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





Verification
Claims the paper makes
6 Valid · 8 Not valid · 15 Not checked · 92 Own results and interpretations
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“While it is much faster than R-CNN, it still falls short of real-time and takes a significant accuracy hit from not having good proposals.”
What the sources say
- Could not verifycites [20] [20] K. Lenc and A. Vedaldi. R-cnn minus r. arXiv preprint arXiv:1506.06981 , 2015. 5, 6 - sourceExperimental — accuracy not yet measured
The ConvNet-based Object Detection section identifies R-CNN minus R as a method that uses predefined regions instead of region proposals. It gives no runtime measurement or assessment of whether the method achieves real-time detection; searches for real-time performance and speed did not establish that claim. (LLM, conf=0.76)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Could not verify
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“To avoid overfitting we use dropout and extensive data augmentation.”
What the sources say
- Partly supportedcites [18] [18] G. E. Hinton, N. Srivastava, A. Krizhevsky, I. Sutskever, and R. R. Salakhutdinov. Improving neural networks by preventing co-adaptation of feature detectors. arXiv preprint arXiv:1207.0580 , 2012. 4 - sourceExperimental — accuracy not yet measured
The paper states that dropout reduces overfitting (p. 1) and describes using dropout with data augmentation for its ImageNet model (H Models for ImageNet, p. 18). It does not establish that YOLO uses either technique or describe YOLO’s augmentation as extensive. (LLM, conf=0.88)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“However, only 30Hz DPM [31] actually runs in real-time.”
What the sources say
- Supportedcites [31] [31] M. A. Sadeghi and D. Forsyth. 30hz object detection with dpm v5. In Computer Vision-ECCV 2014 , pages 65-79. Springer, 2014. 5, 6 - source
The Introduction (p.1) states that 'except for certain objects including face, pedestrians and certain rigid objects, detectors do not currently run at video rate' and that the presented architecture detects the 20 PASCAL VOC categories simultaneously at 30Hz, i.e. at video/real-time rate. The Abstract (p.1) and Table 2 (Method) bound the comparison to other DPM speed-up efforts: reference DPM at 0.07Hz, the fastest GPU 'Vanilla DPM' at ~1Hz, FTVQ at 0.53s, and 'over an order of magnitude faster than the previous fastest DPM implementation', so none of the listed variants reaches real-time. Thus our copy supports both parts of the attribution: that this 30Hz DPM runs in real-time and that it is the only such DPM among the speed-up efforts compared. (LLM, conf=0.82)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“While it is much faster than R-CNN, it still falls short of real-time and takes a significant accuracy hit from not having good proposals.”
What the sources say
- Could not verifycites [20] [20] K. Lenc and A. Vedaldi. R-cnn minus r. arXiv preprint arXiv:1506.06981 , 2015. 5, 6 - sourceExperimental — accuracy not yet measured
The ConvNet-based Object Detection section identifies R-CNN minus R and says it uses predefined regions in an SPPnet system, but gives no speed comparison with R-CNN. A search for R-CNN minus R and speed found no passage in our copy establishing that it is much faster. (LLM, conf=0.73)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Could not verify
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“While it is much faster than R-CNN, it still falls short of real-time and takes a significant accuracy hit from not having good proposals.”
What the sources say
- Partly supportedcites [20] [20] K. Lenc and A. Vedaldi. R-cnn minus r. arXiv preprint arXiv:1506.06981 , 2015. 5, 6 - sourceExperimental — accuracy not yet measured
The “ConvNet-based Object Detection” section (page unavailable) says R-CNN minus R uses predefined regions instead of region proposals. It does not say that this causes a significant accuracy loss; the paper’s discussion of low accuracy concerns a different system, naïve Faster R-CNN. (LLM, conf=0.83)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
84 more claims
Create a free account to see all 121 claims and to verify the 2 references still open.
- Probably not a substantial claim. 17
- It may state two separate claims as one. 15
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“which was not thoroughly investigated in prevIoUs work such as YOLOv1 [20] and YOLOv2 [51] employing MSE/L2 loss (Mean Squared Error).”
From Object Detection in 20 Years: A Survey (2023) · cites this paper as [20]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“the YOLO series models v2-v5 [144-147] are some of the most advanced object detection methods based on DNN, which have good performance in terms of speed and precision.”
From A survey of model compression strategies for object detection (2023) · cites this paper as [144]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“As a typical and more widely used new form of applications [9], various deep learning-based intelligent services and applications have changed many aspects of people's lives due to the great advantages of Deep Learning (DL) in the fields of Computer Vision (CV) and Natural Language Processing (NLP) [10].”
From Convergence of Edge Computing and Deep Learning: A Comprehensive Survey (2020) · cites this paper as [9]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“A convolutional neural network predicts the bounding boxes as well as class probabilities for all the objects depicted in an image.”
From Object detection using YOLO: challenges, architectural successors, datasets and applications (2023) · cites this paper as [56]
The cited source says what the claim attributes to it.
In the citing paper
“Authors of YOLO [56] have reframed the problem of object detection as a regression problem instead of classification problem.”
From Object detection using YOLO: challenges, architectural successors, datasets and applications (2023) · cites this paper as [56]
6 more claims about this paper
Create a free account to see every claim other papers make about this one.
Citations
Cites
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2577031 · Cited by 73,472
Self-citationFaster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2015) · arXiv · doi:10.48550/arxiv.1506.01497 · Cited by 70,812
Self-citationGoing deeper with convolutions
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298594 · Cited by 48,562
ImageNet Large Scale Visual Recognition Challenge
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-015-0816-y · Cited by 39,380 · cited 1×
“We pretrain our convolutional layers on the ImageNet 1000-class competition dataset [29].”
MethodHistograms of Oriented Gradients for Human Detection
Dalal, N., & Triggs, B. (2005) · 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) · doi:10.1109/cvpr.2005.177 · Cited by 33,584 · cited 2×
“Detection pipelines generally start by extracting a set of robust features from input images (Haar [25], SIFT [23], HOG [4], convolutional features [6]).”
MethodRich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
Girshick, R., Donahue, J., Darrell, T., & Malik, J. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.81 · Cited by 32,684 · cited 2×
“Then, classifiers [35, 21, 13, 10] or localizers [1, 31] are used to identify objects in the feature space.”
MethodSelf-citationGirshick, R. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.169 · Cited by 28,105
Self-citationDelving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
He, K., Zhang, X., Ren, S., & Sun, J. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.123 · Cited by 19,741 · cited 1×
“Convolutional neural networks (CNNs) achieve impressive performance on classification tasks at real-time speeds [13].”
Object recognition from local scale-invariant features
Lowe, D. G. (1999) · Proceedings of the Seventh IEEE International Conference on Computer Vision · doi:10.1109/iccv.1999.790410 · Cited by 16,472 · cited 1×
“Detection pipelines generally start by extracting a set of robust features from input images (Haar [25], SIFT [23], HOG [4], convolutional features [6]).”
MethodRobust Real-Time Face Detection
Viola, P., & Jones, M. J. (2004) · International Journal of Computer Vision · doi:10.1023/b:visi.0000013087.49260.fb · Cited by 14,097 · cited 1×
“Detectors for single classes like faces or people can be highly optimized since they have to deal with much less variation [36].”
Background
Cited by
Items 26,701–26,800 of 51,401
Wu, J., Tao, X., & Gao, P. (2025) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2025.3649074 · Cited by 4
Luan, P., Guo, N., Li, L., Li, B., Zhao, Z., Ma, L., & Liu, B. (2025) · Agriculture · doi:10.3390/agriculture16010071 · Cited by 4
Efficient Weed Detection in Cabbage Fields Using a Dual-Model Strategy
Li, M., Zhu, W., Zhang, X., et al. (2025) · Agronomy · doi:10.3390/agronomy16010093 · Cited by 3
Surveillance to self-driving: a comprehensive review of object detection and tracking paradigms
Das, P., Jain, C., & Gola, K. K. (2026) · Iran Journal of Computer Science · doi:10.1007/s42044-025-00387-w · Cited by 7
Juan, C.-E., Muzakky, H., Chang, C.-C., Chou, P.-L., Li, Y.-H., Lee, T.-Y., Juan, C.-H., Tsai, M.-T., Chen, C.-W., & Juan, C.-J. (2026) · Scientific Reports · doi:10.1038/s41598-025-34596-x · Cited by 4
“S5a) 20,39–41 , which is a powerful CNN-based model enabling quick and accurate identification of abnormalities in medical images, and Real-Time Detection Transformer (RT-DETR) (Fig.”
Fu, Y., Wang, Y., Zhuo, C., & Li, Y. (2026) · Journal of Ambient Intelligence and Humanized Computing · doi:10.1007/s12652-025-05034-7 · Cited by 5
Language of images: Classifying marketing images with transformers and vision language models
Witte, M., Heitmann, M., Hartmann, J., & Tetzlaff, K. (2026) · International Journal of Research in Marketing · doi:10.1016/j.ijresmar.2026.01.001 · Cited by 3
TOTNet: Occlusion-aware temporal tracking for robust ball detection in sports videos
Xu, H., Baniya, A. A., Wells, S., Bouadjenek, M. R., Dazeley, R., & Aryal, S. (2026) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2026.104657 · Cited by 9
Li, J., Le, W., Jia, Z., Zhou, G., Wang, J., Chen, G., Wang, Y., & Guo, Y. (2026) · Applied Sciences · doi:10.3390/app16020793 · Cited by 3
A Novel Vision-Based Approach to Test Sequence Generation for Mobile GUI Testing
Cui, C., Huang, Y., Huang, R., Zhou, L., Wang, R., & Li, T. (2026) · IEEE Transactions on Reliability · doi:10.1109/tr.2025.3648728 · Cited by 8
Casas, G. G., Ismail, Z. H., & Leite, H. G. (2026) · Forests · doi:10.3390/f17010112 · Cited by 4
AI-Based Augmented Reality Microscope for Real-Time Sperm Detection and Tracking in Micro-TESE
Mohamed, M. M., Yuriko, E., Kawagoe, Y., Kawamura, K., & Ikeuchi, M. (2026) · Bioengineering · doi:10.3390/bioengineering13010102 · Cited by 8
“For real-time applications, end-to-end object detection models such as YOLO (You Only Look Once) [20] and SSD (Single Shot MultiBox Detector) [21] were subsequently introduced.”
Multi-Class Malocclusion Detection on Standardized Intraoral Photographs Using YOLOv11
Nebiaj, A., Mühling, M., Freisleben, B., & Sayahpour, B. (2026) · Dentistry Journal · doi:10.3390/dj14010060 · Cited by 8
“Deep learning-based object detection models, particularly current one-stage architectures of the YOLO family, enable image-level localization and multi-class prediction in a single pass [12,13].”
Gu, L., Fang, Q., Попов, Е. Н., Pavlov, V. A., Volvenko, S. V., Makarov, S., & Dong, G. (2026) · Astronautics · doi:10.3390/astronautics1010005 · Cited by 3
“Two-stage detectors first generate region proposals and subsequently perform classification and bounding-box regression [8–10], whereas one-stage detectors conduct dense predictions directly without relying on intermediate proposals [11,12].”
Neighbor-Guided Attention for Robust Face Detection in Crowded Scenes
Phull, A., Nijhawan, R., & Maggu, J. (2025) · International Conference on Computational Intelligence and Computing Applications (ICCICA) · doi:10.1109/iccica67008.2025.11337823 · Cited by 3
“These approaches usually ignore contextual clues that could be used to figure out where occluded or less-visible faces are by looking at neighbouring, clearly visible faces [4] [5] [6].”
Lightweight frameworks for real-time crack monitoring in civil infrastructure
Pandey, V., & Mishra, S. S. (2026) · Ultrasonics · doi:10.1016/j.ultras.2026.107970 · Cited by 3
UAV ‐based remote sensing of bee nesting aggregations with computer vision for object detection
Mueller, T. G., & Buckner, M. A. (2026) · Journal of Applied Ecology · doi:10.1111/1365-2664.70285 · Cited by 4
Dong, F., Gui, B., Wang, W., Fan, W., & Liu, Q. (2026) · Scientific Reports · doi:10.1038/s41598-025-34711-y · Cited by 5
Implementing YOLO and OCR in Product Automation for Object Detection and Text Extraction
Praveen, S. P., Sravya, K. R., Jahnavi, K., et al. (2025) · doi:10.1109/icnsoc66817.2025.00099 · Cited by 3
“Although many OCR systems are currently in use, most of those systems are narrow-scoped; they extract text in images but do not have an object detection capability, which limits their scope in offering a whole solution for product management [8].”
Fu, Y., Türkcan, M. K., Ghasemi, M., Mo, Z., Zang, C., Adhikari, A., Kostić, Z., Zussman, G., & Di, X. S. (2026) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2026.3656165 · Cited by 26
Zhu, J., Ma, L., Ma, X., Xiong, Z., Wu, M., & Xia, Y. (2026) · Journal of Civil Structural Health Monitoring · doi:10.1007/s13349-025-01043-4 · Cited by 3
“Progress has also been made in bridge traffic identi - fication using deep learning (DL)-based object detection models, such as CNN [22], feature pyramid networks (FPN) [23], parallel feature pyramid networks (PFPNet) [24], Fast R-CNN [25], Faster R-CNN [26], and You Only Look Once (YOLO) [27].”
Bang, S., Keum, J., Ji, Y., Kang, Y. J., So, B., Hong, J. K., & Kim, H. (2026) · Artificial Intelligence in Geosciences · doi:10.1016/j.aiig.2026.100191 · Cited by 6
Detection-Guided Deep Unfolding for Joint Underwater Image Enhancement and Object Detection
Yu, H. H., Vo, C. H., & Lee, C. (2026) · IEEE Access · doi:10.1109/access.2026.3659134 · Cited by 3
de Carvalho, H. P., Barros, Q. S., Ferreira, E. J. L., et al. (2026) · Agronomy · doi:10.3390/agronomy16030341 · Cited by 3
Lane detection for autonomous driving: A comprehensive review
Kou, H., Wang, Z., Lv, Z., Wang, C., Guo, Z., & Zhang, Y. (2026) · Neurocomputing · doi:10.1016/j.neucom.2026.132864 · Cited by 8
DSC-DETR: Real-time detection of transmission line defects using dynamic shuffle context
Xin, Y., Huang, J., Xu, M., Chen, J., & Shi, P. (2026) · Advanced Engineering Informatics · doi:10.1016/j.aei.2026.104403 · Cited by 4
Rani, S., Rout, A., Soni, P., Gupta, M., Kumar, N., & Kumar, K. (2026) · Diagnostics · doi:10.3390/diagnostics16030461 · Cited by 7
“In the vast field of image classification, many popular pre-trained models exist, such as VGGNet [36], ResNet [37], YOLO [38], DenseNet [39], MobileNet [40], and EfficientNet [41], etc.”
RT-GalaDet as a real-time model for screening surface-associated health abnormalities in fish
Peng, X., Xiao, Z., & Yu, Y. (2026) · Scientific Reports · doi:10.1038/s41598-026-37288-2 · Cited by 4
“The detection head was kept fixed during both training and evaluation, and the random seed was set to 42, thereby ensuring the determinism and comparability of the experimental process.”
Chinchu, M., Vennila, H., & Bibin, G. S. (2026) · IEEE Access · doi:10.1109/access.2026.3660918 · Cited by 5
The, V. N., De, T. H., & Dinh, H. T. (2025) · Conference on Research, Innovation and Vision for the Future in Computing & Communication Technologies · doi:10.1109/rivf68649.2025.11365250 · Cited by 1
“In parallel, the YOLO (You Only Look Once) family of models, based on CNNs, has evolved through multiple versions—from YOLOv1 [16] to YOLOv10 [9] and YOLOv11 [11] with continuous improvements in speed and accuracy.”
Voets, J., Tercan, H., Meisen, T., & Esen, C. (2026) · Applied Sciences · doi:10.3390/app16031568 · Cited by 6
DeCon-Net: decoupled hierarchical contrast for soccer object detection
Ouyang, Q., Du, T., & Li, J. (2026) · Scientific Reports · doi:10.1038/s41598-026-39084-4 · Cited by 3
Detection of dense fish schools in sonar imagery with a novel YOLOv11-SAS model
Zhang, H., Yang, X., Zhang, R., Gao, N., Wang, N., Zhang, Z., & Zhang, C. (2026) · Ecological Informatics · doi:10.1016/j.ecoinf.2026.103646 · Cited by 5
LMDENet: A Lightweight RGB-IR Object Detection Network for Low-Light Remote Sensing Images
Weng, T., & Niu, X. (2026) · Sensors · doi:10.3390/s26041130 · Cited by 9
A Lightweight Drone Vision System for Autonomous Inspection with Real-Time Processing
Zhou, Z., Wang, W., Wu, H., Wang, T., & Suzuki, S. (2026) · Drones · doi:10.3390/drones10020126 · Cited by 4
“Object detection has evolved over the past decade from multi-stage methods that rely on region proposals such as R-CNN [6], Fast R-CNN [7], Faster R-CNN [8], and Mask R-CNN [9] models to single-stage approaches like YOLO [10] and SSD [11] that directly predict object locations and classes.”
High-clockrate free-space optical in-memory computing
Liang, Y., Wang, J., Xue, K., Ren, X., Yin, R., Ou, S., Zhou, L., Li, Y., Heuser, T., Heermeier, N., et al. (2026) · Light Science & Applications · doi:10.1038/s41377-026-02206-8 · Cited by 9
“…arrays for input activation; (2) spatial fanout coping with diffractive element for parallel processing; (3) large-scale programmable weighting for in-system training; (4) low latency image classification under the You-Only-Look-Once (YOLO) [46] algorithm to provide accurate feature extraction.”
Implementation of an ıntelligent vision approach for automated structural defect detection
Matich, H., & Mousannif, H. (2026) · Discover Artificial Intelligence · doi:10.1007/s44163-026-00961-6 · Cited by 4
Sanogo, M., Gao, F., Littlefield, N. G., Siddiqui, I. A., Carlson, L., Rezaei, A., Bodanki, P., Menezes, Z., Kanda, A., Abedian, M., et al. (2026) · npj Health Systems · doi:10.1038/s44401-026-00072-5 · Cited by 4
FFDNet: An end-to-end lightweight real-time fire detection model for forest fire environments
Yu, Q., Zhang, G., Wang, Y., Wu, X., Xu, H., Kuang, W., He, S., Xiao, J., & Hu, W. (2026) · Physics and Chemistry of the Earth Parts A/B/C · doi:10.1016/j.pce.2026.104325 · Cited by 5
RiceDetect-Net: a lightweight real-time detection framework for rice diseases
Yuan, X., Xu, Q., Wang, T., Gao, L., Zhao, G., Jia, L., & Wang, Y. (2026) · BMC Plant Biology · doi:10.1186/s12870-026-08341-z · Cited by 6
“To meet the real-time demands of agricultural field diagnosis and monitoring, this study adopts the YOLO framework [30], a single-stage detector that enables end-to-end target localization and identification, offering superior speed ideal for mobile or edge device deployment.”
Balancing Accuracy and Speed: Improved D-FINE for Real-Time Ocean Internal Wave Detection
Yu, L., Tian, Y., Chen, J., Chi, C., Li, T., & Li, J. (2026) · Journal of Marine Science and Engineering · doi:10.3390/jmse14040388 · Cited by 4
TEN: A transformer-based efficient network for pneumonia diagnosis with chest x-rays
Bao, Y., Wang, W., Zhao, L., Wu, H., Zheng, Z., Lv, L., & Bardou, D. (2026) · Pattern Analysis and Applications · doi:10.1007/s10044-026-01637-8 · Cited by 4
Render2Seg: Landmark-Guided Patch-Wise Segmentation for Robust 3D Dental Mesh Analysis
Lee, S. J., Kim, G., Jin, Y., et al. (2025) · IEEE/CVF International Conference on Computer Vision Workshops (ICCVW) · doi:10.1109/iccvw69036.2025.00115 · Cited by 3
“2D object detection models such as YOLO [22] and Faster R-CNN [9] have demonstrated strong performance in localizing anatomical structures across various medical imaging tasks.”
Litter detection from aerial imagery: a review of UAV-based approaches and deep learning techniques
Bartolo, M., Hili, G., Seychell, D., Montebello, M., Debono, C. J., Formosa, S., & Makantasis, K. (2026) · Multimedia Tools and Applications · doi:10.1007/s11042-026-21440-1 · Cited by 6
Ton, Q. T., Lưu, K. G., Vu, T. H., Le, T., & Vũ, T. N. (2026) · Data Technologies and Applications · doi:10.1108/dta-08-2025-0745 · Cited by 2
Improving ORB-SLAM3 Accuracy in Dynamic Scenes with YOLO11 Segmentation
Villegas, R. R., Cukla, A. R., Tarnowski, G. A., Mudry, G. A., Lapczuk, S. O., de Paiva, E. C., & Gamarra, D. F. T. (2026) · Sensors · doi:10.3390/s26051487 · Cited by 3
“First proposed in 2015 [4], the algorithm has been continuously improved since then.”
Enhancing Fine-Grained Sketch-Based Image Retrieval Through Contextual Information
Xu, J., Xie, Q., Li, J., et al. (2026) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2026.3668640 · Cited by 3
An improved lightweight YOLOv11 algorithm for weld surface defect detection
Zhang, R., Pan, C., Chen, Z., Fan, J., Chen, Z., & Yuan, B. (2026) · Scientific Reports · doi:10.1038/s41598-026-41568-2 · Cited by 9
“Further, the existing target detection via neural networks is divided into the one-stage network 5,6 and the two-stage network 7,8 .”
GDEIM-SF: A Lightweight UAV Detection Framework Coupling Dehazing and Low-Light Enhancement
Zheng, J., & Li, L. (2026) · Sensors · doi:10.3390/s26051557 · Cited by 3
Liu, Y., Yan, G., Chen, T., & Huo, G. (2026) · IET Image Processing · doi:10.1049/ipr2.70313 · Cited by 4
MCPDNet: multi-scale feature fusion network for maize leaf disease and pest detection
Zhiming, & Li, Y. (2026) · Journal of Real-Time Image Processing · doi:10.1007/s11554-026-01865-5 · Cited by 4
“Two-stage frameworks such as Faster R-CNN [4] deliver superior detection accuracy at the cost of computational speed, whereas one-stage architectures like the YOLO series [5] prioritize real-time inference while maintaining competitive accuracy.”
Dai, X., Guo, D., Tu, J., Quan, Q., & Chen, Y. (2026) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2026.105417 · Cited by 3
Multispectral AI-driven imaging for detection of downy mildew and gray mold in grapevines
Kapetas, D., Christakakis, P., Naounoulis, I., et al. (2026) · Smart Agricultural Technology · doi:10.1016/j.atech.2026.101990 · Cited by 3
A novel autonomous guidance method for welding robot based on point cloud registration and 3D vision
Xiao, R., Xu, Y., Lu, L., et al. (2026) · The International Journal of Advanced Manufacturing Technology · doi:10.1007/s00170-026-17415-z · Cited by 3
“YOLO [22] (You Only Look Once) is an end-to-end one-stage object detection algorithm.”
Wang, J., Chen, Z., Ueda, T., & Dai, J. (2026) · Journal of Computing in Civil Engineering · doi:10.1061/jccee5.cpeng-7482 · Cited by 3
Liu, Z., Dong, L., Li, C., et al. (2026) · Infrared Physics & Technology · doi:10.1016/j.infrared.2026.106527 · Cited by 3
A review of AI and machine learning applications in manufacturing processes
Gorine, M. E. A., Nechak, L., Ichchou, M. N., & Pichenot, Y. (2026) · Journal of Intelligent Manufacturing · doi:10.1007/s10845-026-02826-2 · Cited by 6
YOLOv11-Based Enhanced Framework for Robust Blasthole Detection in Intelligent Tunnel Environments
Jin, Q., Yue, Z., Zhou, X., Xue, K., liu, H., & Chen, J. (2026) · Journal of Computing in Civil Engineering · doi:10.1061/jccee5.cpeng-7337 · Cited by 3
Dong, L., Chen, Y., Ke, W., Wu, H., Deng, L., & Liao, G. (2026) · Information · doi:10.3390/info17040317 · Cited by 5
Artificial intelligence and occupational health and safety: a systematic review
Torre, G. L., Manai, M. V., Meucci, S., Lucente, A., Picerno, A., Ammirati, S., & Sio, S. D. (2026) · Journal of Public Health · doi:10.1007/s10389-026-02738-8 · Cited by 10
Deep learning approaches in computer vision: a comprehensive survey
Reshadi, S., TaghipourEivazi, S., Ghaffari, A., & Seyyedabbasi, A. (2026) · Cluster Computing · doi:10.1007/s10586-026-06045-5 · Cited by 4
“Despite the difficulties in identifying small or closely clustered objects caused by its rough grid layout, improved versions, such as YOLOv2 and YOLOv3, with anchor boxes and multi-scale predictions, enhance performance [83, 84 ].”
Liu, Z., Dong, L., Li, C., & Xu, H. (2026) · Advanced Engineering Informatics · doi:10.1016/j.aei.2026.104641 · Cited by 6
Yang, C. H., Zhou, Z., Hu, Z., Lu, Z., Shen, Y., Zhang, W., & Liang, X. (2026) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2026.114637 · Cited by 3
Hua, W., Wang, R., Ding, C., et al. (2026) · IEEE Transactions on Aerospace and Electronic Systems · doi:10.1109/taes.2026.3683665 · Cited by 3
Zhang, T., Ren, L., Sun, X., Gao, L., & Zhang, B. (2026) · IEEE Transactions on Image Processing · doi:10.1109/tip.2026.3678372 · Cited by 6
Dual-instance automatic segmentation and damage quantification of concrete spalling in RC bridges
Huamani, K., Espinola-Diaz, L., Bedriñana, L. A., et al. (2026) · Structures · doi:10.1016/j.istruc.2026.111817 · Cited by 3
Padmanabha, P., Herath, H. M. S. S., Madusanka, N., Park, H. W., Na, C.-S., Yi, M., & Lee, B.-I. (2026) · Applied Sciences · doi:10.3390/app16083968 · Cited by 4
Agricultural Intelligence: A Technical Review Within the Perception–Decision–Execution Framework
Yu, S., Li, X., Zhao, S., Sun, Q., & Liu, Q. (2026) · Applied System Innovation · doi:10.3390/asi9050095 · Cited by 3
“For real-time pest monitoring and field deployment, Ahmad et al. [12] compared the performance of single-stage detection models, such as You Only Look Once (YOLO) [44], for 23 agricultural pests.”
Li, R. B., Shaghaghi, M., Suzuki, K., Liu, X., Moparthi, V., Du, B., Curtis, W., Renschler, M., Lee, K. M. B., Atanasov, N., et al. (2026) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61042.2026.00240 · Cited by 20
SmokeBench: Evaluating Multimodal Large Language Models for Wildfire Smoke Detection
Qi, T., Li, W., & Barnes, N. (2026) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61042.2026.00108 · Cited by 11
“Further, we examine the effects of smoke volume and contrast on detection performance, finding that larger volumes substantially improve predictions, whereas contrast has a comparatively limited impact.”
Forest Fire Detection Based on Improved YOLO11
Gao, J., Zhao, Y., & Chen, B. (2026) · Sensors · doi:10.3390/s26103094 · Cited by 3
“The second category is one-stage object detection, exemplified by YOLO [10] and SSD [11].”
Mothbox and Mothbot: Automated light trap and data processing system for scalable insect monitoring
Szczygieł, H. A., Johns, B., Fortet, B., Dent, D. H., Quitmeyer, K., & Quitmeyer, A. (2026) · Methods in Ecology and Evolution · doi:10.1111/2041-210x.70327 · Cited by 4
Yoon, S. S., Lee, S. H., Lee, M. J., et al. (2026) · ACS Nano · doi:10.1021/acsnano.6c02822 · Cited by 3
Canh, T. N., Zhang, H., HoangVan, X., & Chong, N. Y. (2026) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2026.105535 · Cited by 8
PlantGFM: A Genomic Foundation Model for Discovery and Creation of Plant Genes
Li, C., Zhang, Q., Chen, H., Lin, K., Luo, C., Yang, M., Xu, W., Yao, F., Yan, J., Yang, Q., et al. (2026) · Advanced Science · doi:10.1002/advs.75772 · Cited by 12
“Finally, considering the imbalance between gene regions and intergenic regions in plants, we designed a loss function by combining Binary Cross-Entropy (BCE) [ 38 ] and Intersection over Union (IoU) [ 39 ].”
Li, R., Yu, C., Bao, S., Li, Z., & Yao, J. (2026) · Mathematics · doi:10.3390/math14111927 · Cited by 4
SINA: A Circuit Schematic Image–to–Netlist Generator Using Artificial Intelligence
Aldowaish, S., Karumanchi, Y., Chiang, K.-C., et al. (2026) · doi:10.23919/date69613.2026.11539285 · Cited by 3
“SINA uses a YOLOv11-based object detection model [11] to identify circuit components, returning bounding boxes, component types, and unique component identifiers, as shown in Fig.”
A Survey on Fine-Grained Multimodal Large Language Models
Peng, Y., Wang, Z., Li, G., Zheng, X., Yin, S., & He, H. (2026) · Chinese Journal of Electronics · doi:10.23919/cje.2025.00.336 · Cited by 34
Xu, T., Yang, H., Hou, H., et al. (2026) · Microsystems & Nanoengineering · doi:10.1038/s41378-026-01360-8 · Cited by 3
“In recent years, vision-only neural networks have been employed for autonomous mineral identi fi cation by leveraging appearance cues such as color, texture, and morphology 37 (Fig.”
A Review on Artificial Intelligence Methods for Plant Disease and Pest Detection
Giakoumoglou, N., Kapetas, D., Papadopoulos, K. M., Christakakis, P., Stathaki, T., & Pechlivani, E. M. (2026) · AI and Precision Agriculture · doi:10.3390/aipa1010002 · Cited by 6
“The YOLO and SSD architectures prioritize real-time performance by processing the entire image at once [96,97].”
Towards Accurate Instance-Level Text Spotting with Guided Attention
Wang, H., Rong, X., & Tian, Y. (2019) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme.2019.00175 · Cited by 4
Nonlinear spectral preprocessing for small-brain machine learning
Vuong, L. T., & Lane, H. (2019) · SPIE Applications of Machine Learning · doi:10.1117/12.2530789 · Cited by 2
Hangar Detection from Satellite Images with Mask-RCNN and YOLOv2 Algorithms
Oral, E. A. (2019) · Brilliant Engineering · doi:10.36937/ben.2020.002.002 · Cited by 3
GPU acceleration design method for driver’s seatbelt detection
Yong-quan, J., Wu, T., Li, J., et al. (2019) · IEEE International Conference on Electronic Measurement & Instruments · doi:10.1109/icemi46757.2019.9101821 · Cited by 3
Racing Bib Number Recognition Method using Deep Learning
Rayhan, M. A., & Lhaksmana, K. M. (2020) · JURNAL MEDIA INFORMATIKA BUDIDARMA · doi:10.30865/mib.v4i3.2270 · Cited by 3
3D-Modeling Dataset Augmentation for Underwater AUV Real-time Manipulations
Wang, C., Huang, C., Lin, C.-H., et al. (2020) · IEEE Asia Pacific Conference on Circuits and Systems (APCCAS) · doi:10.1109/apccas50809.2020.9301679 · Cited by 3
Video Object Detection Using Motion Context and Feature Aggregation
Kim, J., Koh, J., & Choi, J. W. (2020) · International Conference on Information and Communication Technology Convergence (ICTC) · doi:10.1109/ictc49870.2020.9289386 · Cited by 4
Pedestrian Behavior Analytics on Dashcam Videos in Chaotic Environments
Mukherjee, P., & Lall, B. (2021) · IEEE Sensors Journal · doi:10.1109/jsen.2021.3062762 · Cited by 3
Research on intelligent risk early warning of open-pit blasting site based on deep learning
Liu, X., Yang, H., Jing, H., Sun, X., & Yu, J. (2021) · Energy Sources Part A Recovery Utilization and Environmental Effects · doi:10.1080/15567036.2021.1907487 · Cited by 7
Numerical Analysis for Feature Extraction and Evaluation of 3D Sickness
Nakane, K., Ono, R., & Takada, H. (2021) · Advances in Science Technology and Engineering Systems Journal · doi:10.25046/aj0602108 · Cited by 3
The Effect of High Performance Computer on Deep Neural Network
Zhang, X., Zhang, T., Jiang, L., et al. (2021) · Engineered Science · doi:10.30919/es8d461 · Cited by 3
A Deep Learning Technique for Image Inpainting with GANs
Suraj, K., Swamy, S. H., Shetty, S. S., et al. (2021) · Studies in computational intelligence · doi:10.1007/978-3-030-68291-0_4 · Cited by 3
Instance Segmentation Based on Improved YOLACT
Li, L., Fang, M., & Fu, F. (2020) · International Conference on Virtual Reality and Visualization · doi:10.1109/icvrv51359.2020.00042 · Cited by 4
Robust recognition of logo under makeover in the context of content piracy
Patalappa, K. K. J., & Chandramouli, S. M. (2021) · Global Transitions Proceedings · doi:10.1016/j.gltp.2021.08.050 · Cited by 4
High Precision Food Detection Method based on Deep Object Detection Network
Wang, J., Ding, X., & Guo, B. (2021) · IEEE Information Technology, Networking, Electronic and Automation Control Conference (ITNEC) · doi:10.1109/itnec52019.2021.9587189 · Cited by 3
Abdelrauof, D., Essam, M., & Elattar, M. (2021) · Cardiovascular Engineering and Technology · doi:10.1007/s13239-021-00591-2 · Cited by 5
Multi-scale Object Detection Algorithm in Smart City Based on Mixed Dilated Convolution Pyramid
Yin, K., Liang, J., Hou, S., Zhu, R., Yin, G., Wang, C., & Yang, X. (2021) · IEEE SmartWorld, Ubiquitous Intelligence & Computing, Advanced & Trusted Computing, Scalable Computing & Communications, Cloud & Big Data Computing, Internet of People and Smart City Innovation (SmartWorld/SCALCOM/UIC/ATC/CBDCom/IOP/SCI) · doi:10.1109/swc50871.2021.00088 · Cited by 3
Tian, J., Zhang, J., Li, W., Li, J., & Li, Z. (2021) · International Journal of Remote Sensing · doi:10.1080/01431161.2021.2012294 · Cited by 3
Polar Loss for Event-Based Object Detection
Xu, H., Shi, D., Jing, L., et al. (2021) · Proceedings - International Conference on Tools with Artificial Intelligence, TAI · doi:10.1109/ictai52525.2021.00143 · Cited by 3
Channel splitting attention network for low‐light image enhancement
Lu, B., Pang, Z., Gu, Y., & Zheng, Y. (2022) · IET Image Processing · doi:10.1049/ipr2.12418 · Cited by 3
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.