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 47,801–47,900 of 51,398
A deep learning-based approach for RGB Micro-LED defect detection using microscopic vision
Tan, X., Xie, Z., & Chen, M. (2026) · Optics & Laser Technology · doi:10.1016/j.optlastec.2026.115179
Güneş Panellerindeki Arıza Tespiti için Derin Öğrenmeye Dayalı Bir Yaklaşım: YOLOv8 Uygulaması
YOUSEFALTURK, H., & Yakut, Y. B. (2026) · Harran Üniversitesi Mühendislik Dergisi · doi:10.46578/humder.1821648
Chen, J., Wang, X. R., Zhang, L., et al. (2025) · doi:10.1109/cw68232.2025.00042
“These include single-stage models such as SSD (Single Shot MultiBox Detector) [3] and YOLO (You Only Look Once) [4]series, as well as two-stage detectors such as R-CNN[5].”
Cotton seedling detection based on super-resolution reconstruction from UAV remote sensing imagery
Wang, C., Wang, C., Bian, Z., Liu, S., Liang, M., Zhang, L., Yang, W., & Lan, Y. (2026) · Smart Agricultural Technology · doi:10.1016/j.atech.2026.102075
Research on Real-Time Measurement Technology for High-Dynamic Pose Parameters
Lian, S., Zhu, H., & Zhang, W. (2025) · International Conference on Power, Electrical Engineering, Electronics and Control (PEEEC) · doi:10.1109/peeec67807.2025.00040
“…the monocular vision measurement problem can be transformed into the following mathematical model: given the correspondence between n 2D image points and 3D spatial points[6], determine the Euclidean transformation between the target’s own coordinate system V and the camera coordinate system U.”
MOLT: multi-object and lineage tracking in 2D and 3D biomedical time-series imaging
Bausch, B., Naseh, M., Alves, G. G., et al. (2026) · BMC Bioinformatics · doi:10.1186/s12859-026-06434-y
Object Detection Techniques for Live Monitoring of Amoeba in Phase-Contrast Microscopic ImagesPreprint
Chambers, O., & Cadby, A. J. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.03.30.715415 · Cited by 1
Automated Solar Panel Fault Classification Using VGG16-Based Transfer Learning
S, G. G., S, L. K. V., Suthi, G., et al. (2026) · International Conference on Intelligent Sustainable Systems (ICISS) · doi:10.1109/iciss67859.2026.11454098
“Redmon et al. introduced the original YOLO [6] and YOLO9000 [7], establishing a baseline for real-time object detection.”
Development of an Emergency Event Detection API Using YOLOv8 for Security Camera Systems
Nguyen, D. T., Nguyen, N.-D., Ha, V.-N., et al. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-18159-6_34
Helmet and License Plate Detection Using Deep Learning
Abotula, S., Srija, N. P., Koushik, E. S., et al. (2026) · International Conference on Sentiment Analysis and Deep Learning (ICSADL) · doi:10.1109/icsadl67539.2026.11452078
Jayadevan, R., Sebastian, S. M., Goutham, A., et al. (2025) · doi:10.1109/iccspci68199.2025.11451638
“YOLO (You Only Look Once) is a widely adopted single-stage object detection framework known for its real-time performance [11].”
FGL-YOLO: A Lightweight and Efficient Network for Insulator Defect Detection on UAV
Shen, Y., Liu, Y., Ren, J., Wei, Z., Liu, M., & Wang, S. (2026) · International Conference on Communication Networks and Machine Learning (CNML) · doi:10.1109/cnml68938.2026.11453138
“On the other hand, the single-stage detectors such as YOLO [5] and SSD [6] define the detection as a dense prediction problem.”
Yeşilköy, S., Alawami, M. A., & Choi, Y.-H. (2026) · International Conference on Artificial Intelligence in Information and Communication (ICAIIC) · doi:10.1109/icaiic68212.2026.11454185
Extraction of Stone Positions from a Sheet Image for Curling Match Database Construction
Suzumura, K., Tamura, Y., Aihara, S., & Yamamoto, M. (2026) · Applied Sciences · doi:10.3390/app16073453 · Cited by 1
Crane Load Fall Zone Monitoring with SAM-2 and YOLO-V11
Deshmukh, P., & Kanade, V. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-14186-6_27
On the Power of Deep Learning for Pest Bird Detection in Agriculture
Tossou, O. N. N. F., Atopia, Y. M. S., Ba, M., et al. (2026) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-032-15154-4_8
Development of a System for Detecting Defects in Power Transmission Poles
Loginov, N. A., Martirosyan, A. V., & Shaltumaev, T. S. (2026) · doi:10.1109/elcon-cp69823.2026.11452171
A text-guided vision model for enhanced recognition of small instances
Jung, H.-K. (2026) · Applied Computer Science · doi:10.35784/acs_7850 · Cited by 2
Self-guiding system for blind people
Patra, J. P., Jagtap, A., Kumar, R., et al. (2026) · AIP conference proceedings · doi:10.1063/5.0322621
PPE-Det: Evaluating Lightweight Object Detection Models for Edge-Based Safety Monitoring
Serour, A., Gamea, A., Hassan, A., Mohamed, A., & Gomaa, W. E. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-15784-3_13 · Cited by 1
Wang, F.-B., Geng, S.-L., & Dang, M.-C. (2025) · International Conference on Cyberworlds · doi:10.1109/cw68232.2025.00035
“YOLO [16] revolutionized real-time detection with its global regression approach, with YOLOv8 further optimizing speed-accuracy trade-offs through anchor-free detection and enhanced architectures.”
Islam, M. M. (2026) · Interdisciplinary Journal of AI Machine Learning & Data Science · doi:10.66261/g609t885
Parameter-Efficient Image Denoising for Noise-Robust Object Detection
Miyata, T. (2026) · International Conference on Artificial Intelligence in Information and Communication (ICAIIC) · doi:10.1109/icaiic68212.2026.11454299
Deep Learning-Based Approaches for Crime Detection in CCTV Surveillance
Pai, A. B., & Shetty, J. (2026) · International Conference on Intelligent Sustainable Systems (ICISS) · doi:10.1109/iciss67859.2026.11454000
“…suspicious behavior in a surveillance video in a matter of milliseconds and are appropriate for a time-sensitive task like surveillance, research work has highlighted the effectiveness of using Convolutional Neural Networks in identifying the resultant visual features in the video frames [1], [10].”
Sun, M., Yang, X., Peng, C., et al. (2025) · International Conference on Computer Science and Management Technology (ICCSMT) · doi:10.1145/3795154.3795293
Zurovac, S., Jevremović, J., Miletić, N., & Joksimović, V. (2025) · Scientific Technical Review · doi:10.5937/str2600007z
Wang, J., Liu, L., & An, F. (2026) · IEEE Internet of Things Journal · doi:10.1109/jiot.2026.3679322
“To enhance detection speed and reduce computational cost, Redmon et al. [16] proposed the YOLO model, which refor-mulates target detection as a single regression task that directly predicts class probabilities and bounding box coordinates.”
M, S., Vijayalakshmi, M., Thahir Ahamed, T., et al. (2026) · International Conferences on Information Science and System · doi:10.1109/iciss67859.2026.11453739
“Object detection frameworks such as Faster R-CNN [1] and YOLO [2] have played indispensable roles in modernizing AV perception due to their strong accuracy and real-time performance.”
Enhancing tuberculosis diagnosis with YOLOv5 for real-time x-ray image detection
Singh, J. P., Bhosale, S., Chauhan, S., Pandey, A., Bhatt, D., & Yadav, L. (2026) · AIP conference proceedings · doi:10.1063/5.0322788
Framework for Civic Issue Resolution in Smart City Complaint Systems
Chandru Deva Kannan, P., Dhinakaran, T., & Saravanan, K. (2026) · International Conference on Sentiment Analysis and Deep Learning (ICSADL) · doi:10.1109/icsadl67539.2026.11451821
“Moreover, real-time object detection systems have shown to be applicable in urban settings and can identify a wide variety of urban challenges [14].”
LW-YOLO: A Lightweight Enhanced YOLOv8-Based Model for Mosquito Detection
Duan, J., Liu, L., Ma, D., et al. (2026) · Algorithms · doi:10.3390/a19040267
YOLO-LitePi: A Lightweight Real-Time Traffic Sign Recognition Pipeline Optimized for Raspberry Pi 5
Vinh, N. Q., Duy, N. Q., & Tran, T. T. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-21628-1_36
IM-YOLO: lowering missed detections in real time for tiny defect inspection on paper containers
Xiang, Z., 闫锋欣, Peng, Z., & Wang, J. (2026) · Journal of Real-Time Image Processing · doi:10.1007/s11554-026-01872-6 · Cited by 1
“The YOLO model, from the pioneering YOLOv1 [22] to the latest YOLOv12 [25], has undergone numerous version iterations, establishing it as the most promising technical route for such industrial quality inspection tasks.”
Energy Box: Multi Scale Bounding Box Optimization Using Energy Based Models
Dang, D. T., Nguyen, K. T., & Huynh, H. X. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-18159-6_47
P2AW-YOLO11n: Improving Drone-Based Small Object Detection via AFPN and Enhanced Loss Functions
Li, X., Wang, W., Wang, F. L., et al. (2025) · doi:10.1109/cw68232.2025.00032
“The classification of contemporary object detection algorithms within the deep learning domain can be broadly divided into two major categories: two-stage methods, exemplified by Faster R-CNN [8], and one-stage methods, represented by the YOLO series [9], [10].”
Computer Vision for Healthcare and Medicine: Unlocking Insights from Visual Data
Ray, A., Firouzi, F., Farahani, B., & Chakrabarty, K. (2026) · Springer eBooks · doi:10.1007/978-3-032-06286-4_5 · Cited by 1
FireLight-YOLO: A Lightweight Model Based on the C2f_Fork Dual-Branch Architecture
Liu, L., Chen, Y., Lu, Q., et al. (2025) · International Conference on Vision, Image and Signal Processing (ICVISP) · doi:10.1109/icvisp68610.2025.11451184
Graph Cut-based automatic image segmentation driven by seeds from deep semantic segmentation models
Kumagai, S., Otake, T., Aomori, H., et al. (2026) · Nonlinear Theory and Its Applications IEICE · doi:10.1587/nolta.17.508
Automated Control of Product Labeling System Based on Computer Vision
Bogachev, M. A., Rudyy, M., Inechkin, D., et al. (2026) · doi:10.1109/elcon-ee69794.2026.11452900
“Compact model architectures designed for resource-limited conditions were employed, including versions of Tiny YOLO, MobileNet, EfficientDet-Lite, and others [6].”
YOLOv8-D: Aero-Engine Pipeline Segmentation Framework Based on Dynamic Sampling
Wang, C., Xie, Z., Ma, Y., et al. (2025) · doi:10.1109/cw68232.2025.00033
“…the network's ability to express image features is enhanced by doubling the number of channels; at the same time, the batch normalization layer [23] is introduced to effectively stabilize the training process, prevent model overfitting, and improve training efficiency and generalization…”
FuzzyCoMobile for Multi-label Chest X-Ray Classification
Tran, T.-K.-N., Nguyen, H.-H. T., & Phan, A.-C. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-21628-1_5
Ye, S., Ma, H., Zhang, Z., et al. (2026) · Algorithms · doi:10.3390/a19040268
Nguyen, H. V., Park, H., Yoo, N., & Yang, J. (2026) · International Conference on Artificial Intelligence in Information and Communication (ICAIIC) · doi:10.1109/icaiic68212.2026.11454372
Efficient Multimodal Fusion of Skeleton and Posture Cues for Robust Behavior Understanding
Zhang, Y., Liu, X., Li, J., et al. (2026) · International Conference on Communication Networks and Machine Learning (CNML) · doi:10.1109/cnml68938.2026.11452298
“The YOLO-OpenPoseNet behavior recognition model consists of three parts: the YOLOv5 [13], the OpenPose module, and the MobileNetV3 [14], which together achieve human behavior recognition and classification.”
Klawa, T., & Tanner, F. R. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-18474-0_28 · Cited by 1
Liu, A. (2025) · doi:10.1109/itcem68692.2025.00053
“Besides, the non-Maximum Suppression (NMS) filters the optimal results, enabling real-time detection through a single neural network [10].”
GMS-YOLO: A Lightweight Algorithm for SAR Ship Target Detection Based on YOLOv8n
Liu, X., Zhou, X., Li, X., & Xu, J. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-8405-5_29
Li, T., Yang, X., Sun, H., & Li, Z. (2026) · IEEE Transactions on Components Packaging and Manufacturing Technology · doi:10.1109/tcpmt.2026.3680077
“2, taking the YOLO [13] framework as an example, the features of minute defects progressively shrink through successive downsampling operations, often reducing to a single pixel or even disappearing in intermediate layers.”
Shang, W., Jia, X., Cui, Y., et al. (2026) · Symmetry · doi:10.3390/sym18040595
Image Characterization by Morphological Hierarchical Representations
Fehri, A. (2018) · theses.fr (ABES) · doi:10.70675/f777371az8039z4665z9802zdd7fdf59ebaf · Cited by 1
Tassan-Din, E., Gunessee, A., Vong, P., Marqué, C., Dolla, L., Picar, A. M., & Monstein, C. (2026) · Journal of Space Weather and Space Climate · doi:10.1051/swsc/2026014 · Cited by 1
Object representation in local feature spaces : application to real-time tracking and detection
Tran, A. (2017) · theses.fr (ABES) · doi:10.70675/78c97c06z6102z41bfz89d4zd4f73cea31c4
Intrinsic motivation mecanisms for incremental learning of visual saliency
Craye, C. (2017) · theses.fr (ABES) · doi:10.70675/922227cfzcecaz436azb9fez23e8903dbf49 · Cited by 3
PMDet: Patch-Aware Enhancement and Fusion for Multispectral Object Detection
Li, J. C., Sui, C., Wang, J., & Zhou, J. (2026) · Remote Sensing · doi:10.3390/rs18071068 · Cited by 1
Détection et estimation de pose d'instances d'objet rigide pour la manipulation robotisée
Brégier, R. (2018) · theses.fr (ABES) · doi:10.70675/b2ed3784z950bz4443z9cebz4e1fe7bfbfb8
Fourure, D. (2017) · theses.fr (ABES) · doi:10.70675/b54dd90bz6e92z43fez8df3z313ad61607ea · Cited by 1
LEC-YOLO:Real-Time Tiny Object Detection via Cross-Scale Feature InteractionPreprint
Dai, Y., & Guo, X. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6512540
DF-DETR: An Algorithm for Small Object Detection in UAV Aerial Images
Bu, L., Yang, H., & Yang, B. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-8417-8_42
Cho, W., Ha, T., Son, T., & Woo, W. (2026) · IEEE Conference on Virtual Reality and 3D User Interfaces (VR) · doi:10.1109/vr67842.2026.00073 · Cited by 1
“To ensure both speed and robustness in typical environments, we adopt YOLO [54], us-ing the release of YOLO-v11.”
Research on Vehicle Target Detection in Rainy Environment Based on Improved RT-DETR Model
Yang, L., Peng, L., Mali, H., Wei, L., Xuehua, L., & Zhousen, Z. (2026) · Computer Science and Technology · doi:10.57237/j.cst.2026.02.001
“) [4] ; 单阶段检测算法则无需候选区域生成步骤,将目标检 测任务直接建模为回归问题,代表性算法包括 YOLO ( You Only Look Once )系列 [5] 、 SSD ( Single Shot MultiBox Detector ) [6] 、 DETR ( Detection Transformer ) [7] 以及其高效实时版本 RT-DETR ( Real-Time Detection Transformer ) [8] 等,在速度与精度平衡上更具优势。 现有方法在常规场景下表现良好,但在雨天环境 中,雨滴遮挡、图像模糊、对比度低等问题仍会导致检…”
Benamara, M. A. (2018) · theses.fr (ABES) · doi:10.70675/e49aef1az8750z4e7cz9dfaz37142454e5f8
Multi-object detection and tracking in video sequences
Mhalla, A. (2018) · theses.fr (ABES) · doi:10.70675/6d64f9c8ze926z44d0zb444z11cb37d67638
Regularization schemes for transfer learning with convolutional networks
Li, X. (2019) · theses.fr (ABES) · doi:10.70675/2a5899e3zcf74z465bz9e1dz147af509a193
DPENet: A Dual Prototype-Enhanced Network for Few-Shot Object Detection
Huang, J., Wang, H. M., Wu, Q., Li, J., & Gao, X. (2026) · IEEE Transactions on Image Processing · doi:10.1109/tip.2026.3678751
SSD-VUPV: A Novel SSD-Based Model for Automated Pulmonary Nodule Detection
Ji, Z., Pang, J., Liu, J., Dai, C., Shengnan, H., & Ганчев, И. (2026) · WSEAS TRANSACTIONS on SYSTEMS archive · doi:10.37394/23202.2026.25.16
Approches jointes texte/image pour la compréhension multimodale de documents
Delecraz, S. (2018) · theses.fr (ABES) · doi:10.70675/1dbcf5c1zf620z42d0za4dfzdccac062b8dc · Cited by 1
Öztürk, L., & Şin, B. (2026) · Ciência e técnica vitivinícola/Ciência e técnica vitivinícola · doi:10.1051/ctv/20264101001
Estimation automatisée sur vidéos de la biodiversité et de l’abondance des poissons coralliens
Villon, S. (2019) · theses.fr (ABES) · doi:10.70675/db0cb978z2664z4be3zaceaz64b91e4d1da1 · Cited by 2
zongxiang, H., & Abas, A. (2026) · International Journal of Latest Technology in Engineering Management & Applied Science · doi:10.51583/ijltemas.2026.150300016
Conception d'architectures profondes pour l'interprétation de données visuelles
Mordan, T. (2018) · theses.fr (ABES) · doi:10.70675/7263c670z2517z402dzad8fz1f991ba5d034
Vision-based human gestures recognition for human-robot interaction
Mazhar, O. (2019) · theses.fr (ABES) · doi:10.70675/3d2ca177zb310z4cddz828fz42baea348aef
Des systèmes d'aide à la conduite au véhicule autonome connecté
Monot, N. (2019) · theses.fr (ABES) · doi:10.70675/b4b9a315z1a5fz46ccz8cf2z65b5ef861ea3 · Cited by 2
Learning to detect visual relations
Peyre, J. (2019) · theses.fr (ABES) · doi:10.70675/e491bc42z84b1z4107zadf9z95414bcd6961
Interactive computer vision through the Web
Pizenberg, M. (2020) · theses.fr (ABES) · doi:10.70675/31d3db07z1123z48dczb7e2zd4e471c8fa5c
Structures for deep learning and topology optimization of functions on 3D shapes
Poulenard, A. (2020) · theses.fr (ABES) · doi:10.70675/6044d6a1zfadbz445fzbedezf0da1fdd6ec8
2D Image Processing Applied to 3D LiDAR Point Clouds
Biasutti, P. (2019) · theses.fr (ABES) · doi:10.70675/d0812af5z93f7z4351zb740ze1349e44dcb5
Abdallah, H. B. (2020) · theses.fr (ABES) · doi:10.70675/59a9ff2ez3209z438eza072z650ee3a132ec · Cited by 2
Sémantisation à la volée de nuages de points 3D acquis par systèmes embarqués
Roynard, X. (2019) · theses.fr (ABES) · doi:10.70675/8f872df1z141bz4874zbdedz8be0859ef26d
du Terrail, J. O. (2018) · theses.fr (ABES) · doi:10.70675/083d206az0a4ez4480z866ez53e9de431d15 · Cited by 1
Sarron, J. (2019) · theses.fr (ABES) · doi:10.70675/a99364fbzb3c5z4278z8a00z9f3d436f086b · Cited by 5
Learning from electrophysiology time series during sleep : from scoring to event detection
Chambon, S. (2018) · theses.fr (ABES) · doi:10.70675/9bc9b3a7z17c4z400ez9f55za529aad4f8f1
Exploiting edge features for scene text understanding systems and scene text searching applications
Van, D. N. (2018) · theses.fr (ABES) · doi:10.70675/4ce0778cz6984z4318zb5f9z718ee470e35a
MoSA-Det: motion state adaptive object detection for sports videos
Yang, L., Sun, W., & Ren, J. (2026) · Scientific Reports · doi:10.1038/s41598-026-43231-2
Classification de données massives de télédétection
Audebert, N. (2018) · theses.fr (ABES) · doi:10.70675/e7e6756dzea11z49c1z99dfz2a794a46b421 · Cited by 4
Real-time scene analysis for 3D interaction
Kaiser, A. (2019) · theses.fr (ABES) · doi:10.70675/3f01cf2bzae9cz4996z99adz1ac064278490 · Cited by 1
Learning Image-to-Surface Correspondence
Güler, R. A. (2019) · theses.fr (ABES) · doi:10.70675/5c92c11bzafbaz442fz9accz878a6d7dbaf1
Reconfigurable hardware acceleration of CNNs on FPGA-based smart cameras
Abdelouahab, K. (2018) · theses.fr (ABES) · doi:10.70675/88c8fb7dz3228z4c3cz926cz62f365d6d2d7 · Cited by 6
Robust Learning of a depth map for obstacle avoidance with a monocular stabilized flying camera
Pinard, C. (2019) · theses.fr (ABES) · doi:10.70675/14bf1a7dz78a9z4170zbfacz9b660a96e7db · Cited by 2
Structured deep learning for video analysis
Baradel, F. (2020) · theses.fr (ABES) · doi:10.70675/2a8e4991z61e3z4030z8b4cz030a297ed81c
QoS-aware resource and energy management for autonomous mobile
Ho, D.-K. (2020) · theses.fr (ABES) · doi:10.70675/913ebd96z2fc2z457bz8646zd91e7738b9a2 · Cited by 2
Ruffenach, M. (2020) · theses.fr (ABES) · doi:10.70675/11daff85z6ce9z4753z8102z779a11c29d86 · Cited by 3
Shuvo, M. K., Huang, X., Fei, L., et al. (2026) · Optical Fiber Technology · doi:10.1016/j.yofte.2026.104780
Détection des adventices par imagerie aérienne
Bah, M. D. (2020) · theses.fr (ABES) · doi:10.70675/1b2b47f5z2ea5z45aez891fz2240f70d124d
Spatial techniques for video understanding
Sydorov, V. (2021) · theses.fr (ABES) · doi:10.70675/ab9825adz1fb8z4f1cz9217zef67d5530022 · Cited by 1
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.