You Only Look Once: Unified, Real-Time Object Detection
Open accessThe DOI matches its Crossref record; 53 of the 53 references it cites were found in a registry or an index; 8 of the 25 sources its claims cite were checked for support.
Abstract
We present YOLO, a new approach to object detection. Prior work on object detection repurposes classifiers to perform detection. Instead, we frame object detection as a regression problem to spatially separated bounding boxes and associated class probabilities. A single neural network predicts bounding boxes and class probabilities directly from full images in one evaluation. Since the whole detection pipeline is a single network, it can be optimized end-to-end directly on detection performance. Our unified architecture is extremely fast. Our base YOLO model processes images in real-time at 45 frames per second. A smaller version of the network, Fast YOLO, processes an astounding 155 frames per second while still achieving double the mAP of other real-time detectors. Compared to state-of-the-art detection systems, YOLO makes more localization errors but is less likely to predict false positives on background. Finally, YOLO learns very general representations of objects. It outperforms other detection methods, including DPM and R-CNN, when generalizing from natural images to other domains like artwork.
Overview
CoChat Summary
TL;DR
YOLO reframes object detection as a single regression problem, using one convolutional network to predict bounding boxes and class probabilities directly from full images. It achieves real-time detection speeds while remaining competitive with, and complementary to, slower region-based detectors.
Key findings
- YOLO runs at 45 FPS on a Titan X GPU, and Fast YOLO runs at 155 FPS; Fast YOLO reaches 52.7% mAP on PASCAL VOC 2007, more than double prior real-time detectors, while YOLO reaches 63.4% mAP.
- On PASCAL VOC 2012, YOLO scores 57.9% mAP; combining Fast R-CNN with YOLO raises Fast R-CNN from 71.8% to 75.0% mAP on VOC 2007, a 3.2% gain.
- YOLO makes fewer background false positives than Fast R-CNN: Fast R-CNN has 13.6% background false positives among top detections and is almost 3× more likely to predict background detections than YOLO.
- YOLO generalizes better to artwork: on Picasso, YOLO gets 53.3 AP versus R-CNN’s 10.4 AP and DPM’s 37.8 AP; on People-Art, YOLO gets 45 AP versus R-CNN’s 26 AP and DPM’s 32 AP.
Methods
- Detection is modeled as a single CNN regression: the image is divided into an S×S grid; for PASCAL VOC, S=7, B=2, C=20, producing a 7×7×30 tensor of bounding boxes, confidence scores, and class probabilities.
- The base network has 24 convolutional layers followed by 2 fully connected layers; Fast YOLO uses 9 convolutional layers. Convolutional layers are pretrained on ImageNet at 224×224, then detection training uses 448×448 input.
- Training uses PASCAL VOC 2007 and 2012 for about 135 epochs, batch size 64, momentum 0.9, decay 0.0005, sum-squared error with λ_coord=5 and λ_noobj=0.5, dropout, and data augmentation.
Limitations
- The paper states YOLO imposes strong spatial constraints because each grid cell predicts only two boxes and one class, limiting nearby objects and struggling with small objects in groups such as flocks of birds.
- The paper states YOLO struggles to generalize to objects in new or unusual aspect ratios or configurations, uses relatively coarse features due to downsampling, and its loss treats small and large box errors equally; its main error source is incorrect localization.
- The paper states YOLO still lags state-of-the-art detection accuracy and struggles to precisely localize some objects, especially small ones.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Figures





Verification
Claims the paper makes
6 Valid · 8 Not valid · 15 Not checked · 92 Own results and interpretations
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“While it is much faster than R-CNN, it still falls short of real-time and takes a significant accuracy hit from not having good proposals.”
What the sources say
- Could not verifycites [20] [20] K. Lenc and A. Vedaldi. R-cnn minus r. arXiv preprint arXiv:1506.06981 , 2015. 5, 6 - sourceExperimental — accuracy not yet measured
The ConvNet-based Object Detection section identifies R-CNN minus R as a method that uses predefined regions instead of region proposals. It gives no runtime measurement or assessment of whether the method achieves real-time detection; searches for real-time performance and speed did not establish that claim. (LLM, conf=0.76)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Could not verify
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“To avoid overfitting we use dropout and extensive data augmentation.”
What the sources say
- Partly supportedcites [18] [18] G. E. Hinton, N. Srivastava, A. Krizhevsky, I. Sutskever, and R. R. Salakhutdinov. Improving neural networks by preventing co-adaptation of feature detectors. arXiv preprint arXiv:1207.0580 , 2012. 4 - sourceExperimental — accuracy not yet measured
The paper states that dropout reduces overfitting (p. 1) and describes using dropout with data augmentation for its ImageNet model (H Models for ImageNet, p. 18). It does not establish that YOLO uses either technique or describe YOLO’s augmentation as extensive. (LLM, conf=0.88)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“However, only 30Hz DPM [31] actually runs in real-time.”
What the sources say
- Supportedcites [31] [31] M. A. Sadeghi and D. Forsyth. 30hz object detection with dpm v5. In Computer Vision-ECCV 2014 , pages 65-79. Springer, 2014. 5, 6 - source
The Introduction (p.1) states that 'except for certain objects including face, pedestrians and certain rigid objects, detectors do not currently run at video rate' and that the presented architecture detects the 20 PASCAL VOC categories simultaneously at 30Hz, i.e. at video/real-time rate. The Abstract (p.1) and Table 2 (Method) bound the comparison to other DPM speed-up efforts: reference DPM at 0.07Hz, the fastest GPU 'Vanilla DPM' at ~1Hz, FTVQ at 0.53s, and 'over an order of magnitude faster than the previous fastest DPM implementation', so none of the listed variants reaches real-time. Thus our copy supports both parts of the attribution: that this 30Hz DPM runs in real-time and that it is the only such DPM among the speed-up efforts compared. (LLM, conf=0.82)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“While it is much faster than R-CNN, it still falls short of real-time and takes a significant accuracy hit from not having good proposals.”
What the sources say
- Could not verifycites [20] [20] K. Lenc and A. Vedaldi. R-cnn minus r. arXiv preprint arXiv:1506.06981 , 2015. 5, 6 - sourceExperimental — accuracy not yet measured
The ConvNet-based Object Detection section identifies R-CNN minus R and says it uses predefined regions in an SPPnet system, but gives no speed comparison with R-CNN. A search for R-CNN minus R and speed found no passage in our copy establishing that it is much faster. (LLM, conf=0.73)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Could not verify
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“While it is much faster than R-CNN, it still falls short of real-time and takes a significant accuracy hit from not having good proposals.”
What the sources say
- Partly supportedcites [20] [20] K. Lenc and A. Vedaldi. R-cnn minus r. arXiv preprint arXiv:1506.06981 , 2015. 5, 6 - sourceExperimental — accuracy not yet measured
The “ConvNet-based Object Detection” section (page unavailable) says R-CNN minus R uses predefined regions instead of region proposals. It does not say that this causes a significant accuracy loss; the paper’s discussion of low accuracy concerns a different system, naïve Faster R-CNN. (LLM, conf=0.83)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
84 more claims
Create a free account to see all 121 claims and to verify the 2 references still open.
- Probably not a substantial claim. 17
- It may state two separate claims as one. 15
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“which was not thoroughly investigated in prevIoUs work such as YOLOv1 [20] and YOLOv2 [51] employing MSE/L2 loss (Mean Squared Error).”
From Object Detection in 20 Years: A Survey (2023) · cites this paper as [20]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“the YOLO series models v2-v5 [144-147] are some of the most advanced object detection methods based on DNN, which have good performance in terms of speed and precision.”
From A survey of model compression strategies for object detection (2023) · cites this paper as [144]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“As a typical and more widely used new form of applications [9], various deep learning-based intelligent services and applications have changed many aspects of people's lives due to the great advantages of Deep Learning (DL) in the fields of Computer Vision (CV) and Natural Language Processing (NLP) [10].”
From Convergence of Edge Computing and Deep Learning: A Comprehensive Survey (2020) · cites this paper as [9]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“A convolutional neural network predicts the bounding boxes as well as class probabilities for all the objects depicted in an image.”
From Object detection using YOLO: challenges, architectural successors, datasets and applications (2023) · cites this paper as [56]
The cited source says what the claim attributes to it.
In the citing paper
“Authors of YOLO [56] have reframed the problem of object detection as a regression problem instead of classification problem.”
From Object detection using YOLO: challenges, architectural successors, datasets and applications (2023) · cites this paper as [56]
6 more claims about this paper
Create a free account to see every claim other papers make about this one.
Citations
Cites
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2577031 · Cited by 73,472
Self-citationFaster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2015) · arXiv · doi:10.48550/arxiv.1506.01497 · Cited by 70,812
Self-citationGoing deeper with convolutions
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298594 · Cited by 48,562
ImageNet Large Scale Visual Recognition Challenge
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-015-0816-y · Cited by 39,380 · cited 1×
“We pretrain our convolutional layers on the ImageNet 1000-class competition dataset [29].”
MethodHistograms of Oriented Gradients for Human Detection
Dalal, N., & Triggs, B. (2005) · 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) · doi:10.1109/cvpr.2005.177 · Cited by 33,584 · cited 2×
“Detection pipelines generally start by extracting a set of robust features from input images (Haar [25], SIFT [23], HOG [4], convolutional features [6]).”
MethodRich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
Girshick, R., Donahue, J., Darrell, T., & Malik, J. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.81 · Cited by 32,684 · cited 2×
“Then, classifiers [35, 21, 13, 10] or localizers [1, 31] are used to identify objects in the feature space.”
MethodSelf-citationGirshick, R. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.169 · Cited by 28,105
Self-citationDelving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
He, K., Zhang, X., Ren, S., & Sun, J. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.123 · Cited by 19,741 · cited 1×
“Convolutional neural networks (CNNs) achieve impressive performance on classification tasks at real-time speeds [13].”
Object recognition from local scale-invariant features
Lowe, D. G. (1999) · Proceedings of the Seventh IEEE International Conference on Computer Vision · doi:10.1109/iccv.1999.790410 · Cited by 16,472 · cited 1×
“Detection pipelines generally start by extracting a set of robust features from input images (Haar [25], SIFT [23], HOG [4], convolutional features [6]).”
MethodRobust Real-Time Face Detection
Viola, P., & Jones, M. J. (2004) · International Journal of Computer Vision · doi:10.1023/b:visi.0000013087.49260.fb · Cited by 14,097 · cited 1×
“Detectors for single classes like faces or people can be highly optimized since they have to deal with much less variation [36].”
Background
Cited by
Items 45,001–45,100 of 51,399
Underwater Multi-objective Detection by Using Swin Transformer Based YOLO Network
Luo, W., Lin, C., & Zhou, H. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-7175-5_23
YOLORIG: A One-Step DNA Origami Molecular Detection Optimization
Sun, H. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-9891-2_1
YOLO-CM: Class-Aware Instance Segmentation Using Combine-Mask
Wu, R., Wen, X.-B., Liao, S., Li, J., Liu, L., & Kui, X. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-9891-2_35
Brain tumor classification using convolutional neural network
Minarno, A. E., Mustaqim, M. C., Munarko, Y., & Basuki, S. (2025) · AIP conference proceedings · doi:10.1063/5.0259412
Optimization of Object Detection Capabilities in a FPGA SoC Using the Yolo-Tiny Model
Tang, M.-P. L., Nguyen, X.-D., Dang, T.-T., et al. (2025) · International Conference on Electronics, Computers and Artificial Intelligence (ECAI) · doi:10.1109/ecai65401.2025.11095474
“To alleviate this burden, the YOLO [5] method was developed, which allows simultaneous prediction of boundary boxes and class classification in a single calculation, thus significantly reducing resource requirements.”
Local Classification Guiding Attention for Malania Oleifera Recognition
Sun, Y., Cao, Y., Kou, W., et al. (2025) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2025.3595537
Effect of Mowing, Imaging Technique, and Annotation Method on Weed Detection in Turfgrass Using YoloPreprint
Gurjar, B., Torres, U., Coleman, G., Straw, C. M., & Bagavathiannan, M. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5378473
Li, X., Jia, Y., Yu, J., & He, F. (2025) · Tsinghua Science & Technology · doi:10.26599/tst.2024.9010249
Pear Green Fruit Thinning Strategy in Complex Environments Based on Improved Yolov8Preprint
Chen, Z., Lei, X., Lv, X., et al. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5379543
Gu, S., Sun, M., Zhang, Z., et al. (2025) · Symmetry · doi:10.3390/sym17081237
Implementation Of YOLO Through DevOps for Automated Vehicle Number Plate Recognition
Haidari, M. M. A., Nasim, M. F., Zubair, S., et al. (2025) · Annual Methodological Archive Research Review · doi:10.63075/fz07qr96
AI for Root Cause Analysis & Visual Inspection
Kavitha, D., Karthiga, M., & Srinita, J. S. (2025) · International Conference on Control, Communication and Computing (ICCC) · doi:10.1109/iccc64910.2025.11077313
“The Object Detection Stage uses YOLOv8[7] to identify objects, while the Sticker Detection Stage and Bolt Detection Stage specifically detect stickers and bolts, respectively.”
Optimal YOLO-Based Model for Fabric Anomaly Detection
Silabumrungrad, N., Somridjinda, S., Chen, C.-C., Charoensuk, J., & Chootong, C. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-6291-3_6
ViziAssist: Visual Assistance for Visually Impaired Drivers
Arya, K., Arya, M. S., Deshmukh, V., & Dabade, K. (2025) · Communications in computer and information science · doi:10.1007/978-3-031-93688-3_6
iSpace Coding: A System for User-Defined Flexible Spatial Functions in Intelligent Spaces
Yoshida, S., Gupta, K. K., Fujii, Y., Tran, D. T., & Lee, J. (2025) · International Conference on Ubiquitous Robots (UR) · doi:10.1109/ur65550.2025.11078030
“Using YOLOv11, an object detection model from the You Only Look Once (YOLO) series[13], this study performs real-time person detection and skeleton estimation.”
Niu, W., Mei, J., Zhang, D., Li, Y., Jia, F., & Zheng, D. (2025) · IEEE International Instrumentation and Measurement Technology Conference · doi:10.1109/i2mtc62753.2025.11079129 · Cited by 1
“However, mainstream models like YOLO [4] and Faster R-CNN [5] have complex architectures with numerous parameters, which limit their real-time usage in industrial environments.”
Dsh_Yolo: Tomato Seedling Internode Length Detection Network Based on Multi-Scale FusionPreprint
Jin, X., Zhang, L., Li, M., et al. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5357492
Enhancing Fisheye Object Detection Using Frequency-Domain Attention and Dual Aggregation Transformer
Alade, O., Khan, N. F., & Aboah, A. (2025) · IEEE Access · doi:10.1109/access.2025.3596026
An End-to-End Intelligent Review System for Architectural Engineering Drawings
Li, Y., Cui, G., Wang, J., et al. (2025) · Chinese Control and Decision Conference (CCDC) · doi:10.1109/ccdc65474.2025.11090521
Object-level Visual Semantic SLAM Based on Geometric Constraints and Outlier Removal
Wang, L., Feng, W., & Li, H. (2025) · Chinese Control and Decision Conference (CCDC) · doi:10.1109/ccdc65474.2025.11090992
“YOLO (You Only Look Once) [22] is a real-time object detection algorithm that rapidly detects and classifies objects in images.”
Robot Visual Localization via Improved YOLOv8 Based Segmentation of Depth Map
Di, B., Yuan, S., & Xu, H. (2025) · Chinese Control and Decision Conference (CCDC) · doi:10.1109/ccdc65474.2025.11090547
An Intelligent Situation Interpretation System Based on Multimodal Information Fusion
Wu, X., Hou, Y., Sun, L., et al. (2025) · Chinese Control and Decision Conference (CCDC) · doi:10.1109/ccdc65474.2025.11090938
“The YOLO series is a family of well-known real-time object detection algorithms designed to achieve fast and accurate object localization and classification [8].”
Improved YOLOv8n Algorithm for Rapid Detection of Auto Parts
Xie, Z., Chai, L., & Li, B. (2025) · Chinese Control and Decision Conference (CCDC) · doi:10.1109/ccdc65474.2025.11091129
Complex Traffic Scence Object Detection Algorithm Based on IYOLO-RepS
(2025) · Chinese Control and Decision Conference (CCDC) · doi:10.1109/ccdc65474.2025.11090551
Adaptive Valve Selection Algorithm for PET Bottle Sorting Equipment Based on Segment Anything Model
Li, C., Liu, L., Zhao, Y., et al. (2025) · Chinese Control and Decision Conference (CCDC) · doi:10.1109/ccdc65474.2025.11091266
Reagent Container Detection Based on PC-YOLO Algorithm
Yuan, Z., Li, M., & Zhang, L. (2025) · Chinese Control and Decision Conference (CCDC) · doi:10.1109/ccdc65474.2025.11090437
“Single-stage detection algorithms, such as the YOLO series [3] This work is supported by Key R&D Program Project of Shandong Province, NO.2024TSGC0012 and Central Guidance Local Science and Technology Development Fund Project NO.”
PYOLO : A Plus YOLO Model for Occlusion Pedestrian Detection
Hu, Z., Xu, Y., Ma, H., Zhao, G., & Jin, Y. (2025) · Chinese Control and Decision Conference (CCDC) · doi:10.1109/ccdc65474.2025.11090698
Axle Type Recognition System for Moving Vehicle Based on Object Detection
Li, Y., & Liu, X.-Y. (2025) · Chinese Control and Decision Conference · doi:10.1109/ccdc65474.2025.11090644
“Current object detection algorithms are categorized into single-stage and two-stage algorithms [11,12] .”
Monocular Gate Perception Based on ICP-like Optimization for Autonomous Drone Racing
Cao, X., Fang, H., & Hua, J. (2025) · Chinese Control and Decision Conference (CCDC) · doi:10.1109/ccdc65474.2025.11090738
“A series of solutions such as YOLO[10] have also made real-time target detection possible.”
A Novel and Robust AIS-Camera Fusion Method for Situational Awareness in Autonomous Ships
Xiao, J., Lu, J., Li, J.-C., et al. (2025) · Chinese Control and Decision Conference (CCDC) · doi:10.1109/ccdc65474.2025.11090511
“Powerful object detection models, such as Region-based Convolutional Neural Networks (R-CNN) [7] and You Only Look Once (YOLO) [8], enable the efficient extraction of geometric and positional information of vessels from images.”
Yolov8-Based Defect Detection in Pv Modules Using Adaptive Feature Fusion for El Images
Yang, Z., Song, R., Ding, S., & Chen, C. (2025) · Chinese Control and Decision Conference (CCDC) · doi:10.1109/ccdc65474.2025.11090351
“Since 2015, researchers proposed single-stage object detection algorithms, such as the You Only Look Once (YOLO) series to address the limitation of speed [10]-[15].”
Research on Charging Socket Detection Algorithm Based on YOLOv8n Improved Algorithm
Zhao, Y., & Tingting, W. (2025) · Chinese Control and Decision Conference (CCDC) · doi:10.1109/ccdc65474.2025.11090674
“On the other hand, first-level methods such as SSD [5] and YOLO [6] directly perform end-to-end object detection, represented by SSD and YOLO.”
A Multi-Object Tracking Framework Based on Skeleton and Identity Context Guidance
Hu, N., Zhang, J., & Zhu, H. (2025) · Chinese Control and Decision Conference (CCDC) · doi:10.1109/ccdc65474.2025.11090553
“…of deep learning and target detection technologies has led to significant advances in detection-based tracking methods for multi-target tracking tasks [2] [3], such as the YOLO [4] [5] [6] [7] series, and multi-camera fusion and other technologies to improve the performance of the tracking system.”
AI Assisted Diagnosis in Pathological Diagnosis
Wu, J., Wang, P., & Song, C. (2025) · Chinese Control and Decision Conference (CCDC) · doi:10.1109/ccdc65474.2025.11091091
IFY-Net: Detecting Surface Defects in Real-Time on Intricate Steel Samples
Zhang, S., He, X., Li, Y., Wang, M., & Liu, Z. (2025) · Chinese Control and Decision Conference (CCDC) · doi:10.1109/ccdc65474.2025.11090562
“One-stage algorithms have made notable progress in addressing this challenge, with You Only Look Once (YOLO) series networks[6] serving as a prominent example.”
Wei, Y. J., Cai, J., Xu, S., et al. (2025) · Chinese Control and Decision Conference (CCDC) · doi:10.1109/ccdc65474.2025.11090887
“Two-stage object detection algorithms include R-CNN [2] and Fast R-CNN [3], while one-stage algorithms include the YOLO [4] series and SSD [5].”
C2CNet: Connect to Casual Feature Pyramid Net for Target Detection
Li, H., & Wang, H. (2025) · International Conference on Machine Intelligence Theory and Applications (MiTA) · doi:10.1109/mita66017.2025.11100266
“In recent years, with the development of Convolution Neural Network (CNN), some networks such as R-CNN [1], Faster R-CNN [2], and YOLO [3] have become the most commonly used target detection networks nowadays.”
An Improved YOLOv8 Algorithm for Printed Circuit Board Defect Detection
Ma, G., & Zhang, J. (2025) · Chinese Control and Decision Conference (CCDC) · doi:10.1109/ccdc65474.2025.11091089
“In this paper, the YOLOv8s [10] algorithm is used to detect PCB small target defects.”
MIND-Stack: Modular, Interpretable, End-to-End Differentiability for Autonomous Navigation
Jahncke, F., & Betz, J. (2025) · IEEE Intelligent Vehicles Symposium · doi:10.1109/iv64158.2025.11097814
“The black-box nature of full neural network-based algorithms is a continuous area of research under the term Explainable Artificial Intelligence (AI) [24], [25].”
Q-Loc: Visual Cue-Based Ground Vehicle Localization Using Long Short-Term Memory
Malinchock, C., Yu, J., Thapa, P., Ungrupulithaya, D., & Yoon, M.-K. (2025) · IEEE Intelligent Vehicles Symposium · doi:10.1109/iv64158.2025.11097732
“YOLO [41] treats object detection as a regression problem, as opposed to region proposal like in F ASTER R-CNN.”
InfluentialWatanabe, K., Masuda, S., Xiao, L., & Yamasaki, T. (2025) · International Conference on Automatic Face and Gesture Recognition · doi:10.1109/fg61629.2025.11099276
“Specifically, the framework integrates You Only Look Once (YOLO) [20] for accurate person detection and tracking, and GPT-4o [1] for robust action understanding and generation.”
Research on Road Defect Detection Technology Based on Improved YOLOv11n
Yi, W., Chen, C., Deng, J., et al. (2025) · doi:10.1109/eicct65471.2025.11099808
“The most recent advancements in deep learning have brought about creative solutions, particularly in the form of convolutional neural network-based object identification models like YOLO[4] and Faster R-CNN[5].”
Fool the Stoplight: Realistic Adversarial Patch Attacks on Traffic Light Detectors
Pavlitska, S., Robb, J., Polley, N., Yazgan, M., & Zöllner, J. M. (2025) · IEEE Intelligent Vehicles Symposium · doi:10.1109/iv64158.2025.11097717 · Cited by 1
“In our recent work [20] three categories of CNN-based approaches were analyzed: (1) modifications of generic detectors like YOLO [21] or SSD [22] for the traffic light detection [23]–[30], (2) multi-stage approaches encompassing rule-and CNN-based components [31]–[33], and (3) task-specific…”
Machine Learning and Computer Vision for Collection of Statistical Data from Vegetable Fields
Kotev, V. K., Ivanov, I. S., Ranchev, S., et al. (2025) · Studies in computational intelligence · doi:10.1007/978-3-031-96311-7_14
Dual Focus: Transforming Negatives into Knowledge
Măduța, A.-P., Ileni, T. A., & Darabant, A. S. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-00891-6_21
Sato, I. (2025) · Springer eBooks · doi:10.1007/978-981-96-6635-5_4
Tamura, M., Matsui, Y., & Muragaki, Y. (2025) · Springer eBooks · doi:10.1007/978-981-96-6635-5_8
MCMM: Garbage detection and sorting via a multi-column convolution based MatMul-free modeling
Yang, Z. (2025) · Journal of Computational Methods in Sciences and Engineering · doi:10.1177/14727978251366534
Zhao, L., Wang, Y., & Xu, F. (2025) · Scientific Reports · doi:10.1038/s41598-025-14927-8
Secure Reversible Image Obscuration for Content Protection
Noyé, V., Puteaux, P., & Puech, W. (2026) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2026.3680804
Le, T. C., Le, V. N., Ha, L. T., et al. (2025) · Digital Applications in Archaeology and Cultural Heritage · doi:10.1016/j.daach.2025.e00448
Adversarial Patch Robustness against Occlusion: A case study
Bunzel, N., & Gelbing, E. (2025) · doi:10.1145/3709021.3737664 · Cited by 2
“Deep neural networks have revolutionized image recognition [15, 33, 34], but their deployment in sensitive applications such as facial recognition and autonomous driving raises significant security concerns due to their susceptibility to adversarial attacks [4, 6, 11, 18, 30, 31].”
InfluentialA dual-path feature learning neural network for enhancing image classification in marine biology
Asam, Y., & Zhou, Z. (2025) · Multimedia Tools and Applications · doi:10.1007/s11042-025-21010-x
“Models like R-CNN [ 25 ] and Faster R-CNN [ 26 ] extract features and emphasize classification in two stages, while one-stage models like You Only Look Once (YOLO) [ 27 ] and Single Shot Detector (SSD) [ 28] prioritize real-time detection speed.”
A Lightweight Neural Network Search Method Suitable for Heterogeneous Computing Environments
Shih, C.-T., & Wu, C. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-6294-4_19
An End-to-End System Based on Deep Learning for Oral Disease Detection
Trong, D. T., Hiep, N. M., Thanh, T. T., et al. (2025) · Communications in computer and information science · doi:10.1007/978-3-031-98164-7_9
A Fusion-Based Deep Learning Approach for Enhanced Polyp Detection in Medical Imaging
Hieu, T. N. S., Do, N.-T., & Nguyen, Q.-H. (2025) · Communications in computer and information science · doi:10.1007/978-3-031-98164-7_1
Fuquan, 秦. Q., & Yan, 魏. W. (2025) · Laser & Optoelectronics Progress · doi:10.3788/lop250731
Enhancing Fishery Pond Security with Machine Learning Techniques
Jayanthi, K. B., Kumar, V. B., Guhan, R., et al. (2025) · doi:10.1109/ginotech63460.2025.11077015
Row Line Detection of Pineapple Planting Based on the RLYOLOv11 Model
Li, J., Chen, H., Li, J., et al. (2025) · International Conference on Electrical Engineering, Control and Robotics (EECR) · doi:10.1109/eecr64516.2025.11077306
“The initial model, YOLOv1, was proposed by [8], and it has evolved to YOLOv11 to date.”
Hu, S. J., Xing, R., Han, L., & Liu, T. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5356537
Lo, S., & Lo, M.-R. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5356322
Real-Time Vision-Based Monitoring of Mining Vehicles for Intelligent Industrial SystemsPreprint
He, L., & Zhou, Y. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5355956
PushPull-YOLO: A biologically inspired framework for robust object detection under image corruptions
Akyürek, H. A. (2025) · Ömer Halisdemir Üniversitesi Mühendislik Bilimleri Dergisi · doi:10.28948/ngumuh.1662465
Lu, G., Li, C., Xu, N., Yao, Y., Sun, H., Huang, X., Grzegorzek, M., & Zeng, Q. (2025) · Lecture notes in electrical engineering · doi:10.1007/978-981-96-2771-4_45
Automatic Detection of Obstacles in Underground Railway Tracks for Collision Prevention
Zhao, K., Zhang, X., & Chen, L. (2025) · International Journal of Pattern Recognition and Artificial Intelligence · doi:10.1142/s0218001425500247
OPTIMIZED YOLOv9-PES ARCHITECTURE FOR ENHANCED MICROSCOPIC DETECTION OF MYCOBACTERIUM TUBERCULOSIS
Li, Z.-R., XIA, P.-C., CAO, J.-W., et al. (2025) · Journal of Mechanics in Medicine and Biology · doi:10.1142/s0219519425400640
Stark, T., Pardo, J., Wurm, M., et al. (2025) · Joint Urban Remote Sensing Event (JURSE) · doi:10.1109/jurse60372.2025.11076000
“As the latest iteration in the YOLO series, YOLOv8 is renowned for its real-time object detection capabilities [13], [14].”
CR‐YOLOv8‐Based Detection Method for Identifying Non‐Functional Satellite Components
Bian, H., Zhang, D., Li, C., Zhang, Z., Liu, W., Cao, J., Mei, C., & Zhang, G. (2025) · IET Image Processing · doi:10.1049/ipr2.70153
Confucius: A Knowledge Graph-Enhanced LLM Agent for Intelligent Teaching Video Supervision
Cao, Y., Chen, R., Xiong, X. B., Shao, X., Ren, D., Gao, Y., Zhang, Z., & Liu, S. (2025) · International Conference on Computer Science and Technologies in Education (CSTE) · doi:10.1109/cste64638.2025.11092023
“This study evaluates the performance of the proposed system in educational supervision tasks through comparative experiments with baseline models[12].”
Chang, P., Wei, Y., Xu, Q., & Xiao, G. (2025) · International Conference on Computer Science and Technologies in Education (CSTE) · doi:10.1109/cste64638.2025.11092251
“The You Only Look Once [5] (YOLO) series is renowned for its efficient, real-time object detection on public datasets like MS-COCO [6].”
Comparative study of pavement anomaly detection using detection models with rotated bounding boxes
Ji, S., Niu, F., & Qin, Y. (2025) · PLoS ONE · doi:10.1371/journal.pone.0329844
A Novel Drowning Detection System and Its Performance Analysis
Iampanit, T., Somprakij, P., Siriwanna, N., Iampanit, N., & Jirakittayakorn, N. (2025) · International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology (ECTI-CON) · doi:10.1109/ecti-con64996.2025.11100770 · Cited by 1
“The object detection step of the proposed system was performed using the YOLO framework [7], renowned for real-time performance and high accuracy in detecting several objects within an image.”
RETRACTED ARTICLE: Advanced Fuzzy Inference Integration with MobileNetV2 for Ovarian Cyst Detection
Bilgaiyan, S., Swain, A., Das, S., et al. (2025) · SN Computer Science · doi:10.1007/s42979-025-04200-0
“The motivation for this work stems from the need to reduce diagnostic errors, support clinical decision-making and enhance patient outcomes by providing a more efficient and precise method of detecting ovarian cysts.”
RetractedEMSPENet: an efficient multi-scale perceptual enhancement network for aluminum detection
Li, Y., Jiang, Z., Wang, T., et al. (2025) · Journal of Real-Time Image Processing · doi:10.1007/s11554-025-01746-3
“The prevailing surface defect detection algorithms encompass the one-stage target detection algorithm, exemplified by the you only look once (YOLO) [9–15], and the two-stage target detection algorithm, exemplified by the region convolutional neural network (R-CNN) [16–18].”
A Lightweight and High-Precision Target Detection Algorithm for Unmanned Surface Vehicles
Li, Y. (2025) · International Conference on Computer Engineering and Application (ICCEA) · doi:10.1109/iccea65460.2025.11102459
“The YOLO (You Only Look Once) algorithm was initially introduced by Redmon et al. in 2016 [2], marking a significant advancement in real-time object detection.”
MFS-YOLO: An Object Detection Network for Drones
Lv, H., Hu, H., Yan, C., Wang, Y., & Jiang, B. (2025) · International Conference on Computer Engineering and Application (ICCEA) · doi:10.1109/iccea65460.2025.11102163
“YOLO series [2], as a single-stage object detection algorithm, has characteristics of fast, precise and efficient, so it has been popularly used.”
Real-Time Rat Pose Estimation System via Miniature Stereo Vision for Robot-Rat Interaction
Shi, Q., Jia, G., Guo, X., Chen, Z., & Dong, C. (2025) · IEEE/ASME Transactions on Mechatronics · doi:10.1109/tmech.2025.3593778
“For detection, we use YOLOv8 [30] due to its excellent performance in moving-object detection.”
Applying Monolithic to Microservices Strategy for Elastic Container Deployment for AI Applications
A, A. H. P., Anusha, O., Jose, B. A., et al. (2025) · IEEE World AI IoT Congress (AIIoT) · doi:10.1109/aiiot65859.2025.11105358
Cross-Modal Distillation for 2D/3D Multi-Object Discovery from 2D motion
Lahlali, S., Kara, S., Ammar, H., Chabot, F., Granger, N., Borgne, H. L., & Pham, Q.-C. (2025) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52734.2025.02284 · Cited by 1
Once-Tuning-Multiple-Variants: Tuning Once and Expanded as Multiple Vision-Language Model Variants
Yu, C., Chen, T., & Gan, Z. (2025) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52734.2025.01371
“…networks have been proven successful in many mono-modal tasks, both in the vision domain (such as image classification [18, 33], object detection [42, 60], and segmentation [27, 45]) and in the language domain (such as summarization [17], machine translation [24], question answering [34],…”
Cross-YOLO: Enhancing YOLOv10-N via Efficient Multi-scale Cross 1D Convolutions
Du, W. (2025) · Lecture notes in networks and systems · doi:10.1007/978-3-031-92608-2_9
Smart Stick Assistant for Visually Impaired People
Raut, J. S., Ingale, V. S., & Salunkhe, J. A. (2025) · Lecture notes in networks and systems · doi:10.1007/978-981-96-4170-3_18
Evaluating Real-Time Object Detection Models for Autonomous Vehicle Vision
Bahri, S., & Mouftah, H. T. (2025) · IEEE World AI IoT Congress (AIIoT) · doi:10.1109/aiiot65859.2025.11105268
“This architecture facilitates speedier processing, making YOLO extremely appropriate for time-sensitive applications, such as autonomous vehicles [3, 10].”
A Hybrid RNN-CNN Approach to Automate Traffic Pattern Analysis in Roundabouts
Zeudom, F. A., Grsossman, J., & Khorbotly, S. (2025) · IEEE International Conference on Electro Information Technology · doi:10.1109/eit64391.2025.11103599
Comparative Study of Lightweight YOLO Architectures for UAV-Based Detection of Aerial Targets
Andronic, V.-B., & Dobrea, D.-M. (2025) · International Symposium on Signals, Circuits and Systems · doi:10.1109/isscs66034.2025.11105669
“The original YOLO model was developed by Joseph Redmon and his colleagues [5], who later received significant improvements through community contributions.”
Enhanced YOLOv11n with Ghost Convolution for Automatic Detection of Pistachio Leaf Disease
Dikici, B., Açıkgöz, H., & Özbay, S. (2025) · International Symposium on Innovative Approaches in Smart Technologies (ISAS) · doi:10.1109/isas66241.2025.11101806
“From 2013 until today, many object detection versions were introduced, such as Region-Based Convolutional Neural Network (R-CNN) [4], Single Shot Detector (SSD) [5], and You Only Look Once (YOLO) [6].”
A Novel Approach to Integrated Semantic Segmentation and Feature Detection
Ramya, B. S., Pradeep, V., Aniruddha, H. D., et al. (2025) · doi:10.1109/etcc65847.2025.11108585
“The YOLO made detection of objects in real time possible by switching to a faster single-stage approach instead of using a step-by-step process [1], [5].”
InfluentialKaur, N., & Rani, R. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5389831
Vision-Based Slam Algorithm Using Yolov8 in Indoor EnvironmentsPreprint
Xu, J., Ma, M., Li, Y., et al. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5389825
Optimizing Object Detection Model Training Using ChatGPT for Dataset Reduction
Stokanović, A., Milošević, M., & Lukač, Ž. (2025) · Zooming Innovation in Consumer Technologies Conference (ZINC) · doi:10.1109/zinc65316.2025.11103554
“Models like the YOLO (You Only Look Once) family have become industry standards due to their ability to detect and classify objects in real-time with high accuracy [1].”
Weather Resilient Object Detection: Focus On Foggy Weather Conditions
Annaboina, V., Srinivas, Sriram, I. S., & Meghana, T. (2025) · International Conference on Emerging Technologies in Engineering Applications (ICETEA) · doi:10.1109/icetea64585.2025.11099818
“Because of its real-time capabilities, it has become a core concept that influences contemporary frameworks for high-speed object identification [5].”
YOLO-Based Depth Estimation from Monocular Camera Images for Object Detection at Sea
Fabijanić, M., & Ferreira, F. (2025) · MTS/IEEE OCEANS Conference (OCEANS) · doi:10.1109/oceans58557.2025.11104564
“Among the most popular, the You Only Look Once (YOLO) algo-rithm [15] has been used in the context of boat detection using cameras [16]–[23].”
Smart social junction traffic control using reinforcement learning on real data
Barzilai, O., Rika, H., & Hassine, Y. (2025) · Journal of Computational Social Science · doi:10.1007/s42001-025-00418-3
“In YOLO, the image is divided into a predetermined grid structure, where each grid cell is tasked with predicting objects whose central points are situated within that grid [ 52].”
Urban Traffic Congestion Reduction Through Dynamic Scheduling
Rahman, H., Abid, A. S., Rasmiya, et al. (2025) · doi:10.1109/icetea64585.2025.11099916
“…processes and refines these features to help detect objects at different scales; and the head, which generates the final predictions by classifying objects and predicting their bounding boxes, all in one forward pass making the model both fast and accurate for real-time object detection [25].”
A Light Weight YOLOv5 Model for Strawberry Disease Detection and Classification
Bhaskar, K., Ancha, V. K., Maharajan, R., et al. (2025) · doi:10.1109/eaic66483.2025.11101433
“Outbreaks of strawberry powdery mildew produce a high volume of spores that can easily be transmitted to neighboring leaves through air currents within a short 4-7-day timeframe [6].”
Choi, J., Choi, Y., & Han, S. (2025) · doi:10.1109/oceans58557.2025.11104679
“Recent studies have shown that deep learning techniques, such as YOLO [7], can significantly improve detection accuracy by us-ing large datasets and complex feature extraction capabilities.”
Yolo Based Real-Time Object Detection for Vehicles
Anish, I., & Yuvaraj, K. (2025) · doi:10.1109/icetea64585.2025.11100069
“Self-driving vehicles represent the future transportation technology because these vehicles enhance road safety operations, operate efficiently, and minimize human errors in highway driving [1].”
Acoustic Simulated Sonar Data and Neural Networks for Marine Mine Detection
Peltier, C. L., Lopez, S. B., Gall, Y. L., Haugeard, J., Hassan, D., Malkasse, J., Burlet, N., & Mari, Z. (2025) · MTS/IEEE OCEANS Conference (OCEANS) · doi:10.1109/oceans58557.2025.11104554 · Cited by 1
“The family of YOLO (You Only Look Once) algorithms comprises about ten versions of deep learning models designed for object detection in images and videos [18].”
Song, Z., Zhang, X., & Ni, Z. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5387550
A Method of Visual Positioning of Tank Truck Openings via Two-Stage Fine-Tuning
An, M.-S., Zhao, X., Xu, F., Lim, H.-Y., & Kang, D.-S. (2025) · Communications in computer and information science · doi:10.1007/978-3-031-94962-3_14
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.