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 45,201–45,300 of 51,399
Pushing the Limits of Real-Time Face Detection: A Comparative Analysis of YOLOv11 Models
Bokash, M., Almaktari, A., & Humbe, V. T. (2025) · International Conference on Emerging Smart Technologies and Applications (eSmarTA) · doi:10.1109/esmarta66764.2025.11132186
“YOLOv1 [9] set the foundation, with subsequent versions (YOLOv2 [10], YOLOv3 [11], and later iterations) refining the approach through techniques like anchor boxes, multi-scale training, and feature pyramid networks.”
A Parallel Weight Aggregated Ensemble of pre-trained models for Open Parking Space Detection
Nair, R. S., Phansalkar, S., Kalbhor, A., Patel, S., Solanki, A., Jadhav, A., Ambati, H., & Ghorpade, U. (2025) · International Conference on Emerging Trends in Industry 4.0 Technologies (ICETI4T) · doi:10.1109/iceti4t63625.2025.11132132
“You Only Look Once (YOLO)v5 [17] and (YOLO)v7 has been proved better in object detection.”
Detection of Forklift Trucks in Warehouses using Transfer Learning Techniques
Hingorani, S., Teli, A., Nair, R. S., Garware, C. P., & Pathak, G. R. (2025) · International Conference on Emerging Trends in Industry 4.0 Technologies (ICETI4T) · doi:10.1109/iceti4t63625.2025.11132230 · Cited by 1
“…Deep learning models such as AlexNet [12], Regions with CNN features (RCNN) [13], You Look Only Once (YOLO): Unified, Real-Time Object Detection [14], GoogleNet [15], SSPNet, FastRCNN, FasterRCNN, MaskRCNN , VGGNet [16], ResNet [17], DetNet [18], SquuezeNet [19], Xception [20], ShuffleNet [21]…”
Efficient Object Detection Using Quasi-2D LiDAR Data for Autonomous Vehicles
Das, S., Clemens, J., Ghugare, D., & Schill, K. (2025) · International Conference on Information Fusion (FUSION) · doi:10.23919/fusion65864.2025.11124054 · Cited by 2
“We apply three state-of-the-art 2D object detection models to the different input encodings: Faster-RCNN [3], RetinaNet [5], and YOLO [4].”
Source Detection in Broadband Passive SONAR with Vision Transformers and Poisson RFS Loss
Shaw, W., Fontana, M., Üney, M., Colquitt, D. J., Riches, S., & Jones, C. (2025) · International Conference on Information Fusion (FUSION) · doi:10.23919/fusion65864.2025.11124186
“Common object detection frameworks, such as YOLO [19], [21] and Faster R-CNN [22], [23], rely on bounding boxes and spatial coherence of objects, making them less suitable for passive SONAR.”
Joint Vessel Multilateration and Classification Using Coastal Surveillance Cameras
Dias, S. S., Braga, A. R., Martinho, W. C. S., Rangel, P., de Oliveira, J. R. P., & de Carvalho, J. G. (2025) · International Conference on Information Fusion (FUSION) · doi:10.23919/fusion65864.2025.11124176
“Additionally, fine-tuning data-driven models like those of the YOLO family [3] often requires a huge amount of manually annotated samples to properly detect ships typically present in a geographical region; a very laborious task.”
Fire detection models based on attention mechanisms and multiscale features
Zhang, S., Chen, M., Li, K., Wen, H., & Sun, L. (2025) · Computer Science and Information Systems · doi:10.2298/csis241225059z
Deep Learning for Eddy Detection in the Arctic Marginal Ice Zone by Spaceborne SAR
Zi, N., Li, X.-M., Yuan, H., et al. (2025) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2025.3603543
Framework for Filtering Neural Network Predictions for Robust State Estimation
Walia, R., & Leahy, K. (2025) · IEEE Engineering Reliable Autonomous Systems (ERAS) · doi:10.1109/eras63351.2025.11135859
“However, they develop a regression architecture using a combination of deep learning [8] and classical vision techniques, and use Breach [9] to find counterexamples for this architecture and given a specification.”
Mining a Century of Swiss Trademark Data
Travaglia, D., Findahl, J., D’Ambros, M., Mocci, A., & Parchet, R. (2025) · ACM Symposium on Document Engineering (DocEng) · doi:10.1145/3704268.3742704
“The success of R-CNN served as a foundation for the development of other models, including YOLO [25] and RetinaNet [15].”
Villanova-Aparisi, D., Martínez-Hinarejos, C.-D., Romero, V., & Pastor-Gadea, M. (2025) · ACM Symposium on Document Engineering (DocEng) · doi:10.1145/3704268.3742699
Marine plankton species classification and microbial activity analysis using deep learning
Cho, M.-J., Jeung, M., Baek, S., & Baek, S. (2025) · Environmental Engineering Research · doi:10.4491/eer.2025.155
Serikbay, A., Nurmanova, V., Akhmetov, Y., Zollanvari, A., & Bagheri, M. (2025) · International Transactions on Electrical Energy Systems · doi:10.1155/etep/8669289
Yen, M.-H., Lin, Y.-X., Huang, K.-P., et al. (2025) · Electronics · doi:10.3390/electronics14173435
Wang, D., Chen, Y., Mao, X., et al. (2025) · Lecture notes in networks and systems · doi:10.1007/978-3-031-94898-5_10
An Enhanced YOLO-Based Framework for Wiring Harness Connector Object Detection
Lei, C., Wong, K. Y., Azlan, N. A. A. N., & Gao, C. (2025) · Lecture notes in networks and systems · doi:10.1007/978-3-031-94898-5_11
Object Recognition for the Visually Impaired Using Machine Learning
Gomathi, V., & Suganya, S. (2024) · International Conference on Communication, Computing, Smart Materials and Devices (ICCCSMD) · doi:10.1109/icccsmd63546.2024.11015119
An Advanced YOLOv8-Nano Model with Attention Neck Network for PCB Bubble Detection
Wang, Z., Lee, J., Kim, S., Joe, I., Cho, S., Kim, H., & Sung, D. (2025) · Lecture notes in networks and systems · doi:10.1007/978-3-031-96759-7_41
Palanisamy, M., Ashwin, J. B., Kaimal, S., et al. (2024) · doi:10.1109/icccsmd63546.2024.11015135
Ao, Y., Zhu, D., Li, C., et al. (2025) · Neural Processing Letters · doi:10.1007/s11063-025-11798-y
Li, Y., Qiu, H., Wang, X., Dong, N., & Yu, X. (2025) · SoftwareX · doi:10.1016/j.softx.2025.102328
Ren, W., Qian, T., Li, G., et al. (2025) · International Conference on Computer Information and Big Data Applications (CIBDA) · doi:10.1145/3746709.3746745
Smart Detection and Measurement: The Real-AODM System
Peng, B., & Hu, F. (2025) · Communications in computer and information science · doi:10.1007/978-3-031-98235-4_7
Depth Estimation for Autonomous Vehicles with Enhanced Perception
Venkatraman, K., Nanduri, A., & Reddy, D. (2025) · Algorithms for intelligent systems · doi:10.1007/978-981-96-4539-8_7
Automatic Detection of Erythrocytes for Sickle Cell Disease Identification Based on YOLOv8n Network
Aiswarya, S., Krishnaveni, M., Subashini, P., et al. (2025) · Algorithms for intelligent systems · doi:10.1007/978-981-96-4539-8_21
K, P. M., Divya, V. S., Pavitra, Saika, K., & Wadi, S. J. (2025) · International Journal of Advanced Research in Science Communication and Technology · doi:10.48175/ijarsct-28718
Zhang, Y., Ren, H., Pan, J., Xian, L., Ma, Q., Han, C., Liu, G., Huang, X., Yang, L., & Chen, Y. (2025) · IEEE Access · doi:10.1109/access.2025.3604252
MMGT: Motion Mask Guided Two-Stage Network for Co-Speech Gesture Video Generation
Wang, S., Liu, J., Wang, W., Jin, Y., Du, J., & Han, Z. J. (2025) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2025.3604109 · Cited by 3
“These steps aim to align technological progress with social responsibility while encouraging socially beneficial uses.”
Aircraft Surface Crack Detection Using an AI-Powered UAV System
Khan, A. A., Prakash, V., & Jaiswal, K. (2025) · International Conference on Advances in Computing, Communication, Embedded and Secure Systems (ACCESS) · doi:10.1109/access65134.2025.11135539
“Automated image analysis is performed using powerful object detection algorithms such as YOLO [8], which allows capturing UAV high-quality images quickly and searching defects [9], [10].”
Detection of Varroa Mites from Bee Images Using YOLO Architecture
Le, T.-N., Nguyen, D.-T., Phan, T.-T.-H., et al. (2025) · International Conference on Multimedia Analysis and Pattern Recognition (MAPR) · doi:10.1109/mapr67746.2025.11133726
“The first version, YOLOv1 [12], was proposed in 2016 and employed a single neural network that simultaneously detects object locations and classifies objects.”
Vehicle Identification and Classification using Convolutional Neural Networks
Patni, J. C., S, C. K., Bahadure, N. B., Shweta, S., Poornima, B. M., Chaturvedi, S. K., Ravipraksh, B. P., & Anup, S. B. (2024) · International Conference on Innovative Sustainable Computational Technologies (CISCT) · doi:10.1109/cisct62494.2024.11134211
Vo, K.-T., Phan, A.-M., Le, H.-D., & Pham, V.-C. (2025) · International Conference on Multimedia Analysis and Pattern Recognition (MAPR) · doi:10.1109/mapr67746.2025.11133773
“The introduction of deep learning led to CNN-based object detectors, including Fast R-CNN [4], YOLO [5], SSD [6], and DETR [7], significantly improving detection accuracy and efficiency.”
Development of Comfortable and Energy-Saving Driving System Based on OBDII and YOLOv7 Neural Network
Lin, Y.-X., Yen, M.-H., Guan, Y.-H., et al. (2025) · International Symposium on Computer, Consumer and Control · doi:10.1109/is3c65361.2025.11130996
Systematic evaluation of deep learning-based vehicle detection methods
Tran, B.-C., Nguyen, N., Vu, P. T. D., et al. (2025) · International Conference on Multimedia Analysis and Pattern Recognition (MAPR) · doi:10.1109/mapr67746.2025.11133912
YOLOv11-Based Real-Time PCB Inspection for Smart Manufacturing
Chiang, P.-H., Chen, K.-H., Hou, Y.-Y., et al. (2025) · International Symposium on Computer, Consumer and Control · doi:10.1109/is3c65361.2025.11131011
“In contrast, one-stage detectors such as SSD[4] and YOLO[5] eliminate the proposal generation step and directly predict bounding boxes and class probabilities from feature maps, achieving substantial improvements in detection speed.”
Minh, T. H., Bao, L. L., Thuan, P. N., Tien, T. N., Phong, H. N., Do, T., Le, D.-D., & Ngo, T. D. (2025) · International Conference on Multimedia Analysis and Pattern Recognition (MAPR) · doi:10.1109/mapr67746.2025.11133808
“The advent of deep learning and convolutional neural networks (CNNs) [3] revolutionized object detection, with models like Faster R-CNN [4], YOLO [5], and SSD [6] enabling real-time vehicle detection.”
Optimizing Cattle Detection in Smart Farming Using YOLO and Attention Mechanisms
Deepak, D., & D’Mello, D. A. (2025) · Lecture notes in networks and systems · doi:10.1007/978-981-96-4151-2_35
MedVidDeID: Protecting privacy in clinical encounter video recordings
Mopidevi, S., Jang, K. J., Alasaly, B., Pugh, S., Park, J., Batugo, A., Hwang, S., Eaton, E., Mowery, D. L., & Johnson, K. B. (2025) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2025.104901 · Cited by 3
“Current computer vision techniques use models for object detection and pose estimation to de-identify individuals frame-by-frame, either by blurring identifiable features or by generating new faces to replace the original [38–41].”
Line segment using displacement prior
Zhu, X., Yu, H., Zhang, Y., et al. (2025) · Open Computer Science · doi:10.1515/comp-2025-0035
Xiao, J., Wang, Y., Xiang, S., et al. (2025) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-031-97352-9_17
Rose Disease Detection Using YOLO. A Deep Learning-Based Approach
Islam, P., Ziden, Z. D., Abdullah, S., Hasan, M. A., Asif, M. A., Khan, M., & Mittra, T. (2025) · Lecture notes in networks and systems · doi:10.1007/978-981-96-5607-3_13
Leaf Disease Detection Using YOLOv8
Kumari, L., & Majumder, A. (2025) · Lecture notes in networks and systems · doi:10.1007/978-981-96-5822-0_7
Object Detection on Complex Architectural Floor Plans with Efficient Attention Mechanisms
Xu, Z., Jha, N., Mehadi, S., Maity, S. P., & Mandal, M. K. (2025) · Lecture notes in networks and systems · doi:10.1007/978-981-96-4273-1_8
YOLO for Urban Traffic: Insights from Helsinki Port Surveillance
Sharma, S., Singotam, S., Kayastha, A., Jafari, O., Happonen, A., Skön, J.-P., Heikkonen, J., & Kanth, R. K. (2025) · Lecture notes in networks and systems · doi:10.1007/978-981-96-5958-6_2
A Comprehensive Review of Steganography Techniques Using Object Detection
Mittal, P., & Dalal, M. (2025) · Lecture notes in networks and systems · doi:10.1007/978-981-96-5958-6_48
An Optimized CNN-Based Approach for Efficient Object Detection Using YOLO
Patil, M. B., Bag, V. V., Aherwadi, N., & Potraj, S. (2025) · Springer proceedings in mathematics & statistics · doi:10.1007/978-3-031-84517-8_34
Smart Traffic Control System Leveraging YOLOv8 and OCR for Improved Urban Mobility
Shaikh, S., Dani, D., & Reddy, M. (2025) · Lecture notes in networks and systems · doi:10.1007/978-981-96-5955-5_17
Drone Detection and Antidrone System Using YOLO: An Effective Approach to Airspace
Astudillo, J., Chachalo, R., Iza, C., & Zhinín-Vera, L. (2025) · Communications in computer and information science · doi:10.1007/978-3-031-98287-3_30
“Visualization” Technology of Concrete Construction Using AI and Image Analysis
Matsumoto, S., Mizuno, K., Watanabe, K., et al. (2024) · Concrete Journal · doi:10.3151/coj.62.9_781
Navarro, J. M., Morales, J., & Martínez, J. L. (2025) · Jornadas de Automática · doi:10.17979/ja-cea.2025.46.12062
Luo, J., Liu, Z., Martynov, S. A., Zhao, X., Tan, J., & Lu, S. (2025) · Signal Image and Video Processing · doi:10.1007/s11760-025-04446-4
“In contrast, single-stage algorithms, such as the YOLO (You Only Look Once) family [19] and SSD (Single Shot MultiBox Detector) [18], directly predict objects from the input image without the need for region proposal steps, significantly reducing computational overhead and improving inference speed.”
Xie, S., Quan, T., Luo, J., et al. (2025) · Agriculture · doi:10.3390/agriculture15171854
Explainable Artificial Intelligence for Object Detection in the Automotive Sector
Siganos, M., Grammatikis, P. I. R., Λάγκας, Θ., et al. (2025) · doi:10.3390/engproc2025107044
Generative Grasp Detection and Estimation with Concept Learning-Based Safety Criteria
Farhad, A.-H., Abuibaid, K., Plociennik, C., Wagner, A., & Ruskowski, M. (2025) · Mechanisms and machine science · doi:10.1007/978-3-032-02106-9_60
Deep Learning for Visual Inspection of Ball Bearings
Tepavčević, T., Lazović, S., & Petrović, V. M. (2025) · Mechanisms and machine science · doi:10.1007/978-3-032-02106-9_8
Yılmaz, Y., Nayır, S., & Erdoğdu, Ş. (2025) · Structural Concrete · doi:10.1002/suco.70317
“21 Ren et al. 22 proposed an improved deep learning-based network called CrackSegNet.”
Khazmi, K., & Lachiri, Z. (2025) · doi:10.1109/ic_etc65981.2025.11141306
“When Joseph Redmon et al. originally announced YOLO in CVPR 2016 [27], it was a game-changer for object detection research since it could detect objects in real time with an accuracy one step ahead of other models.”
Simulated Attacks and Defenses Using Traffic Sign Recognition Machine Learning Models
Lin, C., Yu, C.-T., & Chen, Y. (2025) · doi:10.3390/engproc2025108011
“We used the YOLOv5 machine learning model [5], which is an object detection model proposed by Joseph Redmon in 2015 with a one-stage detection method.”
Luo, X., & Matsumoto, T. (2025) · Lecture notes in civil engineering · doi:10.1007/978-981-96-8464-9_1
A Multi-Camera-Based Pedestrian Tracking and Re-Identification Solution
谭, 丽. (2025) · Computer Science and Application · doi:10.12677/csa.2025.159220
Self-guided interpretation of images for blind users based on multi-layered interaction
Bousnitra, W., Hervás, R., Díaz, A., Leo, D., Martín, C. A., & Sosa, S. (2025) · Universal Access in the Information Society · doi:10.1007/s10209-025-01256-w
“Models like YOLO (You Only Look Once) can detect objects in real-time with high efficiency [ 12].”
Chen, L., Deng, H., Xu, Q., & Han, X. (2025) · Tsinghua Science & Technology · doi:10.26599/tst.2025.9010055 · Cited by 1
İnsansız Hava Aracı Görüntülerinden Beton Yüzeyi Çatlaklarının Yolo Mimarileri ile Tespiti
Ödübek, E., & Atik, M. E. (2025) · Adıyaman Üniversitesi Mühendislik Bilimleri Dergisi · doi:10.54365/adyumbd.1554821
Ai-Powered Football Match Analysis Using YOLOv8 and Spatial Analytics
Arun, S., Mohamed Rizwan, H., & Sindhuja, M. (2025) · doi:10.1109/icdici66477.2025.11135176
YOLOv10-CS: A Model for Enhancing Recognition of Small Targets
Zhou, Z., Wang, X., Ding, L., et al. (2025) · doi:10.1109/crsit66101.2025.11141629
Real-Time UAV Tracking: A Comparative Study of YOLOv8 with Object Tracking Algorithms
Russo, T., & Vitzilaios, N. I. (2025) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra55743.2025.11128602
“A prominent example is You Only Look Once (YOLO) [10].”
Research on Rail Surface Crack Detection Based on Improved YOLOv5
Zhang, Z., Wu, X., Ye, M., et al. (2025) · International Symposium on Robotics, Artificial Intelligence and Information Engineering (RAIIE) · doi:10.1109/raiie65740.2025.11140528
“CNN-based target detection methods, such as Regional Convolutional Neural Network (R-CNN) [9], FasterR-CNN [10], YOLO (YouOnlyLookOnce) [11], and Single-Shot Multi-Frame Detector (SSD) [12], are able to achieve a balance between real-time and detection accuracy by extracting image features through…”
Efficient Detection of Grab Based on Improved Lightweight MC-YOLOv5s
Bian, X., Zhou, C., Cui, R., et al. (2025) · International Symposium on Robotics, Artificial Intelligence and Information Engineering (RAIIE) · doi:10.1109/raiie65740.2025.11140559
Deep Learning-based Key Equipment Recognition Method for Substation Inspection Robots
Chen, Z., Zhou, S., Zheng, X. W., Yan, Y., Zeng, X., Yang, B., Deng, M., & Wei, S. (2025) · International Symposium on Robotics, Artificial Intelligence and Information Engineering (RAIIE) · doi:10.1109/raiie65740.2025.11140318
“These include other YOLO - series algorithms, the Fully Convolutional One - Stage (FCOS) target detection algorithm [15], Faster Region Convolutional Neural Network (Faster RCNN) [16], AHIPDNet [17], RepViT algorithm [18], and OFN algorithm [19].”
YOLO-ACNet: A Lightweight Multiscale Object Detection Network for Autonomous Driving
Xin, H., & Deng, L. (2025) · International Symposium on Robotics, Artificial Intelligence and Information Engineering (RAIIE) · doi:10.1109/raiie65740.2025.11140258
“Beginning with YOLOv7 [14], the YOLO series [8]– [19] has integrated attention mechanisms (e.g., E-ELAN) to mitigate occlusion issues.”
Feedback RoI Features Improve Aerial Object Detection
Ren, B., Xu, B., Wang, J., Gao, H., Yu, Q., & Deng, Z. (2025) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra55743.2025.11127970 · Cited by 1
“Despite impressive advances in object detection [1]±[4], detecting objects in aerial images remains a challenging problem for two reasons: (a) the objects vary drastically in orientation, scale, aspect ratios, and density; (b) the qualities of images vary significantly due to factors such as sensor…”
Deep Learning-Based System for Detection and Classification of Household Entry Points Using YOLOv11
Kotevski, B., Koceski, S., & Koceska, N. (2025) · MIPRO ICT and Electronics Convention (MIPRO) · doi:10.1109/mipro65660.2025.11131769
“The proposed real-time object detection and classification workflow based on You Only Look Once (YOLO) v11 [21] object detection model is depicted on Fig.”
SY-YOLOv5s: An Improved YOLOv5s Module for Road Vehicle and Pedestrian Target Detection
Yang, R., Cai, Y., Wei, T., et al. (2025) · doi:10.1109/dmcis65888.2025.11138411
“In contrast, single-stage object detectors, such as YOLO [4]– [6] and SSD [7], [8], perform classification and regression tasks simultaneously.”
Target-Aware Viewpoint Generation for Active Robotic Exploration in Unknown Environments
Xu, P., Liu, H., Li, Z., Bai, Z., & Fang, Z. (2025) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra55743.2025.11127467
“Next, we project downsampled points to RGB image and obtain potential target points C sub ⊂ C uni within the 2D bounding boxes detected by YOLOv5 [23].”
Yolo- Driven Machine Learning System for Enhanced Object Recognition and Automation
Singh, S., Dhanda, N., & Gupta, K. K. (2025) · International Conference on Data Intelligence and Cognitive Informatics (ICDICI) · doi:10.1109/icdici66477.2025.11134982
Chemistry3D: Robotic Interaction Toolkit for Chemistry Experiments
Li, S., Huang, Y. H., Guo, C., et al. (2025) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra55743.2025.11128846
“For this task, we selected YOLOv5 [63] as our algorithm.”
Zheng, Q., Hu, J., Liu, Y., Zeng, Z., Wang, F., & Lam, T. L. (2025) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra55743.2025.11128621
“Single-stage methods [24] [25] [26] [27] offer faster processing but lower precision due to the absence of a fine processing step.”
ICSnet: An efficient object detection network for industrial complex scenes
Li, D.-J., Bai, F., Li, S.-L., et al. (2026) · Measurement · doi:10.1016/j.measurement.2025.118836 · Cited by 1
Hava Araçları için Otonom İniş Sistemi: Derin Öğrenme ve Bilgisayarlı Görü Tabanlı Bir Yaklaşım
Şatır, E., Demirtaş, E., Ağdemir, H., & Yıldız, F. (2025) · Iğdır Üniversitesi Fen Bilimleri Enstitüsü Dergisi · doi:10.21597/jist.1644324
Diver to Robot Communication Underwater
Codd-Downey, R., & Jenkin, M. R. M. (2025) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra55743.2025.11128628
“In [23] we presented a weakly-supervised approach to identify the diver gestures shown in Figure 2 using Yolo [24].”
CA-IoU: Central-Gaussian Angle-IoU for Robust Bounding Box Regression
Jang, J., Kim, D., & Paik, J. (2025) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra55743.2025.11127790
Flying Through Moving Gates without Full State Estimation
Römer, R., Emmert, T., & Schoellig, A. P. (2025) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra55743.2025.11127465 · Cited by 1
Key Operator Vectorization for LeNet and ResNet Based on Buddy Compiler
Chen, J., Chen, W., & Cai, Z. (2025) · Applied Sciences · doi:10.3390/app15179523
Enhancing Public Safety Situational Awareness Using Edge Intelligence
Lira, P., Loss, S. M., Costa, K., de Araújo, D. S. A., Neto, A. R., Cacho, N., Batista, T., Cavalcante, E., Lopes, F., & Nogueira, E. (2025) · WiPiEC Journal - Works in Progress in Embedded Computing Journal · doi:10.64552/wipiec.v11i1.88
An Efficient Method for Object Detection with Automatic Illumination Correction
Kumar, C. K., Kumar, C. K., Sethi, G., & Rawal, K. (2025) · International Journal of Electrical and Electronics Research · doi:10.37391/ijeer.130302
Bo, L., Siaw, F. L., Thio, T. H. G., et al. (2025) · International Journal of Electrical and Electronics Research · doi:10.37391/ijeer.130305
Real-Time Oil Spill Detection with YOLO Framework for Marine Ecosystem Surveillance
Talasila, S., Gurrala, V. K., Varshini, M., et al. (2025) · International Journal of Electrical and Electronics Research · doi:10.37391/ijeer.130310
Contactless Pulse Rate Assessment: Results and Insights for Application in Driving Simulators
Nešković, Đ. D., Stojmenova, K., Sodnik, J., & Miljković, N. (2025) · Applied Sciences · doi:10.3390/app15179512 · Cited by 1
“Additionally, advanced machine learning techniques for motion compensation and facial skin segmentation could further improve the proposed approach.”
Chiaroni, F., Ayub, A., & Ahmad, O. S. (2025) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra55743.2025.11127615 · Cited by 2
“Key innovations such as object detection [33], [34], [5], scene understanding [31], and image segmentation [16], as well as vision-based real-time path planning and navigation [28], [40], now enable robots to interpret and analyze their surroundings more effectively, leading to more efficient…”
Stable Tracking of Eye Gaze Direction During Ophthalmic Surgery
Hong, T., Cai, S., Li, B., et al. (2025) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra55743.2025.11128581
“Firstly, a fine-tuned Y OLO [16] model is employed to accurately identify the sclera and iris regions, effectively overcoming the limitations associated with face detection.”
Repmobip: A Re-parameterized Lightweight Multi-Task Network for Panoptic Driving PerceptionPreprint
Zhang, J., Zhang, Y., & Wang, H. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5434963
LUNAR: Periodicity-aware time-series analysis framework for LUNg Auscultation Respiratory detection
Lee, J., Park, S.-Y., Park, J. S., Suh, D. I., & Kim, K. (2025) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2025.110947 · Cited by 1
Zynq-Based Deep Learning for Lightweight Recognition of Acetone Concentration in FAIMS System
Li, H., Tang, X., Li, Y., Zhang, R., & Du, X. (2025) · IEEE Sensors Journal · doi:10.1109/jsen.2025.3603745
“YOLO is a state-of-the-art end-to-end target detection framework first proposed by Redmon et al. [34].”
Enhancing Underwater Human-Robot Communication: Real-Time Hand Gesture Recognition Using YOLO Models
Sharma, A. R., Mourya, S., Singh, J., et al. (2025) · IEEE Applied Sensing Conference (APSCON) · doi:10.1109/apscon63569.2025.11144250
Development of an Intelligent Transportation System for Next-Gen AI
Kumar, C. A., Chikoti, V. K., Ramsai, J., et al. (2025) · International Conference on Computing Methodologies and Communication (ICCMC) · doi:10.1109/iccmc65190.2025.11140814
“However, the business world has been significantly disrupted by CNNs and the "You Only Look Once" (YOLO) mentality [5][6].”
Shen, W., Wang, Y., Liu, M., Wang, J., & Ding, R. (2025) · IEEE International Conference on Real-time Computing and Robotics (RCAR) · doi:10.1109/rcar65431.2025.11139788
“The YOLO (You Only Look Once) series [17] [18] [19] [20] [21] represents one of the most prominent one-stage object detection models, renowned for its high detection speed and accuracy.”
Instrument Image Detection and Recognition Based on YOLOv8n-CFCA Algorithm*
Wang, D., Wang, C., Li, A., Li, L., Chen, B., & Shao, H. (2025) · IEEE International Conference on Real-time Computing and Robotics (RCAR) · doi:10.1109/rcar65431.2025.11139667
SmartSight: Object and Obstacle Detection for the Visually Impaired
Preethi, R., V, Bharadwaj, A. R., Durrani, A., et al. (2025) · International Conference for Emerging Technology (INCET) · doi:10.1109/incet64471.2025.11140122
“Recent studies emphasize the efficiency of YOLO (You Only Look Once) in real-time object detection [1, 2, 3].”
Optimizing Traffic Sign Recognition for Autonomous Vehicles Using SSD-MobileNet_v2
Jabe, M. M. N., Hasan, M. S., & Ahmed, A. (2025) · International Conference on Information Science, Computer Technology and Transportation (ISCTT) · doi:10.1109/isctt66403.2025.11137882
“The only downside with this GPU is that it is designed to support Raspberry’s Compute Unit Device Architecture (CUDA) [5] for speeding-up its deep learning computation process.”
Fang, K., Xu, Y., Xu, H., et al. (2025) · International Conference on Information Science, Computer Technology and Transportation (ISCTT) · doi:10.1109/isctt66403.2025.11137990
“They mainly include the YOLO [5] series, SSD [6] , and RetinaNet [7], among others.”
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.