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 28,401–28,500 of 51,400
Mun, J. Y., Cho, W.-H., & Rehman, K. (2024) · Journal of the Korean Society of Marine Environment and Safety · doi:10.7837/kosomes.2024.30.6.527 · Cited by 3
Fan, Y., Wen, B., & Deng, H. (2025) · The Visual Computer · doi:10.1007/s00371-024-03762-z · Cited by 3
Infrared Ship Detection Based on Improved YOLO-11
Hu, Y. (2024) · International Conference on Computational Intelligence and Communication Networks (CICN) · doi:10.1109/cicn63059.2024.10847489 · Cited by 3
Wang, T., Xia, H., Xie, J., Li, J., & Liu, J. (2025) · Agriculture · doi:10.3390/agriculture15030262 · Cited by 4
Semantic feature refinement of YOLO for human mask detection in dense crowded
Zhang, D., Gao, Q., Chen, Z., & Lin, Z. (2025) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2025.104399 · Cited by 3
A Content-Aware Method for Detecting External-Force-Damage Objects on Transmission Lines
Liu, M., Chen, M., Wu, B., Wu, M., Wang, J., Wang, J., Hu, H., & Ye, Y. (2025) · Electronics · doi:10.3390/electronics14040715 · Cited by 3
Samson, M., Muraccioli, B., & Kanehiro, F. (2025) · IEEE/SICE International Symposium on System Integration (SII) · doi:10.1109/sii59315.2025.10870971 · Cited by 5
Chen, H., Huang, W. X., & Zhang, T. (2025) · International Journal of Multimedia Information Retrieval · doi:10.1007/s13735-025-00355-x · Cited by 7
Traffic Sign Detection Based on Improved YOLOv5-S
Wang, Z., Luo, W., Li, X., et al. (2024) · China Automation Congress (CAC) · doi:10.1109/cac63892.2024.10865409 · Cited by 3
Mishchuk, V., & Podorozhniak, A. (2024) · IEEE KhPI Week on Advanced Technology (KhPIWeek) · doi:10.1109/khpiweek61434.2024.10878035 · Cited by 10
Enhancing Trustworthiness in Real Time Single Object Detection
Tarkasis, K., Kaparis, K., & Georgiou, A. C. (2025) · Information Systems Frontiers · doi:10.1007/s10796-025-10584-4 · Cited by 4
Bhattacharyya, A., Sau, A., & Mahato, S. K. (2025) · International Conference on Communication Systems & Networks (COMSNETS) · doi:10.1109/comsnets63942.2025.10885668 · Cited by 4
The Cognitive System of Robots Based on Deep Learning with Stable Convergence
Hsu, M.-J., Hsu, C.-C. J., Chien, Y.-H., & Wang, W. (2025) · International Journal of Fuzzy Systems · doi:10.1007/s40815-024-01972-0 · Cited by 3
Optimizing Real-Time Object Detection in a Multi-Neural Processing Unit System
Oh, S., Kwon, Y., & Lee, J. (2025) · Sensors · doi:10.3390/s25051376 · Cited by 16
Pedestrian Detection in Foggy Weather Through YOLOv8 Based on FEAttention
Sun, M., Zhu, J., Yang, B., et al. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-82024-3_9 · Cited by 3
Shu, J., Wang, Q., Zhang, W., Du, M., & Lin, J. (2025) · Marine Geophysical Research · doi:10.1007/s11001-025-09567-6 · Cited by 3
Lin, X. Y., Wang, S., & Shen, J. (2025) · Structural Concrete · doi:10.1002/suco.202401373 · Cited by 3
Models to Identify Small Brain White Matter Hyperintensity Lesions
Castillo, D., Rodríguez-Álvarez, M. J., Samaniego, R., & Lakshminarayanan, V. (2025) · Applied Sciences · doi:10.3390/app15052830 · Cited by 4
Liu, J., Liu, Z., Wang, Y., et al. (2024) · doi:10.1109/isdh64927.2024.00010 · Cited by 3
Safe robot affordance-based grasping and handover for Human-Robot assistive applications
Blengini, C. L., Cheng, P. D. C., & Indri, M. (2024) · Annual Conference of the IEEE Industrial Electronics Society (IECON) · doi:10.1109/iecon55916.2024.10905268 · Cited by 4
Liu, Z., Blut, C., & Blankenbach, J. (2025) · Geo-spatial Information Science · doi:10.1080/10095020.2025.2465311 · Cited by 3
RSSD: A regional-level Resource-Saving Snow Detection Model for winter road surface maintenance
Pan, G., Zhou, X., Zheng, W., Liu, Z., & Zhang, A. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.127155 · Cited by 4
Söffker, D., Boschmann, W., & Shyshova, O. (2025) · Journal of Marine Engineering & Technology · doi:10.1080/20464177.2025.2476862 · Cited by 3
Lightweight traffic sign detection algorithm based on improved YOLOv5 in snowy environments
Wang, Z., Qu, M., Wang, N., et al. (2025) · Signal Image and Video Processing · doi:10.1007/s11760-025-03998-9 · Cited by 3
Segmentation refinement of thin cracks with Minimum Strip Cuts
Hou, W., He, J., Cui, C., Zhong, F., Jiang, X., Lu, L., Zhang, J., & Tu, C. (2025) · Advanced Engineering Informatics · doi:10.1016/j.aei.2025.103249 · Cited by 3
Krawi, O., & Rada, L. (2025) · IEEE Access · doi:10.1109/access.2025.3552928 · Cited by 3
KHAIT: K-9 Handler Artificial Intelligence Teaming for Collaborative Sensemaking
Wilchek, M., Wang, L., Dickinson, S., Feuerbacher, E. N., Luther, K., & Batarseh, F. A. (2025) · ACM International Conference on Intelligent User Interfaces (IUI) · doi:10.1145/3708359.3712107 · Cited by 5
A Lightweight Network for UAV Multi-Scale Feature Fusion-Based Object Detection
Deng, S., & Wan, Y. (2025) · Information · doi:10.3390/info16030250 · Cited by 3
Enhanced Road Safety Through AI-Enabled Voice Assistance
Kumpatla, M. V. G., Tej, G. K., Sahil, G., et al. (2025) · Lecture notes in electrical engineering · doi:10.1007/978-981-97-4711-5_11 · Cited by 3
SiamYOLOv8: a rapid conditional detection framework for one-shot object detection
Desmarescaux, M., Kaddah, W., Alfalou, A., & Badoc, I. (2025) · Applied Intelligence · doi:10.1007/s10489-025-06513-2 · Cited by 5
Li, X. O., Jiao, L., Liu, K., et al. (2025) · Agriculture · doi:10.3390/agriculture15070779 · Cited by 3
RESEARCH ON YOLOv5-BASED VISUAL SLAM OPTIMISATION METHOD IN FARM DEPOT ENVIRONMENT
Pengcheng, L. V., & ZhenWei, L. I. (2025) · INMATEH Agricultural Engineering · doi:10.35633/inmateh-75-07 · Cited by 3
Dong, C., Zeng, H., Li, Y., et al. (2025) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2025.3558167 · Cited by 3
Enhancing Vision-Language Few-Shot Adaptation with Negative Learning
Zhang, C., Stepputtis, S., Sycara, K. P., & Xie, Y. (2025) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61041.2025.00576 · Cited by 14
Hierarchical diffusion models for generating various pattern vehicles in infrared aerial images
Zhang, N., Liu, Y., Liu, H., Tian, T., Ma, J., & Tian, J. (2025) · Pattern Recognition · doi:10.1016/j.patcog.2025.111658 · Cited by 3
A Lightweight and Effective YOLO Model for Infrared Small Object Detection
Wen, S., Li, L., & Ren, W. (2025) · International Journal of Pattern Recognition and Artificial Intelligence · doi:10.1142/s0218001425510097 · Cited by 4
FSGFuse: Feature synergy-guided multi-modality image fusion
Shao, Q., Guan, Z., Wang, X., & Li, H. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.110691 · Cited by 3
Visual SLAM with semantic and geometric constraints in dynamic environments
Li, Z., Zhang, X., Fan, L., & Li, J. (2025) · Journal of Electronic Imaging · doi:10.1117/1.jei.34.2.023050 · Cited by 4
Enhancing Few-Shot SAR Ship Recognition: Pseudospectrum Information Generation and Fusion
Gao, G., Liu, W., & Zhang, X. (2025) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2025.3561516 · Cited by 5
A MaskFormer EfficientNet instance segmentation approach for crowd counting
Goel, S., & Koundal, D. (2025) · Scientific Reports · doi:10.1038/s41598-025-95174-9 · Cited by 3
“There are many CNN-based architectures specifically designed for object detection such as You Only Look Once (YOLO) 16 , Single Shot Multibox Detector (SSD) 17 , Faster-RCNN 18 , Fast-RCNN 19 , Region-based CNNs(R-CNN) 19 and the more popular convolutional neural network models 20,21 .”
Xue, Y., Palstra, A. P., Blonk, R. J. W., Mussgnug, R., Khan, H. A., Komen, H., & Bastiaansen, J. W. M. (2025) · Aquaculture · doi:10.1016/j.aquaculture.2025.742607 · Cited by 4
Liang, C., Jiang, S., Yang, J., Hu, W., Liu, Y., Zhu, P., He, G., & Shi, C. (2025) · IEEE Access · doi:10.1109/access.2025.3561234 · Cited by 4
George, R., Francis, A., & Devassy, B. R. (2025) · doi:10.1109/icvadv63329.2025.10961898 · Cited by 3
Pan, J., Yang, Z., Shen, Q., et al. (2025) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2025.3562067 · Cited by 3
EFSOD: Enhanced Feature based Small Object Detection Network in Remote Sensing Images
Yi, J., Liu, Y., Li, Y., & Xie, W. (2025) · Chinese journal of information fusion. · doi:10.62762/cjif.2025.845143 · Cited by 4
Takyi, S., Antwi, R. B., Özgüven, E. E., Okine, L., & Moses, R. (2025) · Sustainability · doi:10.3390/su17093909 · Cited by 4
Porto, J. V. D. A., Szemes, P. T., Pistori, H., & Menyhárt, J. (2025) · IEEE Access · doi:10.1109/access.2025.3565901 · Cited by 4
Evaluating YOLOv5s and YOLOv8s for Kitchen Fire Detection: A Comparative Analysis
Ismail, N. D., Ramli, R., & Rahman, M. N. A. (2024) · EMITTER International Journal of Engineering Technology · doi:10.24003/emitter.v12i2.882 · Cited by 4
Efficient Edge AI Based Annotation and Detection Framework for Logistics Warehouses
Mori, Y., Asai, Y., Higashiura, K., Katayama, S., Urano, K., Yonezawa, T., & Kawaguchi, N. (2025) · IEEE Consumer Communications and Networking Conference · doi:10.1109/ccnc54725.2025.10976142 · Cited by 5
Zhang, C., Qin, Q., Zhao, B., Yu, C., Wang, S., Chai, J. S., & Jiang, F. (2025) · Humanities and Social Sciences Communications · doi:10.1057/s41599-025-04936-3 · Cited by 6
“The YOLOv8 model has the advantages of fast speed, high accuracy, and strong generalization ability (Redmon et al., 2016), while it is dependent on the quality of the training dataset.”
BSoNet: Deep Learning Solution for Optimizing Image Quality of Portable Backscatter Imaging Systems
Lil, L., Wei, W., Lu, Y., Zhang, W., Zhang, Y., & Zhao, W. (2025) · IEEE Transactions on Computational Imaging · doi:10.1109/tci.2025.3567817 · Cited by 6
“In recent years, deep learning has found widespread applications across disciplines [4], [27], such as object detection [28], [29], image restoration [30], semantic segmentation [31], and image synthesis [32].”
Unmanned aerial vehicle maritime rescue object detection based on improved YOLO11
Zhang, S., Liu, Z., Zhang, L., Ou, W., & Zhang, K. (2025) · Journal of Electronic Imaging · doi:10.1117/1.jei.34.3.033015 · Cited by 3
Hezil, N., Bouridane, A., & Rogov, O. Y. (2025) · International Symposium on iNnovative Informatics of Biskra (ISNIB) · doi:10.1109/isnib64820.2025.10983064 · Cited by 3
Wu, C., Cai, C., Xiao, F., Wang, J., Guo, Y., & Ma, L. (2025) · Information · doi:10.3390/info16050393 · Cited by 5
PMSE-YOLO: an efficient framework for detecting surface defects of hot-rolled strip steel
Zhou, M., Wang, R., & Chen, Y. (2025) · Signal Image and Video Processing · doi:10.1007/s11760-025-04189-2 · Cited by 6
“The main one-stage detection algorithms include SSD [21 ] and the YOLO [ 22] series.”
Romero, S. F. L., de Souza, M. A., & Serpa-Andrade, L. J. (2025) · Technologies · doi:10.3390/technologies13050198 · Cited by 6
Deep learning‐based seabird detection in fisheries for seabird protection
Leong, J., Zhao, J., Xue, B., Gibson, W., & Zhang, M. (2025) · Journal of the Royal Society of New Zealand · doi:10.1080/03036758.2025.2500998 · Cited by 4
“To overcome this limitation, Redmon et al. (2016) proposed a faster and more e ffi cient object detection model titled the ‘ You Only Look Once ’ or the YOLO model.”
Automated Caries Detection Under Dental Restorations and Braces Using Deep Learning
Mao, Y.-C., Lin, Y.-J., Hu, J.-P., et al. (2025) · Bioengineering · doi:10.3390/bioengineering12050533 · Cited by 3
“The YOLO object detection algorithm enables real-time localization with high accuracy and speed [23,24].”
A study of behavioural characteristics of the elderly based on computer vision technology
Lei, W., & He, W. (2025) · International Journal of Urban Sciences · doi:10.1080/12265934.2025.2504680 · Cited by 3
BugBook: Data analysis methods in studies of insects for food and feed
Smetana, S. M., Coudron, C. L., Deruytter, D., Francis, A., Pascual, J. J., Klammsteiner, T., Lemke, N. B., Sandrock, C., & Zanoli, R. (2025) · Journal of Insects as Food and Feed · doi:10.1163/23524588-bja10209 · Cited by 6
Weld defects detection based on improved YOLO-V7
Li, D., Yang, T., & Wang, M. (2025) · Engineering Research Express · doi:10.1088/2631-8695/addc35 · Cited by 3
Liu, Y., Wu, J., Song, X., & Zhang, H. (2025) · IEEE Sensors Journal · doi:10.1109/jsen.2025.3569295 · Cited by 3
Deep-Learning-Based Cognitive Assistance Embedded Systems for People with Visual Impairment
Ngo, H., Le, H. L., & Lin, F. (2025) · Applied Sciences · doi:10.3390/app15115887 · Cited by 6
“This system uses YOLOv1 [73] to detect objects and alerts the user through a headphone when it detects obstacles.”
The Research on an Improved YOLOX-Based Algorithm for Small-Object Road Vehicle Detection
Liu, Z., & Zhang, Z. (2025) · Electronics · doi:10.3390/electronics14112179 · Cited by 4
MCUBench: A Benchmark of Tiny Object Detectors on MCUs
Sah, S., Ganji, D. C., Grimaldi, M., Kumar, R., Hoffman, A., Rohmetra, H., & Saboori, E. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-91979-4_22 · Cited by 7
AEA-YOLO: Adaptive Enhancement Algorithm for Challenging Environment Object Detection
Kariri, A., & Elleithy, K. M. (2025) · AI · doi:10.3390/ai6070132 · Cited by 5
YOLO-DKM: A Flame and Spark Detection Algorithm Based on Deep Learning
Shang, L., Hu, X., Huang, Z., Zhang, Q., Zhang, Z., Li, X., & Chang, Y.-Z. (2025) · IEEE Access · doi:10.1109/access.2025.3581968 · Cited by 4
An Improved Lightweight Model for Defect Detection on Paths in Images
Cui, Z., Xu, Y., Jin, X., & Li, Y. (2025) · Applied Sciences · doi:10.3390/app15137014 · Cited by 3
Automated Test Process for Highly Configurable Software-Defined Mobility Systems in CI/CD
Hettich, L., Pett, T., Nägele, A.-T. T., Schindewolf, M., Eriş, H., Wagner, S., Sax, E., Schaefer, I., & Weyrich, M. (2025) · SAE technical papers on CD-ROM/SAE technical paper series · doi:10.4271/2025-01-0297 · Cited by 5
SAR Ship Detection via Knowledge Transfer: From Optical Image
Zhao, G., Jiang, J., Dong, G., & Liu, H. (2025) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2025.3582808 · Cited by 7
A New Perspective on AI Safety Through Control Theory Methodologies
Ullrich, L., Zimmer, W. M. X., Greer, R., Graichen, K., Knoll, A., & Trivedi, M. M. (2025) · IEEE Open Journal of Intelligent Transportation Systems · doi:10.1109/ojits.2025.3585274 · Cited by 8
“Methods like YOLO [214], Fast R-CNN [215], and K-means clustering-based image segmentation [216] are frequently used for tasks such as object recognition and scene analysis.”
Real-Time Object Detection Model for Electric Power Operation Violation Identification
Qian, X., Luo, L., Li, Y., Zeng, L., Chen, Z., Wang, W., & Deng, W. (2025) · Information · doi:10.3390/info16070569 · Cited by 3
Nigam, N., Singh, D. P., Choudhary, J., & Solanki, S. (2025) · Discover Computing · doi:10.1007/s10791-025-09660-9 · Cited by 3
“YOLO was developed by Redmon and Farhadi [25].”
Deng, G., Zhou, F., Dong, H. C., et al. (2025) · Applied Sciences · doi:10.3390/app15147789 · Cited by 3
Video-Based Traffic Light Recognition by Rockchip RV1126 for Autonomous Driving
Fan, M., Kong, X., Xu, S., Xiong, H., & Liu, X. (2025) · IEEE Intelligent Vehicles Symposium · doi:10.1109/iv64158.2025.11097730 · Cited by 6
Pursuing Temporal-Consistent Video Virtual Try-On via Dynamic Pose Interaction
Dong, L., Zhong, W., Yu, W. B., Pan, Y., Zhang, D., Yao, T., Han, J., & Mei, T. (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/cvpr52734.2025.02109 · Cited by 10
“The pose estimator is trained offline using YOLOv8 [38].”
Liu, B., Wu, W., Wu, H., et al. (2025) · GIScience & Remote Sensing · doi:10.1080/15481603.2025.2541429 · Cited by 3
“…methods is the single-stage detection models, such as the single shot multibox detector (SSD) model (W. Liu et al. 2016), the YOLO series of models (Redmon et al. 2016), and RetinaNet (T.-Y. Lin et al. 2020), which achieve the location task and classification task of tailings ponds directly.”
CODNet: Infrared Small-Target Detection by Mitigating the Curse of Dimensionality
Du, S., Chen, F., Xiao, Y., et al. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2025.3597777 · Cited by 3
LSH-YOLO: A Lightweight Algorithm for Helmet-Wear Detection
Liu, Z., Wang, F., Wang, W., et al. (2025) · Buildings · doi:10.3390/buildings15162918 · Cited by 3
Li, S., Wang, R., Wang, S., Yue, P., & Guo, G. (2025) · Sensors · doi:10.3390/s25165106 · Cited by 3
Na, J., Lee, J., Shin, H., & Yun, I. D. (2025) · Applied Sciences · doi:10.3390/app15169000 · Cited by 3
Nambiar, G. K. P. K., Kumar, N. M., Veena, G., & Thushara, M. G. (2025) · International Conference on Computing for Sustainable Global Development · doi:10.23919/indiacom66777.2025.11115637 · Cited by 4
SMA-YOLO: A Novel Approach to Real-Time Vehicle Detection on Edge Devices
Liu, H., Song, Y., Lin, Y., & Tie, Z. (2025) · Sensors · doi:10.3390/s25165072 · Cited by 4
“Conversely, single-stage detection algorithms, such as Single Shot Multi-Box Detector (SSD) [35], YOLO [13], Effi-cientDet [36], and RetinaNet [37], provide high real-time performance and fast detection rates, at the cost of slightly lower accuracy compared to two-stage algorithms.”
Lightweight CFE-YOLOv8s-Seg Model for Tomato Ripeness Instance Segmentation
Nguyen, N.-L., Nguyen, Q.-A., Kim, T. D., et al. (2025) · Lecture notes in networks and systems · doi:10.1007/978-3-032-00267-9_17 · Cited by 3
An Efficient Defect Detection Method for MLCC Based on EHL-DETR Deep Learning Model
Chen, M., Liang, Z., Fu, Z., Kong, D., & Zhang, D. (2025) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2025.3612639 · Cited by 3
CerberusDet: Unified Multi-dataset Object Detection
Tolstykh, I., Chernyshov, M., & Kuprashevich, M. (2025) · Communications in computer and information science · doi:10.1007/978-3-032-01169-5_6 · Cited by 5
Development and Adaptation of Robotic Vision in the Real World: The Challenge of Door Detection
Antonazzi, M., Luperto, M., Borghese, N. A., & Basilico, N. (2025) · Journal of Field Robotics · doi:10.1002/rob.70084 · Cited by 8
Liang, R., Jiang, M., & Li, S. (2025) · Applied Sciences · doi:10.3390/app152010921 · Cited by 5
Flexible content-aware image synthesis for maritime tasks with diffusion models
Xue, Z., Hu, Y., Lu, A., Chen, Z., Zang, Y., & Miao, Z. (2025) · Applied Ocean Research · doi:10.1016/j.apor.2025.104511 · Cited by 3
Yilmaz, I., Alazab, H. M., Doganay, F., et al. (2026) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2025.109216 · Cited by 3
2D recurrent neural networks: a high-performance tool for robust visual tracking in dynamic scenes
Masala, G. L., Casu, F., Golosio, B., & Grosso, E. (2017) · Neural Computing and Applications · doi:10.1007/s00521-017-3235-x · Cited by 3
Finding the Secret of CNN Parameter Layout under Strict Size Constraint
Liao, L., Zhao, Y., Wei, S., Wang, J., & Liu, R. (2017) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3123266.3123346 · Cited by 3
Interactive Hierarchical Object Proposals
Chen, M., Zhang, J., He, S., Yang, Q., Li, Q., & Yang, M. (2017) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2017.2775446 · Cited by 3
Chinese text-line detection from web videos with fully convolutional networks
Yang, C. H., Pei, W.-Y., Wu, L.-H., & Yin, X.-C. (2018) · Big Data Analytics · doi:10.1186/s41044-017-0028-2 · Cited by 3
Shallow and Deep Model Investigation for Distinguishing Corn and Weeds
Yu, X., Yao, H., Sun, X., et al. (2018) · Lecture notes in computer science · doi:10.1007/978-3-319-77380-3_66 · Cited by 3
Akogo, D., & Palmer, X. (2019) · Lecture notes in networks and systems · doi:10.1007/978-3-030-12385-7_13 · Cited by 4
Recognition on Images from Internet Street View Based on Hierarchical Features Learning with CNNs
Liu, J., & Yang, M. (2018) · Journal of Information Technology Research · doi:10.4018/jitr.2018070105 · Cited by 3
An Empirical Study on the Optimal Batch Size for the Deep Q-Network
Choi, M. (2018) · Advances in intelligent systems and computing · doi:10.1007/978-3-319-78452-6_8 · Cited by 3
CNOT-Measure Quantum Neural Networks
Lukáč, M., Abdiyeva, K., & Kameyama, M. (2018) · IEEE International Symposium on Multiple-Valued Logic (ISMVL) · doi:10.1109/ismvl.2018.00040 · Cited by 8
Vision-based Robotic Grasp Success Determination with Convolutional Neural Network
Zhang, H., Lan, X., Zhou, X., Wang, J., & Zheng, N. (2017) · IEEE International Conference on Cyber Technology in Automation, Control, and Intelligent Systems · doi:10.1109/cyber.2017.8446360 · 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.