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 46,501–46,600 of 51,399
Lauro, M. D., Sediyono, E., Sembiring, I., et al. (2025) · International Conference on Awareness Science and Technology (iCAST) · doi:10.1109/icast68191.2025.11300226
“YOLO is a single-shot object detection algorithm that processes an entire image in a single neural network to predict bounding boxes, calculate confidence score, and class probabilities for objects [23].”
Yu, Y., Zhang, K., Zhu, L., et al. (2025) · doi:10.1109/aipip66876.2025.11299194
“…parameter count by 38.7% [1] and shrinking inference time to 16.1ms (NVIDIA MX250), thereby improving edge energy efficiency; Redmon's YOLO achieves real-time detection via a single-stage architecture [2], while Howard's MobileNet reduces computational load through separable convolutions [3].”
InfluentialRobot móvil para agarre de objetos por color, con visión artificial y control difuso Mamdani
Buitrago, D. G. S., García, B. S. M., & Mora, Y. A. B. (2025) · Tecnura · doi:10.14483/22487638.22525
A Multi-Agent Environment With Artificial Intelligence for English Language Learning and Teaching
Slyusar, V. I. (2025) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3373-3561-2.ch006
A Comparative Study of YOLOv3 and YOLOv10 for hCAPTCHA Challenge Solving
Bisen, V. D., & Isafiade, O. E. (2025) · doi:10.1109/c4d65382.2025.11306462
“…solutions typically use computer vision techniques such as extracting visual features from the images, such as shapes, colors, textures, and edges; and object detection and classification [17], which rely on machine learning models trained to interpret and analyze visual patterns [15], [23], [24] .”
Kokubo, S., & Hidaka, A. (2025) · Proceedings of the ISCIE International Symposium on Stochastic Systems Theory and its Applications · doi:10.5687/sss.2025.87
Huang, C., Huang, J., Lian, Z., Yuan, H., Chen, H., Yang, Z., & Duan, J. (2025) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2025.111346
Zhang, Y., & Jiang, Y. (2025) · Scientific Reports · doi:10.1038/s41598-025-26970-6
“YOLOv1 19 is fast in detection but performs poorly on similar or small objects.”
Comparison of Attacks on Traffic Sign Detection Models for Autonomous Vehicles
Lin, C., & Chen, G.-W. (2025) · doi:10.3390/engproc2025120007
Semantic-Enhanced Multi-Modal Fusion for Beam Prediction in Real-World Wireless Systems
Gao, W., Li, X., & Liu, F. (2025) · IEEE Communications Letters · doi:10.1109/lcomm.2025.3648762
Low-light image segmentation using sine-curve enhancement and cross-resolution attention mechanism
Xu, L., Li, G., Ji, X., & Song, Y. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.113566
Automated Corn Kernel Counting from Multiple Views
Yurushkin, M. V., Gornostal, A. A., Babich, P. V., et al. (2025) · Lecture notes in networks and systems · doi:10.1007/978-3-032-13612-1_3
A motion strategy for finding human faces with a drone
Antonio, E., Becerra, I., & Murrieta-Cid, R. (2025) · Advanced Robotics · doi:10.1080/01691864.2025.2608303
“It can be considered as a problem of active vision [1], where the ability of a vision algorithm to classify an image [2] is not sufficient.”
TRAFİK GÜVENLİĞİNİ ARTIRMAK İÇİN DERİN ÖĞRENME TEMELLİ UYKU DURUM TESPİTİ VE UYARI SİSTEMİ
Gökgöz, M. M., Sülün, B., KILIÇ, E., et al. (2025) · International Journal of 3D Printing Technologies and Digital Industry · doi:10.46519/ij3dptdi.1745778
Nguyen, T., Bennett, S. J., & Carter, W. J. (2021) · Journal of Current Research in Oral Surgery · doi:10.51847/kmiyo81bar
Application of the YOLOv5 model in the construction method of internal thread defect data
Huang, L.-P., Hsu, Q.-C., Lai, Y.-R., et al. (2025) · Engineering Computations · doi:10.1108/ec-12-2024-1118
Ding, X., Sun, W., Chen, Y., et al. (2025) · International Conference on Artificial Intelligence and Intelligent Information Processing (AIIIP) · doi:10.1145/3778534.3778550
“YOLO (You Only Look Once) [7] series models have achieved remarkable success in object detection, offering a strong balance between detection speed and accuracy.”
Enhancing data association in Multi-Object Tracking via learning-based Human Trajectory Prediction
Carreras, A., Velázquez, J. M. R., & Hayet, J.-B. (2025) · International Conference on Pattern Recognition Systems (ICPRS) · doi:10.1109/icprs66293.2025.11302821
“With deep neural network-based detectors such as R-CNN [11] or YOLO [12], the accuracy and speed of the detection process have improved dramatically, making it feasible to detect objects in real time.”
Novel Deep Learning Approach for Collision Warning and Speed Recommendation System for Driver
Kushnure, D. T., Jaiswal, S., & Gopalan, L. N. (2025) · IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT) · doi:10.1109/conecct65861.2025.11306749
“Algorithms like YOLO (You Only Look Once) [5] [6], SSD (Single Shot Multibox Detector) [7], and Faster R-CNN [8] have been extensively applied for real-time traffic analysis.”
Yokoyama, N., Ferwerda, B., & Nakajima, T. (2025) · ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp) · doi:10.1145/3714394.3754386
“GuessScape supports three interaction modes, shown in Figure 1. modes, the image is processed with on-device object detection using YOLO, a real-time object detection model [20].”
Udvaros, J., & Forman, N. (2025) · IEEE International Symposium on Computational Intelligence and Informatics (CINTI) · doi:10.1109/cinti67731.2025.11311735
Potapov, A. S., Фадеев, Е. С., & Malykh, K. M. (2025) · Problems of fisheries · doi:10.36038/0234-2774-2025-26-4-103-112
Enhancing Tiny Object Detection in Super-Resolved Sentinel-2 Imagery for Naval and Airbase Analysis
Amieva, J. F., Ayala, C., Perko, R., & Aleksandrowicz, S. (2025) · IEEE International Geoscience and Remote Sensing Symposium (IGARSS) · doi:10.1109/igarss55030.2025.11314033
“Incontrast, one-stage detectors, such as the You Only Look Once (YOLO) series [13–15] and RetinaNet [16], combine localization and classification in a single pass.”
Real-time computer vision system for monitoring conveying systems
Halawa, F., Sadeghzadeh, S., & Mohammed, R. (2025) · The International Journal of Advanced Manufacturing Technology · doi:10.1007/s00170-025-17188-x · Cited by 3
“Multiple studies compared different object detection algorithms such as YOLO [20], SSD (Single Shot Multi - box Detector) [ 21 ], and Faster R-CNN [ 22 ], and showed that different versions of YOLO algorithm often outperform other existing algorithms in detecting small or overlapping objects at…”
Siddiquee, M. A., Hasan, M. M., Arman, S. E., Islam, M. S., & Azad, A. K. M. (2025) · Astronomy and Computing · doi:10.1016/j.ascom.2025.101048
Investigating Adversarial Robustness Against Preprocessing Used in Blackbox Face Recognition
Croft, R., Du, B., Joseph, D., & Kumar, S. (2025) · International Conference on Digital Image Computing: Techniques and Applications (DICTA) · doi:10.1109/dicta68720.2025.11302421
“We consider seven face detection models from the Python DeepFace library [31]; MTCNN [33], OpenCV [34], Dlib [35], MediaPipe [36], YOLOv8 [37], Centerface [38], and RetinaFace [39].”
Extracting Lip Region from Video Images for Dental Aesthetic Analysis
Oi, K., Kihara, N., Washio, A., et al. (2025) · International Conference on Control, Automation and Systems (ICCAS) · doi:10.23919/iccas66577.2025.11301318
“The two-step structure of object detection has been problematic in terms of processing speed, but YOLO has succeeded in improving the processing speed by performing detection and identification simultaneously [4].”
Feasibility Study of Automatic Cat Litter Cleaning System Using Robotic Arm
Ikeda, H., & Nakasho, K. (2025) · International Conference on Control, Automation and Systems (ICCAS) · doi:10.23919/iccas66577.2025.11301359
“YOLO (You Only Look Once) [2], known for real-time, high-accuracy image recognition crucial for waste detection, has seen continuous improvements [3] and wider application [4].”
Substation drawing intelligent parsing framework with dense augmentation and semantic alignment
Yan, T., Zhu, C., Zhang, X., & Zeng, Y. (2025) · Energy Informatics · doi:10.1186/s42162-025-00584-8 · Cited by 1
“For critical equipment detection, advanced object detection models such as You Look Only Once (YOLO) series [9] and Fast Region-based Convolutional Network (Fast R-CNN) [10] are employed to accurately identify major substation components, including main power transformers, switchgear assemblies,…”
OpenBeePose: A Remote Sensing Framework for Bee Pose Estimation Using Deep Learning
Sabzi, S., Najar, A., Pourdarbani, R., García-Mateos, G., Fernández-Beltrán, R., & Rohban, M. H. (2025) · Applied Sciences · doi:10.3390/app16010303
Detection and Recognition of Rare Freshwater Fish with Foundation Models
MADOKORO, H., Suzuki, M., TSUJI, M., et al. (2025) · International Conference on Control, Automation and Systems (ICCAS) · doi:10.23919/iccas66577.2025.11301168
Predictive Imbalance: Bipartite Matching in DETR-Like Detectors
Alam, M. M. (2025) · International Conference on Digital Image Computing: Techniques and Applications (DICTA) · doi:10.1109/dicta68720.2025.11302474
“In classical object detection models [4], [6], [10], cross-entropy is commonly used for binary classification.”
Image Classification of Raw Beef Cuts Based on the Improvement of YOLOv11n Using Wavelet Convolution
Liao, H., Hu, Y., Zhang, M., et al. (2025) · Applied Sciences · doi:10.3390/app16010332
Remote-Sensing Image Object Detection with Adaptive Spatial Attention
Chen, Y., & Chen, Z. (2025) · doi:10.1109/icdm68174.2025.11309389
Wiseman, M. S., Woods, J. L., Hartgrave, C. R., et al. (2025) · PLoS ONE · doi:10.1371/journal.pone.0333253
NABEUCHI, S., Makita, A., & Matsunaga, N. (2025) · International Conference on Control, Automation and Systems (ICCAS) · doi:10.23919/iccas66577.2025.11301144
“The head-mounted display (HMD) uses the object detection algorithm Tiny YOLO v2[5][6] to detect where the object to be picked is placed.”
Arunachalam, R., & Mohana, J. (2025) · International Conference on Sustainable Communication Networks and Application (ICSCNA) · doi:10.1109/icscn67106.2025.11308588
“Various networks, including R-CNN [5], SPP-net [6], Fast R-CNN [7], Faster R-CNN [8], SSD [9], YOLO [10], R-FCN [11], and others [12], [13], have also been employed for object recognition tasks.”
Şevik, U. (2025) · Düzce Üniversitesi Orman fakültesi ormancılık dergisi/Düzce Üniversitesi Orman Fakültesi ormancılık dergisi · doi:10.58816/duzceod.1814094 · Cited by 1
Pajura, I., & Korga, S. (2025) · Journal of Computer Sciences Institute · doi:10.35784/jcsi.8020
“Modern methods, explored in [1] among others, learn hierarchical representations, where higher layers amplify relevant aspects of the input data [1].”
Luo, H., Guo, W., & Gao, L. (2025) · IEEE China International Youth Conference on Electrical Engineering (CIYCEE) · doi:10.1109/ciycee67631.2025.11309027
Hu, C.-Y., Chou, P., Lin, C.-H., et al. (2025) · IEEE International Conference on Recent Advances in Systems Science and Engineering (RASSE) · doi:10.1109/rasse64831.2025.11315406
Fake Number Plate Detection Using Vehicle Image Analysis: A Robust Verification System
Gayaki, U., Nishane, O. P., Warkad, N., et al. (2025) · doi:10.1109/icecst66106.2025.11307270
“Convolu-tional Neural Networks like YOLO or Faster R-CNN have been applied in end-to-end plate detection and recognition across a broad range of plate formats [14], [17].”
Analysis of Thyroid Gland Cytological Images Using Computer Vision
Lozhkin, I. A., Mironov, A., Zaytsev, K., et al. (2025) · International journal of open information technologies · doi:10.25559/injoit.2307-8162.13.202508.13-19
An autonomous inspection robot for extra-high voltage substations
Moustris, G. P., Flessa, T., Mermigkas, P., et al. (2025) · IEEE PES Innovative Smart Grid Technologies Conference Europe (ISGT Europe) · doi:10.1109/isgteurope64741.2025.11305645
“To detect ECs, we use YOLOv11n [14], a computationally efficient and high performance single-stage object detection method, suitable for deployment on mobile robots.”
Application of Emotion Analysis in Deep Learning Techniques
Uysal, M., Demiral, M. F., & IŞIK, A. H. (2025) · DÜMF Mühendislik Dergisi · doi:10.24012/dumf.1757225
Dong, Y., Xiao, J., & Wei, F. (2025) · PLoS ONE · doi:10.1371/journal.pone.0337541
“Notable examples of classic single-stage networks include the YOLO series (You Only Look Once) [7–12], the SSD (Single Shot Multibox Detector) [13], and Reti-naNet [14].”
YOLO ALGORİTMASI İLE KALİTE KONTROL SÜREÇLERİNDE GÖRÜNTÜ İŞLEME
Karamuk, S., Özdemi̇r, Y., Yıldırım, M., & Özdemir, G. (2025) · İstanbul Sabahattin Zaim Üniversitesi Fen Bilimleri Enstitüsü Dergisi · doi:10.47769/izufbed.1755090
Implementation of Object Detection Method Using YOLOv8n for Hompimpa Game
Dewi, E. N. F., Hidayat, E. W., Rachman, A. N., et al. (2025) · International Conference on Informatics and Computing (ICIC) · doi:10.1109/icic68054.2025.11309696
“As the name implies, You Only Look Once, this model detects objects by only reading the image data once to get the object information in it [18][22].”
Wheat-Yolov11: A Lightweight Detection Algorithm for Wheat Heads under Growth Light Interference
Yu, H., Guo, W., Gao, L., et al. (2025) · IEEE China International Youth Conference on Electrical Engineering (CIYCEE) · doi:10.1109/ciycee67631.2025.11308800
Perception and Exception Detection of Road Pavement based on an Enhanced DETR model
Zheng, D., Liu, Y., & Zhao, H. (2025) · IEEE China International Youth Conference on Electrical Engineering (CIYCEE) · doi:10.1109/ciycee67631.2025.11308817
“Eldor et al. [12] employed You Only Look Once (YOLO) algorithm [13] to generate bounding boxes that locate potholes accurately.”
Heterogeneous Algorithm for Ship Detection Based on Feature Fusion of PConv Combined with SAM
Xiangming, Q., & Xinyao, W. (2025) · IEEE International Conference on Information Systems and Computer Aided Education (ICISCAE) · doi:10.1109/iciscae66104.2025.11307432
“The YOLO [1-5] series predicts target categories and positions on feature maps with high speed and strong real-time performance.”
CASOEP-YOLOv11: The Object Detection Model for Border Area Security
Zhao, X., Yu, F., Zhang, H., Meng, S., & Liu, D. (2025) · IEEE International Conference on Electronic Measurement & Instruments · doi:10.1109/icemi66537.2025.11306708
“Its primary function is to convert the object identification job into a regression issue and use regression to directly forecast the target's category, position, and bounding box [13].”
Ye, Q., Chen, Y., Deng, Z., & Liu, Z. (2025) · IEEE China International Youth Conference on Electrical Engineering (CIYCEE) · doi:10.1109/ciycee67631.2025.11308853
“However, existing circuit diagram recognition research has primarily focused on general-purpose circuit applications, lacking comprehensive solutions tailored to the specific needs of power equipment fault diagnosis [16-19].”
Lightweight Pedestrian Detection for Mobile Robots Based on Improved YOLOv8
Zhao, W. (2025) · IEEE International Conference on Information Systems and Computer Aided Education (ICISCAE) · doi:10.1109/iciscae66104.2025.11307243
Deep Learning-based Multimodal Fusion and Cloud-Enabled Diagnosis of Rheumatic Heart Disease
S, S. S. K., Saranya, D., & Jayabharathi, P. (2025) · International Conference on Sustainable Communication Networks and Application (ICSCNA) · doi:10.1109/icscn67106.2025.11308199
Wang, B., Cui, W., Zhao, X., et al. (2025) · IEEE International Conference on Information Systems and Computer Aided Education (ICISCAE) · doi:10.1109/iciscae66104.2025.11307733
“In recent years, neural networks have been widely applied in various fields [1-3], and in the field of image recognition, with the development of computer technology, digital image processing methods have also been widely used in the field of image analysis [4-8].”
Detection and Comparative Analysis of Mucilage from Satellite Images Using Deep Learning Methods
Çukur, Y. E., & Erdağı, E. (2025) · Bitlis Eren Üniversitesi Fen Bilimleri Dergisi · doi:10.17798/bitlisfen.1773151
MFF-Net: Flood Detection from SAR Images Using Multi-Frequency and Fuzzy Uncertainty Fusion
Gao, Y., Wang, X., Zhang, Z., Chen, X., Liu, R., & Liang, X. (2025) · Remote Sensing · doi:10.3390/rs18010123
A survey: AI Techniques for Medical Image Analysis
Mohammed, S. J., Ahmed, R. I., & Mohsin, R. M. (2025) · Basrah Researches Sciences · doi:10.56714/bjrs.51.2.17
“Additionally, a supervised edge-specific module is integrated into the original mask [24].”
Chen, Z., Fan, K., Ye, J., Xu, Z., & Wei, Y. (2025) · Drones · doi:10.3390/drones10010020 · Cited by 3
Custom Image-To-Graph Transformation Strategies for Object Detection with GATs on the KITTI Dataset
BENFOUINA, R., & Maliani, A. D. E. (2025) · International Conference on Wireless Networks and Mobile Communications (WINCOM) · doi:10.1109/wincom65874.2025.11313466
“Their efficacy has been proven by architectures like YOLO [2], R-CNN [3], and their variations.”
Zero-Shot YOLOv8 Descriptors for Low-Latency Object Tracking
El-Alami, A., Nadir, Y., & Mansouri, K. (2025) · International Conference on Wireless Networks and Mobile Communications (WINCOM) · doi:10.1109/wincom65874.2025.11313440
Road Surface Damage Detection Algorithm Based on RCGELAN-YOLOv11
殷, 波. (2025) · Artificial Intelligence and Robotics Research · doi:10.12677/airr.2026.151004
Allwin, R., Rakesh, S., Shobin Ferry, P., C., A. D., & Sathiyanathan, M. (2025) · International Conference on Intelligent Technologies for Sustainable Electric and Communications Systems (iTech SECOM) · doi:10.1109/itechsecom64750.2025.11307246
“Consequently, a deficiency persists in the creation of automated systems that can consistently detect paintable mold surfaces while accommodating real-world geometric discrepancies [6], [7], [9]..”
Performance evaluation of different YOLO models for lung nodule detection
Aruk, İ. (2025) · Bitlis Eren Üniversitesi Fen Bilimleri Dergisi · doi:10.17798/bitlisfen.1780664
Effective Marine Animal Detection and Rare Species Classification Using Autonomous Drones
Mohan, V., C, M. V., Vikhas, S. G., et al. (2025) · International Conference on Intelligent Technologies for Sustainable Electric and Communications Systems (iTech SECOM) · doi:10.1109/itechsecom64750.2025.11307511
“Here, the first experiment gives object detection [18] performance metrics (mAP, IOU).”
CF-DETR: Coarse-to-Fine Transformer for Real-Time Object Detection
Shin, W., Kang, D., Park, B., Kang, B. B., Lee, J.-K., & Baek, H. (2025) · IEEE Real-Time Systems Symposium (RTSS) · doi:10.1109/rtss66672.2025.00026 · Cited by 3
“Unlike traditional convolutional detectors (e.g., YOLO series [14]) that only capture local features, DETR employs a patch-based representation and a Transformer architecture to model global context.”
Evaluation of Combined RGB and Thermal Imaging Human Detection Model Performance
Subramaniam, S., Sarjerao, S. M., Natarajan, M., & Marimuthu, B. (2025) · Innovations in Power and Advanced Computing Technologies (i-PACT) · doi:10.1109/i-pact65952.2025.11308029 · Cited by 1
“These methods use convolutional neural networks (CNNs) to process images more efficiently and accurately [3].”
Real-time detection of seat belt usage in overhead traffic surveillance using YOLOv7
Widodo, C. E., Adi, K., Priyono, P., et al. (2025) · Applied Computer Science · doi:10.35784/acs_7594
“YOLO can process at a rate of 45 frames per second with a mean average accuracy of 63.4% (Redmon et al., 2016).”
InfluentialAutomatic Detection of Navigational Signs on Inland Waterways Using YOLO Neural Networks
Adamski, P., & Łubczonek, J. (2025) · TransNav the International Journal on Marine Navigation and Safety of Sea Transportation · doi:10.12716/1001.19.04.18
YOLO based Adaptive Traffic Signals Control System and Real Time Violation Monitoring
Bandi, S. K., Buvanesh Goud, B., Raju, M., Vadla, Y. K. C., Guba, P., & Lingampally, A. (2025) · International Conference on IoT Based Control Networks and Intelligent Systems (ICICNIS) · doi:10.1109/icicnis66685.2025.11315786
“The You Only Look Once (YOLO) algorithm was first presented by Redmon et al. in 2016 [7] and is capable of highly accurate real-time object detection.”
Disruption-Resilient Real-Time Sensor Data Delivery via Neural Multiple Description Coding
Hu, X., Zhang, Q., Ye, W., et al. (2025) · IEEE Military Communications Conference (MILCOM) · doi:10.1109/milcom64451.2025.11310596
“On the edge server, two YOLOv8s [18] models, fine-tuned on the nuScenes and VisDrone datasets respectively, are used to detect objects from the images decoded from the received bitstreams.”
CSRAP: Enhanced Canvas Attention Scheduling for Real-Time Mission Critical Perception
Sakib, M. I. I., Hu, Y. C., & Abdelzaher, T. (2025) · IEEE Military Communications Conference (MILCOM) · doi:10.1109/milcom64451.2025.11310357
“Prior to deployment, we profile inference latency across multiple input resolutions to enable resolution-aware scheduling at runtime.”
WECI-YOLO: Multi-Module Enhanced Steel Surface Quality Defect Detection
Zhou, H., Wang, J., & Jiang, T. (2026) · IEEE Access · doi:10.1109/access.2025.3650430 · Cited by 2
HEA 2 -MAC: A Hybrid Exponent-Aware Approximate MAC for Efficient CNN Processing
Wang, W., Zou, Z., Cao, X. L., Cai, X., Cai, H., & Liu, B. (2025) · International Conference on Integrated Circuits and Microsystems (ICICM) · doi:10.1109/icicm66614.2025.11315908
“In object detection, R-CNNs and YOLO [4, 5] have become widely adopted.”
Demo: V2X Enabled Delivery - Towards an Integration with Robot, Aerial and Ground Vehicle
Ning, L., Bied, M., & Vinel, A. V. (2025) · International Conference on 6G Networking (6GNet) · doi:10.1109/6gnet68413.2025.11314132
“In recent years, many deep learning models, such as Convolutional Neural Networks (CNN) [10], Region Based Convolutional Neural Networks (R-CNN) [11] and YOLO [12], are rapidly developed and applied in the field of object detection and have achieved high utility.”
mmPrism: High-Throughput Perception-Aware mmWave Radar Object Recognition in Contested Environments
Shan, Z., Sakib, M. I. I., Caesar, M., et al. (2025) · IEEE Military Communications Conference (MILCOM) · doi:10.1109/milcom64451.2025.11310209
“High-accuracy detectors such as Faster R-CNN [11], YOLO [12], and DETR [13] often rely on full-frame, high-resolution inference, resulting in substantial latency and computational overhead.”
High-Performance Data Prefetching Accelerator for Real-Time Object Detection
Tang, Y., Zhou, X., Lin, Z., Cheng, M., Jing, N., Jiang, J., Sheng, W., & Wang, Q. (2025) · International Conference on Integrated Circuits and Microsystems (ICICM) · doi:10.1109/icicm66614.2025.11316052
“Modern detectors — such as SSD [1], YOLO [2], RetinaNet [8], and the recent transformer-based DETR family [3] — rely on deep convolutional neural networks (CNNs) to achieve high accuracy.”
Traffic Light Detection Using Yolo Versions for Intelligent Driving
Khalloufi, F. E., Rafalia, N., & Abouchabaka, J. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-03695-7_31
Performance Comparison of Serial and Parallel Fruit Classification Using Pretrained Neural Networks
Mallegowda, M., Parkavi, A., Sanath, S., et al. (2025) · Lecture notes in networks and systems · doi:10.1007/978-981-96-8343-7_56
Savaliya, K., Mandal, S., Kumari, S., & Raman, S. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-08511-5_4
Detect Before Decay: Early Diagnosis of Dental Caries via Intraoral Scans
Verma, M., Dixit, S., Singh, H., et al. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-08508-5_21
Deep Learning for Robotic Vision
Yan, W. Q. (2026) · Advances in computer vision and pattern recognition · doi:10.1007/978-981-95-4360-1_5
Comparative Study of Single-Stage Versus Two-Stage Detectors for ASL Gesture Recognition
Fang, X., & Rivas, P. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-12930-7_27
Diffusion-Detect: Synthetic and Real Data Towards a Robust Fire and Smoke Detection
Khan, D., Motta, J., & Odone, F. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-10192-1_22
Depth and Event-Based Approaches for Human Detection and Pose Estimation
Quan, H., Goudarzi, M., Plizzari, C., Mentasti, S., Palermo, F., Trojaniello, D., & Matteucci, M. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-10185-3_17 · Cited by 1
Performance Analysis of YOLO-Based Architecture for Water Level Monitoring
Bermudo, M. A. G., Alce, A. R. B., & Galido, A. P. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-10824-1_28
AI-Assisted Chest X-Ray Reading Improves Sensitivity Without Reducing Specificity: A Crossover Study
Trabalková, Z., Števík, M., Zeleňák, K., Dandár, J., Straka, Z., Kvak, D., Kvaková, K., & Ovesná, P. (2026) · Smart innovation, systems and technologies · doi:10.1007/978-981-95-1353-6_38 · Cited by 2
Smart Recycling Assistant: An Integrated AI-Powered Waste Classification and Management System
Saha, T., Gupta, R., Kumar, A., Sohail, M. D., & Sarkar, I. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-04539-3_42
A Review on Deep Learning Models and Fractal Residual Learning in Detection of Different Tumors
Jakhar, S. P., Nandal, A., & Dhaka, A. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-11488-4_18
Monitoring with Machines: A Review of Computational Bioacoustics
Gibbons, A., Donohue, I., & Parnell, A. C. (2025) · Springer eBooks · doi:10.1007/978-3-032-05821-8_16 · Cited by 2
A Review of Object Detection Techniques for Novel Power Systems
Zhang, F., Deng, S., Ding, Z., Liu, Q., Shen, Z., & Yang, L. (2026) · Communications in computer and information science · doi:10.1007/978-981-95-4828-6_14
SLI-Net: Efficient Lightweight Networks Focused on Critical Defect Detection
Wang, X., Li, Z., Yu, J., Lin, Z., & Sun, W. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-5699-1_9
Akter, T., Rahman, S., Billah, A., et al. (2026) · Lecture notes in networks and systems · doi:10.1007/978-981-96-9275-0_14
Incremental Object-Based Novelty Detection with Feedback Loop
Caldarella, S., Ricci, E., & Aljundi, R. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-10185-3_1
Object Risk Estimation for Autonomous Driving Safety
Khan, A. H., Shafiq, S., van Elst, L., & Dengel, A. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-12840-9_27 · Cited by 1
Merkmale und Merkmalsrepräsentation
Hemmje, M., & Wagenpfeil, D.-I. S. (2026) · Multimedia Information Retrieval · doi:10.1007/978-3-662-71887-2_2
EVCS: A Benchmark for Fine-Grained Electric Vehicle Charging Station Detection
Chen, L., Sudbeck, S., Riggers, C., Geib, T., Cordes, K., & Broszio, H. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-12840-9_6
Face Detection in Historic Manuscripts A Case Study on the Wenceslas Bible
Hofbauer, H., Hintersteiner, J., Kern, M., et al. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-11317-7_41
Real-Time Pothole Detection System Using YOLOv11
Durga, K. H., & Yaduwanshi, R. (2025) · Lecture notes in networks and systems · doi:10.1007/978-981-96-8343-7_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.