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 46,201–46,300 of 51,399
An Improved Small Target Detection Algorithm for YOLOv8 Aerial Images
Wang, Z., Wang, X., Yang, R., et al. (2025) · International Conference on Big Data Engineering and Education (BDEE) · doi:10.1109/bdee67464.2025.00029
“One-stage detection algorithms mainly include the YOLO series [4,5,6] , SSD [7] , and OverFeat [8] , while two-stage detection algorithms mainly include Mask R-CNN [9] , Fast R-CNN [10] , and Faster R-CNN.”
CBAM and CoordAtt in YOLOv8n: Attention Location Effects on KITTI Occlusion Detection
Yusuf, M. M., Ramadhani, K. N., & Firdaus, F. (2025) · International Conference on Information Technology and Computing (ICITCOM) · doi:10.1109/icitcom66635.2025.11265080
“Among various architectures, the YOLO (You Only Look Once) family [3], including its recent iteration YOLOv8n [4], has gained prominence due to its effective balance between processing speed (real-time capability) and detection accuracy.”
A Comprehensive Labeling Protocol and Real-time Inference Framework for Road Hazard Detection
Jeong, J., Woo, Y., Kim, D., et al. (2025) · doi:10.1109/icce-asia67487.2025.11263738
“The YOLO family of models [6]–[8] has evolved continuously to meet these demanding requirements effectively.”
Robust Dual-Camera Lane-Keeping System Using YOLOv8 and ROS2 for Autonomous Driving Education
Park, H. H., Choi, Y. G., Hong, H. J., et al. (2025) · doi:10.1109/icce-asia67487.2025.11263641
“In contrast, object detection models like the YOLO (You Only Look Once) [2] series focus on rapidly detecting lanes as single objects with bounding boxes.”
Choi, Y. G., Park, H. H., Kim, E. H., et al. (2025) · doi:10.1109/icce-asia67487.2025.11263586
“Early studies mainly performed 2D Object Detection [9], [10], [11] on each camera image and estimated the vehicle's 2D position (x, y) by projecting the bottom center point of the detected Bounding Box onto the BEV plane.”
LiDAR-Lane :LiDAR Lane Clustering and Lane Change System
Jeon, Y. W., Choi, Y. G., & Jeon, J. W. (2025) · doi:10.1109/icce-asia67487.2025.11263705
“Simultaneously, models like YOLO[1] have become commonplace for rapid detection of vehicles and relevant road elements in traffic scenes.”
Detection and Tracking of Intruding Unmanned Aerial Vehicles Based on Dual-modality
Zhang, R., Zhang, R., Yang, L., et al. (2025) · International Conference on Big Data Engineering and Education (BDEE) · doi:10.1109/bdee67464.2025.00023
“Single-stage detectors such as SSD[4], YOLOv5[5], and YOLOv8 are selected for testing, while two-stage detectors such as Faster-RCNN[6] and RefineDet[7] are tested to find the detector with the best effect and prepare for adding the improved feature pyramid component later.”
DM-FDA: a dual-modal feature detection algorithm for microscopic impurities
Li, M., Xu, Y., Zhao, Y., Li, J., & Wang, H. (2025) · Signal Image and Video Processing · doi:10.1007/s11760-025-05004-8
“Com - pared to detection methods such as SSD, RetinaNet, and Faster-RCNN, YOLO (You Only Look Once) not only maintains fast computational performance but also achieves higher overall accuracy and recall rates [ 11].”
Hashimoto, S., Nishimura, H., & KUROKAWA, M. (2025) · Journal of the Japan Society for Precision Engineering · doi:10.2493/jjspe.91.1136
YOLOv8-Based Autonomous Ball Detection and Tracking for Rotorcraft UAVs Using Onboard Vision Sensors
Gharsa, O., Touba, M. M., Boumehraz, M., Abderrahmani, N., Ghiloubi, I. B., & Drid, A. H. (2025) · International Electronic Conference on Sensors and Applications (ECSA) · doi:10.3390/ecsa-12-26570
Detection of Printing Defects on Wood-Derived Paper Products Using an Improved YOLOv8n
Zhang, M., Li, S., Zhang, J., Bai, X., Wang, K., & Yuan, H. (2025) · Forests · doi:10.3390/f16121818 · Cited by 1
“In contrast, single-stage methods, such as SSD [26] and the YOLO series [27,28], directly map detection tasks to a single forward pass, thereby reducing computational complexity and enabling high-speed, end-to-end inference.”
HARMONY: A Hardware-Aware Mapping and Optimizing Framework for Computing-in-Memory Accelerators
Li, X., Yang, W., Jing, N., Wang, Q., Mao, Z., & Sheng, W. (2025) · IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems · doi:10.1109/tcad.2025.3641044
“To further validate performance on real-world settings, we evaluate a Conv2D case derived from YOLO-v1 [47], which includes 15 distinct convolutional layers with configurations summarized in Table IV.”
SSC-YOLO: Spectral-Spatial Fusion Convolution for Ship Detection in SAR Imagery
Hoang-Ngoc, D., Nguyen, D. M.-T., & Huynh‐The, T. (2025) · International Conference on Advanced Technologies for Communications · doi:10.1109/atc67618.2025.11268806
“One-stage methods, such as the YOLO [3] families and RetinaNet [4], perform detection in a single pass, Corresponding author: Thien Huynh-The (thienht@hcmute.edu.vn) which offers high inference speed but can struggle with small targets and remains vulnerable to speckle noise.”
A Synthetic Dataset for Manometry Recognition in Robotic Applications
Saraiva, P. A. R., de Souza, E. F., Pinheiro, J. M. H., Segreto, T. H., de Godoy, R. V., & Becker, M. (2025) · Latin American Robotics Symposium, Brazilian Symposium on Robotics and Workshop on Robotics in Education (LARS/SBR/WRE) · doi:10.1109/lars69345.2025.11272958 · Cited by 1
Multispectral Human Presence Detection Using Adapted YOLO Network
Balla, F., & Shrestha, R. (2025) · European Signal Processing Conference (EUSIPCO) · doi:10.23919/eusipco63237.2025.11226498 · Cited by 2
“The backbone consists of multiple convolutional layers and C2f blocks [11], which extract features at different levels.”
Adaptive Traffic Light Control Using YOLOv10 and DeepSort: A Vision-Based Approach for Smart Cities
Kim, T. D., Nguyen-Duc, Q.-A., Thi, T. H. N., et al. (2025) · International Conference on Advanced Technologies for Communications · doi:10.1109/atc67618.2025.11268737
“The You Only Look Once (YOLO) family of models has been instrumental in advancing real-time object detection through its single-stage architecture [19].”
Zhou, Z., Sheng, W., Wang, Y., Fan, X., Chen, S., & Zhang, X. (2025) · CAA Symposium on Fault Detection, Supervision and Safety for Technical Processes (SAFEPROCESS) · doi:10.1109/safeprocess67117.2025.11268086
“With the progress in single-stage object detection models, namely YOLO series [19], methods utilizing a single-stage structure like YOLO-pose [20] are proposed, reaching SOTA of the pose estimation field for its fast speed and high accuracy.”
Real-Time Egg Inspection with YOLOv5-Seg: From Crack Detection to Mobile Application
Nguyen, V. T., Kim, T. D., Nguyen-Duc, Q.-A., et al. (2025) · International Conference on Advanced Technologies for Communications · doi:10.1109/atc67618.2025.11268727
“To address this gap, deep learning, particularly the You Only Look Once (YOLO) architecture, has emerged as a transformative technology for real-time object detection and segmentation [15].”
Research on Safety Hazard Target Detection Method for Open-pit Mines Based on RTDETR
Wang, P., Xie, L., Bian, Y., et al. (2025) · CAA Symposium on Fault Detection, Supervision and Safety for Technical Processes (SAFEPROCESS) · doi:10.1109/safeprocess67117.2025.11268166
“…particularities: small targets such as personnel and small obstacles lack texture information and are easily confused with the background[4]; large-scale targets such as faulty mining equipment have a low proportion of local abnormal areas, and their features are easily masked by…”
Multi-Sensor Fault Detection Based on Wavelet Time-Frequency Maps
Chen, Z., & Chen, M. (2025) · CAA Symposium on Fault Detection, Supervision and Safety for Technical Processes (SAFEPROCESS) · doi:10.1109/safeprocess67117.2025.11268138
Intelligent Surface Defect Detection for Hot-Rolled Steel Strips Using YOLOv11
Li, L., Hu, S., Hou, Y., et al. (2025) · CAA Symposium on Fault Detection, Supervision and Safety for Technical Processes (SAFEPROCESS) · doi:10.1109/safeprocess67117.2025.11267867
“The second category, on the other hand, includes stand-alone detectors like the YOLO [10]and SSD[11].”
LSYOLO-Tracker: A vision algorithm for efficient Monopterus albus detection and tracking
Zhou, F., Liao, W., Yuan, Q., et al. (2025) · Signal Image and Video Processing · doi:10.1007/s11760-025-04982-z
“YOLO (You Only Look Once) is a cutting-edge object recognition algorithm that combines high computational efficiency with the ability to simultaneously predict object locations and categories through a unified framework [5].”
Alegbeleye, O. M., Meddens, A. J. H., Rotimi, Y. O., & Ibeh, K. G. (2025) · Remote Sensing Applications Society and Environment · doi:10.1016/j.rsase.2025.101818 · Cited by 2
Towards Better Detection in the Rain: A Task-Driven Deraining Framework with Semantic Guidance
Chang, Y.-H., & Yang, S. (2025) · ACM International Conference on Multimedia in Asia (MMAsia) · doi:10.1145/3743093.3771052
“Traditional approaches relied heavily on hand-made features, while modern detectors such as YOLO [23], R-CNN [8, 9, 24], and SSD [18] adopt unified end-to-end frameworks, allowing real-time performance and high accuracy.”
Li, C., Xiang, X., Liang, Y., et al. (2025) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2025.3641523
Wider Eyes in the Sky: Scene-Adaptive Video Analytics in Low-Altitude Surveillance Networks
Li, L., Wu, W. R., Fang, S., Wang, S., & Yin, C. (2025) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2025.3641511
Design and Performance Analysis of a Delta Robot for High‐Speed Seed Cutting
Huang, J., Wang, X., Jin, C., et al. (2025) · Journal of Field Robotics · doi:10.1002/rob.70126
“Deep learning ‐ based object detection algorithms, particularly the YOLO series (Jegham et al. 2025; Jocher et al. 2023; Redmon et al. 2016), have demonstrated immense potential in applications such as intelligent potato grading (Su et al. 2018), surface defect detection (Wu, Zhu, et al. 2025), and…”
YOLOv8nGM: An Improved Speed of YOLOv8n Object Detection
Heruatmadja, C. H., Prabowo, H., Warnars, H. L. H. S., & Heryadi, Y. (2025) · Journal of Advances in Information Technology · doi:10.12720/jait.16.12.1724-1733
Zhang, R., Chen, Z., Huo, G., Zhang, X., Luo, W., & Mu, L. (2025) · Remote Sensing · doi:10.3390/rs17243971
Towards a Safe End-to-End AI framework: MISRA C-Compliant YOLO for Object Detection
Fernández, J. H., Agirre, I., Yarza, I., & Perez-Cerrolaza, J. (2025) · Euromicro Conference on Digital System Design (DSD) · doi:10.1109/dsd67783.2025.00021
“YOLO has been implemented in various programming languages since its introduction [11], including C, CUDA, and Python.”
Cati - An Open-Source Framework to Evaluate Attacks on Cameras for Autonomous Vehicles
Kühr, M., Mittmann, M., Hamad, M., & Steinhorst, S. (2025) · Euromicro Conference on Digital System Design (DSD) · doi:10.1109/dsd67783.2025.00078
“Both models are specifically trained versions of the state-of-the-art ML model architecture YOLOv10m [20], [22].”
Application of Artificial Intelligence for Enhancing Travel Preparedness
Pramualsap, A., Arpasat, P., Kungcharoen, K., et al. (2025) · International Conference on ICT and Knowledge Engineering · doi:10.1109/ictke67052.2025.11274438
HSM-YOLO: Hierarchical Screening and Multi-scale YOLOv8
Yang, X., Ma, S., Yang, X., & Gao, Y. (2025) · International Conference on Networking and Network Applications (NaNA) · doi:10.1109/nana66698.2025.00056
“From YOLOv1 [13] to YOLOv2 [14] and YOLOv3 [15], which introduced anchor boxes and multi-scale prediction, and further improvements in architecture and training strategies in later versions [16], the YOLO series has consistently advanced in performance.”
Enhanced CWM-YOLO for Object Detecting Open Water Environment
Wang, J., Wang, T., Zeng, H., et al. (2025) · International Conference on Networking and Network Applications (NaNA) · doi:10.1109/nana66698.2025.00046
“In the domain of object detection, the YOLO (You Only Look Once) series proposed by Redmon et al. [4] reformulates object detection as a regression problem within a single-stage architecture.”
Autonomous charging system via manipulator-UGV docking using zero-shot 6-DoF pose estimation
Jung, M., & Choi, A. J. (2025) · Alexandria Engineering Journal · doi:10.1016/j.aej.2025.12.015 · Cited by 3
TAR‐YOLO: A Novel Deep Learning Model and Dataset for Tennis Action Recognition
Chen, B., Du, L., Fang, W., Cen, Y., Mou, C., Peng, J., Li, J., & Peng, X. (2025) · Scandinavian Journal of Medicine and Science in Sports · doi:10.1111/sms.70177 · Cited by 3
“Meanwhile, the YOLO family has become a cornerstone of real-time object detection since 2016 [33, 34], achieving continuous improvements in accuracy and efficiency while expanding to keypoint estimation and multi-task learning [35–38].”
Thattukolla, S. V., & Thattukolla, S. V. (2025) · Pharmaceutical Development and Technology · doi:10.1080/10837450.2025.2602581 · Cited by 1
“…YOLO model improvements across domains, including YOLOv3, YOLOv4, YOLOv5, and YOLOv8, summarizing their architecture changes, application areas, and performance benchmarks (Redmon 2016; OPTEL Group 2023; Singh 2023; Terven and Cordova-Esparza 2023; Ni et al. 2024; Seed Studio 2024; OpenAI 2025).”
HAS-DETR: a real-time lightweight traffic sign detection model
Dong, J., Liao, H., & Ji, X. (2025) · Journal of Real-Time Image Processing · doi:10.1007/s11554-025-01812-w
“…has demonstrated outstanding performance on general object detection datasets (e.g., COCO [11]), with accuracy surpassing that of mainstream models including YOLOv5, YOLOv7, and YOLOv8 [12], while avoiding the target deletion issue caused by Non-Max-imum Suppression (NMS) in traditional models.”
Selective RGB Channel Jittering for Robust Endoscopic Disease Detection Across Multiple Lesion Types
Çakır, D. (2025) · Sakarya University Journal of Computer and Information Sciences · doi:10.35377/saucis...1771175 · Cited by 1
Performance Evaluation of Real-Time Object Detection for Electric Scooters
Chen, D., Hosseini, A., Smith, A., Nikkhah, A. F., Heydarian, A., Shoghli, O., & Campbell, B. (2025) · ASCE International Conference on Computing in Civil Engineering (i3CE) · doi:10.1061/9780784486115.047 · Cited by 16
Kuang, B., Chen, J., & Hu, Y. (2025) · ASCE International Conference on Computing in Civil Engineering (i3CE) · doi:10.1061/9780784486115.032
Wood-YOLOv11: An Optimized YOLOv11-Based Model for Real-Time Pith Detection in Sawn Timber
Jia, S., Kong, F., Jin, B., Jin, C., & Que, Z. (2025) · Applied Sciences · doi:10.3390/app152413056
Y-LIChess: Live and Interactive Over-The-Board Chess Recognition and Play with Yolo
Benítez-García, G., & Takahashi, H. (2025) · International Conference on Image and Vision Computing New Zealand (IVCNZ) · doi:10.1109/ivcnz67716.2025.11281842
“We use YOLOv5s [9], a lightweight variant of the YOLO [17] family, which is well-known for its balance between accuracy and real-time speed.”
Lightweight Detection Algorithm for SOP Chip Pin Defect Using Enhanced YOLOv8
Lin, D., Zhao, X., Fan, Y., et al. (2025) · International Conference on Information and Automation · doi:10.1109/icia64617.2025.11277663
“In recent years, advances in AI have led to the development of various defect detection methods using object detection frameworks such as Faster R-CNN[3], Mask R-CNN[4], RetinaNet[5], SSD[6], and the YOLO[7] series.”
A Deep Learning-Integrated Visual Servoing Framework for Charging Port Alignment
Luo, J., Zhan, H. L., Zeng, C., & Yang, C. (2025) · IEEE International Conference on Information and Automation (ICIA) · doi:10.1109/icia64617.2025.11277739
“The prevalent object detection algorithms includes mask R-CNN [9] and yolo [10].”
Farahani, M. H., Hassanzadeh, T., & Singh, S. (2025) · International Conference on Image and Vision Computing New Zealand (IVCNZ) · doi:10.1109/ivcnz67716.2025.11281853
“Deep learning, particularly object-detection networks like You Only Look Once (YOLO) [7], offers a promising solution to these challenges.”
PPCHead: A Lightweight Detection Head Designed for UAV Scenarios
Qu, Z., Kong, W., Jia, M., et al. (2025) · International Conference on Information and Automation · doi:10.1109/icia64617.2025.11277472
“In recent years, the YOLO series [4] of object detectors have set high standards for real-time detection tasks due to their well-balanced speed and accuracy.”
Enhanced Small Object Detection Using Multi-Scale Attention for Automated Seabird Detection
Leong, J. C. Y., Zhao, J., Xue, B., et al. (2025) · International Conference on Image and Vision Computing New Zealand (IVCNZ) · doi:10.1109/ivcnz67716.2025.11281847
“One of the most popular object detection models is the You Only Look Once (or YOLO) model by Redmon et al. [7].”
Multi-Scale Feature Aggregation Module for Drone-based Wind Turbine Defect Detection
Li, W., Li, S., Zhou, Y., et al. (2025) · International Conference on Power and Renewable Energy (ICPRE) · doi:10.1109/icpre67300.2025.11274138
“In recent years, deep learning models such as YOLO [8], [9], Faster R-CNN [10], and transformer-based architectures like DETR [11], [12] have been introduced into the domain of wind turbine defect detection.”
Practical Open-Set Face Recognition: Operator-Centric Design with KD-Tree Search
Wattanapornprom, W., Visarnlerdsiri, A., KanokPannachot, C., et al. (2025) · doi:10.1109/incit66780.2025.11276110
“This approach dominates many commercial deployments, such as enterprise access control units and workforce attendance platforms, where enrollment through administrative devices or portals is a prerequisite for enabling entry or logging work hours [1], [2].”
Advancing Diabetic Retinopathy Detection: YOLOv11-Based Real-Time Analysis with OCR Integration
Jadhav, A. B., Jadhav, C., Kaldate, S., & Patil, K. (2025) · International Conference on Industry 4.0 Technology (I4Tech) · doi:10.1109/i4tech64670.2025.11277653
“The mAP is calculated using the following equation: (1) In this formula, APi represents the average precision for lesion class i, while N denotes the total number of classes [23].”
Deep Learning for Lung Cancer Detection in Chest Radiographs: Evaluating YOLOv8 in Clinical Practice
Donisan, P. A., Dascălu, M. I., Haytham, S., Gârlaşu, D., Bratosin, I.-A., Ciungan, D.-A., Dumitrache‐Rujinski, S., Pop, A., Radu, F., & Ștefan, C. (2025) · IEEE International Conference on Bioinformatics and Bioengineering (BIBE) · doi:10.1109/bibe66822.2025.00085
“[14].”
A novel microarray detection method based on deep learning with edge computing
Gan, Z., He, D., Wu, P., Xiong, B., Zeng, N., Liao, L., Guo, F., & Bao, Q. (2025) · Measurement Science and Technology · doi:10.1088/1361-6501/ae2b91
“Since Redmon et al introduced the original YOLO model in 2015 [20], several versions have been released.”
Wongsuwan, S., Siripanichgorn, A., Jirasaksopakun, Y., et al. (2025) · International Conference on Communication, Image and Signal Processing (CCISP) · doi:10.1109/ccisp67522.2025.11282116
“You Only Look Once (YOLO) Based Model YOLO [11] is a real-time object detection framework that jointly predicts bounding boxes and class probabilities.”
Graph-based Pass Receiver Prediction in Soccer with Consideration of Passer’s Body Orientation
Yoshida, R., Goka, R., Maeda, K., Ogawa, T., & Haseyama, M. (2025) · IEEE Global Conference on Consumer Electronics (GCCE) · doi:10.1109/gcce65946.2025.11274936
“1, the proposed method first detects players and the ball in the broadcast image using YOLOv8 [9].”
A Study on Improving the Accuracy of Person Identification by Using Learning Methods
Tanaka, R., & Goto, T. (2025) · IEEE Global Conference on Consumer Electronics (GCCE) · doi:10.1109/gcce65946.2025.11274972
Niu, H., Westphal, A., & Chen, Y. (2025) · International Conference on Industrial Artificial Intelligence (IAI) · doi:10.1109/iai68403.2025.11277022
“The YOLO model is a novel, real-time object detection algorithm introduced by [14].”
Feature Enhancement Based on YOLOv7 for Prohibited Item Detection
Li, Z., Wang, L., Li, Z., et al. (2025) · International Conference on Industrial Artificial Intelligence (IAI) · doi:10.1109/iai68403.2025.11276146
“Representative models include YOLO [12] and SSD [13].”
Improving Accuracy of Vehicle Detection Utilizing Learning Methods
Hayashi, K., & Goto, T. (2025) · IEEE Global Conference on Consumer Electronics (GCCE) · doi:10.1109/gcce65946.2025.11274633
“In the experiments, we prepared 2004 training images, 40 validation images, and 30 test images from the BDD100K dataset [2], the KITTI dataset [3], and the Roboflow Universe dataset [4].”
Performance Analysis of YOLO Models for Real-Time Surveillance Object Detection
Balivada, L., & Priyadharshini, S. (2025) · Annual International Conference on Data Science, Machine Learning and Blockchain Technology (AICDMB) · doi:10.1109/aicdmb64359.2025.11277981
“This approach results in a substantial reduction in computational overhead, enabling YOLO to achieve real-time performance without sacrificing accuracy [5].”
Pomerania Fish: A dataset for fishes across Pomerania freshwater waterbodies in-situ environments
Shi, X., Czerniawski, R., Tanwari, K., Furdyna, A., & Krepski, T. (2025) · Scientific Data · doi:10.1038/s41597-025-06393-8
“Unlike two-stage detection methods, YOLO implements a one-stage detection process using regression, resulting in high accuracy and speed 37 .”
Ali, L. M., Yim, A. K., Gerbi, E., Nguyen, T., Tu, N., Ikede, F., Sampaleanu, R., Grigore, D., Waligorski, J. E., Kremitzki, C. L., et al. (2025) · npj Systems Biology and Applications · doi:10.1038/s41540-025-00627-6
Yang, S., Du, J., Zhang, D., et al. (2025) · Journal of Agricultural Engineering · doi:10.4081/jae.2025.1930
“In contrast, one-stage methods, including SSD (Liu et al ., 2016), RetinaNet (Lin et al ., 2017), and the widely adopted YOLO series (Redmon et al ., 2016; Redmon and Farhadi, 2017; Bochkovskiy et al ., 2020; Khanam and Hussain, 2024a; Luo et al ., 2025; Wang et al ., 2024), directly predict object…”
Feng, X., Yun, L., Wang, C., et al. (2025) · Agronomy · doi:10.3390/agronomy15122868
Huang, C., Peng, X., Shi, F., Song, C., Cao, H., Zhao, X., & Xu, H. (2025) · Nanomaterials · doi:10.3390/nano15241878
“In contrast, single-stage detectors like the YOLO (You Only Look Once) series [14– 16] and SSD [17] achieve an excellent balance between speed and accuracy, rendering them more suitable for industrial online inspection.”
Alguliyev, R. M., Aliguliyev, R. M., & Sukhostat, L. V. (2025) · SN Computer Science · doi:10.1007/s42979-025-04561-6
“The (You Only Look Once), is characterized by higher performance and the ability to find all objects of interest [ 41, 44].”
Environmental Perception Method for Unmanned Surface Vehicles Based on Sea–Sky Line Detection
Yu, Q., Huang, R., & Li, G. (2025) · Systems · doi:10.3390/systems13121123
“As a crucial feature in such images, the sea–sky line helps distinguish the sky from the sea and facilitates target detection [15,16].”
SSM-Det: State Space Model-Based Object Detector for Intelligent Transportation System
Wang, J., Lin, C., Guo, K., & Guo, J. (2025) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2025.3640934
“Contrar-ily, one-stage detector, known as YOLO family [2], [27], [28], [29], formulates detection task as a single regression problem where utilizes one network for both object classification and location regression.”
End-to-End Shipping Container Code Spotting Based on Visual Sensors for Intelligent Inspection
Chen, H., Piao, X., You, S., Jiang, M., Chen, C., & Chen, P. (2025) · IEEE Sensors Journal · doi:10.1109/jsen.2025.3641379
“With the development of scene text detection, container code detection methods could be roughly divided into regression-based [13], [14], [30] and segmentation-based [15], [31], [32].”
Yuan, Z., Yan, S., Yao, C., et al. (2025) · doi:10.1109/piers-spring66516.2025.11276370
“YOLO (You Only Look Once) was initially proposed by Redmon et al. [12] in as a leading method for object detection.”
From Pixels to Patterns: Artificial Intelligence and Digital Imaging for Rock Art Interpretation
Jardim, S., Garcês, S., & Giraldo, H. C. (2025) · International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME) · doi:10.1109/iceccme64568.2025.11277699
“Tsigkas et al. [31] tested YOLO and Tiny-YOLO [32] on three rock art sites, achieving superior accuracy compared to traditional descriptors like SIFT when large datasets were available, but showing weaker performance with limited training data.”
PCN-YOLO: An Improved Lion-Head Goose Detection Method Based on YOLO11
Jiang, J., Du, Z., Wen, B., et al. (2025) · International Conference on Machine Learning and Cybernetics · doi:10.1109/icmlc66258.2025.11280140
“YOLO (You Only Look Once) [8], a groundbreaking innovation in object detection, transforms the task into a regression problem, enabling end-to-end direct prediction and significantly simplifying the detection pipeline.”
C-V2X Based Vehicle Movement Prediction for Connected Vehicle Application
Amin, M. H., Park, J., Konjeti, H. B., & Bhuduri, S. (2025) · International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME) · doi:10.1109/iceccme64568.2025.11277833
“The original YOLO (You Only Look Once) model introduced a groundbreaking approach for conducting object detection in real-time by framing detection as a single regression problem, enabling speed and accuracy in a unified architecture[41].”
Benchmarking SRGAN-Upscaled YOLO for Enhanced Object Detection in Aerial Imagery
da Rocha, W. F., Azzag, H., Lebbah, M., & Mokraoui, A. (2025) · International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME) · doi:10.1109/iceccme64568.2025.11277691
“We focus on basic YOLO architectures [17] up to YOLOv5 to provide a controlled evaluation of SRGAN’s impact, deliberately avoiding additional complexities introduced by state-of-the-art models [7].”
Computer Vision (AI) Based Retailer Shelves Monitoring System
More, S., & Deshpande, G. (2025) · International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME) · doi:10.1109/iceccme64568.2025.11277851
Framework for Identity Privacy through Gender-Based Skeletonization
Hwang, H., Hamad, S. H., Elfiky, N. M., et al. (2025) · IEEE Global Conference on Artificial Intelligence and Internet of Things (GCAIoT) · doi:10.1109/gcaiot68269.2025.11275534
“A real-time object detection neural network was introduced in the original paper for the You Only Look Once (YOLO) architecture by Joseph Redmon et al. [11].”
Wang, Y., Xing, R., Guo, Y., et al. (2025) · Remote Sensing Letters · doi:10.1080/2150704x.2025.2602005
“…algorithm (Viola and Jones 2001), to the Region Proposal Network (RPN) (Ren et al. 2017) and one-stage detectors (e.g., You Only Look Once (YOLO) (Redmon et al. 2016), Single-Shot MultiBox Detector (SSD) (Liu et al. 2016)) that directly predict object categories and bounding boxes in a single…”
MLRT-DETR: A Multi-Directional and Multi-Level Small Object Detection Algorithm from UAV PerspectivePreprint
Song, Y., Zhang, Q., Yan, Y., et al. (2025) · Research Square · doi:10.21203/rs.3.rs-8279195/v1
Sporlarda Çok Kişili Poz Tespiti
Köroğlu, E., & Soylu, E. (2025) · Bilgisayar bilimleri ve mühendisliği dergisi. · doi:10.54525/bbmd.1749324
Nahid, N., Hassan, I., Ahad, M. A. R., & Inoue, S. (2026) · JMIR Aging · doi:10.2196/80102 · Cited by 1
Xie, H., & Zhang, Y. (2025) · International Conference on Biomedical Signal and Image Processing (ICBIP) · doi:10.1109/icbip66535.2025.11284408
“Recent progress in single-stage object detectors, such as YOLO and its variants, suggests that combining detection and classification can be achieved in a single pass, significantly reducing inference time [6], [7].”
Hand Objects Classification for Personality Recognition Using YOLOV5
Rusjayanthi, N. K. D., Putra, I. K. G. D., Sudarma, M., & Sudana, O. (2025) · International Conference on Smart-Green Technology in Electrical and Information Systems (ICSGTEIS) · doi:10.1109/icsgteis68532.2025.11284389 · Cited by 2
“This method uses a regression approach to simultaneously obtain spatially separated bounding boxes and related class probabilities [7], [22].”
PCB Defect Detection Based on Improved YOLOv8n
Wang, A., Yan, J., & Wang, Z. (2025) · International Conference on Artificial Intelligence and Computer Information Technology (AICIT) · doi:10.1109/aicit65974.2025.11282815
Transfer Learning for Pedestrian Detection Across Domains with YOLO and Faster R-CNN
Nantabut, C. (2025) · Research, Invention, and Innovation Congress: Innovative Electricals and Electronics (RI2C) · doi:10.1109/ri2c67120.2025.11282766
“The second category is single-stage object detection, represented by models such as You Only Look Once ( YOLO ) [2], with its most recent version, YOLOv12 [3].”
Real Time Video Segmentation for Object Tracking
Dudhane, S. A., & Redekar, S. (2025) · Asian Conference on Innovation in Technology (ASIANCON) · doi:10.1109/asiancon66527.2025.11280754 · Cited by 1
In and Out People Counting System using Deep Learning Techniques
Manjusha, K. A., Naresh, B., & Deepthi, S. A. (2025) · Asian Conference on Innovation in Technology (ASIANCON) · doi:10.1109/asiancon66527.2025.11280682
“With the rise of deep learning, object detection models such as Faster R-CNN [Ren et al., 2017], YOLO [Redmon et al., 2016], and Mask R-CNN [He et al., 2017] revolutionized real-time detection accuracy and robustness.”
Warehouse Management Models Using Artificial Intelligence: A Review
Kaur, N., Kaur, S., Kaur, G., & Ali, A. (2025) · IEEE International Conference on Advances in Computing Research on Science Engineering and Technology (ACROSET) · doi:10.1109/acroset66531.2025.11281155
MiVOR-Y8: A Multi-Input Vision-Based Object Detection and Face Recognition System with YOLOv8
Vats, S., Shankar, V. G., Bhaskar, B., et al. (2025) · Asian Conference on Innovation in Technology (ASIANCON) · doi:10.1109/asiancon66527.2025.11280760
“…aimed to overcome this gap by creating a Python system incorporating the renowned object detection model YOLOv8 and supplemented by an intensive face recognition module, with the potential of having image, video, and live webcam feeds processed with a high level of precision and speed [1] [2] [12].”
Comprehensive Models and Techniques for Processing Image, Text, Time Series, and Graph Data
Kumar, V. S., Nidhya, M. S., Nath, I., Ramineni, K., Sherin, K. M., & Maram, B. (2025) · International Conference on Innovative Data Communication Technologies and Application (ICIDCA) · doi:10.1109/icidca66325.2025.11280572
Yuan, Q., Raza, M., Salem, S., Kwon, H., Hussain, J., Gu, Y. H., & Al–antari, M. A. (2025) · International Conference on Intelligent Perception and Computer Vision (CIPCV) · doi:10.1109/cipcv65863.2025.00017
“One-stage detectors, such as YOLO [6], and SSD [7] streamline this process by directly predicting object locations and classes, thus enabling high-speed detection suitable for real-time applications.”
Plastic Detection in Water Using Computer Vision
Parmar, H., Bhargava, P., & Murari, U. K. (2025) · doi:10.1109/acroset66531.2025.11280909
“A good labelling strategy using AWS Ground Truth ensures data accuracy and integrity[8] Data sets are commonly split 80/20 for training and testing, with others employing 7/15/15 splits[1].”
Chouhan, D. S., & Sharma, M. (2025) · doi:10.1109/acroset66531.2025.11281211
“• You Only Look Once (YOLO) (2016) Redmon et al. introduced the YOLO (You Only Look Once) algorithm [6], a one-stage deep learning architecture for real-time object detection.”
Kim, D.-K., & Choi, K.-S. (2025) · npj Heritage Science · doi:10.1038/s40494-025-02251-3
Camera-Aided Binary Prior Support-Informed Occupancy Grid Mapping
Zhai, P., Joseph, G., Myers, N. J., et al. (2025) · IEEE Sensors Journal · doi:10.1109/jsen.2025.3642255
“Some existing algorithms are edge detection or advanced deep learning methods such as YOLO networks, RetinaNet, or single-shot detectors [26], [27], [28].”
DexFruit: Dexterous Manipulation and Gaussian Splatting Inspection of Fruit
Swann, A., Qiu, A., Strong, M., Zhang, A., Morstein, S., Rayle, K., & Kennedy, M. (2025) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2025.3645647 · Cited by 4
“Using only a simple webcam, FruitSplat bridges the gap between high-fidelity scanning techniques and traditional deep learning methods.”
Feng, G., Wang, P., Xie, Y., Shen, W., Zeng, J., & Shao, J. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3645096
“Therefore, in certain low-power IoT scenarios, it can be applied to other lightweight object detection networks such as YOLO [35] series, enabling low power consumption, high inference speed, and robust detection.”
Intra-Inter Perspective: An Efficient Network for Logo Detection
Hou, S., Jia, Z., Min, W., et al. (2025) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2025.3644558
Tseng, W. C., Wang, Y.-C., Chen, W.-C., et al. (2025) · Research Square · doi:10.21203/rs.3.rs-8340740/v1
Kaneda, M., Ogaki, S., Nohara, T., Fujita, S., Osako, N., Yagi, T., Tomita, Y., & Ogata, T. (2026) · SLEEP Advances · doi:10.1093/sleepadvances/zpag054
“For every pair of true and predicted events, the intersection over union (IoU) metric was computed as the ratio of the duration of their temporal overlap to the duration of their union [ 55].”
Samas, Z. M., & Mokobombang, N. N. R. A. (2025) · International Conference on New Media Studies (CONMEDIA) · doi:10.1109/conmedia67140.2025.11290450
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.