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 26,501–26,600 of 51,401
Lee, J., Chae, H., Son, S., Seo, J., Suh, Y., Lee, J., Chung, Y., & Park, D. (2025) · Sensors · doi:10.3390/s25113406 · Cited by 8
“Representative models include the R-CNN family, such as Fast R-CNN [39] and Faster R-CNN [20].”
Mghari, M., Tabarnoust, E., Abibou, R., et al. (2025) · Journal of Intelligent & Fuzzy Systems · doi:10.1177/18758967251342289 · Cited by 3
“Ouardirhi et al. (2022) proposed an end-to-end, layout-independent ALPR system using a YOLO-based model trained on a dataset including Moroccan and European license plates, also implementing a voting system to filter the most frequent recognition results for improved accuracy.”
InfluentialWang, H., Huang, G., Huang, Z., et al. (2025) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2025.3575439 · Cited by 3
Sparsity-Driven Gesture Recognition Using Lightweight TCNFormer Networks in Millimeter-Wave Radar
Wu, H., Jin, B., Zhang, Z., Lian, Z., Xu, B., Liang, J., Zhang, X., & Du, G. (2025) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2025.3576011 · Cited by 5
Ain, Q. U., Xia, K., & Fatima, T. (2025) · IEEE Aerospace and Electronic Systems Magazine · doi:10.1109/maes.2025.3577147 · Cited by 4
“The YOLO series encompasses several versions, starting with YOLOv1 [7], designed specifically for the categorization and localization of targets.”
Ding, S., Wang, Z., Yang, Y., Dai, W., & Luo, J. (2025) · Signal Image and Video Processing · doi:10.1007/s11760-025-04282-6 · Cited by 17
“The other category is one-stage object detection meth-ods, including YOLO series [18–30], SSD series [31, 32], RetinaNet [33] and so on.”
Renfei, C., Peng, Y. J., Li, Z., & Hua, S. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.128535 · Cited by 5
Target Detection Algorithm for UAV Aerial Images Based on BMGS-YOLOv8
Ning, Y., & Chen, J. (2025) · International Conference on Advanced Algorithms and Control Engineering (ICAACE) · doi:10.1109/icaace65325.2025.11019851 · Cited by 3
Real-Time B-Spline Path Planning for Vision-Based Collision Avoidance
Liu, J.-J., Evans, C. P., & Beard, R. W. (2025) · IEEE/ION Position Location and Navigation Symposium · doi:10.1109/plans61210.2025.11028267 · Cited by 4
“Recent advancements in the field of object detection include recursive RANSAC for multiple target tracking [19], the You Only Look Once (YOLO) family of algorithms [20], [21].”
Hong, Z., Zhang, Z., Pan, H., Liu, X., Liu, S., Ye, Z., Tao, J., Zhou, R., & Tong, X. (2025) · The Photogrammetric Record · doi:10.1111/phor.70012 · Cited by 4
Investigating Physical Latency Attacks Against Camera-Based Perception
Muller, R., Song, R., Wang, C., Zhan, Y., Monteuuis, J.-P., Man, Y., Li, M., Gerdes, R., Petit, J., & Celik, Z. B. (2025) · IEEE Symposium on Security and Privacy (S&P) · doi:10.1109/sp61157.2025.00236 · Cited by 20
“The proposal threshold T prop is typically set to 30 , 000 [41], accommodating potentially large detections in various general detection scenarios.”
Towards safer roads: benchmarking object detection models in complex weather scenarios
Tran-Le, B.-T., Patel, V., Huynh, V.-T., Tran, M.-K., Agrawal, K., Tran, M., & Nguyen, T. (2025) · Machine Vision and Applications · doi:10.1007/s00138-025-01709-5 · Cited by 3
“● Benchmark evaluation : Our evaluation focuses on widely adopted object detection models, including YOLO (v5 onwards) [10 – 16], DETR [ 1 ], R-CNN [17], Faster R-CNN [ 18 ], RetinaNet [19], and SSD [20].”
Lin, Y., Li, Z., Song, B., Ge, N., Sun, Y., & Gong, X. (2025) · Energies · doi:10.3390/en18123191 · Cited by 4
Li, C., Huang, H., Mo, H., Wen, Z., Zhou, S., & Zhu, Z. (2025) · IEEE Access · doi:10.1109/access.2025.3581313 · Cited by 5
Cluster-NMS: Improving Crowded Object Detection through Clustering Pattern
Liao, J., & Tian, H. (2025) · Signal Image and Video Processing · doi:10.1007/s11760-025-04374-3 · Cited by 3
“In recent years, with the rise of artificial intelligence technology, the powerful learning ability of deep learning networks [12, 15, 16] has greatly improved the accuracy and speed of general object detection.”
STFA-YOLO: An Algorithm for Enhanced Infrared Ship Detection in Complex Marine Environments
Li, T., Hu, Y., & Wen, N. (2025) · International Conference on Computer Supported Cooperative Work in Design (CSCWD) · doi:10.1109/cscwd64889.2025.11033360 · Cited by 3
Detection of Trees and Objects in Apple Orchard from LiDAR Point Cloud Data Using a YOLOv5 Framework
Karim, M. R., Reza, M. N., Ahmed, S., Lee, K., Sung, J., & Chung, S. (2025) · Electronics · doi:10.3390/electronics14132545 · Cited by 7
Autonomous Wheeled Robot For Intelligent Supermarket Restocking
Jaleel, A., Abhijith, P. R., Anto, A., et al. (2025) · doi:10.1109/ictest64710.2025.11042674 · Cited by 3
Yang, J., Zhou, L. J., & Ju, Y. (2025) · Applied Sciences · doi:10.3390/app15137035 · Cited by 3
Lee, J., Kim, B., Kim, D., et al. (2025) · Journal of Civil Structural Health Monitoring · doi:10.1007/s13349-025-00981-3 · Cited by 3
“They evaluated the YOLO [11], YOLOv2 [12], and YOLOv3 [13] models for detecting rails, bolts, and clips.”
Driver Monitoring System: Enhancing Road Safety through Machine Learning and Computer Vision
Kukreja, P. R., Tiwari, A., Kumar, S., & Islam, M. (2025) · International Conference on Recent Advances in Electrical, Electronics, Ubiquitous Communication, and Computational Intelligence (RAEEUCCI) · doi:10.1109/raeeucci63961.2025.11048307 · Cited by 3
Air Leak Detection Using Sobel-Enhanced YOLO Algorithm from Infrared Images
Rong, S., Hamdan, E., Khaleghi, H., et al. (2025) · IEEE International Symposium on Circuits and Systems proceedings · doi:10.1109/iscas56072.2025.11043806 · Cited by 3
Chen, K., Tang, J., Wen, L., Ma, Z., Liu, S., & Li, D. (2025) · Microchemical Journal · doi:10.1016/j.microc.2025.114357 · Cited by 4
A novel architecture for efficient pedestrian detection in autonomous vehicles
Farhat, W., Rhaiem, O. B., Faiedh, H., & Souani, C. (2025) · Connection Science · doi:10.1080/09540091.2025.2529261 · Cited by 5
“Conversely, one-stage detection meth-ods, including YOLO (You Only Look Once) (Redmon et al., 2016), SSD (Wang et al., 2019), and RetinaNet (Chaturvedi & Ghose, 2022), streamline this process by employing a single network to simultaneously classify objects and predict bounding box coordinates using…”
InfluentialBeyond 3D: Generic IoU for 3D Object Detection
Lun, H., Lü, K., Hou, L., Wang, S., & Xue, J. (2025) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2025.3586127 · Cited by 6
SIGNETS: Neural Network Architectures for m-QAM Soft Demodulation
Voggu, A. R., Kanish, R., Akula, N., Maruvada, L., Shimizu, T., & Rao, M. (2025) · IEEE Access · doi:10.1109/access.2025.3586043 · Cited by 5
Plastic water bottle detection model using computer vision in aquatic environments
Heller, A., Jacobs, M., Acosta‐González, G., Basola, A., Beck, J., Garnes, W., Molina, J. A. H., Johnson, A., Kiriazes, R., Lenczewski, M. E., et al. (2025) · Scientific Reports · doi:10.1038/s41598-025-09300-8 · Cited by 3
YOLOv8n-EggplantDiseases: an enhanced model for accurate disease detection in eggplants
Yao, Q., Zhang, C., Feng, Y., & Wang, X. (2025) · Evolving Systems · doi:10.1007/s12530-025-09717-6 · Cited by 4
A Federated Learning Architecture for Bird Species Classification in Wetlands
Mulero-Pérez, D., Rodriguez-Juan, J., Ramírez-Gordillo, T., Benavent-Lledó, M., Ruiz-Ponce, P., Ortiz-Pérez, D., Hernandez-Lopez, H., Iarovikov, A., García‐Rodríguez, J., Sebastián‐González, E., et al. (2025) · Journal of Sensor and Actuator Networks · doi:10.3390/jsan14040071 · Cited by 4
Layer-Wise Query Selection to Eliminate Redundant Queries in DETR
Hong, S.-J., Choi, C.-Y., & Lee, S.-W. (2025) · Applied Sciences · doi:10.3390/app15147686 · Cited by 5
Ji, Q., Zhang, K., Bi, Y., Zhang, G., & Pang, H. (2025) · Mining Metallurgy & Exploration · doi:10.1007/s42461-025-01306-0 · Cited by 5
“Common methods rely on convolutional neural networks (CNNs)[33], which extract features from camera images for object detection and localization.”
Craioveanu, M. G., Stâmâtescu, G., & Popescu, D. (2025) · IEEE Access · doi:10.1109/access.2025.3588184 · Cited by 3
He, X., Tang, C., Liu, X., Zhang, W., Gao, Z., Li, C., Qiu, S., & Xu, J. (2025) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2025.3586155 · Cited by 5
“To further enhance the process, a scaling operator is introduced: where E = e 1 , e 2 , . . . , e t , represents the collection of all e ∗ t values across the spectral and spatial dimensions.”
MST-AI: Skin Color Estimation in Skin Cancer Datasets
Khalkhali, V., Lee, H., Nguyen, J., Zamora-Erazo, S., Ragin, C. C. R., Aphale, A., Bellacosa, A., Monk, E. P., & Biswas, S. (2025) · Journal of Imaging · doi:10.3390/jimaging11070235 · Cited by 7
Wang, K., He, G., & Li, X. (2025) · Sensors · doi:10.3390/s25144381 · Cited by 3
“These methods are typically categorized into two types: single-stage detectors (such as YOLO series [12,13], SSD [14]) and two-stage detectors (such as Faster R-CNN [15], Mask R-CNN [16]).”
FSD3: Few-Shot SAR Object Detection With Dynamic Perception RPN and Category Knowledge Decoder
Wang, J., Yujie, Z., & Bai, X. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2025.3588472 · Cited by 5
UAV-OVD: Open-Vocabulary Object Detection in UAV Imagery via Multi-Level Text-Guided Decoding
Tao, L., Wei, G., Wang, Z., Qi, Z., Li, Y., & Zhang, H. (2025) · Drones · doi:10.3390/drones9070495 · Cited by 5
UES-YOLO: Underwater biological detection based on YOLO with an efficient sampling block
Shen, C., Yang, D., Liu, F., et al. (2025) · Signal Image and Video Processing · doi:10.1007/s11760-025-04508-7 · Cited by 3
“YOLO [14] is an efficient single-stage target detection model that directly predicts the target location and cate-gorybyregressionmethod.”
PCB Defect Detection Algorithm Based on Improved YOLOv9
Chen, S., Xing, E., & Hou, X. (2025) · International Conference on Neural Networks, Information and Communication Engineering (NNICE) · doi:10.1109/nnice64954.2025.11064718 · Cited by 3
Wind Turbine Blade Defect Recognition Method Based on Large-Vision-Model Transfer Learning
Li, X., Tian, J., Pang, X., et al. (2025) · Sensors · doi:10.3390/s25144414 · Cited by 3
Vertical Scaling Can Save Time: Optimizing Container Scheduling to Handle Sudden Bursts
Peri, A., Tsenos, M., & Kalogeraki, V. (2025) · ACM International Conference on Distributed and Event-Based Systems (DEBS) · doi:10.1145/3701717.3730549 · Cited by 3
Automated detection of sea cucumbers in turbid subtidal marine habitats: An explainable approach
Chu, C., Gu, Y., Wong, A., & Russell, B. D. (2025) · Ecological Informatics · doi:10.1016/j.ecoinf.2025.103342 · Cited by 3
Oriol, P., Baños-Castelló, P., Padró, E. M., Francescangeli, M., Toma, D. M., Widmer, M. C., Farran, J. D. P., & Fernández, J. D. R. (2025) · Artificial intelligence · doi:10.5772/intechopen.1011280 · Cited by 4
Mathew, A., Hertel, D., & Bräunig, G. (2025) · The International Journal of Advanced Manufacturing Technology · doi:10.1007/s00170-025-16150-1 · Cited by 5
“This advanced version has demonstrated a notable capacity for accuracy and speed in identifying objects, even those of smaller dimensions [25].”
Jorge, V. L., Boutaleb, Z., Boutin, T., Bendaoud, I., Soulié, F., & Bordreuil, C. (2025) · Metals · doi:10.3390/met15080836 · Cited by 3
Benelmostafa, B.-E., Aitelhaj, R., & Medromi, H. (2025) · IEEE Access · doi:10.1109/access.2025.3593201 · Cited by 8
Yao, X., Yuan, H., Zhao, S., Tian, W., Han, D., Li, X., Wang, F., & Wang, S. (2025) · Sensors · doi:10.3390/s25154714 · Cited by 3
“Several common loss functions were compared—YOLO11’s original BCE With Log-its [35], Classification Loss, Regression Loss [36], Distribution Focal Loss, and Focal Loss—by integrating each into the model and evaluating their impact on performance, the results are shown in Table 4.”
Research on a lightweight cone yarn varieties recognition model
Du, Z., Dai, N., Hu, X., et al. (2025) · Measurement Science and Technology · doi:10.1088/1361-6501/adf24e · Cited by 3
Small Target Detection for Power Line Components in Complex UAV Imagery
Sun, Z., & Wang, X. (2025) · IEEE Access · doi:10.1109/access.2025.3594903 · Cited by 5
Liu, F., Greer, A. T., Mai, G., & Sun, J. (2025) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3711896.3737395 · Cited by 3
“YOLO (You Only Look Once) is a cutting-edge object detection model [24] that has evolved over multiple iterations and gained widespread adoption in various applications due to its speed and accuracy [18, 29, 31].”
A Performance Comparison of Object Detection Algorithms on Traffic Scenes in Indian Roads
Paranjape, B., Naik, A. A., & Sankar, S. P. (2025) · Engineering Technology & Applied Science Research · doi:10.48084/etasr.11105 · Cited by 3
Chen, Y., Li, J., Liu, Y., Jiang, F., Zhou, A., & Li, Y. (2025) · Journal of Educational Computing Research · doi:10.1177/07356331251361806 · Cited by 4
“There is also the YOLO series of algorithms, which signi fi cantly improve the detection speed while ensuring a certain level of detection accuracy and can quickly handle object detection tasks in video streams (Redmon et al., 2016).”
A Real-Time Road Damage Detection System for IoT Edge Devices Using Lightweight Deep Learning Models
Huang, Y.-X., Wang, Z., Yin, Y., et al. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3595099 · Cited by 3
“Redmon et al. [14] transformed object detection 2327-4662 c (cid:2) 2025 IEEE.”
Panja, P., Rayguru, M. M., & Baidya, S. (2025) · Robotics · doi:10.3390/robotics14080108 · Cited by 3
“A similar approach is also taken in [12] for implementing platooning control using the YOLO detector [13].”
Robust Pedestrian Detection via Enriched Dataset
Babu, V., & Raman, R. (2025) · Communications in computer and information science · doi:10.1007/978-3-031-93691-3_3 · Cited by 7
Clabaut, É., Bouffard, J., & Savage, J. (2025) · Insects · doi:10.3390/insects16080813 · Cited by 4
“The seventh iteration of YOLO [25] was chosen as it performed very well on different benchmarks [26] and is easy to fine-tune.”
Oak-YOLO: A high-performance detection model for automated Oak seed defect identification
Li, H., Li, Z., Chen, D. Y., Wu, W., He, X., & Mu, H. (2025) · PLoS ONE · doi:10.1371/journal.pone.0327371 · Cited by 4
“YOLO frameworks [6–8], along with region-based models like Faster R-CNN [9] and single-shot detectors like SSD [10], enable fast and accurate defect identification in real-time.”
Ding, H., Chen, J., Ye, H., & Chen, Y. (2025) · Applied Sciences · doi:10.3390/app15147887 · Cited by 4
Zhang, W., Guo, D., Shang, Y., et al. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3597820 · Cited by 3
“Compared to conventional approaches, Compared to two-stage detection approaches, single-stage frameworks like the YOLO [7] series directly predict object categories and bounding boxes.”
A real-time end-to-end detector for detecting surface defects on oversized rings
Liu, J., Zhang, L., Chen, S., Wang, Y., Wu, B., & Dong, J. (2025) · PLoS ONE · doi:10.1371/journal.pone.0330031 · Cited by 3
“…into two categories: two-stage algorithms, represented by Faster R-CNN [16], which detect objects through generating candidate regions and refining bounding boxes; and one-stage algorithms, represented by SSD [17] and YOLO [18], which classify and refine bounding boxes directly from anchor points.”
Multi-scale defect detection method for involute gear tooth flank in the context of remanufacturing
Liu, Y., Yan, C., Huo, D., Wen, J., Lei, H., Chen, X., Lin, C., & Chen, Z. (2025) · Measurement · doi:10.1016/j.measurement.2025.118680 · Cited by 4
Open vocabulary detection for concealed object detection in AMMW image
Jiang, C., Li, C., & Zhao, X. (2025) · Scientific Reports · doi:10.1038/s41598-025-13935-y · Cited by 4
“…encodes the input text using a text encoder to obtain text embeddings, extracts rich multi-scale image features through the improved YOLO detector 26 and Task-Integrated Block (TIB), and effectively aligns and interacts the lexical features of natural language with the visual features of…”
DNA nanostructures: From molecular folding assembly to target subcellular delivery
Yu, D., Zhong, L., Liu, B., Mao, B., Yang, D., & Chen, X.-Y. (2025) · Colloids and Surfaces B Biointerfaces · doi:10.1016/j.colsurfb.2025.115030 · Cited by 3
Ostrovsky, Z., Barmak, O., Radiuk, P., & Krak, I. V. (2025) · Machine Learning and Knowledge Extraction · doi:10.3390/make7030081 · Cited by 5
“Object detection models from the YOLO family [24,25] are particularly popular for their favorable balance of speed and accuracy.”
Omer, K., & Monteriù, A. (2025) · IEEE International Workshop on Metrology for Living Environment (MetroLivEnv) · doi:10.1109/metrolivenv64961.2025.11106999 · Cited by 3
“• YOLO (You Only Look Once): A popular real-time object detection model that processes images in a single pass, balancing speed and accuracy for diverse applications [18].”
Aiymbay, S., Zhumadillayeva, А., Matson, E. T., et al. (2025) · Symmetry · doi:10.3390/sym17081294 · Cited by 3
How to minimize the annotation effort in aerial wildlife surveys
May, G. B., Dalsasso, E., Delplanque, A., Kellenberger, B., & Tuia, D. (2025) · Ecological Informatics · doi:10.1016/j.ecoinf.2025.103387 · Cited by 9
Qiu, Y., Li, G., Wu, M., Jia, Y., Ye, L., & Ma, Y. (2025) · IEEE Transactions on Circuits and Systems I Regular Papers · doi:10.1109/tcsi.2025.3598287 · Cited by 4
“The Q-K-V generation in transformer [1], combination phase in graph convolutional network (GCN) [2], and convolution layers in convolutional neural networks (CNNs) [3], [4], [5], [6], [7] Fig.”
A Deep Learning Framework for Multi-Object Tracking in Space Animal Behavior Studies
Zhou, Z., Li, S., Lv, Y., Liu, K., Cao, Y., & Guo, S.-C. (2025) · Animals · doi:10.3390/ani15162448 · Cited by 4
“DBT leverages object detectors such as YOLO [16,17] or Faster R-CNN [18], followed by association strategies based on appearance or motion [19].”
Deep Learning for Dynamic Wildlife Monitoring: A Real-Time Approach
Mughal, A. B., Khan, R. U., Rehman, A. U., & Bermak, A. (2025) · IEEE Access · doi:10.1109/access.2025.3600625 · Cited by 9
Wang, Y., Li, Z., Hou, Y., Ren, W., Wang, T., Li, J., Luo, Z., Chunxu, L., & Ding, G. (2025) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2025.3601179 · Cited by 8
Anilkumar, A., Vijayan, P., Veena, G., et al. (2025) · International Conference on Computing for Sustainable Global Development · doi:10.23919/indiacom66777.2025.11115689 · Cited by 3
CV-YOLOv8: a lightweight and high-accuracy model for wind turbine damage detection
Li, T., & Zhanfang, Z. (2025) · Multiscale and Multidisciplinary Modeling Experiments and Design · doi:10.1007/s41939-025-01019-3 · Cited by 4
“(Redmon et al. 2016) designed a more efficient convolu - tional structure, allowing YOLOv2 to significantly reduce computational load while maintaining high accuracy, result - ing in improved real-time detection performance.”
Optimizing an Object Detection Algorithm for Detecting Oil Palm Fruit Bunches and Their Ripeness
Chotikawanid, P., Saeleung, P., Pianroj, Y., et al. (2025) · Applied Computational Intelligence and Soft Computing · doi:10.1155/acis/6263757 · Cited by 3
Ai, D., Kuang, D., Tao, Y., & Zeng, F. (2025) · Sustainability · doi:10.3390/su17177573 · Cited by 6
Vision-based analysis of soft story, short columns, and vertical geometry in RC structures
Yavariabdi, A., Asik, M. F., Doğan, G., & Arslan, M. H. (2025) · Structures · doi:10.1016/j.istruc.2025.109951 · Cited by 3
A Compound-Eye-Inspired Multi-Scale Neural Architecture with Integrated Attention Mechanisms
Neri, F., Yang, M., & Xue, Y. (2025) · International Journal of Neural Systems · doi:10.1142/s0129065725500650 · Cited by 6
Unsupervised Tablet Defect Detection Method Based on Diffusion Model
Zhang, M., Liu, W., He, L., & Wang, D. (2025) · Sensors · doi:10.3390/s25175254 · Cited by 3
“Among them, supervised methods represented by Siamese Network [14], Fast R-CNN [15], and YOLO [16] have fully demonstrated their advantages of a high accuracy and good adaptability.”
Liu, G., Kang, S., Li, T., Xu, Y., & Zhou, J. (2025) · Journal of Robotics · doi:10.1155/joro/8556780 · Cited by 4
Zuo, Z., Wu, Z., Wei, J., Wu, P., Huang, S., & Cheng, Z. (2025) · Photonics · doi:10.3390/photonics12090847 · Cited by 5
Learning the Optimal Path and DNN Partition for Collaborative Edge Inference
Huang, Y., Zhang, L., & Xu, J. (2025) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2025.3602966 · Cited by 11
Wei, Z., Yi, C., Han, X., & Huang, T. (2025) · Infrared Physics & Technology · doi:10.1016/j.infrared.2025.106115 · Cited by 3
Peng, L., Shui, H., Janisch, A. N., et al. (2026) · PLoS ONE · doi:10.1371/journal.pone.0354821 · Cited by 3
“We followed YOLO standard practice in selecting metrics that are relevant to our primary goal of accurate quantification (Redmon et al. 2016).”
Simulation of Deep Learning-Based Multitarget Track Association for Ballistic Target Groups
Chang, W., Chen, D., Cao, H., Bu, L., Wang, C., & Fu, T. (2025) · IEEE Sensors Journal · doi:10.1109/jsen.2025.3601590 · Cited by 3
“We select the You Only Look Once version 8 (YOLOv8) [26], [27] network as our baseline framework.”
MDFAC: multi-dimensional feature adaptive calibration for generalized few-shot object detection
Xie, K., Lai, J., She, Z., Lei, L., & Chen, H. (2025) · Complex & Intelligent Systems · doi:10.1007/s40747-025-02053-x · Cited by 4
“In particular, object detection has benefited from various advanced solutions enabled by the training of large-scale annotated datasets [39, 56, 64].”
Dhungana, A., Yang, X. Y., Paneru, B., et al. (2025) · AgriEngineering · doi:10.3390/agriengineering7090278 · Cited by 3
An optimized lightweight YOLO-MRC framework for enhanced obstacle detection in service robots
Tian, J., Ma, N., Huang, K., Lv, Y., Chi, W., & Sun, L. (2025) · Journal of Real-Time Image Processing · doi:10.1007/s11554-025-01756-1 · Cited by 3
“The pioneering work in the YOLO series, YOLOv1-v3 [1–3], has become the standard algo-rithm for edge devices due to its real-time, end-to-end framework.”
LSOD-YOLO: Lightweight Small Object Detection Algorithm for Wind Turbine Surface Damage Detection
Jiang, H., Liu, H., Chen, Z., et al. (2025) · Journal of Nondestructive Evaluation · doi:10.1007/s10921-025-01253-2 · Cited by 3
“Prominent algo - rithms include SSD [20], and the YOLO [21, 22] series.”
Priadana, A., Nguyen, D.-L., Vo, X.-T., Cao, G. F., Choi, J., & Jo, K.-H. (2025) · International Workshop on Intelligent Systems (IWIS) · doi:10.1109/iwis66215.2025.11142380 · Cited by 5
“Using specialized object detection frameworks such as Faster R-CNN [4] and YOLO (You Only Look Once) [5], these systems can quickly differentiate between weapons and other objects in complex environments.”
Ji, H., Li, J., Han, P., Shi, Z., Liu, X., & Liu, L. (2025) · Scientific Reports · doi:10.1038/s41598-025-15894-w · Cited by 4
Context Graph-Based Visual-Language Place Recognition
Woo, S., & Kim, S.-W. (2025) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra55743.2025.11127699 · Cited by 6
“In contrast, Heikel and Espinosa-Leal [22] obtain object labels from the input image using YOLO [23] to perform a VPR task.”
Rockfall-YOLO Deep Learning Model for Rockfall Motion Object Detection
Su, G., Huang, W., Li, C., et al. (2025) · Journal of Computing in Civil Engineering · doi:10.1061/jccee5.cpeng-6268 · Cited by 3
He, Y., Su, H., Yu, H., Yang, C., Wei, S., Wang, C., & Liu, S. (2025) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra55743.2025.11127317 · Cited by 8
FRT-DETR: faster real-time end-to-end detector for industrial surface defects based on transformer
Xiang, S., Fu, C., Song, W., Wang, X., Chen, J., & Sham, C. (2025) · Journal of Real-Time Image Processing · doi:10.1007/s11554-025-01702-1 · Cited by 6
“Representative examples of these one-stage approaches include SSD[7] and YOLO series, including YOLOv1 [8], YOLOv2 [9], YOLOv3 [10], YOLOv4 [11], YOLOX [12], YOLOv5 [13], YOLOv6 [14], YOLOv7 [15], Q-YOLO [16], YOLOv8 [17], YOLOv10 [18] and so on, which have made substantial contributions to…”
Li, C., Ji, E., Yao, B., Li, S., & Wang, P. (2025) · IEEE Access · doi:10.1109/access.2025.3606032 · Cited by 3
Zhang, X. (2025) · IEEE Access · doi:10.1109/access.2025.3605887 · Cited by 5
Lightweight detection method for weeds in complex paddy fields based on the improved YOLOv5
Ju, J., Ma, X., Yang, C., et al. (2025) · Smart Agricultural Technology · doi:10.1016/j.atech.2025.101418 · Cited by 3
Wang, S., Liu, M., Dong, S., & Chen, S. (2025) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.70276 · Cited by 3
“RT-DETR, a notable improvement on the DETR model in recent years, has demonstrated superior performance in terms of accuracy and real-time capabilities compared to the YOLO series [20].”
Research on a Lightweight Textile Defect Detection Algorithm Based on WSF-RTDETR
Chen, J., Zhang, S., Yang, Y., et al. (2025) · Processes · doi:10.3390/pr13092851 · Cited by 3
ELSD-YOLO: an enhanced lightweight ship detection framework based on YOLO11n
Meng, X. Z., Bi, Z., Jia, L., et al. (2025) · Journal of Real-Time Image Processing · doi:10.1007/s11554-025-01757-0 · Cited by 3
“Successive you only look once (YOLO) [18] versions (e.g., YOLOv3 [19], YOLOv5 [20], YOLOv8 [21], and YOLO11 [22]) have progressively enhanced small-object detection capability, multi-scale feature fusion, and inference efficiency, making them promising candidates for maritime detection tasks.”
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.