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 46,801–46,900 of 51,399
Research on Intelligent Detection Methods for Through-Hole Soldering Defects in Sensor Pins
Cheng, Z., Ji, J., Wang, P., et al. (2025) · 2025 4th International Conference on Image Processing, Computer Vision and Machine Learning (ICICML) · doi:10.1109/icicml67980.2025.11333788
“One-stage detectors, such as YOLO [5] and SSD [6], perform detection in a single step and offer higher real-time capability.”
Haces‐Garcia, F., Glennie, C., Rifai, H. S., & Hoskere, V. (2026) · Journal of Hydrology Regional Studies · doi:10.1016/j.ejrh.2026.103113 · Cited by 1
Smart Quality Test System for E-commerce Using Camera Vision Technology
Nivetha, A., Ranjan, S. K., Shukla, P., et al. (2025) · IEEE International Conference on Computing, Communication and Automation (ICCCA) · doi:10.1109/iccca66364.2025.11325709
“[8] Our approach reframes object recognition as a single regression issue and predicts bounding boxes and class probabilities from full images in a single assessment, based on the YOLO (You Only Look Once) object identification model [9].”
Kim, D. H., Kim, G., Kim, M. J., Lee, S. Y., & Yang, Y. S. (2026) · IEEE Access · doi:10.1109/access.2026.3655178
Computational challenges for the massive production of enriched pre-editions
Gabay, S., Kuenzli, P., Rubino, R., et al. (2025) · doi:10.1109/ieee-ch65308.2025.11279293
“Detection is performed with YOLO [14] v11, an object detection system based on a convolutional neural network (CNN).”
Dual-Model Livestock Visual Warning System
Wu, K., Zhao, L., Ma, H., et al. (2025) · International Conference on Image Processing, Computer Vision and Machine Learning (ICICML) · doi:10.1109/icicml67980.2025.11333428
“…existing YOLO-based detection methods on edge devices (e.g., Raspberry Pi) excel at pre-trained category identification but lack proactive reasoning, while large AI models that address this limitation face computational constraints on edge hardware, struggling to meet real-time demands [1] .”
Mixed 2D–3D Object Recognition for Autonomous Inspection in Industrial Environments
Melacci, S., Nunziati, G., Corradini, B. T., Magistris, G. D., Fiorucci, M., & Schillaci, G. (2025) · International Conference on AI-ML Systems (AIMLSystems) · doi:10.1109/aimlsystems67835.2025.11330526
“Note that setting up a Frustum PointNet system requires: 1) A trained 2D object detector (e.g., the YOLO models [37]) on the RGB images, in order to localize candidate objects of interest.”
Traffic Target and Vehicle Detection Algorithm Based on YOLO
He, J., & Zeng, X. (2025) · International Conference on Machine Learning and Computer Application (ICMLCA) · doi:10.1109/icmlca66850.2025.11336263
“…two-stage detection frameworks such as Faster R-CNN[8], Mask R-CNN[9], and single-stage detection frameworks such as the SSD series[10], YOLO series[11] [12] [13], and Anchor-Free series[14], which realize target localization through cascaded region refinement and dense prediction mechanisms,…”
Bridging the Gap in Assistive Mobility: From Ground Detection to Smart Vision
Arora, D., Maheshwari, P., & Chandani, P. (2025) · IEEE International Conference on Computing, Communication and Automation (ICCCA) · doi:10.1109/iccca66364.2025.11325597
“This brought about glasses that could read words, discern what objects are, or even recognize who's in front of them[6],[9].”
InfluentialMask Wearing Detection and Recognition Based on Improved YOLOv3
Chen, H., Chen, Q., Huang, Z., et al. (2025) · doi:10.23919/aces-china66523.2025.11333247
“In the field of object detection, the YOLO (You Only Look Once) framework developed by Redmon's team [4]”
EFSD-YOLOv5s: Effective Fire and Smoke Detection Method Based on an Improved YOLOv5s Model
Wang, C., Xu, C., Li, N., et al. (2025) · International Conference on Image Processing, Computer Vision and Machine Learning (ICICML) · doi:10.1109/icicml67980.2025.11333508
“Among them, YOLOv5 (You Only Look Once version 5) has gained considerable popularity for real-time object detection, including fire and smoke recognition, due to its commendable balance between speed and accuracy [1].”
FridgeSense: An AI-Powered Solution for Smart Food Tracking and Recipe Planning
Vadlamudi, S., Shashikala, K. S., Shreeya, D., et al. (2025) · IEEE International Conference on Computing, Communication and Automation (ICCCA) · doi:10.1109/iccca66364.2025.11325426
Bio-Inspired Acceleration Fabric: BCU-YOLO on Tianjic Chip for UAV Scenarios
Pan, X., Deng, Y., Geng, X., et al. (2025) · International Conference on Ubiquitous Communication (Ucom) · doi:10.1109/ucom67224.2025.11336987
“As an efficient real-time target detection algorithm, YOLO has been widely used in the field of computer vision [7].”
AI-Assisted Droplet Splitting on a Parallel-Plate Optoelectrowetting Chip
Tian, J., Gao, S., Zhu, T., et al. (2025) · IEEE International Conference on ASIC (ASICON) · doi:10.1109/asicon66040.2025.11325981
“The computer runs a deep learning model based on the You Only Look Once (YOLO) v11 algorithm [15], which accurately detects the spatial position and boundaries of droplets.”
Zhang, F., Chen, M., Cao, Y., & He, W. (2025) · International Conference on Cloud Computing, Big Data Application and Software Engineering (CBASE) · doi:10.1109/cbase67452.2025.11335554
“With the rapid progress of deep learning, convolutional neural network (CNN) [1] -based object detection methods, especially the YOLO (You Only Look Once) [2] family, have been widely applied in plant disease Detection tasks due to their high accuracy and efficiency.”
Research on Multi-scale Lesion Detection in Human Lung CT Images Based on Deep Learning
Duan, J., & Zhao, Y. (2026) · Communications in computer and information science · doi:10.1007/978-981-95-5294-8_14
Assistive Device for Visually Impaired Individuals Featuring Road Object Detection
Nedjar, I., Bekkaoui, M., Hacene, L. F. B., et al. (2026) · Arabian Journal for Science and Engineering · doi:10.1007/s13369-025-11044-6
“TheYouOnlyLookOnce(YOLO)algorithm,firstintroduced by Redmon et al. in 2015 [47], marked a significant advancement in the field of real-time object detection.”
Real‑Time Detection and Segmentation of Tomato Pests with YOLOv8
Şahin, Y. S., Gençer, N. S., & Şahin, H. (2026) · Tarım Bilimleri Dergisi · doi:10.15832/ankutbd.1681258
Mixed 2D-3D Object Recognition for Autonomous Inspection in Industrial Environments
Melacci, S., Nunziati, G., Corradini, B. T., Magistris, G. D., Fiorucci, M., & Schillaci, G. (2025) · International Conference on AI-ML Systems (AIMLSystems) · doi:10.1109/aimlsystems67835.2025.11331264
“Note that setting up a Frustum PointNet system requires: 1) A trained 2D object detector (e.g., the YOLO models [37]) on the RGB images, in order to localize candidate objects of interest.”
Research on Image Detection of Thin-Vein Precious Metal Ores and Rocks Based on Improved YOLOv8n
Zhou, H., Li, Y., Wang, Y., et al. (2026) · Applied Sciences · doi:10.3390/app16020988
Improved Mask R-CNN for Spacer Detection in Transmission Line Images
Zeng, T., Kong, X., Yuan, M., et al. (2025) · International Conference on Intelligent Power and Systems (ICIPS) · doi:10.1109/icips67876.2025.11331913
“In contrast, one-stage detectors like SSD[10] and YOLO[11] significantly outperform region-of-interest (ROI)- based two-stage algorithms (e.g., Faster RCNN[12]) in speed while maintaining high accuracy, making them more suitable for real-time industrial and robotic applications[13].”
Wang, C., Yu, Y., Yue, W., et al. (2025) · International Conference on Machine Learning and Computer Application (ICMLCA) · doi:10.1109/icmlca66850.2025.11336473
“In contrast, one-stage models, particularly the YOLO series [5] , provide a favorable trade-off between accuracy and efficiency.”
RFG ‐ YOLO : Accurate and Lightweight Detection of Multi‐Scale Defects on Metallic Surfaces
Geng, J., Li, M., & Tang, C. (2026) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.70563 · Cited by 2
“Architectures such as the YOLO (You Only Look Once) series [4] and Faster R-CNN [5] have greatly improved both detection accuracy and speed, making real-time defect recognition feasible in industrial settings.”
Automatic Renaming Algorithm for UAV Inspection Photos of Transmission Lines Based on YOLOv5
Wu, W., Ding, J., Wang, Z., et al. (2025) · International Conference on Advances in Electrical Engineering and Computer Applications (AEECA) · doi:10.1109/aeeca65693.2025.00079
“The other one is the first-order algorithm based on regression, such as You Only Look Once (YOLO) [12,13], Single Shot MultiBox Detector (SSD) [14].”
Khalaf, H. H., & Alkawaz, M. H. (2025) · IEEE Symposium on Wireless Technology & Applications (ISWTA) · doi:10.1109/iswta68114.2025.11329774
“YOLOv1 (2016) proposed a "single-pass" method for object detection, which considers the problem as a single regression problem, providing end-to-end training and significantly accelerating the inference step by bypassing the region proposal stage for two-stage detectors, such as in R-CNN [2], [10].”
Real-Time Pothole Detection using Machine Learning
Dani, N., Khan, N., & Agrawal, A. J. (2025) · IEEE International Conference on Computing, Communication and Automation (ICCCA) · doi:10.1109/iccca66364.2025.11325144
“YOLO, a popular one-stage detector, was initially proposed in 2016 [14], then it has its improves and variations (YOLO v2, v3, and Tiny YOLO) for different application domains, e.g., pothole detection [15].”
Beyond CNNs: Efficient Fine-Tuning of Multi-Modal LLMs for Object Detection on Low-Data Regimes
Elamon, N., & Davoudi, R. (2025) · International Conference on Content-Based Multimedia Indexing (CBMI) · doi:10.1109/cbmi66578.2025.11339312
“Traditional CNN-based object detection methods can be broadly classified into one-stage detectors, such as [1] (You Only Look Once) and [11] (Single Shot MultiBox Detector), which prioritize speed and efficiency, and two-stage detectors, such as R-CNN and Faster R-CNN [3], which typically offer…”
Yıldırım, B., & Aydın, E. (2025) · National Conference on Electrical and Electronics Engineering (ELECO) · doi:10.1109/eleco69582.2025.11329263
“Among state-of-the-art architectures, YOLO stands out for its real-time efficiency and high detection accuracy, while Faster Region-Based Convolutional Neural Network (Faster R-CNN) localizes precisely critical objects [6][7].”
Automated Local Measurement of Wall Shear Stress with AI-Assisted Oil Film Interferometry
Youshanlouei, M. M., Lazzarini, L., Talamelli, A., et al. (2026) · Italian National Conference on Sensors · doi:10.3390/s26020701
“The proposed AI-assisted OFI (AI-OFI for short) uses a combination of two CNN algorithms to achieve automated measurement of WSS: a YOLO-based network [40] for the detection of one or more droplets and a VGG16-based network [41] for the prediction of ∆ x .”
Design of YOLO object detection system based on heterogeneous SoC
Liguo, Z., Yu, X. R., & Jin, M. (2026) · Engineering Research Express · doi:10.1088/2631-8695/ae3a41
Ursem, L., Bakker, E. S., Jin, H., et al. (2026) · Restoration Ecology · doi:10.1111/rec.70329
“This is a deep learning model for object detection that can recognize and locate objects in an image in a single step (Redmon et al. 2016).”
Design of a Lightweight YOLO Model Based on an Improved C2f Module
Jiang, H., Fan, H. X., Yu, S., et al. (2025) · International Conference on Machine Learning and Computer Application (ICMLCA) · doi:10.1109/icmlca66850.2025.11336322
“In contrast, the YOLO (You Only Look Once) series of algorithms innovatively employs a single-stage, end-to-end architecture [3] , directly achieving joint output of object localization and classification through grid-based prediction, significantly improving detection efficiency.”
Improved YOLO Algorithm Based on Remote Sensing Image Direction Fusion and Weight Sharing
Bai, Y., Lin, J., & Li, P. (2025) · International Conference on Cloud Computing, Big Data Application and Software Engineering (CBASE) · doi:10.1109/cbase67452.2025.11335453
“While deep learning-based methods such as the YOLO series[1] have achieved a commendable balance between speed and accuracy in natural image detection, their direct application to remote sensing scenarios often yields suboptimal results.”
Zhao, Z., Fu, T., Dong, H., & Zhang, X. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-5628-1_35
TD-Net: a temporal difference-infused lightweight network for flying shuttlecock detection
Fan, Y., & Li, G. (2026) · The Journal of Supercomputing · doi:10.1007/s11227-026-08237-7
“While frameworks like Yolo [10] and SSD [11] have excelled in standard benchmarks, their performance often degrades on small targets, which lack rich appearance features within a single frame.”
Application and Optimization of NLP Pre-trained Models in Image Recognition
Bai, X. (2025) · Journal of safety science and engineering. · doi:10.62517/jsse.202508405
An Adaptive Framework for Violation Detection Using Multimodal Large Models
Ma, Y., Wang, F., Yin, F., Li, X., Yang, Z., & Zhu, L. (2025) · International Conference on Artificial Intelligence and Foundation Model · doi:10.1145/3786709.3786713
“The field evolved from traditional feature-based methods like Histograms of Oriented Gradients (HOG) for human detection [9] to deep learning-based models like Faster R-CNN [10] and YOLO [11].”
Lightweight Multi-scale Feature Fusion Algorithm for Mountain Road Crack Detection
Wang, D., Huang, X., Xu, W., et al. (2026) · Signal Image and Video Processing · doi:10.1007/s11760-026-05123-w
“In contrast, fast road crack detection methods based on the YOLO (You Only Look Once) series of algorithms [27] have gained considerable attention in recent years.”
Bounding Box-Derived Mask Guidance Network for Accurate Surface Defect Detection
Cui, L., Ma, X., Tian, F., et al. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-5764-6_8
DFA-YOLO: An Enhanced Lightweight Object Detection Model for Efficient Keyhole Detection
Li, Z., Huang, Z., Chen, H., et al. (2025) · International Conference on Information Communication and Signal Processing (ICICSP) · doi:10.1109/icicsp66564.2025.11338209
“Joseph et al. [12] introduced YOLO for real-time detection, with versions from YOLOv2 to YOLOv11 [13] improving accuracy and speed.”
CDA-YOLO: An Efficient Remote Sensing Object Detection Model Based on YOLO11
Wang, S.-Y., Zhang, B., & Wu, Y.-T. (2025) · International Conference Robotics and Computer Vision · doi:10.1109/icrcv67407.2025.11349330
“You only look once (YOLO) [5] serves as an exemplary case in point.”
A Lightweight Apple Detection Method in Real Orchard Environments Based on Improved YOLOv8s
Zilong, L., & Hongbo, D. (2026) · IEEE Access · doi:10.1109/access.2026.3656532
Research on Improvement Methods for YOLOv5s Based on Gaussian Decay
Liu, Z., Zhang, X., LIANG, Y., et al. (2025) · International Conference on Electronic Information Engineering and Computer Technology (EIECT) · doi:10.1109/eiect68017.2025.11331828
“In 2016, Joseph Redmon introduced the YOLO algorithm, revolutionizing object detection through bounding box recognition [5].”
PCB Defect Detection Based on MGW-YOLOv11n
Nie, S., Wu, Y., Xu, Q., et al. (2025) · International Conference on Electronic Information Engineering and Computer Technology (EIECT) · doi:10.1109/eiect68017.2025.11332064
“Single-stage methods, such as the YOLO series (YOLOv1–YOLOv9) [11–15], RetinaNet [16], and SSD [17], prioritize computational efficiency by directly predicting object bounding boxes and class probabilities in a single forward pass.”
Interpretable Fault Diagnosis Method for Power Equipment Based on Improved Deep Learning
Zhang, Y., & Xu, Y. (2025) · doi:10.1109/icocta66834.2025.11337308
“Currently, deep learning object detection models such as Faster R-CNN [1] and YOLO [2] series are extensively utilized for UAV power equipment fault diagnosis owing to their exceptional detection precision.”
Jiang, N., Chen, M., Zhang, Z., Lin, Z., Zhu, L., Li, X. L., & Zhang, X. (2025) · International Conference on Electronic Information Engineering and Computer Technology (EIECT) · doi:10.1109/eiect68017.2025.11331738 · Cited by 1
“Therefore, single-stage detectors, epitomized by the YOLO (You Only Look Once) [5] series, have become the mainstream approach in this field due to their excellent balance between speed and accuracy.”
Research on Accident Investigation Report Layout Analysis Method Based on YOLOv10
潘, 令. (2026) · Computer Science and Application · doi:10.12677/csa.2026.161025
CASC-YOLO: Context-Aware Self-Convolution Attention Enhanced YOLO for Traffic Scene Object Detection
Song, Y. (2025) · International Conference on Electronic Information Engineering and Computer Technology (EIECT) · doi:10.1109/eiect68017.2025.11331889
Blockly–ROS Platform for Libras-Based Robotic Navigation with Emphasis on Laterality Training
Holtz, A. G., Pinel, G. S. F., & Brandao, A. S. (2025) · doi:10.1109/icar65334.2025.11338740
“Models like YOLOv8n can perform detection and classification at around 30 FPS on embedded GPUs, maintaining a mean average precision (mAP) above 90% for static gesture datasets [13], [14], making them suitable for educational applications that require fast and accurate responses [15], [16].”
PLD-YOLO: A Lightweight Nectarine Recognition Model in Complex Environments
Cao, Y., & Lu, X. (2025) · International Conference on Electronic Information Engineering and Computer Technology (EIECT) · doi:10.1109/eiect68017.2025.11331612
“The second category is the single-stage approach, exemplified by the YOLO family [7].”
Arioka, K., & Sawada, Y. (2026) · IEEE Access · doi:10.1109/access.2026.3656530 · Cited by 1
An Improved Yolov11 Model for Small Object Detection in Unmanned Aerial Vehicle Aerial Images
Wu, W.-C., Xian, H., & Yan, T. (2025) · 2025 International Conference on Algorithms, Data Mining, and Information Technology (ADMIT) · doi:10.1109/admit67050.2025.11337086
“Compared to traditional two-stage detection methods such as Faster R-CNN[6], one-stage algorithms like the YOLO[7]-[10] series, SSD[11], and RetinaNet[12] offer simpler structures, higher computational efficiency, and stronger end-to-end optimization capabilities.”
PASF-YOLO: A Better Real-Time Detector for Aerial Images
Yu, J., Yi, G., Gao, X., Zhang, S., & Guo, P. (2025) · International Conference on Robotics and Computer Vision (ICRCV) · doi:10.1109/icrcv67407.2025.11349323
“Currently, YOLO [2] and FCO [3] are the mainstream frameworks for state-of-the-art real-time object detection.”
MDS-YOLO: Small Target Detection Algorithm in UAV Aerial Images Based on Multi-scale Feature Fusion
Shi, H., Chen, S., Xu, W., et al. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-5764-6_9
YOLO with Gradient-Aware Dynamic Detection Head for Dense Small Object Detection in Complex Scenes
Cun, X., & Ding, Y. (2025) · International Conference on Robotics and Computer Vision (ICRCV) · doi:10.1109/icrcv67407.2025.11349196
“CNNs[3] and their variants (including YOLO[4], SSD[5] and Faster R-CNN[6]) have enhanced detection accuracy and speed through automatic feature learning.”
Haze-Resistant Multi-Scale Fusion Object Detection Network for Road Scenes
Xiao, Y., Bai, H., Yang, Z., Liu, Q., Wang, H., & Sun, J. (2025) · International Conference on Electronic Information Engineering and Computer Technology (EIECT) · doi:10.1109/eiect68017.2025.11331811
“Liu et al.[4] integrated a fully differentiable image processing module with YOLOv3[5], improving accuracy under fog and low light but introducing noise.”
Crowd Detection in Dense Scenes Based on Deformable DETR
Ma, S., & Zhou, H. (2025) · International Conference on Robotics and Computer Vision (ICRCV) · doi:10.1109/icrcv67407.2025.11349221
Enhanced YOLOv8 Model for Damage Detection of Power Transmission Lines in UAV Inspections
Wang, R., Wu, W., Zhang, W., Chen, Z., & Liang, M. (2025) · International Conference on Information Communication and Signal Processing (ICICSP) · doi:10.1109/icicsp66564.2025.11338278
“Prominent one-stage detectors include YOLO [11] and SSD [12].”
Real-Time Surface Defect Detection and Hardness Prediction in Metals Using YOLOv8
Rajeshkumar, S., Arul, M., Harini, M., et al. (2025) · doi:10.1109/iceamst67459.2025.11335630
“The YOLO (Real time object detector) family affords live defect identification through a single-stage pipeline forecasting both object regions and probability estimates in single stage [11].”
YOLO Model Driving Intelligent Innovation in Ecological Environment Design
Yu, L. Z., Liu, Q., & Zhang, W. (2025) · International Conference on Intelligent Design (ICID) · doi:10.1109/icid67979.2025.11351495
“The early YOLOv1 architecture comprised 24 convolutional layers followed by two fully connected layers [1].”
InfluentialEvidence Theory Based Confidence Fusion for Multi-Sensor 3D Object Detection
He, Y., Yu, M., Zhang, J., et al. (2025) · IEEE International Conference on Control, Electronics and Computer Technology (ICCECT) · doi:10.1109/iccect64621.2025.11339807
“In perceptual techniques, classical object detection algorithms such as Yolo [1], SSD [2] etc. take a single image as input to the detection model.”
Efficient Visual Fault Detection of Side Components in Freight Trains Based on Deep Learning
Bian, Z., & Wang, S. (2025) · IEEE International Conference on Control, Electronics and Computer Technology (ICCECT) · doi:10.1109/iccect64621.2025.11339537
“The YOLO [5] object detection algorithm follows a single-stage detection approach, where the input image is first resized and directly processed by a convolutional neural network (CNN) for feature extraction.”
FReID: advancing small-target object detection with feature reintegration and distribution
Miao, Z., Zhang, Q., He, M., Li, Y., Bi, X., Wang, J., & Hou, Q. (2026) · The Journal of Supercomputing · doi:10.1007/s11227-025-08143-4
“To enhance the detection performance of target detection models, researchers have exhaustively explored CNN-based architectures, ranging from the two-stage detection method exemplified by Faster R-CNN [20–22] to the one-stage detection approach of the YOLO series[2, 23–29].”
Mou, L., Chen, X., & Xiao, X. K. (2025) · International Conference on Cyber-Physical Social Intelligence (ICCSI) · doi:10.1109/cpsi66656.2025.11343903
“Convolutional Neural Networks (CNNs) are widely used in computer vision tasks, such as image classification [1], [2], object detection [3], [4], image segmentation [5], [6], and natural language processing [7], [8].”
Preventing Elderly Injuries: A Pose-Based Framework for Fall Detection
Longarini, L., Rongoni, A., Dragoni, A. F., Pompei, G., & Prist, M. (2025) · IEEE International Conference on Metrology for eXtended Reality, Artificial Intelligence and Neural Engineering (MetroXRAINE) · doi:10.1109/metroxraine66377.2025.11340043
“In this area, methods based on models such as OpenPose [3] and variants of the You Only Look Once (YOLO) [4] algorithm adapted for real-time extraction of human body keypoints [5], [6] have been proposed.”
Intelligent Hierarchical Early Warning System for Power Construction Sites Based on Improved YOLO11
Yang, S., Liang, Y., Wang, L., et al. (2025) · International Conference on Electronic Engineering and Informatics (EEI) · doi:10.1109/eei67650.2025.11334962
“Deep learning has achieved significant progress in the field of object detection, from early two-stage detectors like the R-CNN[3] series to single-stage detectors such as the YOLO[4] series, substantially improving detection accuracy and speed.”
Bezerra, C. D. D. S., Dourado, K. E. R., Lima, A. V. S., Bezerra, C. A. V., & Batista, S. M. A. (2025) · IEEE Colombian Caribbean Conference (C3) · doi:10.1109/c366505.2025.11340214
“Theproposed architecture also demonstrates significant advantages when compared to detection-based methods such as YOLO (You Only Look Once), a well-known model for object detection tasks [5].”
Naimi, R., Dridi, I., Diallo, T., et al. (2025) · doi:10.1109/mecatronics-rem67547.2025.11349508
“Over 70% of large manufacturers have adopted Industry 4.0, with a projected $3.7 trillion impact by 2025 [11], while China advances via “Made in China 2025” [12].”
InfluentialTwo-Stage Modal Feature Enhancement for Multispectral Object Detection
Wang, T., Ren, Z., Zhang, Q., et al. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-5567-3_20
Improved YOLOv8-Based Small Object Detection Method for Traffic Scenarios
Qiao, Y., Yu, R., & Tong, N. (2025) · International Conference on Electronic Engineering and Informatics (EEI) · doi:10.1109/eei67650.2025.11334818
“Representative algorithms include the YOLO series [3-9] and SSD [10].”
AFFNet: Adaptive feature fusion network for defect detection of industrial product surface
Jia, Z., Wang, S., Zheng, J., Han, X., Tang, Y., & Sun, F. (2026) · Applied Intelligence · doi:10.1007/s10489-026-07099-z
“Early versions (YOLOv1-v3) [ 9–11] establish the fundamental architecture of backbone-neck-head networks and introduce multi-scale detection.”
Srilatha, P., Narsimhulu, P., Premchand, K., et al. (2025) · International Conference on Image Information Processing (ICIIP) · doi:10.1109/iciip68302.2025.11346371
“Similarly, a single stage detector named YOLO was proposed by Redmon et al. (2016) [8] for facilitating the real-time performance albert with trade-offs in precision.”
He, X., & Pan, X. (2026) · Aslib Journal of Information Management · doi:10.1108/ajim-01-2025-0024
Zhang, Z., Liu, G., Lu, Y., & Sun, Z. H. (2026) · Advances in Structural Engineering · doi:10.1177/13694332261420435
“Among the numerous existing algorithms, the YOLO series (Redmon et al., 2016) has garnered extensive attention due to its exceptional accuracy, real-time performance, and detection speed, making it highly suitable for dynamic, multi-object detection (Liu and Zeng, 2025).”
Genvision: Enhancing Construction Safety Monitoring With Synthetic Image Generation
Xu, J., Chen, M., & Shi, Y. (2025) · Winter Simulation Conference · doi:10.1109/wsc68292.2025.11338881
“Deep learning-based object detection models, including YOLO (You Only Look Once) (Redmon et al. 2016; Redmon and Farhadi 2017; Redmon and Farhadi 2018; Bochkovskiy et al. 2020; Jocher 2020; Li et al. 2022; Wang et al. 2023; Jocher et al. 2023), Faster R-CNN (Ren et al. 2015), and SSD (Liu et al. 2016), have been widel…”
Lightweight UAV Perspective-Oriented Personnel Detection Algorithm for Search and Rescue Operations
Liu, H. M., Tan, F., Xu, Z., et al. (2025) · International Conference on Artificial Intelligence, Virtual Reality and Visualization (AIVRV) · doi:10.1109/aivrv67401.2025.11349769
“Single-stage algorithms such as YOLO (You Only Look Once)[5] and SSD[6], as well as their improved algorithms, are widely used in various object detection tasks due to their high accuracy and speed in common scenarios.”
Cyberbullying: An Interdisciplinary Survey of the Dark Side of Social Networks
Catalano, A. A., Catalano, C., Chezzi, A., Ingusci, E., & Mainetti, L. (2025) · IEEE International Conference on Metrology for eXtended Reality, Artificial Intelligence and Neural Engineering (MetroXRAINE) · doi:10.1109/metroxraine66377.2025.11340577 · Cited by 1
Flight Path Vector Detection And Tracking Of Aircraft Display System Based On Computer Vision
Xiao, Y., Wang, H., Zheng, K., & Gao, B. (2025) · International Conference on Robotics and Computer Vision (ICRCV) · doi:10.1109/icrcv67407.2025.11349309
“Single-stage detectors such as the Single Shot MultiBox Detector (SSD) [4] and the YOLO [5] series of algorithms prioritize faster detection speeds.”
Comparative Analysis of Feature Extraction Capabilities of YOLO and YOLOv8s
Weng, Z. (2025) · IEEE International Conference on Control, Electronics and Computer Technology (ICCECT) · doi:10.1109/iccect64621.2025.11339693
“The C2f simplification strategy is experimentally validated to reduce the overfitting rate by 17.6% and improve the inference speed by 22fps on the COCO validation set when the number of modules is adjusted from the default [4,4,4] to [3,2,1].”
InfluentialPCFusion: A Unified Image Fusion Network with Perception-Driven Cross-Domain Learning
Xu, S., & Wang, G. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-5567-3_21
Zhang, R., Lei, H., Song, L., et al. (2025) · International Conference on Artificial Intelligence, Virtual Reality and Visualization (AIVRV) · doi:10.1109/aivrv67401.2025.11350470
“YOLO [8], introduced in 2016, is a real-time object detection framework based on single-shot forward propagation.”
ChebSpec-Net: Linear Spectral Graph Restoration for UHD Images
Su, X., Zheng, Z., Chao, J., et al. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-5682-3_9
Detection of urban antispaces using deep learning in northern border cities of Mexico
Martínez-López, J. A., de-la-Torre-Gutiérrez, H., & Hernandez-Lopez, F. J. (2026) · Multimedia Tools and Applications · doi:10.1007/s11042-026-21190-0
Benchmarking of YOLO Variants for Robust Small Object Detection
Kalra, S., & Ghose, U. (2025) · International Conference on Image Information Processing (ICIIP) · doi:10.1109/iciip68302.2025.11346426
“The most recent publications on small object detection from the last 12 months are given in Table [10].”
Intelligent X-Ray Inspection of Crimping Defects in Transmission Line Clamps Based on YOLOv10
Jian, W., Yunyao, W., Guangze, Z., et al. (2025) · IEEE International Conference on Control, Electronics and Computer Technology (ICCECT) · doi:10.1109/iccect64621.2025.11339838
Ma, Y., & Song, Y. (2025) · International Conference on Intelligent Design (ICID) · doi:10.1109/icid67979.2025.11351411
“The YOLOv11 algorithm integrates various advanced techniques, including CNN architectures, attention mechanisms, and data augmentation strategies such as Mosaic data augmentation, Batch Normalization, and DropBlock [4-6].”
Yahia, M. A. B., Dridi, I., Azizi, M. K., et al. (2025) · doi:10.1109/mecatronics-rem67547.2025.11349595
“Algorithms such as OpenCV, YOLO (You Only Look Once), and OpenPose are well suited for posture and motion monitoring in VR-based training systems [10], [11].”
Towards Effortless Brain-Computer Interaction: An SSVEP-Based BCI with Object Detection in FPV
Omer, K., & Monteriù, A. (2025) · IEEE International Conference on Metrology for eXtended Reality, Artificial Intelligence and Neural Engineering (MetroXRAINE) · doi:10.1109/metroxraine66377.2025.11340457
“For real-time frame processing and object detection, we employed YOLOv5 [23], a deep learning model fine-tuned on a set of predefined objects commonly encountered in assistive robotics scenarios (e.g., bottle, book, laptop, screen).”
Fatehi, F., Azadpour, A., & Akhijahani, H. S. (2026) · Smart Agricultural Technology · doi:10.1016/j.atech.2026.101832
Li, S., Nie, C., Yang, S., et al. (2025) · International Conference on Cyber-Physical Social Intelligence (ICCSI) · doi:10.1109/cpsi66656.2025.11343935
“One-stage detectors such as YOLO [3,4,5] and SSD [6] directly predict object categories and locations, offering faster speeds more suitable for resource-constrained drone platforms.”
Lu, Z. (2025) · IEEE International Conference on Control, Electronics and Computer Technology (ICCECT) · doi:10.1109/iccect64621.2025.11339851
“You Only Look Once (YOLO) [9] is a widely used object detection model, and its latest version, YOLOv8 [10], introduced by Ultralytics in 2023, has expanded its application across various tasks.”
Research on the application of visual inspection algorithm in SMT solder joint defect detection
Chen, Z., Lei, W., Jiang, Y., et al. (2025) · IEEE International Conference on Control, Electronics and Computer Technology (ICCECT) · doi:10.1109/iccect64621.2025.11339549
“Existing defect detection equipment is often costly and bulky, making it unsuitable for small and medium-sized enterprises[1].”
An Intelligent Adaptive Traffic Management System Using Real-Time Data and Deep Learning
Pise, G. S., Kamble, Y., Kanawade, V. R., et al. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-14706-6_13
魏, 裕. (2026) · Journal of Image and Signal Processing · doi:10.12677/jisp.2026.151012
YOLOv8-SF: A Chip Defect Detection Model Based on Improved YOLOv8
Yuan, Q. (2025) · IEEE International Conference on Control, Electronics and Computer Technology (ICCECT) · doi:10.1109/iccect64621.2025.11339669
“Common object detection models are divided into two categories: two-stage detection models, such as Fast R-CNN [5], Faster R-CNN [6], and Mask R-CNN [7]; and single-stage detection models, such as SSD [8] and YOLO [9].”
AI on Patrol: An Intelligent System for Helmet Detection and Traffic Enforcement
Kumar, C. A., Kumar, K. A., & Ramsai, J. (2025) · doi:10.1109/iciteics64870.2025.11341259
“In our case, we spent significant time annotating images, labelled each image [6], and that the motorcyclists were wearing a helmet or not wearing a helmet.”
Detección de dos Enfermedad en yuca utilizando YOLOv11
Gordón, O. A. L., Paredes, S. E. M., Castillo, W. E. M., et al. (2026) · Revista Científica Multidisciplinar G-nerando · doi:10.60100/rcmg.v7i1.914
Kurniawan, C., Suvittawat, N., & Soh, D. W. (2026) · Technologies · doi:10.3390/technologies14010075 · Cited by 1
“The first YOLO algorithm was the first one-stage model to achieve true real-time object detection, and was introduced by [47] in 2015.”
Han, X., Wang, W., Zhao, K., et al. (2025) · International Symposium on Computer Science and Intelligent Control (ISCSIC) · doi:10.1109/iscsic67494.2025.11351972
“Compared with other single-stage detection algorithms (such as YOLOv5[8], SSD[9]), the YOLOv8 algorithm has stronger adaptability to small targets and complex environments.”
Ovegård, M., & Valentinsson, D. (2026) · Fisheries Research · doi:10.1016/j.fishres.2026.107666
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.