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 31,301–31,400 of 51,399
A dynamic-confidence 3D multi-object tracking method based on spatio-temporal association
Zeng, R., & Ramezani, M. (2025) · Measurement · doi:10.1016/j.measurement.2025.117864 · Cited by 3
MSFE-Net: Multi-Scale Feature Enhancement Network for Remote Sensing Object Detection
Yuan, K., Li, X., Ren, Y., Zhang, L., Liu, W., & Li, E. (2025) · Applied Artificial Intelligence · doi:10.1080/08839514.2025.2514324 · Cited by 5
“For instance, techniques such as Faster R-CNN (Ren et al. 2015), YOLO (Redmon et al. 2016), and RetinaNet (Lin et al. 2020) have demonstrated high accuracy in natural images.”
Meng, S., Zhang, S., Liang, X., & Hu, J. (2025) · Knowledge-Based Systems · doi:10.1016/j.knosys.2025.113578 · Cited by 5
Feng, Z., Yang, B., & Deng, B. (2025) · The Journal of Supercomputing · doi:10.1007/s11227-025-07427-z · Cited by 2
“Among them, frame-based detection methods are mainly based on YOLO [33], including YOLACT [9] and FCIS [34].”
Ramón-Turner, Ó., Bordón, J. D. R., González-Rodríguez, A., Lorenzo-Navarro, J., Castrillón-Santana, M., Álamo, G. M., Quevedo-Reina, R., Romero-Sánchez, C., Sánchez, A. T. E., Medina, C., et al. (2025) · Sensors · doi:10.3390/s25123604 · Cited by 2
“The ANN used in this work, the Ultralytics YOLOv8 model [28], is based in the original single stage detector architectures described by Joseph Redmon and Ali Farhadi at the University of Washington [29–31].”
Nandini, B. M., Sharmila, B., Kavitha, S. S., et al. (2025) · doi:10.1109/incip64058.2025.11019866 · Cited by 2
Militão, A. A. M., de Andrade, H. G. V., Monteiro, K. H. D. C., et al. (2025) · doi:10.5753/sbcas.2025.7140 · Cited by 2
Traffic sign detection in glare environments
Bai, J., Wang, F., Wang, H., & Guo, J. (2025) · Signal Image and Video Processing · doi:10.1007/s11760-025-04310-5 · Cited by 3
Enhanced Radar Object Detection and Classification with Deep Learning on Range-Doppler (RD) Maps
Islam, M., & Saha, P. K. (2024) · International Conference on Electrical and Computer Engineering (ICECE) · doi:10.1109/icece64886.2024.11024570 · Cited by 2
Computer Vision Technique for Quality Grading of Cardamom Spice
Ahnaf, M. R. A., Nizzad, A. R. M., & Mafaza, N. F. (2025) · International Research Conference on Smart Computing and Systems Engineering (SCSE) · doi:10.1109/scse65633.2025.11031046 · Cited by 2
Multimodal representation fusion method for dense video captioning
Fang, H., Li, Y., & Li, Y. (2025) · Knowledge-Based Systems · doi:10.1016/j.knosys.2025.113856 · Cited by 5
Automated Pipe Defect Identification in Underwater Robot Imagery with Deep Learning
Andani, M. T., & Ameri, F. (2025) · Journal of Marine Science and Application · doi:10.1007/s11804-025-00617-4 · Cited by 2
“Through a single evaluation, the unified neu ‐ ral network computes class probabilities and bounding boxes directly from an entire set of images (Redmon et al., 2016).”
Research on lightweight pipeline defects detection algorithm based on attention mechanism
Liu, R., Shao, Z., Sun, Q., Liu, J., & Yu, Z. (2025) · Measurement Science and Technology · doi:10.1088/1361-6501/ade553 · Cited by 2
AdVision: An efficient and effective deep learning based advertisement detector for printed media
Sayyad, F. Z., Shallari, I., Mousavirad, S. J., et al. (2025) · Machine Learning with Applications · doi:10.1016/j.mlwa.2025.100686 · Cited by 2
CSCP-YOLO: A Lightweight and Efficient Algorithm for Real-Time Steel Surface Defect Detection
Wang, C., Wang, H., Jiang, Y., et al. (2025) · IEEE Access · doi:10.1109/access.2025.3581024 · Cited by 2
Evaluating the Robustness of Foundation Models for Satellite Imagery
Rotich, G., & Sarkar, S. (2025) · IEEE Access · doi:10.1109/access.2025.3581067 · Cited by 9
Liu, R., Wang, H., Hu, K., Wang, S., & Liu, Y. (2025) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2025.3580829 · Cited by 10
Liu, L., Jia, R., Karimi, H. R., & Ma, B. (2025) · Signal Image and Video Processing · doi:10.1007/s11760-025-04313-2 · Cited by 3
Easy data augmentation strategies for enhanced blastomeres detection
Wang, X., Li, C., Yang, J., Huang, G., & Zhang, X. (2025) · Measurement · doi:10.1016/j.measurement.2025.118119 · Cited by 2
Araya-Martinez, J. M., Sardari, S., Lambert, M., Zak, J. A., Töper, F., Krüger, J., & Lambrecht, J. (2025) · ARENA2036 · doi:10.1007/978-3-031-88831-1_23 · Cited by 2
Mo, J., Wu, G., & Li, R. (2025) · doi:10.1109/ainit65432.2025.11035514 · Cited by 2
“YOLO[6] is a single-stage object detection algorithm whose core structure encompasses three major components: Backbone, Neck, and Head.”
Label-Free Machine Learning-Based Segmentation of Whole-Body Bone Marrow Imaging in Multiple Myeloma
Koutoulakis, E., Trivizakis, E., Koutoulidis, V., Moulopoulos, L. A., Terpos, E., Ntanasis‐Stathopoulos, I., Malandrakis, P., Grigoropoulos, P., Papadopoulos, P. D., Nikiforaki, K., et al. (2025) · IEEE International Symposium on Applied Computational Intelligence and Informatics (SACI) · doi:10.1109/saci66288.2025.11030097 · Cited by 4
YOLO11-DL: A Lightweight Eggplant Disease Object Detection Network
Wang, X., Guo, S., Zhang, Y., et al. (2025) · doi:10.1109/ainit65432.2025.11035932 · Cited by 2
Complementary Local–Global Optimization for Few-Shot Object Detection in Remote Sensing
Zhang, Y., Lyu, X., Li, X., Zhou, S., Fang, Y., Ding, C., Gao, S., & Chen, J. (2025) · Remote Sensing · doi:10.3390/rs17132136 · Cited by 2
Jing, W., Guo, B., Li, Z., et al. (2024) · International Conference on Mobility, Sensing and Networking (MSN) · doi:10.1109/msn63567.2024.00096 · Cited by 2
Diverse Target and Contribution Scheduling for Domain Generalization
Long, S., Zhou, Q., Ying, C., Ma, L., & Luo, Y. (2025) · IEEE Transactions on Image Processing · doi:10.1109/tip.2025.3581012 · Cited by 10
Automatic Detection of Ceroxylon Palms by Deep Learning in a Protected Area in Amazonas (NW Peru)
Sánchez-Vega, J. A., Silva-López, J. O., López, R. S., Medina-Medina, A. J., Tuesta-Trauco, K. M., Rivera-Fernandez, A. S., Silva-Melendez, T. B., Oliva, M., Barboza, E., da Silva, C. A., et al. (2025) · Forests · doi:10.3390/f16071061 · Cited by 5
Edge-Guided DETR Model for Intelligent Sensing of Tomato Ripeness Under Complex Environments
Yao, J., Zhou, J., Nie, Y., Xue, J., Lin, K., & Tan, L. (2025) · Mathematics · doi:10.3390/math13132095 · Cited by 5
Hybrid Backbone-Based Deep Learning Model for Early Detection of Forest Fire Smoke
Çınarer, G. (2025) · Applied Sciences · doi:10.3390/app15137178 · Cited by 2
Multiscale Task-Decoupled Oriented SAR Ship Detection Network Based on Size-Aware Balanced Strategy
He, S., Yuan, R., Yang, Z., & Liu, J. (2025) · Remote Sensing · doi:10.3390/rs17132257 · Cited by 5
UCS-YOLO: a novel approach for multi-scale small target detection in UAVs
Sun, G., Zhang, F.-Q., Zhu, Y.-M., & Miao, F. (2025) · The Journal of Supercomputing · doi:10.1007/s11227-025-07536-9 · Cited by 2
“These algorithms directly regress the target’s position and category information, simplifying the region proposal process and thus improving detection efficiency, with typical examples including the YOLO [12–14] series, RetinaNet [15], Centernet [16], and SSD [17] series.”
Warin, K., Limprasert, W., Paipongna, T., Chaowchuen, S., & Vicharueang, S. (2025) · Scientific Reports · doi:10.1038/s41598-025-06318-w · Cited by 4
“It employs an advanced neural network architecture to predict bounding boxes and class probabilities simultaneously in an end-to-end manner 20 .”
Focal Spotter: Small-Object Detection via Inner Scale and Interscale Feature Focalization
Duan, R., Du, Q., Tian, L., Liu, H., & Huo, S. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2025.3584812 · Cited by 7
Na, H., Kim, D., Kang, J. M., & Lee, C. (2025) · Applied Sciences · doi:10.3390/app15137410 · Cited by 2
YED-Net: Yoga Exercise Dynamics Monitoring with YOLOv11-ECA-Enhanced Detection and DeepSORT Tracking
Zhou, Y., Shu, D., Sheng, H., & Ke, W. (2025) · Applied Sciences · doi:10.3390/app15137354 · Cited by 2
Fu, D., SHANG, X., Hu, Z., Chen, Y., Wen, K., & Li, S. (2025) · Journal of Food Science · doi:10.1111/1750-3841.70382 · Cited by 2
Cross-attention multi branch for Vietnamese sign language recognition: CrossViViT
Chu, M. H., Nguyen, H. D., Nguyễn, T. N. A., & Vu, H. N. (2025) · Discover Computing · doi:10.1007/s10791-025-09669-0 · Cited by 5
“Our patch partitioning strategy is also inspired by the concept of multi-view perception commonly found in object detection models such as YOLO [52].”
Mainstream Artificial Intelligence Technologies in Contemporary Ophthalmology
Yin, S., Wang, L., Wu, S., Jiang, J., Qiang, W., Wang, Y., Wang, S., Shao, Y., Chen, W., & Li, Z. (2025) · Advanced Intelligent Systems · doi:10.1002/aisy.202500055 · Cited by 5
Distilling Grounding DINO for an Edge-Cloud Collaborative Advanced Driver Assistance System
Lin, C., Hu, H., Zou, J., Li, L., Liu, J., Gao, Y., Yang, Y., & Shen, H. T. (2025) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2025.3586704 · Cited by 2
“Pixel-based methods [20], [21], [22] operate in a single stage, directly classifying and regressing on predefined anchors or pixels to increase speed.”
CTS-YOLO: Real-Time Object Detection Algorithm Based on Improved YOLO11 in Complex Traffic Scenarios
Gao, X., Huang, K., & Li, P. (2025) · Signal Image and Video Processing · doi:10.1007/s11760-025-04490-0 · Cited by 3
“Typical single-stage methods mainly include the YOLO family [7– 14], SSD [15], RetinaNet [16], and others.”
Gradient-Free Sparse Adversarial Attack on Object Detection Models
Le, C. C., Phan, T., & Luong, N. H. (2025) · Genetic and Evolutionary Computation Conference (GECCO) · doi:10.1145/3712256.3726305 · Cited by 2
BioVIEW: Automatic Remote Platform for Biodiversity Evaluation Using Low Cost Electronics
Molina-Rotger, M., Morán, A., Chueca, M. Á. M., Roca, M., & Alorda, B. (2024) · IEEE Conference on AgriFood Electronics (CAFE) · doi:10.1109/cafe63183.2024.11069357 · Cited by 2
Automatic Underwater Plastics Detection Using YOLOv9
Badawy, W. M., Shabaka, S. H., & Tawfik, M. (2024) · International Japan-Africa Conference on Electronics, Communications, and Computations (JAC-ECC) · doi:10.1109/jac-ecc64419.2024.11061217 · Cited by 2
Wang, G., Sun, D., Li, H., Cheng, J., Yan, P., & Li, H. (2025) · Machine Learning and Knowledge Extraction · doi:10.3390/make7030064 · Cited by 3
“The YOLO (You Only Look Once) architecture family has fundamentally reshaped real-time object detection paradigms since its seminal introduction by Redmon et al. [6], which has been iterated to the YOLOv12 version [14].”
Enhancing Dance Performance for Body Motion Interaction Through Swarm Intelligence and Deep Learning
Kongshi, M., Pan, D., & Wang, M. (2025) · International Journal of Swarm Intelligence Research · doi:10.4018/ijsir.383942 · Cited by 2
VLM-TD: A Visual Language Model for Transmission Defects with Integrated Link Attention
Zhu, D., Liu, D., & Wang, B.-Y. (2025) · doi:10.1109/icccs65393.2025.11069490 · Cited by 2
“Although deep learning-based object detection technologies [5,6,7] can replace manual efforts, the storage and computational power required for processing such vast amounts of image data are substantial.”
Liyuan, Y., Yang, M. B., Osman, G., et al. (2025) · IET Image Processing · doi:10.1049/ipr2.70156 · Cited by 2
Unmanned Aerial-Ground Systems for Wildfire Detection, Global Localization and Suppression
Qin, Q., Dilfanian, E., Zhang, Y. M., et al. (2025) · 2006 14th Mediterranean Conference on Control and Automation · doi:10.1109/med64031.2025.11073311 · Cited by 2
“A custom YOLOv8 algorithm [26] running on ground station is employed for fire and UGVs detection, producing bounding boxes of fire spots and UGVs.”
Star-YOLO: A Lightweight Real-Time Wheat Grain Detection Model for Embedded Deployment
Qu, Z., Liang, X. P., Liang, S., et al. (2025) · IEEE Access · doi:10.1109/access.2025.3591374 · Cited by 2
DSLL-Face: Distributed Supervision-Integrated Framework for Low-Light Face Detection
Chen, S., Chen, K., Wang, G., Wen, S., & Zhou, Z. (2025) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2025.3590911 · Cited by 6
YOLO-PFS: Improved YOLOv11 for Remote Sensing Object Detection and Recognition
Chen, H., Zhou, J., & Zhao, Q. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-9815-8_38 · Cited by 2
SA-FPSC: An Efficient Feature Pyramid Structure for Underwater Small Target Detection
Wang, C., Mohmamed, A. S. A., Noor, M. H. B. M., et al. (2025) · International Conference on Communication Engineering and Technology (ICCET) · doi:10.1109/iccet65872.2025.11082602 · Cited by 2
“The YOLO (You Only Look Once) [ 5 ] series is a single-stage object detection algorithm that performs target detection in a single forward pass.”
Wu, R., & Yang, P. (2025) · Actuators · doi:10.3390/act14080370 · Cited by 2
Small Ship Detection Based on Improved Neural Network Algorithm and SAR Images
Li, J., Huo, H., Guo, L., Zhang, D., Feng, W., Lian, Y., & He, L. (2025) · Remote Sensing · doi:10.3390/rs17152586 · Cited by 3
SRW-YOLO: A Detection Model for Environmental Risk Factors During the Grid Construction Phase
Zhao, Y., Liu, F., Liu, F., et al. (2025) · Remote Sensing · doi:10.3390/rs17152576 · Cited by 2
Plastic bottle localization and ranging using improved YOLO-PB and binocular stereo vision
Yan, H., Huang, J., & Zhou, Z. (2025) · Measurement · doi:10.1016/j.measurement.2025.118469 · Cited by 2
Choudhary, S., Saurav, S., Saini, R., & Singh, S. K. (2025) · Communications in computer and information science · doi:10.1007/978-3-031-93694-4_28 · Cited by 2
Yuzhe, K., Zheng, B., & Shen, W. (2025) · Applied Sciences · doi:10.3390/app15158370 · Cited by 5
Truong, T., Baltruschat, I. M., Klemens, M., Werner, G., & Lenga, M. (2025) · Journal of Imaging Informatics in Medicine · doi:10.1007/s10278-025-01619-y · Cited by 5
SSAM_YOLOv5: YOLOv5 Enhancement for Real-Time Detection of Small Road Signs
Qanouni, F., Massari, H. E., Gherabi, N., et al. (2025) · Digital · doi:10.3390/digital5030030 · Cited by 2
“Its first version was introduced in 2015 by Redmon et al. [6], and its basic principle is to divide an input frame into a series of regions and predict the bounding boxes and class probabilities for each region [7].”
LSD-Det: A Lightweight Detector for Small Ship Targets in SAR Images
Wang, Z., Qin, B., & Gao, S. (2025) · IEEE Access · doi:10.1109/access.2025.3593021 · Cited by 4
DualSight: multi-stage instance segmentation framework for improved precision
Price, S. E., Judd, K. G., Tsaknopoulos, K. L., Neamtu, R., & Cote, D. L. (2025) · Scientific Reports · doi:10.1038/s41598-025-09642-3 · Cited by 2
Detection of cotton pests using an enhanced deep learning model
Jiang, H., Zhong, J., Ma, F., & Wang, C. (2025) · Journal of Asia-Pacific Entomology · doi:10.1016/j.aspen.2025.102450 · Cited by 2
YOLOv7-GPSS: a YOLOv7-based wire rope surface defect detection algorithm
Shi, R., Li, H., Ma, T., et al. (2025) · Signal Image and Video Processing · doi:10.1007/s11760-025-04542-5 · Cited by 2
GDA-YOLOv8n: a lightweight small object detection algorithm based on gradual feature aggregation
Li, X., Wang, P., Wang, J., Zeng, F., & Liu, X. (2025) · Signal Image and Video Processing · doi:10.1007/s11760-025-04456-2 · Cited by 2
“In contrast, single-stage detectors [5–8, 10–14] abandon the complex candidate region generation and subsequent fine-tuning steps of two-stage models, performing a single forward pass on the input image.”
Zhang, X., Wang, X., & Yang, Z. (2025) · Sensors · doi:10.3390/s25144443 · Cited by 2
“Single-stage models use a regression approach, inputting images into convolutional neural networks and directly outputting detection results after processing, such as the YOLO [4] series and SSD [5] algorithms.”
Small target detection algorithm based on the fusion attention mechanism and multi-layer convolution
Li, X., Zhang, H., Hang, Y., & Chen, H. (2025) · PLoS ONE · doi:10.1371/journal.pone.0328003 · Cited by 2
“In contrast, one-stage detection algorithms, such as SSD [3] (Single Shot MultiBox Detector), the YOLO series [4] (You Only Look Once), and RetinaNet [5], directly extract features from images to accomplish object detection tasks.”
Defect Detection Algorithm for Photovoltaic Cells Based on SEC-YOLOv8
Xue, H., Liu, L., Wu, Q., et al. (2025) · Processes · doi:10.3390/pr13082425 · Cited by 2
MLDAAPP: machine learning data acquisition for assessing population phenotypes
Gabidulin, A. R., & Rudman, S. M. (2025) · G3 Genes Genomes Genetics · doi:10.1093/g3journal/jkaf173 · Cited by 3
Sidewalk2Synth: generating synthetic embodied locomotion from real-world streetscapes
Torrens, P. M., & Kim, R. (2025) · Urban Informatics · doi:10.1007/s44212-025-00081-z · Cited by 5
NGD-YOLO: An Improved Real-Time Steel Surface Defect Detection Algorithm
Li, B., Xiao, A., Hu, X., et al. (2025) · Electronics · doi:10.3390/electronics14142859 · Cited by 2
Evaluating Millimeter-Wave RADAR for Resource-Efficient Drone Perception
Mandaokar, D., & Rinner, B. (2025) · International Conference on Distributed Computing in Smart Systems and the Internet of Things (DCOSS-IoT) · doi:10.1109/dcoss-iot65416.2025.00064 · Cited by 4
“We apply YOLOv5 [8] for vision-based detection and classification and compare the performance of the two sensing modalities.”
Deep Learning-Based Object Detection in Thermal Imaging
Raj, S., Pradhan, S. R., Anand, P., Deswal, D., Shah, S. S. H., & Kumar, V. (2025) · Global Conference in Emerging Technology (GINOTECH) · doi:10.1109/ginotech63460.2025.11076813 · Cited by 2
Moltschanov, A., & Metternich, J. (2025) · Procedia CIRP · doi:10.1016/j.procir.2024.12.072 · Cited by 2
Holub, G., Hofer, S., Obermüller, T., Rueckert, E., & Romaner, L. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.111881 · Cited by 3
Wang, Q., Jing, S., Yang, R., Liu, Z., Tang, Y., & Pan, H. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.111907 · Cited by 3
DMSDA-YOLO: Dynamic Multiscale Dilated Attention for Remote Sensing Object Detection
Huang, Z., Xu, Z., Li, X., Zhang, Y., Shi, Y., Li, Q., & Fang, H. (2025) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2025.3596809 · Cited by 3
A lightweight and generalizable detection enhancement method using segmentation feedback
Wang, S., Wei, W., Wang, Z., & Liu, X. (2025) · Machine Vision and Applications · doi:10.1007/s00138-025-01729-1 · Cited by 2
“While Faster R-CNN has excelled in accuracy, its two-stage design has led to slower inference speeds, and then YOLO [32], as a one-stage method, comes into sight.”
LLM-Guided Evolution: An Autonomous Model Optimization for Object Detection
Yu, Y., & Zutty, J. (2025) · Genetic and Evolutionary Computation Conference Companion (GECCO Companion) · doi:10.1145/3712255.3734340 · Cited by 10
Leveraging deep learning models for structural crack detection
Ghosh, T., Gangopadhyay, A., & Das, L. (2025) · Innovative Infrastructure Solutions · doi:10.1007/s41062-025-02202-8 · Cited by 4
Pan, Y., Zeng, H., Zhou, Y., et al. (2025) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2025.3599933 · Cited by 2
Comparative Analysis of YOLOv11 and YOLOv12 for AI-Powered Aerial People Detection
Simic, N., & Gavrovska, A. M. (2025) · International Conference on Electrical, Electronic and Computing Engineering (IcETRAN) · doi:10.1109/icetran66854.2025.11114306 · Cited by 4
A Lightweight Method for Garbage Classification using Improved-YOLOv8
Wang, G., Wang, B., & Zhao, P. (2024) · International Conference on Mechatronics and Computer Technology Engineering (MCTE) · doi:10.1109/mcte62870.2024.11117744 · Cited by 2
Object Detection Characteristics in a Learning Factory Environment using YOLOv8
Schneidereit, T., Gohrenz, S., & Breuß, M. (2025) · Lecture notes in networks and systems · doi:10.1007/978-3-032-00071-2_18 · Cited by 2
An improved YOLOv8s-based UAV target detection algorithm
Wang, X., Hu, Y., Liang, Q., He, Y., & Zhou, L. (2025) · PLoS ONE · doi:10.1371/journal.pone.0327732 · Cited by 3
“On the other hand, regression-based object detection methods, such as the You Only Look Once (YOLO) [14] series and Single Shot MultiBox Detector (SSD) [15], divide the entire image into grids and directly predict the location and category of objects in each grid.”
Liu, J., Yao, D., Liu, N., & Yuan, Y. (2025) · Biomimetics · doi:10.3390/biomimetics10090558 · Cited by 4
CCTV-Gun: Benchmarking Handgun Detection in CCTV Images
Li, Z., Yellapragada, S., Doshi, K., Mhasakar, P. M., Fan, H., Wei, J., Blasch, E., Zhang, B., & Ling, H. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-94895-4_18 · Cited by 15
Ye, Z., Zhou, P., Zhu, D., & Lv, J. (2025) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2025.3602260 · Cited by 3
Tran, H. N., & Quach, N. H. (2025) · International Conference on Intelligent Information Technology (ICIIT) · doi:10.1145/3731763.3731778 · Cited by 2
Orientation of flat bodies of revolution in shear flows at low Reynolds number
Giusto, D. D., Bergougnoux, L., & Guazzelli, É. (2025) · Journal of Fluid Mechanics · doi:10.1017/jfm.2025.10421 · Cited by 3
Reinforcing License Plate Detection Against Adversarial Attacks and Environmental Disruptions
Shafi, S., Soni, P., & Joby, N. J. (2025) · International Conference on Advances in Computing, Communication, Embedded and Secure Systems (ACCESS) · doi:10.1109/access65134.2025.11135734 · Cited by 2
“With advancements in deep learning, object detection models like the YOLO (You Only Look Once) [1] framework have revolutionized license plate recognition by offering high-speed and accurate detection.”
SVN-YOLO: a high-precision ship detection algorithm based on improved YOLOv10n
Wang, Z., Han, D., Han, B., Wu, Z., & Huang, X. (2025) · The Journal of Supercomputing · doi:10.1007/s11227-025-07743-4 · Cited by 2
“This approach eliminates the need for generating candidate frames, as exemplified by YOLO [9], SSD [10], and RetinaNet [11].”
Long, J., & Chamran, M. K. (2025) · IEEE Symposium on Industrial Electronics & Applications (ISIEA) · doi:10.1109/isiea65768.2025.11138423 · Cited by 2
“YOLOv11 is a newer version of the YOLO (You Only Look Once)[7] series model.”
Deep Learning-Based Autonomous Vehicle on SoC
Hwang, G. H., Oh, H., Choi, M., et al. (2025) · International Technical Conference on Circuits/Systems, Computers and Communications (ITC-CSCC) · doi:10.1109/itc-cscc66376.2025.11137739 · Cited by 2
“A prime example is the "You Only Look Once" (YOLO) CNN-based detector, which can identify multiple objects in an image with high accuracy in real time [5].”
Instance Segmentation-Based Hazard Detection with Lunar South Pole Lighting
Cloud, J. M., Buckles, B. C., Muller, T. J., Beksi, W. J., & Schuler, J. M. (2025) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra55743.2025.11127967 · Cited by 3
“You Only Look Once (YOLO) [10], particularly the YOLOv8 variant [11], has demonstrated efficient real-time object detection by treating the task as a regression problem.”
CloudTrack: Scalable UAV Tracking with Cloud Semantics
Blei, Y., Krawez, M., Nilavadi, N., Kaiser, T. K., & Burgard, W. (2025) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra55743.2025.11128514 · Cited by 6
RipGAN: A GAN-Based Rip Current Data Augmentation Method
Qian, S., Harley, M., Razzak, I., et al. (2025) · IEEE International Conference on Robotics and Automation · doi:10.1109/icra55743.2025.11128547 · Cited by 3
“Popular object detectors include YOLO series [14], RCNN series [13], SSD series [26] and DETR series [27].”
Enhanced View Planning for Robotic Harvesting: Tackling Occlusions with Imitation Learning
Li, L., & Kasaei, H. (2025) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra55743.2025.11127892 · Cited by 2
AIoT-Based Smart Traffic Light Management System using YOLO Object Detection and Transfer Learning
Mhaidat, K. M., Yosef, R. N. A., & Sinno, B. A. (2025) · International Conference on Circuit, Systems and Communication (ICCSC) · doi:10.1109/iccsc66714.2025.11135141 · Cited by 2
“…detection techniques to estimate road traffic densities and dynamically control the traffic signal timing, including support vector machines (SVM) [7], Region prposal convoluaiotional neural networks (R-CNN) [8], fast R-CNN [9], faster R-CNN[10], and You-Look-Only-Once (YOLO) [11], [12], [13].”
Deep Architectural Classification of Dental Pathologies Using Orthopantomogram Imaging
Adnan, A., Rizwan, M., Attaullah, H. M., Basheer, S., & Quasim, M. T. (2025) · Computers, materials & continua/Computers, materials & continua (Print) · doi:10.32604/cmc.2025.068797 · Cited by 5
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.