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 31,401–31,500 of 51,399
Privacy‐preserving labeling‐free occupancy counting sensor based on ToF camera and clustering
Jeong, J., & Park, W. (2025) · ETRI Journal · doi:10.4218/etrij.2025-0022 · Cited by 2
“One of the most widely adopted frameworks for object detection and occupancy monitoring is YOLO (you only look once), known for its real-time processing capability and high accuracy in detecting and classifying multiple objects within complex environments [5].”
Li, X., Chen, L., Wang, Q., Zhou, M., Long, J., Chen, X., Zhao, J., Yu, J., & Guo, Y. (2025) · Antibiotics · doi:10.3390/antibiotics14090917 · Cited by 3
“Representative examples include Single-Shot MultiBox Detector (SSD) [27] and the You Only Look Once (YOLO) series [28–36].”
Yang, H., Wang, Y., & Xin, H. (2025) · Measurement · doi:10.1016/j.measurement.2025.118933 · Cited by 2
Su, H., Wang, S., Su, H., Ma, F., Li, Y., & Li, J. (2025) · Agriculture · doi:10.3390/agriculture15181954 · Cited by 3
Retrieval Augmented Generation with Multi-Modal LLM Framework for Wireless Environments
Mohsin, M. A., Bilal, A., Bhattacharya, S., & Cioffi, J. M. (2025) · IEEE International Conference on Communications workshops · doi:10.1109/iccworkshops67674.2025.11162457 · Cited by 14
SeFENet: Robust Deep Homography Estimation via Semantic-Driven Feature Enhancement
Shi, Z., Zhang, Z., Cui, K., An, R., Liu, J., & Jiang, Z. (2025) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2025.3612762 · Cited by 6
Wibowo, P., Wajdi, A. Z., Muliawati, T. H., Fariza, A., & Kiyoki, Y. (2025) · International Electronics Symposium (IES) · doi:10.1109/ies67184.2025.11161008 · Cited by 4
“Initially launched in 2015, YOLO transformed object detection by conceptualizing it as a singular regression issue, enabling the model to directly predict bounding boxes and class probabilities from the entire image in one assessment [10].”
Anchor-Free Object Detection Method in Remote Sensing Image via Adaptive Multi-Scale Feature Fusion
Wang, K., Wu, W., Tie, J., Wu, X., & Fu, Y. (2023) · Journal of Computer-Aided Design & Computer Graphics · doi:10.3724/sp.j.1089.2023.19673 · Cited by 2
Mechanics of rice grain breakage and YOLOV4-based damage quantification
George Ashwehmbom, L. O. O. H., Wang, X., Jiaxin, K., et al. (2025) · Materials & Design · doi:10.1016/j.matdes.2025.114831 · Cited by 2
An advanced adaptive detector for oriented objects in remote sensing imagery
Li, Q., Fan, Z., & Zhao, X. Y. (2025) · Scientific Reports · doi:10.1038/s41598-025-07333-7 · Cited by 3
“On the other hand, one-stage detectors like YOLO 5,6 predict class probabilities and bounding box coordinates directly from the entire image in a single step, offering faster processing times but at the cost of some accuracy due to class imbalance and background confusion issues.”
LDA-YOLO: lightweight dynamic adjustment real-time detection power equipment model
Chen, H., Zhu, C., Bai, H., et al. (2025) · Engineering Research Express · doi:10.1088/2631-8695/ae0f73 · Cited by 2
Rashmi, B. N., Guru, R., Anusuya, M. A., et al. (2025) · Neural Computing and Applications · doi:10.1007/s00521-025-11686-5 · Cited by 2
“YOLOv3 (You Only Look Once Version 3) [41] is a widely used real-time object detection model, known for its ability to detect objects at multiple scales, making it suitable for various applications (Redmon et al., 2018).”
InfluentialThio, T. H. G., Siaw, F. L., & Mohammed, O. H. (2025) · AIP conference proceedings · doi:10.1063/5.0291323 · Cited by 2
Leveraging YOLOv9 for Advanced Colorectal Polyp Detection
Haider, Z., Azar, A. T., & ALmutlaq, S. (2025) · Engineering Technology & Applied Science Research · doi:10.48084/etasr.10701 · Cited by 2
LCPD-DETR: a lightweight object detection model based on RT-DETR for military camouflaged personnel
Chen, L., Chen, M., Zhang, X., & Xie, Z. (2025) · Journal of Real-Time Image Processing · doi:10.1007/s11554-025-01772-1 · Cited by 2
Bamaqa, A., & Alahamade, W. O. (2025) · Scientific Reports · doi:10.1038/s41598-025-19342-7 · Cited by 2
“It incorporates notable improvements that make it particularly suitable for processing high-resolution histopathology images 29 .”
ShapeICP: Iterative Category-Level Object Pose and Shape Estimation From Depth
Zhang, Y., Sawhney, H. S., & Leonard, J. J. (2025) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2025.3619808 · Cited by 2
Wang, K., Suo, B., Qian, W., Zhang, G., Wang, T., & Yang, Y. (2025) · International Journal of Computational Intelligence Systems · doi:10.1007/s44196-025-00982-6 · Cited by 4
YOLO-FMEN: Pixel-Level Image Fusion-Based Nighttime Object Detection Network
Chen, Y.-T., & Da, F. (2025) · Chinese Control Conference (CCC) · doi:10.23919/ccc64809.2025.11179509 · Cited by 2
“Single-stage and two-stage object detection frameworks, such as Region-based Convolutional Neural Network (R-CNN)[3], Single Shot MultiBox Detector (SSD)[4], and You Only Look Once (YOLO)[5], have greatly enhanced detection capabilities in diverse and challenging environments.”
Enhanced RT-DETR: A Lightweight Model for Aerial Infrared Small Target Detection
Ma, L., & Xie, W. (2025) · Chinese Control Conference (CCC) · doi:10.23919/ccc64809.2025.11178700 · Cited by 3
“Convolutional Neural Network (CNN)-based frameworks like the YOLO series [15] leverage anchor designs and multi-scale fusion for general object detection.”
Sánchez‐Nielsen, E., & Martín-Herrera, I. (2025) · IEEE Access · doi:10.1109/access.2025.3620686 · Cited by 6
Dynamic scale-aware vehicle re-identification via optimized YOLO-BFP and RIoU metric learning
Wang, X., Pei, C., He, J., & Lü, Z. (2025) · Multimedia Systems · doi:10.1007/s00530-025-02002-1 · Cited by 2
“YOLO and SSD have improved real-time detection capabilities through a single-stage structure, becoming representatives of efficient detection [18 , 19 ].”
Li, G., Hu, Z., & Zhang, H. (2025) · Traffic Injury Prevention · doi:10.1080/15389588.2025.2557513 · Cited by 3
“From YOLOv1 (Redmon 2016) to YOLOv12 (Tian et al. 2025), it has been known for its speed, high accuracy, and ease of implementation.”
Khaled, L. B., Rahman, M., Ebu, I. A., & Ball, J. E. (2025) · Sensors · doi:10.3390/s25206423 · Cited by 6
“Recent studies have demonstrated substantial improvements in detection accuracy using deep learning models such as YOLO (You Only Look Once), Faster R-CNN (Region-based Convolutional Neural Network), SSD (Single Shot Detector), and their variants [46–48].”
Laser weld spot detection based on MMG-YOLO
Feng, J., Zhao, X., Wang, J., Liu, Z., & Ding, Y. (2025) · The Journal of Supercomputing · doi:10.1007/s11227-025-07958-5 · Cited by 2
“…based on deep learning can be categorized into two primary types: one-stage, end-to-end detection algorithms, including the YOLO series (YOLOv1 [5], YOLOv2 [6], YOLOv3 [7], YOLOv4 [8]) and SSD [9], and two-stage detection algorithms that rely on region proposals, such as R-CNN [10], Fast R-CNN…”
Hwang, J., Li, C., Kang, H., Hosseini, M., & Froehlich, J. E. (2025) · International ACM SIGACCESS Conference on Computers and Accessibility (ASSETS) · doi:10.1145/3663547.3746377 · Cited by 3
“From this small seed dataset, we train the hint model using YOLOv8 [37, 71] for 113 epochs with default settings, which we then run on all two million images from our main cities.”
Gergely, T., Gyalai‐Korpos, M., Fleit, G., & Baranya, S. (2025) · Frontiers in Environmental Science · doi:10.3389/fenvs.2025.1666271 · Cited by 3
FNon R-CNN: A multi-scale ground object detection and recognition network
Yan, Z., Zhu, W., Zhong, X., et al. (2025) · High-Confidence Computing · doi:10.1016/j.hcc.2025.100359 · Cited by 2
Li, Y., Zeng, X., Xue, Z. Y., Zeng, P., Zhang, Z., & Wang, Y. (2025) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3746027.3755030 · Cited by 6
“Over the past few years, artificial neural networks (ANNs) have achieved remarkable success in various domains, such as object recognition [35], object segmentation [14], and natural language processing [42].”
de Souza, J. P. G., Silva, A. C., Congro, M., Roehl, D. D. M., de Paiva, A. C., Pereira, S., & Cunha, A. M. T. D. S. (2025) · Electronics · doi:10.3390/electronics14214208 · Cited by 2
Chen, Y., Li, H., Chen, Y., & Zhao, D. (2025) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme59968.2025.11208899 · Cited by 2
“To overcome this problem, we introduce YOLO [15] to detect common household objects (e.g., table and bed) as a supplement, while Detic [13] is used to detect task-relevant objects and rooms.”
Road Object Detection Method Based on Multi-Scale Spatial-Spectral Attention
Zimeng, L., & Yang, K. (2025) · International Conference on Image and Video Processing (ICIVP) · doi:10.1109/icivp66296.2025.00016 · Cited by 2
“2) One-stage object detection algorithms such as SSD [10], YOLO [11][12], and EfficientDet [13], which directly use a CNN to extract features to generate the location and category information of the objects, converting detection into a regression problem.”
Real-Time Object Detection for Visually Impaired People Using an Improved YOLOv7-Plus Architecture
Bougheloum, L., Bousbia-Salah, M., & Bettayeb, M. (2025) · Arabian Journal for Science and Engineering · doi:10.1007/s13369-025-10821-7 · Cited by 2
“An advanced object detection method called YOLOv7 is based on the You Only Look Once (YOLO) series of algorithms developed by Redmon et al. [34].”
Yang, H., Kim, S., & Choi, Y. (2025) · Journal of the Korean Society of Mineral and Energy Resources Engineers · doi:10.32390/ksmer.2025.62.5.567 · Cited by 2
Gao, F., Chen, F., He, X., Wang, J., Sun, J., & Hussain, A. (2025) · Remote Sensing · doi:10.3390/rs17223663 · Cited by 2
AMAF-YOLO: dynamic cross-region attention and multi-scale fusion for small object detection
Sun, Q., Zhang, J., Zeng, S., Hu, J., & Li, K. (2025) · Nondestructive Testing And Evaluation · doi:10.1080/10589759.2025.2586076 · Cited by 6
A Lightweight Adaptive Attention Fusion Network for Real-Time Electrowetting Defect Detection
Chen, R., Zheng, J., Long, W., Chen, H., & Luo, Z. (2025) · Information · doi:10.3390/info16110973 · Cited by 2
“Single-stage detectors, represented by the YOLO series [10,11], while common two-stage detectors include Faster-RCNN [12], Fast R-CNN [13].”
Robots for Safer Pedestrian Crossing on Two-Lane Roads
Comeca, A. L. F., Masarykova, N., Halinkovič, M., et al. (2025) · IEEE International Automated Vehicle Validation Conference (IAVVC) · doi:10.1109/iavvc61942.2025.11219514 · Cited by 2
“The YOLO [6] machine learning algorithm is used for efficient object detection and classification of pedestrians, cyclists, and vehicles.”
Ingrisch, M. A., Schilling, R. M., Chmielewski, I., & Twieg, S. (2025) · Applied Sciences · doi:10.3390/app152212062 · Cited by 3
IMPMCT: a dataset of Integrated Multi-source Polar Mesoscale Cyclone Tracks in the Nordic Seas
Fang, R., Ding, J., Gao, W., et al. (2025) · Earth system science data · doi:10.5194/essd-17-6049-2025 · Cited by 2
Two-Level Test-Time Adaptation in Multimodal Learning
Lei, J., & Pernkopf, F. (2025) · doi:10.1109/ijcnn64981.2025.11228216 · Cited by 2
He, H., Xie, H., Shen, G., Fu, B., You, H., & Sanchez, V. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11227447 · Cited by 2
“The work in [24] introduces a self-supervised clustering approach that groups unlabeled data into reliable clusters.”
FDC-YOLO: A Blur-Resilient Lightweight Network for Engine Blade Defect Detection
Xu, X., Li, F., Xiong, L., He, C., Peng, H., Zhao, Y., & Song, G. (2025) · Algorithms · doi:10.3390/a18110725 · Cited by 2
Gasparin, A. T., Araujo, C. I. F., de Faria, R. R., Silva, I. L. R., Medeiros, B. R., Hartmann, L. F., Predebon, J. V., Gelain, B., Watanabe, T. C., Beltrame, O. C., et al. (2025) · Communications Medicine · doi:10.1038/s43856-025-01223-9 · Cited by 3
Beluga Whale Detection from Satellite Imagery with Point Labels
Zheng, Y., Yang, J., Chen, Y., et al. (2025) · IEEE International Geoscience and Remote Sensing Symposium (IGARSS) · doi:10.1109/igarss55030.2025.11243110 · Cited by 2
“YOLO (You Only Look Once) [11, 12], an object detection algorithm for locating and classifying objects within imagery, has shown promise in detecting whales using satellite [13] and drone imagery [14].”
Uncertainty-Aware Knowledge Distillation for Compact and Efficient 6DoF Pose Estimation
Ousalah, N. A., Kacem, A., Ghorbel, E., Koumandakis, E., & Aouada, D. (2025) · 2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros60139.2025.11245982 · Cited by 2
Li, D., Ci, X., & Li, C. (2025) · Engineering Research Express · doi:10.1088/2631-8695/ae2762 · Cited by 4
Varaganti, M., Vankayalapati, A., Awad, N., Dion, G. R., & Brattain, L. J. (2025) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc58623.2025.11254047 · Cited by 4
“In contrast, single-stage detectors [29], [30] directly predict bounding boxes and class probabilities from the input image in a single pass, providing faster real-time performance.”
Schäfer, H., Schmidt, C. S., Wutzkowsky, J., Lorek, K., Reinartz, L., Rückert, J., Temme, C., Böckmann, B., Horn, P., & Friedrich, C. M. (2025) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc58623.2025.11254237 · Cited by 7
“Modern approaches employ object detection frameworks (e.g., Faster R-CNN [24], YOLO [25], DETR [26]) trained on annotated datasets to robustly localize check-boxes and classify their states.”
Yu, C., & Gao, L. (2025) · International Conference on Networking and Network Applications (NaNA) · doi:10.1109/nana66698.2025.00052 · Cited by 2
“In educational settings, the YOLO series [17] has been widely used for student behavior recognition in classrooms.”
Quantification of plant trait data from herbarium scans in the DiSSCo Research Infrastructure
Rajendran, R., Weiland, C., Grieb, J., et al. (2025) · Research Ideas and Outcomes · doi:10.3897/rio.11.e160367 · Cited by 2
Mas-Gómez, J., Rubio, M., Dicenta, F., & Martínez‐García, P. J. (2025) · GigaScience · doi:10.1093/gigascience/giaf157 · Cited by 3
“For that purpose, in the second note-book ( 2_Develop_your_segmentation_model_workflow.ipynb ), the YOLO [ 51 ] pretrained algorithm series can be fine-tuned (although in their web mention, “training” really is a fine-tuning [ 52 ]) using our custom labeled dataset.”
Kim, H. Y., Yi, T. J., & Lee, J. Y. (2025) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2025.3548240 · Cited by 2
Single-Camera-Based 3D Drone Trajectory Reconstruction for Surveillance Systems
Hwang, S.-B., & Cho, Y.-J. (2025) · IEEE Access · doi:10.1109/access.2025.3555321 · Cited by 3
Monitoring Leafy Plant Root Morphology with Pattern Recognition Imaging Techniques
Peyal, M. M. K., Shihab, A. U. I., Ocean, S. I., et al. (2025) · IEEE Annual Computing and Communication Workshop and Conference (CCWC) · doi:10.1109/ccwc62904.2025.10903707 · Cited by 2
Improved FCOS rotation detection network in the vision-based robotic arm for order review
Zhu, H., Sun, Y., Yu, X., et al. (2025) · Industrial Robot the international journal of robotics research and application · doi:10.1108/ir-09-2024-0419 · Cited by 2
A Transformer-Based Multi-Task Learning Model for Vehicle Traffic Surveillance
Hermosillo-Reynoso, F., López-Pimentel, J. C., Ruiz-Ibarra, E., Garcia-Berumen, A., Del-Puerto-Flores, J. A., Gilardi-Velazquez, H. E., Kumaravelu, V. B., & Luna-Rodriguez, L. A. (2025) · Mathematics · doi:10.3390/math13233832 · Cited by 4
Sarkar, P., Ronit, K., De, S., et al. (2026) · Lecture notes in networks and systems · doi:10.1007/978-981-96-8998-9_10 · Cited by 2
Detection of Synthetic Face Images: Accuracy, Robustness, Generalization
Petrželková, N., & Čech, J. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-12840-9_29 · Cited by 5
Jeong, H., Oh, J., Lee, D., Kang, J., & Choi, Y. (2026) · Briefings in Bioinformatics · doi:10.1093/bib/bbag037 · Cited by 2
Combining Transformers and CNNs for Efficient Object Detection in High-Resolution Satellite Imagery
Drapier, N., Chetouani, A., & Chateigner, A. (2025) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw69036.2025.00307 · Cited by 7
“Convolutional Neural Networks (CNNs), while efficient for lo-cal feature extraction [11, 12, 23, 28, 29, 47], are limited in Hypothesis We hypothesize that transformers, known for their ability to model complex relationships [39], are better suited for feature extraction in satellite imagery.”
Mezgebo, B. K., Chaffee, R., Castellanos, L. R., Ashraf, S., Burke-Gaffney, J., Pitout, J. D. D., Iorga, B. I., MacDonald, M. E., & Pillai, D. R. (2026) · PLoS ONE · doi:10.1371/journal.pone.0339042 · Cited by 3
“(2016) [12], is a real-time object detection algorithm that leverages convolutional neural networks [12–14].”
Mohsin, M., Rovetta, S., Masulli, F., & Cabri, A. (2026) · IEEE Access · doi:10.1109/access.2026.3679216 · Cited by 5
Corbetta, A., Menkovski, V., & Toschi, F. (2017) · IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS) · doi:10.1109/avss.2017.8078490 · Cited by 2
Robot Vision Applications Using Convolution for Image Processing
Yamazaki, K. (2017) · Journal of the Robotics Society of Japan · doi:10.7210/jrsj.35.644 · Cited by 2
Multi-scale Pyramid Feature Maps for Object Detection
Hao, H., Ye, R., Zhongyu, C., et al. (2017) · International Symposium on Distributed Computing and Applications to Business, Engineering and Science (DCABES) · doi:10.1109/dcabes.2017.59 · Cited by 2
Li, Y., Wang, H., Shi, Q., et al. (2017) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio.2017.8324567 · Cited by 2
p-Faster R-CNN Algorithm for Food Detection
Wan, Y., Liu, Y., Li, Y., et al. (2018) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-030-00916-8_13 · Cited by 2
Video Pedestrian Detection Based on Deep Learning
仝, 小. (2018) · Computer Science and Application · doi:10.12677/csa.2018.810170 · Cited by 2
Focal Loss for Region Proposal Network
Chen, C., Song, X., & Jiang, S. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-03335-4_32 · Cited by 3
Yu, J., Kim, D., & Jeon, M. (2018) · International Conference on Control, Automation and Information Sciences (ICCAIS) · doi:10.1109/iccais.2018.8570503 · Cited by 2
A Novel Vehicle Detection System
Zakaria, Y., Ali, M. A., Munim, H. E. A. E., Yousef, A. H., Ghoneima, M., & Hammad, S. (2018) · International Conference on Computer Engineering & Systems (ICCES) · doi:10.1109/icces.2018.8639380 · Cited by 2
Novelty Detection with Self-Organizing Maps for Autonomous Extraction of Salient Tracking Features
Bernard, Y., Hueber, N., & Girau, B. (2019) · Advances in intelligent systems and computing · doi:10.1007/978-3-030-19642-4_10 · Cited by 2
Analysis of Various Traffic Sign Detectors Based on Deep Convolution Network
Tang, Q., & Jo, K.-H. (2019) · IEEE/SICE International Symposium on System Integration (SII) · doi:10.1109/sii.2019.8700445 · Cited by 2
Putting the Anchors Efficiently: Geometric Constrained Pedestrian Detection
Fang, L., Zhao, X., Song, X., Zhang, S., & Yang, M. Z. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-20873-8_25 · Cited by 2
Using Mobile Eye Tracking to Evaluate the Satisfaction with Service Office
Liu, Z. X., Liu, Y., & Gao, X. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-23535-2_14 · Cited by 2
A Study of Deep Learning Methods for Mitotic Cell Detection Towards Breast Cancer Diagnosis
Kaushik, S., Raghavan, S. V., & Sivaselvan, B. (2019) · Communications in computer and information science · doi:10.1007/978-981-13-9939-8_23 · Cited by 3
Single-Shot Detector with Multiple Inference Paths
Chen, S., & Wang, X. (2019) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2019.8803137 · Cited by 2
ActiVis: Mobile Object Detection and Active Guidance for People with Visual Impairments
Lock, J. C., Tramontano, A. G., Ghidoni, S., & Bellotto, N. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-30645-8_59 · Cited by 2
Machine Learning Versus Human-Developed Algorithms in Image Analysis of Microstructures
Piwowarczyk, A., & Wojnar, L. (2019) · Quality Production Improvement - QPI · doi:10.2478/cqpi-2019-0056 · Cited by 2
Performance of object recognition in wearable videos
Sabater, A., Montesano, L., & Murillo, A. C. (2019) · IEEE International Conference on Emerging Technologies and Factory Automation (ETFA) · doi:10.1109/etfa.2019.8869019 · Cited by 2
Shih, P.-C., Li, H., Lin, X., & Zhang, Y. (2019) · International Conference on Computer Science and Application Engineering (CSAE) · doi:10.1145/3331453.3361326 · Cited by 2
A New End-to-End Secondary Network for High-Efficient Vehicles and License Plates Detection
Peng, Y., Li, H., & Qian, Z. (2019) · International Conference on Smart Grid and Electrical Automation (ICSGEA) · doi:10.1109/icsgea.2019.00010 · Cited by 2
Isayev, M., & Savelyev, D. (2019) · doi:10.18287/1613-0073-2019-2416-417-423 · Cited by 2
Metal surface defect detection based on few defect datasets
Li, R. (2019) · AIP conference proceedings · doi:10.1063/1.5137871 · Cited by 2
PHD: A Deep Learning Based Human Detection Framework for Panoramic Videos
Tang, J., Chen, Z., Huo, Y., et al. (2019) · International Conference on Wireless Communications and Signal Processing (WCSP) · doi:10.1109/wcsp.2019.8928143 · Cited by 2
FlowScan: Estimating People Flows on Sidewalks Using Dashboard Cameras Based on Deep Learning
Hara, Y., Hasegawa, R., Uchiyama, A., Umedu, T., & Teruo Higashino, Y. (2020) · Journal of Information Processing · doi:10.2197/ipsjjip.28.55 · Cited by 2
Selective Subtraction for Handheld Cameras
Bhutta, A. A., Junejo, I. N., & Foroosh, H. (2020) · IEEE Access · doi:10.1109/access.2020.2973655 · Cited by 2
IoT-based Multi-view Machine Vision Systems
Castillo, E. A., & Ahmadinia, A. (2019) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata47090.2019.9005702 · Cited by 5
Detecting stabbing by a deep learning method from surveillance videos
Liu, C., Liu, P., & Xiao, C. (2019) · IEEE International Conference on Imaging Systems and Techniques (IST) · doi:10.1109/ist48021.2019.9010206 · Cited by 2
A Semantic Segmentation Approach to Recognize Assault Rifles in ISIS Propaganda Images
Abeysinghe, B., Veilleux-Lepage, Y., Bloom, M. M., & Sunderraman, R. (2020) · IEEE International Conference on Semantic Computing (ICSC) · doi:10.1109/icsc.2020.00082 · Cited by 2
A New Remote Sensing Image Dataset for Large-Scale Remote Sensing Detection
Xie, D., Cheng, J. S., & Tao, D. (2019) · IEEE International Conference on Real-time Computing and Robotics (RCAR) · doi:10.1109/rcar47638.2019.9043971 · Cited by 2
The Neutrophil’s Morphology Classification Using Convolutional Neural Network
Zhang, X., Li, J., Wang, B., Shi, K., Qin, Q., & Fan, B. (2020) · Communications in computer and information science · doi:10.1007/978-981-15-3415-7_48 · Cited by 2
Kovbasiuk, S., Kanevskyy, L., Sashchuk, I., & Romanchuk, M. P. (2019) · International Scientific-Practical Conference Problems of Infocommunications Science and Technology · doi:10.1109/picst47496.2019.9061496 · Cited by 3
Tsai, Y.-T., & Chen, K.-Y. (2019) · International conference on Fuzzy Theory and Its Applications · doi:10.1109/ifuzzy46984.2019.9066218 · Cited by 3
Fröhlich, H. B., Grozmani, N., Wolfschläger, D., Gonçalves, A. A., & Schmitt, R. H. (2020) · The International Journal of Advanced Manufacturing Technology · doi:10.1007/s00170-020-05253-6 · Cited by 1
Research on SSD Algorithm Based on Occlusion Detection
Zhang, Y., & Jianqiang, L. (2019) · International Conference on Electronic Information Technology and Computer Engineering (EITCE) · doi:10.1109/eitce47263.2019.9094772 · Cited by 2
A Robust Structured Tracker Using Local Deep Features
Javanmardi, M., Farzaneh, A. H., & Qi, X. (2020) · Electronics · doi:10.3390/electronics9050846 · Cited by 2
Application of YOLOv3 in road traffic detection
Ren, A., Niu, X., & Bai, J. (2019) · IEEE International Conference on Electronic Measurement & Instruments · doi:10.1109/icemi46757.2019.9101888 · Cited by 2
Metadata
- Authors
- Redmon, J., Divvala, S., Girshick, R., & Farhadi, A.
- Affiliations
- University of Washington (US)
- Meta (United States) (US)
- Venue
- 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2016-06
- Pages
- 779-788
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W1483870316
- Cited by
- 53,803
- References
- 42
- Citations by year
- 2026: 5347 · 2025: 8912 · 2024: 8953 · 2023: 8264 · 2022: 6785 · 2021: 5741 · 2020: 4223 · 2019: 3286 · 2018: 1560 · 2017: 635 · 2016: 90
- FWCI
- 644.23
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Zenodo (CERN European Organization for Nuclear Research) (cc-by)
- Funders
- National Science Foundation (1338054)
- Office of Naval Research (N00014-13-1-0720, N00014)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image and Video Retrieval Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Visual Attention and Saliency Detection
- Keywords
- object detection, YOLO, real-time detection, bounding box regression, end-to-end learning, false positive reduction, domain generalization
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol and qwen3.8-omni-flash).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.