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 29,501–29,600 of 51,399
Cardarelli, L. (2025) · Digital Applications in Archaeology and Cultural Heritage · doi:10.1016/j.daach.2025.e00452 · Cited by 6
VLPose: Bridging the Domain Gap in Pose Estimation With Language-Vision Tuning
Li, J., Chen, P., Ju, X., Liu, S., Xu, H. L., & Jia, J. (2025) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2025.3594097 · Cited by 7
Patel, A. K., Zhang, T., Avestruz, C., & Regier, J. (2025) · The Astronomical Journal · doi:10.3847/1538-3881/adef32 · Cited by 7
Detection of Hot Spots in PV Modules with the CBAM-Enhanced Yolo Model
Bekçioğulları, M. F., Açıkgöz, H., & Özbay, S. (2025) · International Symposium on Innovative Approaches in Smart Technologies (ISAS) · doi:10.1109/isas66241.2025.11101735 · Cited by 4
“The detection of the object is completed with bounding boxes with a value higher than the specified threshold value [6].”
Shi, J., You, L.-J., Dang, J. F., et al. (2025) · Petroleum Science · doi:10.1016/j.petsci.2025.08.018 · Cited by 2
Zhang, P., Liu, J., Zhang, J., & Li, X. (2025) · IET Image Processing · doi:10.1049/ipr2.70177 · Cited by 2
Zhang, K., Li, Z., Gao, Y., Liu, L., & Liu, J. (2025) · Journal of Real-Time Image Processing · doi:10.1007/s11554-025-01743-6 · Cited by 3
“Notable examples of one-stage detectors include the SSD [17] and YOLO series [18–21], RetinaNet [22], CenterNet [23], and others.”
Mbietieu, M. A., Tapamo, H., Kouamou, G. E., & Tsopzé, N. (2025) · Science of Remote Sensing · doi:10.1016/j.srs.2025.100270 · Cited by 3
Li, J., Liu, M., Peng, H., Liu, L., Zheng, X., Chen, Y., Liu, G., Zhou, J., & Lyu, F. (2025) · Peer-to-Peer Networking and Applications · doi:10.1007/s12083-025-02079-5 · Cited by 2
“From the early developments of R-CNN [17], Faster R-CNN [18], and FPN [19], to the emergence of the YOLO series [20], detection accuracy and computational efficiency have sig-nificantly improved.”
Zhang, N., Salili‐James, A., Poon, S. T. S., Hollister, J. D., & Scott, B. (2025) · Advanced Intelligent Systems · doi:10.1002/aisy.202500005 · Cited by 3
Qingjiang, 陈. C., & Lu, 李. L. (2025) · Laser & Optoelectronics Progress · doi:10.3788/lop242287 · Cited by 2
Lightweight Method for Insulator Defect Detection Based on Improved Convolutional Neural Networks
Liu, J., Ou, Y., Zhou, Z., et al. (2025) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2025.3599701 · Cited by 2
Detection of Screen Usage During Eating Events Among Preschool-Aged Children
Ghosh, T., Hossain, M. B., Holiday, S., Cribbet, M. R., White, S., Gan, Y., & Sazonov, E. E. (2025) · Proceedings - International Conference on Image Processing · doi:10.1109/icip55913.2025.11084752 · Cited by 2
Multi-Granularity Relation Enhancement Network for Tiny Defect Detection on Printed Circuit Board
Guo, F., Chen, Z., Chen, B., Jing, M., & Zuo, L. (2025) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2025.3597003 · Cited by 4
Wang, C., & Liu, F. (2025) · IEEE Access · doi:10.1109/access.2025.3600840 · Cited by 2
FX-DETR: A Lightweight and Efficient Model for Maritime Small Object Detection
Feng, X.-Y., Ran, Y., Zhang, Y., et al. (2025) · International Conference on Automation, Control and Robotics Engineering · doi:10.1109/cacre66141.2025.11119563
“Over the past time, some deep learning models such as YOLO[1],SSD[2],Faster R-CNN[3] are widely used in real-time object detection, which are known for its speed and efficiency.”
YOLO-GL for efficient multi-target detection in large FOV via hierarchical feature fusion
Chen, X., Dong, C., Cui, T., Lv, G., & Ren, Y. (2025) · Scientific Reports · doi:10.1038/s41598-025-16617-x · Cited by 2
Unlabeled data augmentation with diffusion model for semi-supervised object detection
Lu, Z., Gu, R., Cheng, H., Xu, M., Xu, P., Kinoshita, Y., Ye, J., Jia, G., & Wu, Q. F. (2025) · The Visual Computer · doi:10.1007/s00371-025-04103-4 · Cited by 3
Dilated Strip-Wise Spatial Feature Pyramid: An Efficient Network for Object Detection
Sundaralingam, H., Suresh, T., Akilan, T., & Ahmed, S. B. (2025) · IEEE International Symposium on Industrial Electronics (ISIE) · doi:10.1109/isie62713.2025.11124807 · Cited by 2
“Another popular one-stage method is YOLO [11] with its many versions [4], [12]–[14] (e.g., YOLO-v9 and YOLO-v10).”
CLAD: Criterion learner and attention distillation for automated CNN prunning
Li, Z., Li, J., Liu, S., Zhao, B., & Liu, D. (2025) · Journal of Automation and Intelligence · doi:10.1016/j.jai.2025.08.002 · Cited by 4
FPH-DEIM: A Lightweight Underwater Biological Object Detection Algorithm Based on Improved DEIM
Li, Q., & Wenguang, S. (2025) · Applied System Innovation · doi:10.3390/asi8050123 · Cited by 2
A Two-stage Faster R-CNN Approach for Road Surface Damage Detection
Le, V. T. V., Keivanmarz, A., & Sharifzadeh, H. (2025) · IEEE Annual Computers, Software, and Applications Conference (COMPSAC) · doi:10.1109/compsac65507.2025.00077 · Cited by 2
“Object detection, a key task in computer vision, has been extensively applied to road surface damage detection using methods like Faster R-CNN [11], SSD, YOLO [12], and Mask R-CNN [13].”
Ahmed, M. S., Giordano, S., & Adami, D. (2025) · Applied Sciences · doi:10.3390/app15179345 · Cited by 3
Automated Footwear Surface Inspection System Based on the Deep Learning Object Detection
Cho, J., Nam, J., & Cho, H. (2025) · IFIP advances in information and communication technology · doi:10.1007/978-3-032-03550-9_23 · Cited by 2
Full-Scale Fusion Attention Network for Infrared Small Target Detection
Cui, X., Li, X., Wu, P., He, S., Wang, K., & Guo, Q. (2025) · IEEE Transactions on Aerospace and Electronic Systems · doi:10.1109/taes.2025.3602756 · Cited by 3
“Sincethemainstreamvisible imagetargetdetectionmodels(SSD[24],R-CNN[25], andYOLOseries[26])donotperformwellwhenapplied directlytoIRSTDtasks,anexistinggeneralizedtargetde-tectionnetworkwasadjustedbyMcIntoshetal.”
Multi-order feature learning with global–local attention for real-time X-ray security inspection
Guo, L., Xu, Y., & Chen, S. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.112058 · Cited by 2
Liu, P., Ding, Z., Wang, S., Zhang, W., Ren, Z., & Yang, X. (2025) · Measurement Science and Technology · doi:10.1088/1361-6501/ae0062 · Cited by 2
“The YOLOv8 model represents the latest development in the YOLO series [30], building upon and refining the methods of earlier versions.”
HERITAGE WATCH AI: Design and development of PreserveNet for Structural Health defect identification
Ramalingam, A., Benita Jael, J., Feslin Sherina, S., & George, S. V. (2024) · International Conference on Communication, Computing, Smart Materials and Devices (ICCCSMD) · doi:10.1109/icccsmd63546.2024.11015223 · Cited by 2
EFENet: An Efficient Edge-Feature Enhanced Network for power insulator detection
Zhang, J., Chen, C., Lu, M., Li, L., Shen, Y., Du, J., Chen, Z., Wang, Y., & Zhang, L. (2025) · International Journal of Electrical Power & Energy Systems · doi:10.1016/j.ijepes.2025.111019 · Cited by 2
Sun, Y., Gong, L., Dai, J., et al. (2025) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra55743.2025.11127686 · Cited by 2
“In the S To ascertain the final semantic label for each point and ensure high semantic availability in S 2 BEV, a Convolutional N eural Network (CNN) [20] coupled with a Monte Carlo method[21] is used for preliminary semantic label determination.”
Vision-Based Movement Primitives for Lunar Hazard Avoidance
Cloud, J. M., Beksi, W. J., & Schuler, J. M. (2025) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra55743.2025.11128448 · Cited by 3
“Recent advancements include terrain classification using random forests [20], convolutional neural network-based semantic segmentation [11], and instance segmentation models like You Only Look Once (YOLO) variants [21], [22], [17], [23].”
Li, G., Cheng, J., Liu, Y., Li, J., Lv, Z., & Li, Q. (2025) · Applied Soft Computing · doi:10.1016/j.asoc.2025.113841 · Cited by 2
A Review of Deep Space Image-Based Navigation Methods
Lin, X., Li, T., Hua, B., Li, L., & Zhao, C. (2025) · Aerospace · doi:10.3390/aerospace12090789 · Cited by 4
Towards Safe and Efficient Through-the-Canopy Autonomous Fruit Counting with UAVs
Yang, T., Ibrahimov, R., & Mueller, M. W. (2025) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra55743.2025.11127839 · Cited by 2
Dark-DENet: A Lightweight Enhancement Network for Low-Light Object Detection
Wu, X., Shao, Y., & Jin, X. (2025) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra55743.2025.11127459 · Cited by 2
“Two-stage detectors, such as Faster R-CNN [1], and single-stage detectors, such as YOLO and SSD [2], [3] , have demonstrated outstanding performance in various benchmark datasets [4], [5].”
Fusion of Thermal and RGB Images for Traffic Object Detection
Nandakumar, A., Vanajakshi, L., & Lakshminarayanan, C. (2025) · IEEE Applied Sensing Conference (APSCON) · doi:10.1109/apscon63569.2025.11144056 · Cited by 2
Lv, Z., Wang, G., Li, H., et al. (2025) · Journal of Marine Science and Engineering · doi:10.3390/jmse13091710 · Cited by 2
Luo, J., Yang, X., Dai, Q., Qiu, W., Nie, S., Wu, J., & Zeng, M. (2025) · Sensors · doi:10.3390/s25175550 · Cited by 2
“…by the related work [18,19], considering the detection accuracy, real-time performance, and compatibility with edge computing platforms, YOLOv8 [20] is adopted in this study to infer information such as the empty status and passenger count inside the elevator car, serving as an auxiliary input…”
YOLO-EDH: An Enhanced Ore Detection Algorithm
Wan, L., Huang, X., & Qiu, Z. (2025) · Minerals · doi:10.3390/min15090952 · Cited by 4
Du, X., & Wu, X. H. (2025) · Remote Sensing · doi:10.3390/rs17173094 · Cited by 6
Periodontitis bone loss detection in panoramic radiographs using modified YOLOv7
Ragab, M. G., Abdulkadir, S. J., Qaid, N., Gondal, T. M., Alqushaibi, A., Qureshi, R., & Shaukat, F. (2025) · PeerJ Computer Science · doi:10.7717/peerj-cs.3102 · Cited by 5
Seo, J., Kim, C. H., Kim, K., et al. (2025) · Ecological Processes · doi:10.1186/s13717-025-00641-w · Cited by 2
“YOLOv7’s architecture, which incorporates E-ELAN modules, is well-suited for extracting fine-grained features from such small and ambiguous objects (Li et al. 2022; Redmon et al. 2016; Wang et al. 2022).”
Xing, Y., Fang, X., Zhou, Y., Zhang, J., & Chen, H. (2025) · Journal of Real-Time Image Processing · doi:10.1007/s11554-025-01755-2 · Cited by 3
“As the first proposed single-stage detector, YOLOv1 [10] is significantly faster than the two-stage detector, achieving nearly the same detection accuracy.”
A YOLO Ensemble Framework for Detection of Barrett’s Esophagus Lesions in Endoscopic Images
Lin, W.-C., Wang, C., Tsai, M., Huang, C.-Y., Lin, C.-C., & Tseng, M. (2025) · Diagnostics · doi:10.3390/diagnostics15182290 · Cited by 3
“Frameworks such as the R-CNN family [10] and YOLO (You Only Look Once) [11] have significantly improved detection accuracy and processing speed and are now widely adopted in domains, including surveillance, autonomous driving, and medical image analysis.”
Ichi, A. E., Kaddah, W., Bouz, M. E., et al. (2025) · Signal Image and Video Processing · doi:10.1007/s11760-025-04301-6 · Cited by 2
“…handling this task, such as transformers (ViT [4], Detection Transformer (DETR) [1], and SWIN [15]), One-Stage methods (YOLO in different versions [17, 18, 23]), and Two-Stage methods (Region-Based Convolu-tional Neural Networks (R-CNN) [5], Fast R-CNN [6], Faster R-CNN [19, 20], and Mask R-CNN…”
Robust Object Detection Under Adversarial Patch Attacks in Vision-Based Navigation
Gu, H., Yoon, H. J., & Jafarnejadsani, H. (2025) · Automation · doi:10.3390/automation6030044 · Cited by 4
Demirel, S., & Yıldız, O. (2025) · PeerJ Computer Science · doi:10.7717/peerj-cs.3198 · Cited by 3
“The proposed system utilized two deep learning models: You Only Look Once (YOLO) ( Redmon et al., 2016 ) and Visual Geometry Group 16 (VGG16) ( Simonyan & Zisserman, 2014 ).”
Picello, N., Herrero, F., Hernández, S., López, A., & Santamaria‐Navarro, À. (2025) · IEEE Access · doi:10.1109/access.2025.3607191 · Cited by 4
IP-YOLOv8: A Multi-Scale Pest Detection Algorithm for Field-Scale Applications
Yang, C., Wang, Y., Yun, L., Wang, H., Han, Y., & Chen, Z. (2025) · Horticulturae · doi:10.3390/horticulturae11091109 · Cited by 3
Skor-Xg: Skeleton-Oriented Expected Goal Estimation in Soccer
Xu, Y., Bretzner, L., Wang, T., & Maki, A. (2025) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw67362.2025.00594 · Cited by 5
“With recent advances in object detection [42, 51] and pose estimation [6, 10, 24], 3D player skeleton data is becoming increasingly accessible in professional soccer games.”
Real-Time AI-Powered Occupancy Monitoring for Modern Jeepneys in Bacolod City, Philippines
Daba-ay, M. A., Bibangco, E. J. P., Javier, R. K. T., & Moncera, C. J. A. (2025) · International Conference on Data Science and Its Applications (ICoDSA) · doi:10.1109/icodsa67155.2025.11157597 · Cited by 2
“This footage serves as the primary source of the dataset used for developing AI models using YOLOv10 [26] and establishing the ground truth.”
Segment and Recover: Defending Object Detectors Against Adversarial Patch Attacks
Gu, H., & Jafarnejadsani, H. (2025) · Journal of Imaging · doi:10.3390/jimaging11090316 · Cited by 3
“(Top Row) Due to the added patches, the PAD [20] (baseline approach) yields significantly (Bottom Row) The inference results of SAR (our YOLOv11x [40] Faster RCNN [41] DETR [42]”
Multi-Feature Re-Identification Enhanced Dual Motion Modeling for Multi Small-Object Tracking
Ma, R., Sheng, Q., Chen, Y., Tao, Z., Wang, S., Niu, X., & Chen, S. (2025) · Sensors · doi:10.3390/s25185732 · Cited by 3
“With technological advancements, single-stage detectors—represented by the YOLO [11–13] series—have become the main-stream choice, thanks to their speed and efficiency.”
A Novel Clustering-Based Anomaly Detection Approach Using a Game Engine for Road Safety
Amirgaliyev, B., Mukhidenov, D., Yedilkhan, D., et al. (2025) · doi:10.1109/amlds63918.2025.11159425 · Cited by 2
“Object detection was performed using an already trained YOLOv8 model, which effectively identifies vehicles in video frames, even considering that the video stream was made on synthetic data [20].”
A multi-scale detection model for tomato leaf diseases with small target detection head
Sun, H., Li, X., Li, X., et al. (2025) · Frontiers in Plant Science · doi:10.3389/fpls.2025.1598534 · Cited by 2
Adapting Vision-Language Models for Hindi OCR
Bhattacharyya, S., Ghosh, S., Deb, P., Mondal, A., & Jawahar, C. V. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-04624-6_34 · Cited by 4
Deep Learning-Based Violence Detection: A YOLO V7 Approach for Real-World Security Applications
Sethi, P. M., Mohapatra, H., Dalai, A. K., Landge, P. B., & Mishra, S. R. (2025) · International Conference on Advancements in Smart, Secure and Intelligent Computing (ASSIC) · doi:10.1109/assic64892.2025.11158209 · Cited by 4
“One of the most prominent deep learning architectures in this field is the ”You Only Look Once” model, which has demonstrated remarkable performance in real-time object detection [1].”
Raj, A., & Thakkar, H. K. (2025) · International Conference on Advancements in Smart, Secure and Intelligent Computing (ASSIC) · doi:10.1109/assic64892.2025.11158337 · Cited by 2
“In 2015, R. Joseph and associates presented the concept of YOLO [7] model.”
A robust detect and describe framework for object recognition in early childhood education
Lv, L., & Yao, S. (2025) · PeerJ Computer Science · doi:10.7717/peerj-cs.3080 · Cited by 3
“To better understand everyday objects, systems for object detection and recognition have been proposed ( Redmon et al., 2016 ).”
Ma, J., Bian, M., Fan, F., Kuang, H., Liu, L., Wang, Z., Li, T., & Running, Z. (2025) · Remote Sensing · doi:10.3390/rs17183203 · Cited by 5
Li, J., Dong, D., Zheng, M., Zhang, J., Hang, Y., Zhang, L., & Zhao, L. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-04927-8_24 · Cited by 6
BFRDNet: A UAV Image Object Detection Method Based on a Backbone Feature Reuse Detection Network
Zhou, L., Yang, J., Xie, Y., Zhang, G., Liu, C., & Liu, Y. (2025) · ISPRS International Journal of Geo-Information · doi:10.3390/ijgi14090365 · Cited by 2
“The one-stage methods, represented by the Single Shot MultiBox Detector (SSD) [13] and You Only Look Once (YOLO) [14] series of algorithms, are widely used in real-time object detection applications.”
Research on Dense Small Target Scrap Steel Type Recognition Algorithm Based on YOLO-SSNP
Yin, J., Xiao, P., Zhu, L., Wang, C., & Jin, Y. (2025) · IEEE Access · doi:10.1109/access.2025.3612731 · Cited by 2
Importance-Weighted Locally Adaptive Prototype Extraction Network for Few-Shot Detection
Wang, H., Tao, Y., Zhou, Z., Wang, Y., Xu, F., & Wang, X. (2025) · Sensors · doi:10.3390/s25195945 · Cited by 3
“Recent breakthroughs in deep neural networks have enabled significant progress across a broad spectrum of vision tasks [1].”
Raja Rao, P. B. V., Ramesh, K. N. V. P. S. B., Murthy, B. S., et al. (2025) · International Conference on Sustainable Computing and Data Communication Systems (ICSCDS) · doi:10.1109/icscds65426.2025.11167194 · Cited by 2
“Object detection algorithms, YOLO, have also been employed for VNPD&R. Redmon et al. [7] introduced the YOLO object detection system, which has been successfully applied to numerous computer vision tasks.”
Underwater Visual Docking Systems for AUVs: a Comprehensive Review
Zhu, W., Sun, K., & Li, Y. (2025) · International Annual Conference on Complex Systems and Intelligent Science (CSIS-IAC) · doi:10.1109/csis-iac65538.2025.11161659 · Cited by 5
“Against this backdrop of technological evolution, the YOLO series of algorithms have gradually become the research focus of underwater object detection and recognition due to their unique single-stage detection architecture and real-time performance advantages[77].”
Chen, X., Gu, H., Wang, C., Mu, H., Zheng, J., Du, J., Ren, J., Fan, Z., & Li, J. (2025) · Publications of the Astronomical Society of the Pacific · doi:10.1088/1538-3873/ae051f · Cited by 3
A hyperparameter-fusion neural networks for deposition prediction
Ding, L., Pang, K., Li, J., Shao, H., Liu, N., Chen, R., Li, Z., Yao, Z., & Li, L. X. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.112434 · Cited by 3
AI for Lesion Detection in Musculoskeletal Radiology
Kim, S. J., Lee, H. S., Hwang, S., & Yoon, Y. (2025) · Journal of the Korean Society of Radiology · doi:10.3348/jksr.2025.0081 · Cited by 2
Li, Y., Li, X., Fu, R., Cheng, Z., Yu, J., Wang, X., & Sun, H. (2025) · BMC Plant Biology · doi:10.1186/s12870-025-07268-1 · Cited by 3
“As an end-to-end single-stage detection framework, YOLO divides the input image into grids and parallelly predicts the target bounding boxes and class confidence scores on each grid cell, completing the detection of the entire image with just one forward pass [8].”
Qin, F., Tang, W., Tian, H., & Chen, Y. (2025) · Sensors · doi:10.3390/s25196023 · Cited by 2
“Single-phase target detection algorithms, such as RetinaNet [7], SSD [8], and the You Only Look Once (YOLO) series algorithms [9–20], are very suitable for deployment in real applications, especially in arithmetic devices such as UAVs.”
Yildirim, G., & Soleimani, F. (2025) · Lecture notes in social networks · doi:10.1007/978-3-031-91643-4_5 · Cited by 2
Bhat, Y. R., Keller, K. L., Brick, T. R., & Pearce, A. L. (2025) · Frontiers in Nutrition · doi:10.3389/fnut.2025.1610363 · Cited by 2
“YOLOv7 (46, 47) is used to develop a lightweight face detector to reduce computational costs.”
Wang, Y., Wang, X., Wu, B., et al. (2025) · Signal Image and Video Processing · doi:10.1007/s11760-025-04809-x · Cited by 2
“YOLOv5 [26] is a deep learning model for end to end problem solving, which has good performance in recognition accuracy and running speed and is widely used in daily operation and maintenance of substation scenes.”
Shuai, Z., Yu, T., Zhang, B., Ren, C., Wang, L., Jiang, X., Li, L., & Shuai, J. (2025) · IEEE Transactions on Evolutionary Computation · doi:10.1109/tevc.2025.3617095 · Cited by 3
“Object detection [6] is a fundamental task in computer vision, and YOLO [7] is an end-to-end solution that employs a single deep neural network (DNN) to directly predict bounding boxes and class probabilities for each object in an image.”
Logistics Planning of Autonomous Air Cargo Vehicles with Deep Learning Methods: A Literature Review
Gör, M. S., & Çelik, C. (2025) · Applied Sciences · doi:10.3390/app151910709 · Cited by 3
A Multi-modal Approach for Face Anti-spoofing in Non-calibrated Systems Using Disparity Maps
Larey, A., Rond, E., & Achrack, O. (2025) · Communications in computer and information science · doi:10.1007/978-3-032-01169-5_3 · Cited by 5
Shan, P., Liang, T., He, D., Pan, G., Zhi, M., & Zhao, Y. (2025) · Measurement · doi:10.1016/j.measurement.2025.119155 · Cited by 4
Feng, X., Peng, L., Tang, Y., et al. (2025) · Sensors · doi:10.3390/s25196211 · Cited by 2
“The YOLO algorithm [28], features an end-to-end single-stage detection framework, delivering outstanding real-time performance and highly efficient object localization capabilities.”
Yamada, K., Yin, L., Hu, Q., Ding, N., Iwashita, S., Ichikawa, J., Kotani, K., Yeung, C., & Fujii, K. (2025) · ACM International Workshop on Multimedia Content Analysis in Sports (MMSports) · doi:10.1145/3728423.3759400 · Cited by 12
Lightweight detection model of foreign objects in airport runway based on the improved NanoDet-Plus
Sun, X., & Zhuang, X. (2025) · doi:10.1109/icimct.2025.00018 · Cited by 2
“In 2015, since the YOLOv1 was proposed by Redmon et al. [5], the YOLO algorithm has attracted widespread attention and has been continuously updated and developed.”
Tian, X., Zheng, Y., Huang, L., Bi, R., Chen, Y., Wang, S., & Su, W. (2025) · Mathematics · doi:10.3390/math13193231 · Cited by 4
Lai, N., Dewi, D. A., & Maidin, S. S. (2025) · SICE Journal of Control Measurement and System Integration · doi:10.1080/18824889.2025.2567085 · Cited by 4
“Following citation counts of 115 and 98, respectively, and link strengths of 988 and 915, were Liu et al. [44] and Redmon et al. [45].”
Fa-yolo: multi-scale feature fusion for spectral image object detection in complex scenes
Wang, Y., Zhao, Y., Zhao, Y., Ablameyko, S., & Zuo, F. (2025) · Multimedia Systems · doi:10.1007/s00530-025-02011-0 · Cited by 3
“Since the launch of YOLOv1 [40] in 2016, which transformed object detection into a regression problem, YOLO has significantly boosted detection efficiency.”
FFTLNet: A Find-first-then-look network for railway signal detection
Wang, Y., Huang, W., Li, Q., & Du, G. (2025) · Digital Signal Processing · doi:10.1016/j.dsp.2025.105653 · Cited by 3
Gesture Control Based Home Automation Using Raspberry Pi
Vijayaraghavan, V., Uppala, N. T., Gumma, P., et al. (2025) · International Conference on Inventive Systems and Control (ICISC) · doi:10.1109/icisc65841.2025.11188184 · Cited by 2
“Scalability can be achieved by designing the system to support multiple devices and rooms using modular hardware IoT protocols like MQTT [13].”
Rady, M., Karim, N. A. E., Maaod, Y., Elaziz, M. A., Abdelfattah, A. M., Elmeligy, Y. M., AboZaid, A. R., & Elsayed, M. (2025) · International Telecommunications Conference (ITC-Egypt) · doi:10.1109/itc-egypt66095.2025.11186680 · Cited by 2
“The introduction of single-stage detectors such as YOLO (You Only Look Once) [2] marked a paradigm shift toward real-time detection capabilities, framing object detection as a regression problem rather than a classification task applied to proposed regions.”
Scale-invariant object detection by adaptive convolution with unified global-local context
Singh, A. D., & Mukherjee, S. (2025) · Evolving Systems · doi:10.1007/s12530-025-09749-y · Cited by 3
ImbDef-GAN: Defect Image-Generation Method Based on Sample Imbalance
Jiang, D., Tao, N., Zhu, K., Wang, Y., & Shao, H. (2025) · Journal of Imaging · doi:10.3390/jimaging11100367 · Cited by 3
Neural Network Detection of Runway and Taxiway Marking Lines
Zotov, A. V., Lebedev, M. A., & Комаров, Д. В. (2025) · Pattern Recognition and Image Analysis · doi:10.1134/s1054661825700312 · Cited by 2
“This is a very large number of anchors, which automatically leads to an excessive number of predictions at the output of the neural network detector and the need to use NMS (nonmaximum suppression) postprocessing [14] to filter out redundant predictions.”
GTpick: A deep neural network for Cryo-EM particle detection
Ni, S., Yang, C., Liu, Y., Zhang, Y., Shi, Y., Qian, A., Kong, R., & Chang, S. (2025) · Computational and Structural Biotechnology Journal · doi:10.1016/j.csbj.2025.10.029 · Cited by 3
“…which uses the AlexNet architecture [10] for iterative training, suffers from instability when data are limited. crYOLO [11] leverages the YOLO [12] target detection framework to achieve high-precision automated detection but lacks generalization when faced with significant variation in…”
Zhang, J., Chen, S., Wang, W., & Wang, Q. (2025) · Sensors · doi:10.3390/s25206445 · Cited by 3
“To accelerate detection process, Redmon, J. et al. [22] introduced the YOLO algorithm, which significantly improved detection speed while maintaining high accuracy.”
Phan, Q.-H., Setyawan, B., Duong, T.-P., & Tsai, F.-T. (2025) · Plants · doi:10.3390/plants14203219 · Cited by 2
“YOLO has undergone numerous enhancements since its introduction [11–13], with each version building on the successes and lessons of its predecessors [14–16].”
FROG: a new people detection dataset for knee-high 2D range finders
Amodeo, F., Pérez-Higueras, N., Merino, L., & Caballero, F. (2025) · Frontiers in Robotics and AI · doi:10.3389/frobt.2025.1671673 · Cited by 4
Pang, Y., Li, Z., Du, C., Wang, Y., & Guo, Z. (2025) · Signal Image and Video Processing · doi:10.1007/s11760-025-04871-5 · Cited by 3
“Under such B Zhixing Li lizhixing@bucea.edu.cn 1 School of Mechanical, Electrical and Vehicle Engineering, Daxing District, Beijing University of Civil Engineering and Architectur, No.15 Yongyuan Road, Huangcun TownBeijing 102600, China conditions, the risk of accidents increases sharply.”
Oriented feature aggregation and sinkhorn distance fusion for few-shot object detection
Han, K., Wei, D., Wang, X., & Li, P. (2025) · Image and Vision Computing · doi:10.1016/j.imavis.2025.105775 · Cited by 4
Yoon, Y., Jeon, Y., Kim, J., Han, S., Kim, H., & Kwon, S. (2025) · Computer Applications in Engineering Education · doi:10.1002/cae.70096 · Cited by 3
Hu, Z., Wen, G., & Liu, X. (2025) · IEEE Sensors Journal · doi:10.1109/jsen.2025.3621690 · Cited by 3
“(e.g., R-CNN, Faster R-CNN, Grid R-CNN [2], [3], [4]) and single-stage detectors (e.g., the you only look once (YOLO) series [9]).”
Machine Learning Techniques for Nematode Microscopic Image Analysis: A Systematic Review
Jimenez, J. L., Gandhi, P., Ayyappan, D., Gorny, A. M., Ye, W., & Lobaton, E. J. (2025) · AgriEngineering · doi:10.3390/agriengineering7110356 · Cited by 2
TSDGFusion: A text and semantic dual-guided model for infrared and visible image fusion
Liu, J., Sun, G., Zheng, B., & Dong, L. (2025) · Displays · doi:10.1016/j.displa.2025.103266 · Cited by 8
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.