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 50,901–51,000 of 51,398
A Dual-Scale Collaborative Vision Framework for UAV-Based Drowning Behavior Recognition
Shen, J., Yu, J., Zhang, R., & Wang, N. (2026) · Applied Sciences · doi:10.3390/app16189007
A Lightweight Dual-Scale YOLO Framework for Small PCB Defect Detection
Zhou, Z., & Sui, T. (2026) · International Conference on Computer Information Science and Application Technology (CISAT) · doi:10.1109/cisat71030.2026.11682147
“Compared with two-stage detectors with relatively complex inference procedures, YOLO-style one-stage detectors are faster, more compact, and easier to deploy in online industrial scenarios[3].”
Research on Intelligent Grading of Appearance Quality of Red Fuji Apple Based on Improved YOLOv11
Pan, Y., Zhao, L., Hou, Z., et al. (2026) · International Conference on Computer Information Science and Application Technology (CISAT) · doi:10.1109/cisat71030.2026.11682290
“[13] III.”
Real-Time Object Detection Using YOLOv8 and Lightweight CNNs on Edge Devices
Ravi, G., Boakai, E. S., Sridevi, P. R. S., Kumari, R. K., & Gopatoti, A. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-33581-4_28
Dual-Path Attention Network for Small Object Detection in Road Traffic Scenarios
Wang, P., Xu, J., & Du, B. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-31236-5_36
Deng, Y.-X., Sub-r-pa, C., & Chen, R.-C. (2026) · Electronics · doi:10.3390/electronics15184106
YOLO vs ViT: A Performance Analysis for Drone Detection in Anti-drone Systems
Bangde, S., Kumar, N., Verma, S., & Verma, O. P. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-19521-0_12
A Vision-Based Vehicle Collision Warning Algorithm Integrating YOLOv8 and DeepSORT
Qin, X., & Li, W. (2026) · SAE technical papers on CD-ROM/SAE technical paper series · doi:10.4271/2026-99-1107
Khan, M. M. H., Hu, Q., Prabhu, R., Zheng, H., Huang, H., & Liu, Z. (2026) · Journal of Imaging · doi:10.3390/jimaging12090433
“In recent years, deep learning models such as the YOLO family [8], particularly YOLOv8, have achieved strong performance in detecting and recognising objects in many practical applications [9].”
A YOLO11 Object Detection Algorithm Based on ResNet18 Backbone Optimization for UAV Small Targets
Li, B., & Song, Y. (2026) · International Conference on Computer Information Science and Application Technology (CISAT) · doi:10.1109/cisat71030.2026.11682159
“To mitigate the issue of small target feature loss under the UAV perspective, this paper optimizes the YOLO11 backbone network by employing the ResNet18 residual network to enhance the feature representation capacity of the model [8].”
Comparative Analysis of CNN and Transformer Architectures for Real-Time Fire and Smoke Detection
Živanović, M. M., Luković, V., Ristić, O., Stefanovic, H. Z., Antić, S., & Savić, A. (2026) · Symmetry · doi:10.3390/sym18091519
Qian, C. X., Ibrahim, F., Shah, N. M., & Rui, H. B. (2026) · International Journal of Imaging Systems and Technology · doi:10.1002/ima.70440
“Target detection allows the network to find the attention region quickly, which results in a higher accuracy [31, 38].”
InfluentialAircraft Skin Defect Detection Based on Dual-Domain Wavelet Feature Enhancement
Zheng, C., Li, H., & Wang, C. (2026) · IEEE Signal Processing Letters · doi:10.1109/lsp.2026.3732997
Multi-Object Tracking and Spatio-Temporal Graph-Based Relational Pattern Mining
Seo, T., & Chung, K. (2026) · Electronics · doi:10.3390/electronics15184086
Sarıkaya, S. B., Yılmaz, A., & Ulukaya, S. (2026) · International Conference on Computer Systems and Technologies (CompSysTech) · doi:10.1109/compsystech69798.2026.11683024
“You Only Look Once(YOLO) is one of the real-time object detection models [22].”
Huang, M., Wang, L., & Jia, X. (2026) · International Conference on Cloud Computing and Big Data Analytics (ICCCBDA) · doi:10.1109/icccbda69573.2026.11676437
Deep Learning-Based Scene Understanding for Adaptive UI Placement in Mobile Augmented Reality
Gandikota, L. R., Swamy, V. R., Gudipati, S. K. A., PONUGOTI, S., & Konda, S. T. R. (2026) · International Conference Virtual and Augmented Reality Simulations · doi:10.1109/icvars70356.2026.11683203
“Redmon et al. [4] established the YOLO family of single-shot detectors, and subsequent iterations have progressively improved the accuracy-efficiency tradeoff.”
YOLOv11 Aplicado a la Segmentación y Clasificación de Quemaduras en la Piel
Avena-Caro, I., Gabaldón-Márquez, A., Cornejo-García, R., et al. (2025) · Revista ELECTRO · doi:10.67458/re2025a6314319
“YOLO ( You Only Look Once ) es un algoritmo de detección de objetos propuesto por Redmon et al.[10], el cual aborda esta tarea como un problema de regresión.”
Zhou, Y., Cao, Y., & Sun, Y. (2026) · International Joint Conference on Information and Communication Engineering (JCICE) · doi:10.1109/jcice71302.2026.11682373
“…fixed grid and simultaneously predict bounding boxes, confidence scores, and class probabilities within a single forward pass of one convolutional network, achieving interactive frame rates on embedded hardware [13], and embedded GPU platforms make on-site deployment of such models practical [14].”
InfluentialSDP-RTDETR: a real-time end-to-end detector for small pcb surface defects
Yi, M., Xia, C., Lin, Q., & An, W. A. (2026) · Machine Vision and Applications · doi:10.1007/s00138-026-01922-w
“In contrast, one-stage detectors such as YOLO [8] and SSD [9 ] offer higher inference speed and better deployment effi - ciency.”
FPGA Acceleration of YOLOv8-Style Inference with an Instruction-Driven Convolution Datapath
Li, S., Jiang, D., Tan, Z., Wang, D., Que, M., & Wang, X. (2026) · International Symposium on Semiconductor and Electronic Technology (ISSET) · doi:10.1109/isset70600.2026.11682130
“YOLO-style detectors reduce algorithmic latency by performing object localization and classification in one pass [1], and recent YOLO variants preserve this real-time one-stage design [2], [3].”
DA-F2F: Domain-Adaptive Object Detection with Feature-to-Feature Modulation and Alignment
오호택, Kim, H., & Lee, H.-J. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37016-7_8
Yordanov, M., Stoykova, V., & Kiryakova, G. (2026) · International Conference on Computer Systems and Technologies (CompSysTech) · doi:10.1109/compsystech69798.2026.11683110
“They were developed as an alternative to two-stage object detection (also called region-based) and provide real-time processing of video streams [7].”
ISD-YOLO: A lightweight and efficient feature extraction network for invoice seal detection
Song, X., Zhao, X., Ma, C., et al. (2026) · PLoS ONE · doi:10.1371/journal.pone.0358190
“Particularly, SSD [9] and the YOLO suite [10–13] have attracted substantial attention because of their swift inference times.”
Ali, M. A., Kassem, A., Dornaika, F., Charafeddine, J., & Hotiet, H. (2026) · Springer eBooks · doi:10.1007/978-3-032-30647-0_5
Chen, Z., Zhao, Y., Bao, M., Zhou, F., Shen, Q., Guo, X., & Zhang, L. (2026) · Animals · doi:10.3390/ani16182870
“The You Only Look Once family of object-detection algorithms is based on deep convolutional neural networks and provides an end-to-end, single-stage framework for real-time object detection [32,33].”
Intelligent Wire Pairing Method Based on Machine Vision for Aircraft Cable Breakage Repair
Huang, M., Jengshan, S., & Jia, X. (2026) · International Conference on Cloud Computing and Big Data Analytics (ICCCBDA) · doi:10.1109/icccbda69573.2026.11676508
“Although initially developed for pedestrian recognition, HOG (Histograms of Oriented Gradients) algorithm has been successfully applied to other object detection problems [7].”
He, Z., Tan, X.-H., Zhou, Y., et al. (2026) · Welding in the World · doi:10.1007/s40194-026-02619-4
Nettari, Y., & Berrimi, F. (2026) · doi:10.1109/icsmartgrid70882.2026.11680673
“YOLO emerged as one of the most efficient real-time methodologies [1].”
An Improved YOLOv8 Object Detection Method With Dual Attention and Adaptive Weighting
Zhao, P., Wang, J.-M., & Lu, B. (2026) · International Conference on Cloud Computing and Big Data Analytics (ICCCBDA) · doi:10.1109/icccbda69573.2026.11676548
“YOLOv1 [1] first framed object detection as a regression problem, enabling end-to-end training and inference.”
PO-IoU: Point-Offset-Guided Zero-Shot Knee Joint Segmentation for Osteoarthritis Assessment
Yoo, J.-C., & Yoo, J. (2026) · Journal of the Korea Computer Graphics Society · doi:10.15701/kcgs.2026.32.4.67
Wheat Disease Detection Based on YOLOv12 with Capsule Networks and FPN
幸, 南. (2026) · Artificial Intelligence and Robotics Research · doi:10.12677/airr.2026.155109
Huang, Y., Cao, X., Liu, F., et al. (2026) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2026.112421
Temür, G. (2026) · Pamukkale University Journal of Engineering Sciences · doi:10.65206/pajes.23735
A Stream-Batch Integrated Road Damage Detection System in Big Data Scenarios
Guo, Y., & Liu, H. (2026) · International Conference on Cloud Computing and Big Data Analytics (ICCCBDA) · doi:10.1109/icccbda69573.2026.11676579
Yang, Z., Liu, R., Wang, F., et al. (2026) · Remote Sensing · doi:10.3390/rs18183124
Liu, H., Cao, Z., Ma, Z., et al. (2026) · Foods · doi:10.3390/foods15183211
“The other category is regression-based single-stage detection algorithms, with typical representatives including the You Only Look Once (YOLO) series [17], Single Shot MultiBox Detector (SSD) [18], and Retina Network (RetinaNet) [19].”
Explicit Semantic–Spatial Alignment for Open-Vocabulary Object Detection
Su, P., Ren, W., Han, S., Dong, Q., Xu, H., Ai, X., Wang, Z., Wang, Z., & Liu, H. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37281-9_35
Jiang, S., Hua, Y., Wang, L., et al. (2026) · Optics & Laser Technology · doi:10.1016/j.optlastec.2026.116383
Lightweight identification and positioning technology for marigold corolla
Tohti, G., Fan, Y., Kanghang, Z., et al. (2026) · Signal Image and Video Processing · doi:10.1007/s11760-026-05703-w
“YOLOv1-v3 [15] [13] [14] established the core single-stage framework for multi-scale object detection.”
Adaptive Operator Fusion with Subproblem Decomposition for Enhanced Memory Efficiency
Shi, H., Guan, X., & Yao, J. (2026) · Proceedings of the International Conference on Parallel Processing · doi:10.1145/3832810.3832848
“We take RTX 4070 Ti Super GPU to showcase the results since it is built under one of the latest GPU design, i.e., the Ampere GPU architecture, with leap-forward boost from the previous versions.”
Task aligned contrastive Gaussian learning network for infrared small target detection
Dai, D., Zhang, B., Zhang, X., et al. (2026) · Knowledge-Based Systems · doi:10.1016/j.knosys.2026.117019
Mask‐Guided Local Feature Quantization for Small Object Detection
Dong, H., & Lv, Z. (2026) · IET Image Processing · doi:10.1049/ipr2.70476
Wilks, R., KING, S. E., King, R., et al. (2026) · Ecological Solutions and Evidence · doi:10.1002/2688-8319.70320
Wu, Y., Han, D., & Wang, P. (2026) · Lecture notes in electrical engineering · doi:10.1007/978-981-92-3570-4_31
Xu, S., Wan, S., Ke, R., Liu, X., Yu, B., & Lin, Y. (2026) · Infrared Physics & Technology · doi:10.1016/j.infrared.2026.106901
NGSRNet: Neighbor-Guided Semantic Refinement Network for Drowsy Driving Detection
Liu, Y., Jia, S., Wang, M., et al. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-38401-0_30
FPGA-Based Printed Circuit Board Defect Detection With A Deep Learning AlgorithmPreprint
Öner, E. E., & Güney, S. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7454766
Xia, L. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-38401-0_50
Video‑Based Machine Learning Approaches for Quantifying Pedestrian Safety in Traffic Intersections
Fleischer, J., Ranjan, Y., Banerjee, T., et al. (2026) · Lecture notes in electrical engineering · doi:10.1007/978-981-92-3566-7_49
Enhancing Quality Control in Cashew Nut Production Through Deep Learning: A Case of the M23 Variety
Yamate, K., & Kato, T. (2026) · Springer eBooks · doi:10.1007/978-981-95-9276-0_16
Han, B., Wu, Y., Feng, W., & Mi, X. (2026) · Sensors · doi:10.3390/s26185801
Wang, X. J., Wang, Y., Yuan, H., Sun, J., & Wang, Y. (2026) · Springer proceedings in physics · doi:10.1007/978-981-92-4349-5_48
Salam, K. A. E., ElSayed, H., Abdel‐Kader, R. F., et al. (2026) · Automation · doi:10.3390/automation7050142
宋昊华, & Cai, L. (2026) · International Conference on Intelligent Systems and Robotics (CISR) · doi:10.1109/cisr70722.2026.11680279
“Deep-learning-based object detection methods, especially one-stage YOLO-series detectors, have been widely used in agricultural vision tasks because of their fast inference speed and convenient deployment [3]-[7].”
Liu, S., & Ampatzidis, Y. G. (2026) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2026.112418
Indu (2026) · Journal for Research in Applied Sciences and Biotechnology · doi:10.55544/jrasb.5.4.14
“Faster R-CNN uses region proposals before classification, whereas YOLO predicts object locations and classes within a unified detector [18, 19].”
Naseer, U., & Benedict, B. (2026) · International Journal of Engineering and Management Research · doi:10.31033/ijemr/16.4.2026.1937
CNN Vision Multi-Modal Perception for Robo-Arm Manipulation in Automotive Repair Tasks
Sanikal, V., Narendruni, S. K., Konduru, R., et al. (2026) · doi:10.1109/icadaai64945.2026.11679212
“CNNs have found wide-ranging applications in robotic manipulation in understanding objects, semantic segmentation, and pose estimation [11].”
Liu, Z., Zhang, Y., Yang, Y., Wen, B., Sha, Y., & Lin, Y. (2026) · Aquaculture International · doi:10.1007/s10499-026-02666-0
“End-to-end detectors represented by YOLO provide an effective balance between accuracy and inference efficiency (Redmon et al. 2016).”
A Lightweight RPR-DETR for Prohibited Item Detection in X-Ray Security Inspection Images
Song, J., & Wei, J. (2026) · Electronics · doi:10.3390/electronics15184145
Ren, Y., Wen, G., Zhou, L., et al. (2026) · Journal of Marine Science and Engineering · doi:10.3390/jmse14181697
Research on the Application of AR Technology in Intelligent Inspection of TEG Dehydration Units
刘, 宁. (2026) · Mine Engineering · doi:10.12677/me.2026.145132
Lamy, L., Pacher, C. M. G., Portella, K. F., et al. (2026) · Metals · doi:10.3390/met16091020
AI Based Smart Surveillance System using Thermal Imaging
Jain, S., Singh, A. V., Gupta, R., & Jesrani, K. A. (2026) · MEC International Conference on Big Data and Smart City (ICBDSC) · doi:10.1109/icadaai64945.2026.11679157
A metamorphic testing technique for object detection networks
Wang, Z., Ma, S., Guo, J., Guo, Z., Zhang, Z., & Zhang, W. (2026) · Information and Software Technology · doi:10.1016/j.infsof.2026.108330
Frequency-oriented adaptive real-time object detector for cluttered traffic scenes
Li, Z., Gao, T., Li, S., Chen, T., An, Y., Wen, Y., & Lei, T. (2026) · Nature Communications · doi:10.1038/s41467-026-76346-1 · Cited by 2
Toward generalizable robotic disassembly: A visuo-tactile pipeline for screw unfastening
Goenka, P., Kumar, H., & Chopra, N. (2026) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2026.105743
Resendiz-Ventura, D., Márquez-Olivera, M., Hernández-Herrera, V., et al. (2026) · Diagnostics · doi:10.3390/diagnostics16182976
“YOLO-family architectures were selected because of their one-stage detection design, computational efficiency, and ability to extract hierarchical multiscale features [40].”
Improved YOLOv8n for Lightweight Rail Surface Defect Detection
Wang, L., Si, Y., Wang, J., Liao, L., & Xie, W. (2026) · Technologies · doi:10.3390/technologies14090583 · Cited by 1
Development of an IoT-Based QR Code Access Control and Payment System using Arduino and ESP8266
Tejaswai, G., Manasa, C., Sri, A. S., Sravani, A., Thanusree, C., & Akhila, K. L. (2024) · Journal of Science and Technology · doi:10.46243/jst.2024.v9.i06.pp20-32 · Cited by 7
Rajalakshmi., K., Varsha, P., Komala Devi, K., Muthakshi., S., & Sakthieshwaran, R. (2026) · International Conference on Inventive Systems and Control (ICISC) · doi:10.1109/icisc69558.2026.11681499
Fu, R., Deng, F., Wu, Z., et al. (2026) · Journal of Agricultural Engineering · doi:10.4081/jae.2026.2095
Raj, S. M., Hemanth, V., Nikhil, N., Kumar, R., Sashanka, P. B., & Reddy, D. K. K. (2026) · International Conference on Inventive Systems and Control (ICISC) · doi:10.1109/icisc69558.2026.11681783
“The absence of an authentic smart and available navigation support in the context of the increasing urbanization and technological overload of surrounding environment becomes an increasing gap that should be bridged with the first priority [2][6][7].”
Huang, C., Yang, Z., Chen, J., et al. (2026) · doi:10.1145/3833450.3833501
“At the software level, the YOLOv10 algorithm is applied for image object detection [ 7 ][ 8 ] , and large language models (e.g., Qwen) are invoked to implement elderly-oriented voice companionshi [ 9 ][ 10 ] .”
Confidence-Aware DEYOLO: Calibration Analysis of RGB-IR Object Detection
Aswathi, A., Sreevidhya, K., & Gopal, S. (2026) · International Conference on Inventive Systems and Control (ICISC) · doi:10.1109/icisc69558.2026.11681411
“CNN-based models like Sparse R-CNN [1], CenterNet2 [2], and the You Only Look Once (YOLO) series [3,4,5] as well as Transformer-based models like DETR [6] and Swin Transformer [7] have significantly advanced modern object detection approaches.”
Chen, J., Jianhe, Z., Li, W., et al. (2026) · doi:10.1145/3829641.3829701
“While YOLO models [2] have advanced medical imaging, they often struggle with multi-scale modeling and small-object perception, failing to meet clinical reliability standards.”
Andreev, V. P., & Karpov, M. V. (2026) · Power engineering research equipment technology · doi:10.30724/1998-9903-2026-28-4-223-233
Mantena, G., Satheesh, R., Sreekumar, S., et al. (2026) · Electrical Engineering · doi:10.1007/s00202-026-03759-y
Qu, S., Liu, Z., Zhao, H., et al. (2026) · PLoS ONE · doi:10.1371/journal.pone.0357034
“…Only Look Once), which follows a one-stage detection paradigm, has attained considerable research attention for real-time pest surveillance, primarily owing to its compact structural design, rapid inference characteristics, and its practicality for deployment on edge computing platforms [15,16].”
Machine Vision-Based Smart Basketball System and Hardware Implementation
Ren, W., Li, S., Wang, B., et al. (2026) · Electronics · doi:10.3390/electronics15184206
YOLO-TDH: An object detection framework for power transmission line inspection
Song, B., Zhao, S., Liu, W., & Xue, Y. (2026) · Advanced Engineering Informatics · doi:10.1016/j.aei.2026.105273
Multi-Scale Feature Enhanced YOLOv11 for Silkworm Health Detection
Yi, Y., Shi, X., Shi, Y., et al. (2026) · doi:10.1145/3829641.3829719
“…detection methods generally fall into two categories: two-stage detectors, like Fast R-CNN [1], which achieve high accuracy but incur higher computational latency, and one-stage detectors, such as the YOLO [2] series, which combine localization and classification for millisecond-level inference.”
Task-Oriented and Fog-Severity-Stratified Evaluation of Image Dehazing for UAV Object Detection
Ci, W., Hu, T., Shao, Y., Lin, W. S., Mao, H., Lai, X., & Liu, J. (2026) · IEEE Access · doi:10.1109/access.2026.3733830
Pacharne, V., Rananaware, S., Thoke, A., Dasi, M., & Prof Dongre, A. G. (2026) · International Conference on Inventive Systems and Control (ICISC) · doi:10.1109/icisc69558.2026.11681137
“The system YOLO, developed by Redmon et al. [6], has developed into a real-time detection framework, and one of the following developments of this technology was YOLOv3 [7].”
An Improved Lightweight Dense Pedestrian Detection Algorithm Based on YOLOv11
Kuang, L., & Li, Y. (2026) · Lecture notes in electrical engineering · doi:10.1007/978-981-95-6825-3_42
Wu, Y., Zhang, Y., Zhang, S., et al. (2026) · Journal of Imaging Informatics in Medicine · doi:10.1007/s10278-026-02292-5
Humanes, A. C., Calil, A. L. A., Wawruk, H. D., et al. (2026) · International Journal of Legal Medicine · doi:10.1007/s00414-026-04013-7
Aldoski, Z. N., Koren, C., & Miletics, D. (2026) · Sensors · doi:10.3390/s26185843
“In recent years, vision-based detection systems leveraging deep learning have achieved significant success in traffic sign recognition tasks, thanks to their ability to learn complex visual representations from large-scale data [2].”
Li, Y., Zhang, F., & Achim, A. (2026) · Remote Sensing · doi:10.3390/rs18183172
“A common strategy for efficient SAR ship detection is to adopt compact one-stage pipelines derived from real-time detectors such as You Only Look Once (YOLO) [20] and RTMDet [21].”
DECA-YOLO: Dual-pooling efficient channel attention for real-time pedestrian detection
S, S. B. V., & Raman, R. (2026) · Multimedia Tools and Applications · doi:10.1007/s11042-026-21903-5
“The YOLO [29] family of models has remained a popular choice for real-time detection.”
Anusuya, S. (2026) · International Conference on Inventive Systems and Control (ICISC) · doi:10.1109/icisc69558.2026.11680997
“These combinations obtained mAP@50 scores of only about 0.38 – 0.46 on the NEU-DET benchmark [16] and, more importantly, were unable to generate bounding-box localizations, making them unusable for closed-loop robotic repair [2][3].”
InfluentialEnhancing gaze estimation using dilated CNN architectures with transfer learning
Lin, H., Huang, Y.-H., Kuo, P., et al. (2026) · Journal of the Chinese Institute of Engineers · doi:10.1080/02533839.2026.2720029
Sateesh, B. S. A. D. (2026) · International Journal of Advanced Research in Science Communication and Technology · doi:10.48175/ijarsct-38402
BOM-YOLOv12n: A Lightweight Detection Model for Protective Equipment in Smart Construction Sites
Wang, H., Zhou, S., Zhu, G., et al. (2026) · Electronics · doi:10.3390/electronics15184198
MSN-TE: a network for multi-scale object detection in turbid environments
Xu, H., & Zhang, W. (2026) · Ships and Offshore Structures · doi:10.1080/17445302.2026.2731429
M, A. K., Avins, V. R., & Nath, A. S. (2026) · International Conference on Inventive Systems and Control (ICISC) · doi:10.1109/icisc69558.2026.11681229
“YOLO models approached object detection as a unique regression problem that consolidated everything to one phase thus enabling reall-time inference [13].”
Tyagi, S., Rawat, P., Yadav, D., & Upadhyay, P. (2026) · Expert Systems · doi:10.1111/exsy.70422
AN INTELLIGENT RECYCLING SORTING SYSTEM BASED ON YOLOV8 IMAGE RECOGNITION AND A MOBILE ROBOTIC ARM
Chen, P.-C., & Pan, C. (2026) · International Journal of Research -GRANTHAALAYAH · doi:10.29121/granthaalayah.v14.i8.2026.7076
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.