 fully connected layers; Fast YOLO uses 9 convolutional layers. Convolutional layers are pretrained on ImageNet at 224×224, then detection training uses 448×448 input.
- Training uses PASCAL VOC 2007 and 2012 for about 135 epochs, batch size 64, momentum 0.9, decay 0.0005, sum-squared error with λ_coord=5 and λ_noobj=0.5, dropout, and data augmentation.
Limitations
- The paper states YOLO imposes strong spatial constraints because each grid cell predicts only two boxes and one class, limiting nearby objects and struggling with small objects in groups such as flocks of birds.
- The paper states YOLO struggles to generalize to objects in new or unusual aspect ratios or configurations, uses relatively coarse features due to downsampling, and its loss treats small and large box errors equally; its main error source is incorrect localization.
- The paper states YOLO still lags state-of-the-art detection accuracy and struggles to precisely localize some objects, especially small ones.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Figures





Verification
Claims the paper makes
6 Valid · 8 Not valid · 15 Not checked · 92 Own results and interpretations
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“While it is much faster than R-CNN, it still falls short of real-time and takes a significant accuracy hit from not having good proposals.”
What the sources say
- Could not verifycites [20] [20] K. Lenc and A. Vedaldi. R-cnn minus r. arXiv preprint arXiv:1506.06981 , 2015. 5, 6 - sourceExperimental — accuracy not yet measured
The ConvNet-based Object Detection section identifies R-CNN minus R as a method that uses predefined regions instead of region proposals. It gives no runtime measurement or assessment of whether the method achieves real-time detection; searches for real-time performance and speed did not establish that claim. (LLM, conf=0.76)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Could not verify
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“To avoid overfitting we use dropout and extensive data augmentation.”
What the sources say
- Partly supportedcites [18] [18] G. E. Hinton, N. Srivastava, A. Krizhevsky, I. Sutskever, and R. R. Salakhutdinov. Improving neural networks by preventing co-adaptation of feature detectors. arXiv preprint arXiv:1207.0580 , 2012. 4 - sourceExperimental — accuracy not yet measured
The paper states that dropout reduces overfitting (p. 1) and describes using dropout with data augmentation for its ImageNet model (H Models for ImageNet, p. 18). It does not establish that YOLO uses either technique or describe YOLO’s augmentation as extensive. (LLM, conf=0.88)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“However, only 30Hz DPM [31] actually runs in real-time.”
What the sources say
- Supportedcites [31] [31] M. A. Sadeghi and D. Forsyth. 30hz object detection with dpm v5. In Computer Vision-ECCV 2014 , pages 65-79. Springer, 2014. 5, 6 - source
The Introduction (p.1) states that 'except for certain objects including face, pedestrians and certain rigid objects, detectors do not currently run at video rate' and that the presented architecture detects the 20 PASCAL VOC categories simultaneously at 30Hz, i.e. at video/real-time rate. The Abstract (p.1) and Table 2 (Method) bound the comparison to other DPM speed-up efforts: reference DPM at 0.07Hz, the fastest GPU 'Vanilla DPM' at ~1Hz, FTVQ at 0.53s, and 'over an order of magnitude faster than the previous fastest DPM implementation', so none of the listed variants reaches real-time. Thus our copy supports both parts of the attribution: that this 30Hz DPM runs in real-time and that it is the only such DPM among the speed-up efforts compared. (LLM, conf=0.82)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“While it is much faster than R-CNN, it still falls short of real-time and takes a significant accuracy hit from not having good proposals.”
What the sources say
- Could not verifycites [20] [20] K. Lenc and A. Vedaldi. R-cnn minus r. arXiv preprint arXiv:1506.06981 , 2015. 5, 6 - sourceExperimental — accuracy not yet measured
The ConvNet-based Object Detection section identifies R-CNN minus R and says it uses predefined regions in an SPPnet system, but gives no speed comparison with R-CNN. A search for R-CNN minus R and speed found no passage in our copy establishing that it is much faster. (LLM, conf=0.73)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Could not verify
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“While it is much faster than R-CNN, it still falls short of real-time and takes a significant accuracy hit from not having good proposals.”
What the sources say
- Partly supportedcites [20] [20] K. Lenc and A. Vedaldi. R-cnn minus r. arXiv preprint arXiv:1506.06981 , 2015. 5, 6 - sourceExperimental — accuracy not yet measured
The “ConvNet-based Object Detection” section (page unavailable) says R-CNN minus R uses predefined regions instead of region proposals. It does not say that this causes a significant accuracy loss; the paper’s discussion of low accuracy concerns a different system, naïve Faster R-CNN. (LLM, conf=0.83)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
84 more claims
Create a free account to see all 121 claims and to verify the 2 references still open.
- Probably not a substantial claim. 17
- It may state two separate claims as one. 15
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“which was not thoroughly investigated in prevIoUs work such as YOLOv1 [20] and YOLOv2 [51] employing MSE/L2 loss (Mean Squared Error).”
From Object Detection in 20 Years: A Survey (2023) · cites this paper as [20]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“the YOLO series models v2-v5 [144-147] are some of the most advanced object detection methods based on DNN, which have good performance in terms of speed and precision.”
From A survey of model compression strategies for object detection (2023) · cites this paper as [144]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“As a typical and more widely used new form of applications [9], various deep learning-based intelligent services and applications have changed many aspects of people's lives due to the great advantages of Deep Learning (DL) in the fields of Computer Vision (CV) and Natural Language Processing (NLP) [10].”
From Convergence of Edge Computing and Deep Learning: A Comprehensive Survey (2020) · cites this paper as [9]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“A convolutional neural network predicts the bounding boxes as well as class probabilities for all the objects depicted in an image.”
From Object detection using YOLO: challenges, architectural successors, datasets and applications (2023) · cites this paper as [56]
The cited source says what the claim attributes to it.
In the citing paper
“Authors of YOLO [56] have reframed the problem of object detection as a regression problem instead of classification problem.”
From Object detection using YOLO: challenges, architectural successors, datasets and applications (2023) · cites this paper as [56]
6 more claims about this paper
Create a free account to see every claim other papers make about this one.
Citations
Cites
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2577031 · Cited by 73,472
Self-citationFaster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2015) · arXiv · doi:10.48550/arxiv.1506.01497 · Cited by 70,812
Self-citationGoing deeper with convolutions
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298594 · Cited by 48,562
ImageNet Large Scale Visual Recognition Challenge
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-015-0816-y · Cited by 39,380 · cited 1×
“We pretrain our convolutional layers on the ImageNet 1000-class competition dataset [29].”
MethodHistograms of Oriented Gradients for Human Detection
Dalal, N., & Triggs, B. (2005) · 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) · doi:10.1109/cvpr.2005.177 · Cited by 33,584 · cited 2×
“Detection pipelines generally start by extracting a set of robust features from input images (Haar [25], SIFT [23], HOG [4], convolutional features [6]).”
MethodRich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
Girshick, R., Donahue, J., Darrell, T., & Malik, J. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.81 · Cited by 32,684 · cited 2×
“Then, classifiers [35, 21, 13, 10] or localizers [1, 31] are used to identify objects in the feature space.”
MethodSelf-citationGirshick, R. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.169 · Cited by 28,105
Self-citationDelving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
He, K., Zhang, X., Ren, S., & Sun, J. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.123 · Cited by 19,741 · cited 1×
“Convolutional neural networks (CNNs) achieve impressive performance on classification tasks at real-time speeds [13].”
Object recognition from local scale-invariant features
Lowe, D. G. (1999) · Proceedings of the Seventh IEEE International Conference on Computer Vision · doi:10.1109/iccv.1999.790410 · Cited by 16,472 · cited 1×
“Detection pipelines generally start by extracting a set of robust features from input images (Haar [25], SIFT [23], HOG [4], convolutional features [6]).”
MethodRobust Real-Time Face Detection
Viola, P., & Jones, M. J. (2004) · International Journal of Computer Vision · doi:10.1023/b:visi.0000013087.49260.fb · Cited by 14,097 · cited 1×
“Detectors for single classes like faces or people can be highly optimized since they have to deal with much less variation [36].”
Background
Cited by
Items 45,801–45,900 of 51,399
A Systematic Performance Comparison of YOLO Models for Human Identification in Visual Scenes
Gandhi, D., Srivastava, A., Soni, R., et al. (2025) · Lecture notes in networks and systems · doi:10.1007/978-3-032-06671-8_25
Sharma, P. K., Jain, N., Singh, R. K., et al. (2025) · Lecture notes in networks and systems · doi:10.1007/978-3-032-06694-7_3
Guo, Y., Zhao, X., Zhong, Z., & Zhong, X. (2025) · The Journal of Supercomputing · doi:10.1007/s11227-025-08006-y · Cited by 3
Doubly Smoothed Density Estimation with Application on Miners’ Unsafe Act Detection
Zeng, Q., Han, M., Xu, K., et al. (2025) · Technometrics · doi:10.1080/00401706.2025.2582628
“In Section 3.2, we then extend this framework by incorporating an additional layer of kernel smoothing across the spatial domain, leading to the proposed DS estimator.”
InfluentialReal-Time Measurement of Catenary Steady Arm Orientation Angle Based on YOLO
Tian, Y., Jiang, Y., Wang, D., Lu, Y., & Hao, D. (2025) · IEEE Instrumentation & Measurement Magazine · doi:10.1109/mim.2025.11224700
“Object detection (e.g., Faster R-CNN [7], YOLO [8], and SSD [9]) methods have been applied to railway systems [10]–[12].”
Tang, S., Xia, X., Bilal, M., Dou, W., & Xu, X. (2025) · IEEE Transactions on Consumer Electronics · doi:10.1109/tce.2025.3627545 · Cited by 4
“Since image process-based intelligent applications are common in MRAs, we select the original YOLO [58] with 24 convolutional layers as the representative of inference models, with the input data set in the interval [2000 KB, 3000 KB].”
Clinical Deployment of Socially Assistive Robot for Physical Health Assessment
Lachaux, K., Gagnon, É., Thullier, F., Maítre, J., Bouchard, K., Gagnon, C., Duchesne, É., & Gaboury, S. (2025) · IEEE RO-MAN · doi:10.1109/ro-man63969.2025.11217564 · Cited by 1
“These algorithms are implemented as Python modules, leveraging several libraries, including OpenCV for image processing 2 , SciPy, NumPy, and Pandas for scientific computations, OpenPose [6] for skeletal extraction, and YOLO for classification tasks related to the 10mWT test [15], [29].”
Robot Delivery of Actionable Counterfactual Neural Network Explanations: Results in Group Perception
Narcomey, A., Claure, H., & Vázquez, M. (2025) · IEEE RO-MAN · doi:10.1109/ro-man63969.2025.11217869
“Examples include Object Detection (e.g., explaining the class probability map output by a YOLO model [30] for an input image captured by a robot) or Group Detection [42](explaining the likelihood that pairs of people interact with each other, as in Sections IV–VI).”
Unde, J., Urata, T., Kamei, S., Ito, Y., Kihara, R., Colan, J., & Hasegawa, Y. (2025) · IEEE RO-MAN · doi:10.1109/ro-man63969.2025.11217663
“A stereo camera (Intel RealSense D456) uses YOLO v5 for real-time detection [19] and the library OpenCV is then used for edge extraction and target point determination [20].”
Adaptive Speed Breakers Powered by YOLOv8 and MRF Dampers
Chilwan, S., Powar, S., Shaikh, K., et al. (2025) · doi:10.1109/icamida64673.2025.11209718
“The proposed system uses the advanced technologies like YOLOv8, which is a deep learning-based object detection model, to adjust its behavior at run time based on the real-time speed of approaching vehicles [2].”
Zhang, H., Liu, C., Wang, Z., Ma, N., Liu, C., Ji, B., Liu, S., Si, H., Xu, L., & Li, Z. (2025) · International Journal of Pattern Recognition and Artificial Intelligence · doi:10.1142/s0218001425500399
Yao, H., Pan, S., Fan, Y.-N., et al. (2025) · Comput. Aided Civ. Infrastructure Eng. · doi:10.1111/mice.70121 · Cited by 2
“The emergence of algorithms such as single shot multibox detector (W. Liu et al., 2016), YOLO (you only look once; Bochkovskiy et al., 2020; Redmon et al., 2016; C. Li et al., 2022; C. Y. Wang et al., 2023), fully convolutional one-stage object detection (Tian et al., 2020), and others have…”
Detection of Microplastics in Coastal Environments Based on Semantic Segmentation
Lorenzo-Navarro, J., Salas-Cáceres, J., Castrillón-Santana, M., Gómez, M., & Herrera, A. (2026) · Microplastics · doi:10.3390/microplastics5020066
Indoor Object Measurement Through a Redundancy and Comparison Method
Faria, P., Simões, T., Marques, T. N., & Finn, P. D. (2025) · Sensors · doi:10.3390/s25216744
Monocular Image-Based 3D Object Detection for Industrial Pick-and-Place Tasks
Jun, J., Park, B., & Jeong, J. (2025) · WSEAS TRANSACTIONS on SYSTEMS archive · doi:10.37394/23202.2025.24.65
Zhang, D., Xu, Z., Fan, L., et al. (2025) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2025.3620759
“YOLO [38] is a real-time object detection algorithm that achieves fast and accurate detection by converting the object detection task into an end-to-end regression problem of a single neural network.”
RGBT Fusion-Based Airborne Synthetic Aperture Occlusion Removal Target Imaging
Yue, Y., Tian, C., Jiang, Z., Li, X., Chen, S., & Hou, D. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2025.3628638
Peng, X. (2025) · doi:10.1109/mcte67374.2025.11213713
“In deep learning-based object detection, there are two mainstream approaches: One is the single-stage algorithm, represented by SSD [2] and the YOLO series [3-10].”
Research on Multi-scale Vehicle Detection Method Based on Improved YOLOv11n
Wang, Y. (2025) · International Conference on Mechatronics and Computer Technology Engineering (MCTE) · doi:10.1109/mcte67374.2025.11213605
“Object detection methods based on convolutional neural networks (CNNs), such as R-CNN [1], Fast R-CNN [2], Faster R-CNN [3], and the YOLO series [4, 5, 6, 7] have significantly improved the accuracy and efficiency of detection and have gradually become the mainstream approach to vehicle detection.”
Cao, Y. J., & Yang, Q. (2025) · doi:10.1109/icbdse65491.2025.11220050
“Contemporary insulator detection approaches typically employ YOLO-series detectors [1, 2, 3], leveraging their simplicity and high efficiency.”
From Lab to Real-World: Industrially Oriented AI Training Without High-Performance Hardware
Wijewardana, D., Alexander, J. T., Adel, A., Fedorov, V., Alani, N., & Mozhaeva, A. (2025) · International Conference on Engineering Management of Communication and Technology (EMCTECH) · doi:10.1109/emctech65814.2025.11220561
“For example, YOLO (You Only Look Once) demonstrates exceptional efficiency for real-time applications in surveillance and robotics, performing well on modest hardware due to its single-step processing [21].”
Chen, J.-R., Weng, C.-L., & Shih, P.-C. (2025) · IEEE International Conference on Big Data Analytics (ICBDA) · doi:10.1109/icbda65366.2025.11211025
Pujari, J. J., Bikku, T., Anusha, K., Teerdala, R., Kumar, M. K., & Rao, K. V. G. (2025) · IEEE World Conference on Applied Intelligence and Computing (AIC) · doi:10.1109/aic66080.2025.11211898
“Nevertheless, transformers alone are not without limitations, and there remains room for improvement, particularly in minimizing loss and optimizing computational efficiency in high-dimensional data spaces [14-17].”
Real-Time Road Rage Prevention Using Enhanced Traffic Surveillance with Attention and FusionPreprint
Shen, N., Wang, J., & Wang, Y. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5704098
Chen, H., Song, J., Zhang, F., Gu, Y., Ye, Z., Chen, X., & Yin, L. (2025) · Lifeline Emergency and Safety · doi:10.26599/lles.2025.9660004
Chang, X., Zhang, L., Wang, Y., et al. (2025) · Remote Sensing · doi:10.3390/rs17213646
“The YOLOv8 architecture belongs to the YOLO (You Only Look Once) [38] family of object detection models, which use a single neural network to predict the bounding boxes of objects in an image and their labels.”
Enhancing Fruit Freshness Detection Through Hybrid CNN-Random Forest Architecture
Rezer, E. T., Lairan, N., & Jingga, K. (2025) · International Conference on Artificial Intelligence and Data Sciences (AiDAS) · doi:10.1109/aidas67696.2025.11213754
“To enhance its performance on varying image quality, especially in low-resolution scenarios, we further combine it with a Random Forest classifier for improved generalization and robustness [11].”
Object Detection and Classification Using Deep Learning Applied to Aquaculture
Raghavendra, C. G., George, A. A., & Prasad, P. R. (2025) · doi:10.1109/iacis65746.2025.11211264
“Prior works such as YOLO-Fish, improved YOLOv5, and AquaYOLO have shown strong results (mAP up to 96%), but most were tested in controlled or synthetic settings, limiting real-world applicability [4].”
Biodegradable Waste Classification for Children Using YOLOv9
Ridzuan, P. N. Z. N., Abdul-Rahman, S., Sabri, N. M., et al. (2025) · International Conference on Artificial Intelligence and Data Sciences (AiDAS) · doi:10.1109/aidas67696.2025.11213735
“In 2016, [16] published a study titled "You Only Look Once: Unified, Real-Time Object Detection," which introduced YOLO.”
InfluentialEnhancing MSL Alphabet Learning for Deaf Children in Malaysia Through YOLO V5-Based Recognition
Romihadi, N. H. B., Noh, N. M., & Halim, S. A. (2025) · International Conference on Artificial Intelligence and Data Sciences (AiDAS) · doi:10.1109/aidas67696.2025.11213779
“Existing research has explored various techniques for sign language recognition, including Convolutional Neural Networks (CNNs), Long Short-Term Memory (LSTM) networks, and different versions of YOLO [5, 6, 7].”
Dynamic Semantic SLAM via Multimodal-Guided Object Masking
Sun, B., Gao, S., Pei, H., et al. (2025) · International Conference on Computer Network, Electronic and Automation (ICCNEA) · doi:10.1109/iccnea66167.2025.11212069
“Conversely, lightweight detection networks like YOLO and SSD provide only approximate bounding boxes, which may compromise segmentation accuracy [3].”
RF-YOLO-RASFF: An End-to-End Framework for Nighttime Road Defect Detection
Bai, J., & Zhang, S. (2025) · International Conference on Computer Network, Electronic and Automation (ICCNEA) · doi:10.1109/iccnea66167.2025.11211868
“Traditional image processing methods [1] and existing object detection models [2-5] struggle to maintain accuracy under such conditions, especially for small or low-contrast defects.”
Research on Pedestrian Recognition Based on Multiple Edge Features Extraction Technology of YOLOv11
Liu, L., & Shi, J. (2025) · International Conference on Computer Network, Electronic and Automation (ICCNEA) · doi:10.1109/iccnea66167.2025.11212045
“In recent years, the YOLO series models have gained popularity for their end-to-end high-speed and high-precision performance [6].”
Research on Pedestrian Detection Technology Based on YOLO11s Algorithm
Ma, Y., Liu, B., & Liu, J. (2025) · International Conference on Computer Network, Electronic and Automation (ICCNEA) · doi:10.1109/iccnea66167.2025.11211939
“…deep detection frameworks represented by detection frameworks can be generally divided into two-stage methods (e.g., R-CNN [2], Fast R-CNN [3], Faster R-CNN [4]) and one-stage approaches (such as the YOLO [5] and SSD [6] families) have become the mainstream of current pedestrian detection research.”
Research on a Method of Improving Cartographer Algorithm
Li, Y., Xu, S., & Yang, H. (2025) · International Conference on Computer Network, Electronic and Automation (ICCNEA) · doi:10.1109/iccnea66167.2025.11212023
“This work addresses ORB-SLAM3's limitations by proposing an enhanced framework that combines an optimized YOLOv5s detector with optical flow tracking to actively identify and exclude dynamic features during pose estimation [8].”
Research on Industrial Parts Recognition Based on YOLOv8n
Ma, Y., Liu, B., & Li, J. (2025) · International Conference on Computer Network, Electronic and Automation (ICCNEA) · doi:10.1109/iccnea66167.2025.11212099
“Single-stage object detection algorithms represented by YOLO [4] SSD [5].”
Hybrid Machine VisionDigital Twin Approach for Quality Control
Rico, S. I., Martínez, S. S., Estévez, E., García, A. S., & Gila, D. M. M. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-10489-2_16
Assessing Olive Tree Detection Performance in UAV Images
Latorre-Hortelano, P., Cano, F., Jurado-Rodríguez, D., & Parra-Cabrera, G. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-10489-2_17
Research on Remote Sensing Image Target Detection Algorithm Based on Transformer
魏, 玉. (2024) · Computer Science and Application · doi:10.12677/csa.2024.144081
Analyzing Student Interaction in Classroom Environments using YOLOv8 and DeepSORT-based Multi-Object
Kim, T. (2025) · doi:10.1145/3760678.3760680
“This study proposes a system that leverages YOLOv8, a state-of-the-art object detection model, and DeepSORT, a widely used multi-object tracking algorithm, to detect, track, and analyze interactions between students during classroom activities [1].”
Contrastive Proposal Alignment: Advancing vision-language models for microscopic cell detection
Li, P., Feng, L., Zhu, S., Xin, Z., & Xie, M. (2025) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2025.109103
Improving Image-Based Tool Detection in Industrial Workstations using Data Augmentation
Ouarab, S., Garcia, D., Ragot, N., et al. (2025) · Proceedings of the Annual Conference of the IEEE Industrial Electronics Society · doi:10.1109/iecon58223.2025.11221035
Enhanced Drift-Aware Computer Vision Architecture for Autonomous Driving
Hossain, M. S. A., Ahammed, A. S., Mukherjee, S., & Obermaisser, R. (2025) · Annual Conference of the IEEE Industrial Electronics Society (IECON) · doi:10.1109/iecon58223.2025.11221461
“Redmon et al. [9] introduced YOLO as a unified model that performs detection in real time without significantly compromising accuracy, making it suitable for embedded autonomous driving systems.”
Luo, J., & Chen, J. (2025) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2025.3629830
Hidaka, K. (2025) · Annual Conference of the IEEE Industrial Electronics Society (IECON) · doi:10.1109/iecon58223.2025.11221104 · Cited by 1
“In S1, the robot measures its surroundings using a stereo camera and detects obstacles [15], [16].”
Real-time Recognition of Hand-Drawn Objects using YOLO Detector
Hric, L., Bačík, J., Perduková, D., & Pástor, M. (2025) · International Conference on Electrical Drives and Power Electronics (EDPE) · doi:10.1109/edpe66853.2025.11224231
“One of the most prominent families of one-stage object detectors is the YOLO (You Only Look Once) series [8, 9], developed by Ultralytics.”
Dilfanian, E., Dong, H., Zhang, Y. M., et al. (2025) · Proceedings of the Annual Conference of the IEEE Industrial Electronics Society · doi:10.1109/iecon58223.2025.11221647
“For forest fire detection in real-time, single-shot networks like YOLO [6] are preferred as they are faster in inference compared to region-proposal-based detection models like Sparse R-CNN [7].”
An Object Detection Algorithm Based on YOLO-LLD for Low Light Detection
Hu, C., Qi, Q., & Shi, C. (2025) · doi:10.1109/icahn67688.2025.00023
“In contrast, one-stage methods, including YOLO [3] and SSD [4] , utilize an end-to-end regression strategy that combines detection and classification tasks into a single network.”
Gómez, A. E. R., Cuenca, D. F. B., Serrezuela, R. R., et al. (2025) · doi:10.1109/amitic68284.2025.11214625
“Since its introduction by [1], YOLO has undergone successive versions that have progressively enhanced its accuracy, speed, and usability, including YOLOv3 [2], YOLOv4 [3] and the Ultralytics YOLOv5 [4] and YOLOv8 [5], series, the latter featuring a modular design and optimization for production…”
Human Detection and following by a Mobile Robot using YOLO Structured Convolutional Neural Network
Majidi, Y., & Hassanabadi, A. H. (2025) · doi:10.1109/icee67339.2025.11213908 · Cited by 1
Hakasin, G. A., Efendi, D., Winatra, H. J., et al. (2025) · Procedia Computer Science · doi:10.1016/j.procs.2025.09.071
Real-Time Wildfire Detection and Segmentation using an Optimized Attention U-Net
Shlomo, A. B., Filis, D., & Cohen, M. W. (2025) · Procedia Computer Science · doi:10.1016/j.procs.2025.09.584
Enhancing Precision Agriculture: UAV-Based Detection and Management of Giant Hogweed
Mouakher, A., Tekfa, B. B., Ayoub, N., et al. (2025) · Procedia Computer Science · doi:10.1016/j.procs.2025.09.409
3D Scene Reconstruction for Real-Time Video Editing. A Performance Study Conducted on Web Browsers
Vlad, V., & Buraga, S. C. (2025) · Procedia Computer Science · doi:10.1016/j.procs.2025.09.239
Performance of YOLO based traffic analysis in high resolution video stream
Kudłacik, P., Kaszuba, K., & Lubowiecki, P. (2025) · Procedia Computer Science · doi:10.1016/j.procs.2025.09.565 · Cited by 2
Kalia, R., Aledhari, M., Rahouti, M., & Chehri, A. (2025) · Procedia Computer Science · doi:10.1016/j.procs.2025.10.061 · Cited by 1
Suela, M. M., Ferrão, L. F. V., Adunola, P., et al. (2025) · Research Square · doi:10.21203/rs.3.rs-7704872/v1
Open World Object Detection with Explicit Objectiveness Measure
Yang, T., Zhang, H., Wang, R., et al. (2025) · IEEE International Conference on Intelligent Rail Transportation (ICIRT) · doi:10.1109/icirt66379.2025.11216691
“Conversely, single-stage architectures represented by YOLO [12] eliminate proposal generation through direct regression of spatial coordinates and class probabilities, greatly improving computational efficiency and making them suitable for real-time applications such as autonomous navigation…”
Strip-Convolution Feature Fusion Network for Foreign Object Intrusion Detection in Railway Scene
Wang, N., Li, J., & Ruan, T. (2025) · IEEE International Conference on Intelligent Rail Transportation (ICIRT) · doi:10.1109/icirt66379.2025.11216775
“To address this limitation, regression-based end-to-end models such as SSD[19] and YOLO[20] have been proposed.”
Improved RT-DETR for Passenger Flow Detection in Subway Stations
Pan, H., Gao, X., & Su, S. (2025) · IEEE International Conference on Intelligent Rail Transportation (ICIRT) · doi:10.1109/icirt66379.2025.11216752
“Redmon et al. [10] proposed YOLOv1, a single-stage object detection algorithm.”
Backdoor in Seconds: Unlocking Vulnerabilities in Large Pre-trained Models via Model Editing
Guo, D., Hu, M., Guan, Z., Guo, J., Hartvigsen, T., & Li, S. (2025) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3746252.3761408 · Cited by 8
Cross-phenological domain adaptation for early-stage peach detection
Zhai, Q., Shi, J., Li, Y., et al. (2025) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2025.111195
Bringing CLIP to the Edge: A Lightweight Fire Detection System for Real-Time Monitoring with UAV
Lee, H., & Nadeem, M. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-4398-4_21
Monocular Gait Video-Based Estimation of Musculoskeletal Disorders Using 3D Skeletal Models
Ofuchi, T., Furuya, T., Furukawa, S., et al. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-4398-4_7
Non-correlative Feature Interaction for Classification of Real and Fake Scene Images
Das, A., Shivakumara, P., Pal, U., Antonacopoulos, A., Pletschacher, S., & Liu, C. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-4398-4_17
Chen, Y., Yang, N., Cai, H., & Shao, G. (2025) · Communications in computer and information science · doi:10.1007/978-981-95-3739-6_13
EA-DETR: an enhanced attention and multi-scale fusion detector for UAV images
Cao, Q., Lian, Z., & Zhao, Y. (2025) · Signal Image and Video Processing · doi:10.1007/s11760-025-04924-9
U-Net- and YOLOv8-based pipeline for license plate recognition in adverse weather
Padmakumar, P., Lisho, E., Esther Moriah, A., & Johanan Joysingh, S. (2025) · Signal Image and Video Processing · doi:10.1007/s11760-025-04943-6 · Cited by 1
“Third, the YOLO-based model [31] is uti-lizedforlicenseplatedetectiontoobtainaccuratelocalization even in low-quality images [32].”
A Study on Improving Campus Spaces for Physical Activity using AI-Based Analysis
Hwang, M., Park, E. J., Oh, S., et al. (2025) · 한국생활환경학회지 · doi:10.21086/ksles.2025.10.32.5.593
Explainable AI for lung cancer detection using YOLOv11 and LLMs
Sharma, D. K., Pal, M. K., & Singh, A. K. (2025) · Life Cycle Reliability and Safety Engineering · doi:10.1007/s41872-025-00372-z · Cited by 2
“If we talk about object detection and localization, YOLO (You Only Look Once) is a great tool (Redmon et al. 2016; Redmon and Farhadi 2017).”
TE-Net: remote sensing image detection network with resistance to background
Wang, Y., Li, Z., Zhu, S., et al. (2025) · Remote Sensing Letters · doi:10.1080/2150704x.2025.2586471
“For instance (Redmon et al. 2016), designed a lightweight decoupled head to address inter-class similarity.”
HitoMi-Cam: A Shape-Agnostic Person Detection Method Using the Spectral Characteristics of Clothing
Ono, S. (2025) · Journal of Imaging · doi:10.3390/jimaging11110399
“…neural network (CNN)-based object detectors, typified by the You Only Look Once (YOLO) system, have become a standard technology in various applications such as autonomous driving, surveillance cameras, and robotics, due to their high accuracy and real-time processing capabilities [1,2].”
RefineFuse: Light-Adaptive Cross-Spectrum Feature Integration for Night Vision Enhancement
Gao, W., Wei, Y., Zhang, Y., et al. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-4378-6_17
Towards Feature Enhanced Small Object Recognition in X-ray Safety Inspection
Yang, J., Kan, H. Y., & Lyu, E. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-4378-6_16
Ye, Z., & Zhou, P. (2025) · Remote Sensing · doi:10.3390/rs17223671
“Representative one-stage detectors include the You Only Look Once (YOLO) series [8–10], Single Shot MultiBox Detector (SSD) [11], and RetinaNet [12].”
Breast Cancer Detection Using YOLOv8 with Intersection over Union Technology
Bouslama, H., Rouijel, A., Elloubi, I., Addouni, A. E., & Ghazi, H. E. (2025) · Lecture notes in networks and systems · doi:10.1007/978-3-032-02312-4_13
Improved YOLOv5 for Small Pest Detection: Algorithm Design and Performance Evaluation
Li, X.-Y., Jiang, Q., Guo, Y., et al. (2025) · International Journal of Pattern Recognition and Artificial Intelligence · doi:10.1142/s0218001425500296
An, J., Chen, W., Ni, Y., & Chang, F. (2025) · Journal of Real-Time Image Processing · doi:10.1007/s11554-025-01801-z · Cited by 1
“One-stage algorithms address this limitation; their mainstream representatives include You Only Look Once (YOLO) [9–11], SSD [12], RetinaNet [13], and RT-DETR [14].”
Color Is Not Enough: Dataset and Method for Identifying Relevant Traffic Lights in Driving Scenes
Trinci, T., Magistri, S., Bianconcini, T., et al. (2025) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2025.3626165
“Behrendt et al. [13] employ a standard YOLO [19] for tra ffi c light localization and leverage a custom convolutional network, fed with the cropped bounding boxes, to infer the current states of the detected tra ffi c lights.”
Dong, Y., Peng, Z., Liu, W., & Gan, H. (2025) · Applied Sciences · doi:10.3390/app152211990
Enhancing Person Tracking in Dynamic Environments with Siamese Networks and Probabilistic Models
Ojha, A. R., Vanshika, Rajput, H., & Gupta, N. (2025) · Algorithms for intelligent systems · doi:10.1007/978-981-95-0493-0_19
A deep learning-based MRI automatic detection model for spinal schwannoma and meningioma
Liu, Y., Liu, Y., Cai, J., et al. (2025) · Medical & Biological Engineering & Computing · doi:10.1007/s11517-025-03468-x
“The single-stage detection algorithms are typified by the YOLO family [8–10], which uses an end-to-end network design to achieve efficient detection.”
Mashaallah, Z., Cirillo, E., & Prete, A. D. (2025) · Lecture notes on data engineering and communications technologies · doi:10.1007/978-3-032-10344-4_21
Real-Time Detection of Road Defects Using YOLO Architectures: A Comparative Study
Khlifati, O., Baba, K., Kostali, Z. E., et al. (2025) · doi:10.1109/ipta66025.2025.11222038
“To address this gap, YOLO (You Only Look Once) has gained attention as a real-time object detection algorithm based on deep CNNs [13].”
Eye-Closure-Based Alertness Detection via Adaptive Eye Region Extraction and Deep Learning
Nocentini, O., Lagomarsino, M., Lorenzini, M., et al. (2025) · doi:10.1109/ipta66025.2025.11222028
Şenocaklı, A. G., & Yüksel, S. E. (2025) · doi:10.1109/ipta66025.2025.11222057
“After training, the model is validated (precision, recall, mAP) and exported to ONNX format for deployment [12], [13], enabling real-time detection and accurate localization in challenging radar environments [10], [11].”
Deep Vision of Mobility for Urban Detection From Street-View Projections
Akgül, B. A., Parlak, İ. B., & Adel, M. (2025) · doi:10.1109/ipta66025.2025.11222018
“Following the original YOLO algorithm [12], our study focuses on two recent versions, YOLOv8 [13] and YOLOv10 [14], which offer significant advancements in speed, modularity, and real-time performance.”
Chagas Parasite Semi-Supervised Classification in Blood Sample Images Using Different Deep Learning
Kumar, P., Loeza, C. F. B., & Rada, L. (2025) · doi:10.1109/ipta66025.2025.11222044
Detection of spheno-occipital synchondrosis fusion stages using artificial intelligence
Uzun, S., Mağat, G., & Evli, C. (2025) · Frontiers in Physiology · doi:10.3389/fphys.2025.1682917 · Cited by 1
“The original YOLO (You Only Look Once) introduced by Redmon (2016) revolutionized object detection by predicting bounding boxes and class probabilities simultaneously (Hussain, 2023).”
Bui, S. T. (2025) · Lecture notes in networks and systems · doi:10.1007/978-981-95-1746-6_22
Research on Bearing Defect Recognition Based on YOLOv5-CBAM
Qiu, Y., Wei, X., Jia, X., et al. (2025) · Lecture notes in networks and systems · doi:10.1007/978-981-96-5006-4_12
UrbanFix AI: Smart Reporting System for Road Safety and Management
Jarali, A., Lad, S., Kavathekar, S., et al. (2025) · Lecture notes in networks and systems · doi:10.1007/978-3-032-06697-8_25
A Category-Guided Keypoint Detection Framework for Industrial Binary Images
Ni, T., Chen, Y., Wen, X., et al. (2025) · Communications in computer and information science · doi:10.1007/978-981-95-4097-6_19
Real-time object detection using mobile net SSD and OpenCV
Jhade, S., Uppununthala, S. H., Rangdal, P., et al. (2025) · AIP conference proceedings · doi:10.1063/5.0298417
AI-Powered Application for Classifying Recyclable Materials
Çakır, Ş. N., & Altay, E. V. (2025) · International Artificial Intelligence and Data Processing Symposium (IDAP) · doi:10.1109/idap68205.2025.11222312
“In contrast to commonly adopted approaches in the litera-ture—such as YOLO [12] and MobileNet-based models— [21] this study employs the InceptionV3 architecture [22], which has been fine-tuned for the task of waste classification.”
Exploring the Use of Synthetic Data to Improve Pedestrian Detection in CNN
Montanha, R., & Musse, S. R. (2025) · SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI) · doi:10.1109/sibgrapi67909.2025.11223354 · Cited by 1
YOLOT: A Recurrent YOLO Model for Robust Video-Based Automotive Object Detection
Baxter, D., & Zhang, J. (2025) · IEEE International Conference on Multimedia Information Processing and Retrieval (MIPR) · doi:10.1109/mipr67560.2025.00059
“Among the most influential approaches for this task are YOLO (You Only Look Once) models [1], a family of deep convolutional networks that perform detection in a single forward pass, associating each prediction with a grid cell in the input image.”
Exploring Light-Weight Object Recognition for Real-Time Document Detection
Wojcik, L., Coelho, L., Granada, R., et al. (2025) · SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI) · doi:10.1109/sibgrapi67909.2025.11223364
“The YOLO [15] series of models innovated in the fact that a single pass was enough for the entire network’s pipeline to run, meaning it was a more efficient model.”
Diversity-Informed Fusion for Sclerotinia Sclerotiorum and White Mold Detection
Pereira, R. D. C., Borges, D. L., Lobo, M., Torres, R. D. S., & Pedrini, H. (2025) · SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI) · doi:10.1109/sibgrapi67909.2025.11223383 · Cited by 3
“These include the Single-Shot Detector (SSD) [18], Detection Transformer (DETR) [19], the Faster R-CNN [20], and three detectors from the YOLO family [21]–[24]: YOLOv8, YOLOv9, and YOLOv10.”
Irvandy, D., Bagaskoro, G., Wicaksono, N., et al. (2025) · International Conference on Technology and Policy in Energy and Electric Power (ICT-PEP) · doi:10.1109/ict-pep67281.2025.11231941
“Recent advances in AI, deep learning, and computer vision have enabled automated gauge reading via visual analysis [6], [7], [8].”
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.