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 46,901–47,000 of 51,399
An edge-compute machine-vision system for measuring billet length on a mill conveyor
Wixted, B., Busch, A. W., & Bartels, R. (2026) · Sugar Industry international · doi:10.36961/si34201
Improved Faster R-CNN for Aircraft Detection in SAR Images
Wei, J., Xia, Z., Fan, M., Wang, Y., & Huo, W. (2025) · International Conference on Signal Processing Systems (ICSPS) · doi:10.1109/icsps66615.2025.11347873
“In contrast, single-stage algorithms, including SSD [9] and the YOLO series [10], directly predict target categories and bounding boxes through a single forward propagation, eliminating the need for region proposal generation.”
SLR-Net: Lightweight and Accurate Detection of Weak Small Objects in Satellite Laser Ranging Imagery
Zhu, W. B., Hu, J., Gong, W., et al. (2026) · Sensors · doi:10.3390/s26020732
“…architecture (e.g., Faster R-CNN [17]) that pursues high precision via a “coarse-to-fine” strategy; the one-stage architecture (e.g., YOLO [18–20]) that models detection as a regression problem to balance efficiency; and the Transformer paradigm (e.g., DETR [21]) that introduces…”
HFFN: Hierarchical feature fusion network for RGB-infrared object detection
Zhang, J., Gao, M., Wang, Y., Li, C., Fang, D., & Wei, Z. (2026) · Infrared Physics & Technology · doi:10.1016/j.infrared.2026.106429 · Cited by 4
Harshitha, K., Anees, M., Rajesh, K. R., et al. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-15401-9_2
Optimised light sources reduce nocturnal insect attraction at railway stationsPreprint
Ludreschl, C., Kirse, A., Hartke, T. R., Bhansali, S., Bourlat, S. J., Ott, D., Bott, F., Rutte, D., Siemt, P., Espeland, M., et al. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6126581
Irwan, Z., Yang, C.-K., & Lai, Y.-C. (2025) · International Conference on Signal Processing Systems (ICSPS) · doi:10.1109/icsps66615.2025.11347625
“Recent advancements in deep learning, particularly real-time object detection models like You Only Look Once (YOLO), offer promising solutions for automated weed detection [3,4].”
Enhancing Shared Vehicle Management with AI: A Study on Interior Damage Detection Models
Dixe, S., Loureiro, C., Miranda, B., Ferreira, D., Aston, T., Fernandes, D., & Peixoto, H. (2025) · Experiment@International Conference · doi:10.1109/exp.at2565440.2025.11348472
“Models like Faster R-CNN [6], SSD [7], and variants of the YOLO family [8], [9] are widely used in object detection applications due to their real-time efficiency.”
On-shelf availability (OSA) detection using machine learning approach
Das, B. B., Desu, D. S. S., Jupalle, R. K., & Ram, S. K. (2026) · Multimedia Tools and Applications · doi:10.1007/s11042-026-21323-5
“The paradigm shifted with single-shot detection methods where Redmon et al. [11] introduced YOLO for object detection, showcasing its advanced applications compared to Faster R-CNN.”
TrafficMan: Bridging Vehicle Detection, Tracking, and RL for Intelligent Traffic Management
Gupta, M. P., Malhotra, P., & Patidar, S. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-15401-9_3
Hand Gesture Detection for Sign Language Using YOLO11 Architecture
Shradha, K., Hegde, C., Bevoor, K., et al. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-14041-8_15
Mkechera, R., & Dahiya, S. (2026) · Environmental Monitoring and Assessment · doi:10.1007/s10661-026-14979-x · Cited by 4
“…the Single Shot MultiBox Detector (SSD) (Lee & Park, 2020; Liu et al., 2016; Zhang et al., 2022), You Only Look Once (YOLO) (Redmon & Farhadi, 2018; Redmon et al., 2015), and region-based convolutional neural network (RCNN) (Girshick et al., 2013) have been involved much in improving the detection…”
Wang, S., Wang, Q., Gao, Y., et al. (2025) · International Symposium on Computer Science and Intelligent Control (ISCSIC) · doi:10.1109/iscsic67494.2025.11351987
“Representative algorithms include YOLO and SSD [9], [10].”
Image Captioning Method Based on a CNN-Transformer Hybrid Architecture with Attention Mechanism
He, X., Xu, Y., & Xie, J. (2025) · International Conference on Big Data and Internet of Things (BDIOT) · doi:10.1145/3779153.3779163
“Meanwhile, object detection frameworks such as YOLO [2] have been integrated to enhance regional awareness, yet they still struggle with generating linguistically coherent captions.”
InfluentialYagoda-Aharoni, D., Dotan, E., Dudaie, M., et al. (2026) · Cytometry Part A · doi:10.1002/cytoa.70008
An Improved Lightweight YOLOv8 Algorithm for Traffic Sign Detection
Liu, Y. (2025) · IEEE International Conference on Power, Intelligent Computing and Systems (ICPICS) · doi:10.1109/icpics66386.2025.11347341
“In contrast, one-stage regression-based algorithms, such as SSD [1] and YOLO [2], offer higher efficiency.”
Research on Lane Recognition and Path Planning of Autonomous Vehicles Based on Improved YOLOv8
Yao, Q., Cao, Y., Liu, L., et al. (2025) · IEEE International Conference on Power, Intelligent Computing and Systems (ICPICS) · doi:10.1109/icpics66386.2025.11347096
“The YOLO series regards lane detection as a specific target detection task, and YOLOv5 Lane achieves a 30ms inference speed through preset anchor box optimization, but has a higher missed detection rate for dense small targets [10] (such as dashed lines).”
Accurate Monitoring of the Slagging during Converter Tapping
Pang, S., Liu, J., Yan, M., Zhang, X., Li, Q., Luo, Q., & Li, W. (2025) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc58881.2025.11343691
“To address the limitations of R-CNN-based and DETR-based object detection algorithms in industrial applications, the YOLO series [10 – 13] has been widely adopted across various industrial scenarios.”
Liu, S., & Zheng, L. (2025) · International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP) · doi:10.1109/iccwamtip68645.2025.11352658
“The YOLO series, a landmark framework for single-stage object detection, was first proposed by Redmon et al. [9] in 2015.”
Research on Intelligent Identification of Transmission Tower Bolts Using Improved YOLO Algorithm
Guo, K., Gu, Z., & Jia, P. (2025) · IEEE International Conference on Power, Intelligent Computing and Systems (ICPICS) · doi:10.1109/icpics66386.2025.11347385
“As an important version of the YOLO series [4,5], YOLOv5 performs well in target identification tasks, and has the advantages of lightweight model, fast reasoning speed, and easy deployment.”
Wu, X., Zhong, W., Zhang, J., Wang, G., Fu, Y., Xu, Y., Yang, Y., & Wang, P. (2025) · IEEE International Conference on Power, Intelligent Computing and Systems (ICPICS) · doi:10.1109/icpics66386.2025.11347314
“For instance, bolts on transmission line towers, as typical small targets, are often small in size, have indistinct features, and are frequently mixed with complex backgrounds (e.g., trees, buildings), significantly increasing detection difficulty [5].”
YOLO-CCOF: An Algorithm for Aluminum Defect Detection Based on Improved YOLOv8
Han, J., Ding, Y., Chen, H., et al. (2025) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc58881.2025.11342845
Ghaffar, F., Khan, B., Jalali, S. M. J., & Lim, C. P. (2025) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc58881.2025.11343042
“In 2D detection, architectures such as Faster R-CNN [21], YOLO [22], and CenterNet [23] have achieved strong performance.”
Tian, H., Zou, P., Zhang, A., Chen, R., Bai, H., Zhao, W., Fan, Q. N., & Chang, G. (2026) · Animals · doi:10.3390/ani16030410
“The resulting annotations were then converted to a format compatible with deep learning models, such as COCO [25] or YOLO [26].”
Comparison of Low-Cost Object Detection Models for Character Product Image Detection from SNS
Funada, M., & Sakurai, Y. (2025) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc58881.2025.11342703
“Redmon et al. [5] introduced YOLO as a novel approach to object detection.”
Liu, X., & Liu, W. (2025) · IEEE International Conference on Power, Intelligent Computing and Systems (ICPICS) · doi:10.1109/icpics66386.2025.11347340
“From YOLOv1-v3 (2016-2018) [2-4], which pioneered the single-stage detection paradigm (45 FPS, small object AP only 12%), to YOLOv4-v5 (2020-2021) [5-6], which introduced CSPNet and PANet for improved feature fusion (COCO mAP 44.5%, 86M parameters), and up to YOLOv6-v8 (2022-2023) [7-9], which…”
InfluentialFood-YOLO: An Improved Food Detection Algorithm based on YOLOv9
Zhu, Y., & Dib, O. H. (2025) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc58881.2025.11342896
“Despite advances in computer vision [4], mainstream object detectors such as SSD [5], Faster R-CNN [6], Reti-naNet [7], Deformable DETR [8], and various YOLO series [9] have not fully addressed these domain-specific difficulties.”
Visão Computacional Aplicada à Identificação e Segmentação de Animais: Uma Revisão da Literatura
Antunes, L. J., Santos, M., Cunha, H. S., & Silva, J. S. (2025) · doi:10.5753/eri-mt.2025.17241
“Os detectores de um estágio ( One-Stage ), como o YOLO ( You Only Look Once ), proposto por Redmon et al. (2016), e o SSD ( Single Shot MultiBox Detector ), de Liu et al. (2016), tratam a detecção como um problema de regressão, prevendo as caixas delimitadoras e as classes diretamente em uma única…”
Wang, L., & Zhou, Y. (2025) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc58881.2025.11343405
“In contrast to two-stage algorithms, one-stage algorithms exemplified by YOLO [19](You Only Look Once) and SSD (Single Shot MultiBox Detector) [20]directly predict the locations and classes of objects in the images without generating candidate regions, greatly accelerating the detection speed.”
Efficient Cattle Tracking in Aerial Videos Using YOLO11n and Lightweight Algorithms *
Leal, I., Gonçalves, A. J. R., Benjamín, M., Rabelo, R., & Veloso, R. (2025) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc58881.2025.11342485
“Detection algorithms can be divided into two main groups: two-stage detectors, such as Faster R-CNN and Mask R-CNN [4], [6], which prioritize accuracy; and single-stage detectors, such as SSD and the YOLO series [8], [7], which offer greater speed and computational simplicity.”
Improving Real-Time End-To-End Object Detection with Cross-Feature Interaction
Ge, J., Huang, B., Lv, J., & Wang, M. (2025) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc58881.2025.11343447
Zhou, C., Wu, L., Kan, Z., & Wang, H. (2026) · IEEE Access · doi:10.1109/access.2026.3658620 · Cited by 2
A Modular Approach to Autonomous Vehicle Prototyping with Real-Time Performance Assessment
J, A. N. P., Tiju, N. E., Sriram, P. L., et al. (2025) · doi:10.1109/icrm66809.2025.11349053
Fixing Broken Graphs: LLM-Powered Automatic Code Optimization for DNN Programs
Wang, H., Sui, Y., Xie, Y., Liu, Y., Sun, Y., Shi, C., & Zhang, Y. (2025) · IEEE/ACM International Conference on Automated Software Engineering (ASE) · doi:10.1109/ase63991.2025.00144 · Cited by 1
FCD-YOLO: An Accurate and Efficient Method for Underwater Object Detection
Yang, Z., Zhang, J., Li, M., et al. (2025) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc58881.2025.11343160
AI-Based Image Inspection System for Automated Aero-Engine Damage Detection
Srinivasan, R., Dhavale, S., & Agrawal, P. (2025) · doi:10.1109/icrm66809.2025.11349055
“This system uses a custom-trained object detection model [5], [6] like YOLOv8 model [7], [8], [9] and contour extraction [10] methods to detect, classify, and measure damage during inspections.”
Low-Light Object Detection Using YOLOv8 with Zero-DCE-Based Image Enhancement
Saravanan, G., & Naveen Prasad, S. (2025) · doi:10.1109/icrm66809.2025.11349035
“Redmon et al. [14] have introduced YOLO, a unified object detection method that processes the entire image in a single pass enabling real-time detection with high speed and accuracy along with good efficiency.”
Intelligent Guidance for the Visually Impaired: A Wearable Smart Helmet System
Zhang, J. Z. H., Duan, Z., Yu, M., & Chen, W. (2025) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc58881.2025.11342932
“The emergence of object detection networks such as Faster R-CNN[13], SSD[14], and YOLO[15], among others, has made accurate obstacle detection possible.”
Huang, L. (2025) · IEEE International Conference on Power, Intelligent Computing and Systems (ICPICS) · doi:10.1109/icpics66386.2025.11347175
“One-stage frameworks (single shot multibox detector (SSD) [4] and you only look once (YOLO) [5]) balance speed and accuracy through end-to-end designs but exhibit weaknesses in multi-scale feature fusion and occlusion handling.”
Lei, D., Zhao, B., Mao, Y., Li, W., & You, D. (2025) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc58881.2025.11343512
“Unlike two-stage methods, single-stage models like YOLO [7] and SSD [8] integrate detection into a unified network that simultaneously predicts object categories and bounding boxes.”
SkyNet: An Extensible Edge-Cloud Collaborative Framework for Robots in Long-Horizon Tasks
Jiang, X., Wang, G., Lu, R., & Tang, S. (2025) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc58881.2025.11342935
“Traditional robots employ mature technologies to perform basic tasks [10], [2].”
YOLO-ESS: Improved Citrus Recognition under Natural Orchard Conditions
Jing, H., Fan, R., Hong, L., et al. (2025) · IEEE International Conference on Sensing, Diagnostics, Prognostics, and Control (SDPC) · doi:10.1109/sdpc68151.2025.11347840
“Typical representatives include SSD (Single Shot Multibox Detector)[9] and the YOLO (You Only Look Once) series[10][11][12].”
DSK-YOLO: Feature-level Super Resolution Boosted Industrial Defect Detection
Mu, M., Liu, M., Zhang, S., & Du, S. (2025) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc58881.2025.11343713
“Due to their suitability for these requirements, lightweight real-time detection methods, such as the YOLO series [4]–[8], have been widely adopted.”
Lightweight and Dynamic Content-Augmented Object Detection for UAVs
SadeghiBakhi, M., Leung, H., & Wang, X. (2025) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc58881.2025.11342542
“In contrast, one-stage detectors like YOLO [13] and SSD [12] predict object classes and locations in a single pass, offering faster inference with a slight trade-off in accuracy.”
Two-Stage Fire Detection and Analysis Method Based on the Collaboration of Large and Small Models
Cao, Y., Hou, Y., Cao, Y., Chen, R., Cheng, Q., Ma, Y., Zhang, Y., & Zhao, Z. (2025) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc58881.2025.11343355
“…of the two-stage approach lies in that a single model struggles to balance efficient detection with intelligent analysis: small models (like YOLO[1]) have strong real-time performance but limited reasoning capabilities, while large models (such as multimodal large language models) possess…”
Prasad, G., P., G., Dath, G. A., et al. (2025) · International Conference on Robotics and Mechatronics · doi:10.1109/icrm66809.2025.11349086
“The massive use of groundwater for irrigation in countries such as Bangladesh, China, India, and the US has led to the catastrophic depletion of key aquifers [5].”
王, 少. (2026) · Open Journal of Transportation Technologies · doi:10.12677/ojtt.2026.151009
A Lightweight YOLOv9 Agricultural Detection Algorithm Based on GhostConv and Coordinate Attention
Zeng, G., Chen, J., Siyu, et al. (2025) · IEEE International Conference on Power, Intelligent Computing and Systems (ICPICS) · doi:10.1109/icpics66386.2025.11347439
“The YOLO series has evolved from YOLOv1 [5] to YOLOv9, which introduces dynamic feature learning and lightweight attention mechanisms to achieve a better trade-off between accuracy and inference speed.”
Small Target Detection of Ships in SAR Imaging Based on Improved DETR Algorithm
Lv, X., & Kan, F. (2025) · IEEE International Conference on Power, Intelligent Computing and Systems (ICPICS) · doi:10.1109/icpics66386.2025.11347247
“Double stage object detection algorithms such as R-CNN [6], FastR-CNN [7], Faster R-CNN [8], etc. Single stage object detection algorithms are divided into algorithms such as SSD [9], YOLO [10] series, etc.”
Gaeta, R., Corradini, F., Santo, M. D., et al. (2025) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc58881.2025.11342578
“Of all the methods, YOLOv3 [21] [22] was identified as the best.”
Research on CenterNet-Based Rotated Object Detection Algorithm for Remote Sensing Images
Zhao, Z., & Yao, Z. (2025) · International Workshop on Advanced Algorithms and Control Engineering (IWAACE) · doi:10.1109/iwceaa68605.2025.11352326
“Redmon et al. [4] proposed the YOLO in 2016, which performs bounding box prediction and classification on the top-level feature map and is the first algorithm capable of real-time detection.”
A Shiitake Mushroom Fruiting Body Detection Method Based on Multi-Modal Feature Fusion
Wang, F., Wang, X. R., Lv, X., et al. (2025) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc58881.2025.11343667
“With the rapid advancement of deep learning and computer vision technologies, a variety of efficient object detection algorithms have emerged, including Faster R-CNN [6], SSD [7], Mask R-CNN [8], and YOLO [9]-[10].”
Geotagging Based Automated Tree Counting using Aerial Imaging From Drone
Diwani, D., Pawar, H. M., Ambulkar, S. S., et al. (2025) · doi:10.1109/inspect67393.2025.11350608
“YOLO11 [10] [11] was used for detection with a confidence threshold of 0.3.”
InfluentialMdimegh, I., Hamzaoui, M., Bouzidi, M., Kasmi, R., Zghibi, A., & Zouari, F. (2025) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc58881.2025.11342836
“Subsequently, in order to detect the chessboard, we used a YOLOv11 model (You Only Look Once) and fine-tuned it on over 10,000 images to reach 90% accuracy for corner detection [20].”
Specific Proposal Feature R-CNN with Hybrid-Residual Feature Pyramid Network
Yao, X., Pan, Y., Li, Q., & Liu, L. (2025) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc58881.2025.11343490
“One stage detectors, such as YOLO series [12] and SSD series [13].”
HyT-Pose: Accurate Pose Estimation by Iteratively Fusing Global and Local Context
Liu, Y., & Pan, J. (2026) · IEEE Access · doi:10.1109/access.2026.3658675
A Multi-Modal Semantic Fusion for UAV Detection Under Intense Illumination Background
Chen, H., Qu, Y., Pan, G., et al. (2025) · doi:10.1109/wcsp68525.2025.1010393
“Among these, vision-based approaches, typically built on deep learning-based detectors including YOLO [10], SSD [11], and Faster R-CNN [12], exhibit lightweight structures and high inference efficiency in well-lit, clutter-free environments.”
StrawDet-YOLO: A Real-Time and High Precision Object Detection for Strawberry
Hu, Y., Jiang, X., & Guan, J. (2025) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc58881.2025.11343179
YOLO-BT: A High-Performance Framework for Accurate Brain Tumor Detection and Localization
Liu, J., Wan, H., & Li, J. (2025) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc58881.2025.11342474
“The YOLO (You Only Look Once) detection system [6] is renowned for its outstanding speed and efficiency in image recognition, making it a powerful tool for real-time applications.”
Efficient Weed Detection in Corn Fields Based on ESL-YOLOv8
Li, M., Li, A., Yu, J., et al. (2025) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc58881.2025.11342715
“Single-stage methods, such as YOLO [9] and SSD [10], directly predict class labels and bounding boxes from input images with high computational efficiency.”
RFA-Net: A Feature Refining-Focused Network for Aircraft Fine-Grained Recognition
Wang, J., Wu, Y., Ma, M., et al. (2026) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2026.3658231
Li, Y., Wang, Y., Feng, S., et al. (2026) · ASCE International Conference on Computing in Civil Engineering (i3CE) · doi:10.1061/9780784486443.033
Insulator Multi-Defect Detection Method Based on YOLOv8-SSL
Hu, J., & Xie, X. (2025) · IEEE International Conference on Power, Intelligent Computing and Systems (ICPICS) · doi:10.1109/icpics66386.2025.11347241
“Representative algorithms in this category include SSD [10], RetinaNet [11], and YOLO [12].”
Monocular Multiple People Tracking in Thermal Images Using Time-Series Depth Estimation
Taki, K., & Kondo, K. (2025) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc58881.2025.11343421
“For person tracking in thermal images, we proposed a basic re-identification method[6] that combines the depth information estimated by a monocular depth estimation model, MiDaS[7], with object detection algorithms known as YOLO[8] and StrongSORT[9] for tracking, rather than relying solely on conventional matching bas…”
Yuan, M., Liu, X., & Zhou, S. (2025) · IEEE International Conference on Power, Intelligent Computing and Systems (ICPICS) · doi:10.1109/icpics66386.2025.11347447
“In 2016, J. Redmon et al. [20]established the single-stage detection framework of the YOLOv1 model, which makes up of four parts: Input, Backbone, Neck, and Head.”
Detection of Strawberry Growth Status Based on Bot-Net-YOLOv7
Wang, Z., Yao, J., Chen, H., et al. (2025) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc58881.2025.11342680
“The most common object detection algorithms are Currently, the most common object detection algorithms are the Faster-CNN[5]series and YOLO[6]-[7] series and other classical algorithms.”
A Low-Cost Air Bearing based ADCS Calibration System
Foo, K. J. E., Goh, S. T., Yang, C., Wei, Y., Tissera, S. C., & Rai, A. (2026) · AIAA SciTech Forum · doi:10.2514/6.2026-0178
Xijie, Z., Jianyuan, X., Xinmiao, S., et al. (2025) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc58881.2025.11343548
“One-stage methods, like the YOLO series [17]–[19] and SSD [20], directly predict object locations and categories without intermediate candidate regions.”
Chang, K.-C., Lin, H.-Y., & Li, T. S. (2025) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc58881.2025.11343648
Few-Shot Substation Anomaly Object Detection via Variational Aggregation and Multi-Head RPN
Bi, Z., Guo, Y., Zhang, W., & Dai, D. (2025) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc58881.2025.11342620
“One-stage detectors make direct predictions of objects via neural networks [13], whereas two-stage detectors generate object proposals using RPN before performing classification and regression on these proposals [14].”
Cascade-YOLO: Enhancing Small Object Detection in Remote Sensing Imagery
Zeng, X., Wang, Y., Zhou, W., Zhang, Q., & Liu, Y. (2025) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc58881.2025.11343175
“While early deep learning-based detectors [3]- [5] improved feature learning through convolutional architectures, they remained suboptimal for small object detection due to the progressive degradation of feature representations caused by repeated convolution and pooling operations.”
Multi-scale Dynamic Dilated Transformer for UAV Real-time Ship Inspection
Miao, H., Zhang, J., Yan, J., & Zhou, J. (2025) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc58881.2025.11343529
“Object detection models such as YOLO[12], Faster R-CNN[13] and SSD[14] improve detection efficiency by combining feature extraction, object detection, and categorization within a unified network, it undergoes comprehensive end-to-end training.”
A review on brain tumor detection using machine learning
Tanuja, T., Kavitha, K. J., & Siddesh, K. B. (2025) · i-manager’s Journal on Image Processing · doi:10.26634/jip.12.3.22362
High-Precision Pipeline Defect Detection via YOLO with Asymmetric Attention Convolution
Liu, C., Wang, Z., Wu, Y., et al. (2025) · IEEE International Conference on Data Science and Computer Application (ICDSCA) · doi:10.1109/icdsca67083.2025.11350141
“In contrast, one-stage detectors, such as the YOLO [7] and SSD series [8], predict bounding boxes and classes via a single, unified network.”
Steel Surface Defect Detection Algorithm Based on DCD-YOLO
唐, 世. (2026) · Computer Science and Application · doi:10.12677/csa.2026.162035
Detection and Mitigation of Urban Heat Island Effect Using Vision-Language Models
Ayeshmantha, S. K. S., Kumara, B. D. A. N., Silva, G. M. S. S., et al. (2025) · International Conference on Advancements in Computing (ICAC) · doi:10.1109/icac69156.2025.11361519
“Recent research has shown promise in employing more adaptive, data-efficient segmentation models like YOLO [15] and Meta AI’s SAM [16].”
A Method for Detecting Defects on Heavy-Load Railway Tracks Based on the Improved YOLOv8 Model
于, 永. (2026) · Open Journal of Transportation Technologies · doi:10.12677/ojtt.2026.151015
Theocharis, T., Makris, E., Fotis, G. P., et al. (2025) · Proceedings/Proceedings - Symposium on Reliable Distributed Systems · doi:10.1109/srds69199.2025.00059
“On the server side, the frames are processed by a pipeline that applies the YOLO [4] object detection model to identify aircraft, personnel, and vehicles in real time.”
GraphReco: Probabilistic Structure Recognition for Chemical Molecules
Wang, H., Yu, Y., & Liu, J. (2026) · ChemistryOpen · doi:10.1002/open.202500537
“MolMiner [9] applies a YOLO [27] model to detect atoms and bonds and then assemble them into a molecule graph.”
SBD-YOLO: An Efficient Speed Bump Detector for Active Suspension Preview Control
Mao, R., Wu, J., Wu, Y., Wang, H., Li, J. Q., & Wu, G. (2026) · SAE International Journal of Connected and Automated Vehicles · doi:10.4271/12-09-03-0018
An Enhanced Yolov11-Based Algorithm for Real-Time Object Detection in Autonomous Driving
Wang, M. N., Jiang, Y., & Liu, B. (2025) · IEEE International Conference on Data Science and Computer Application (ICDSCA) · doi:10.1109/icdsca67083.2025.11350290
“Redmon et al. [6] reformulated detection as regression with YOLOv1, achieving 45 FPS and strong generalisation.”
A Modified YOLOv11 Algorithm for Localization of Defects in Power Line Insulators
Li, H., Sun, Y., Luo, K., et al. (2025) · IEEE International Conference on Civil Aviation Safety and Information Technology (ICCASIT) · doi:10.1109/iccasit66611.2025.11348897
“The second paradigm is the end-to-end single-stage detection framework, exemplified by the YOLO [3] series of algorithms.”
LECA: Statistical-Prior Guided Learnable Channel Attention Enhancement for Screw Detection
Li, Z., Zhang, D., Yan, L., et al. (2025) · International Conference on Computer, Internet of Things and Control Engineering (CITCE) · doi:10.1109/citce67565.2025.11360008
“Against this backdrop, object detection algorithms such as the YOLO family [2], [4] have steadily advanced, achieving a practical balance between speed and accuracy in industrial applications.”
MAE and MSE Position Loss Based on Threshold Convergence
Yin, J., Liao, X., Li, Q., Shen, B., Tian, Z., Su, Z., Ding, C., & Liu, Z. (2025) · IEEE International Conference on Civil Aviation Safety and Information Technology (ICCASIT) · doi:10.1109/iccasit66611.2025.11348920
“…is extensively applied in classification networks such as VGG[6], AlexNet[7], InceptionV3[8] and ResNet[9], segmentation networks like ImageNet[10] and UNet[11], object detection networks such as YOLO[4], as well as in related fields of machine learning such as correlation analysis and clustering.”
Agbenu, I. K. N., Tian, J., Wang, Q., et al. (2025) · International Conference on Automation, Control and Robots (ICACR) · doi:10.1109/icacr68388.2025.11360071
“The proposed approach employs a parallel dual-stream architecture that processes stereo depth estimation through a lightweight SeqStereoBackbone (86,304 parameters) and object detection through YOLOv11m concurrently [8], [9], targeting real-time performance on consumer-grade hardware.”
Designing Extremely Memory-Efficient CNNs for On-device Vision and Audio Tasks
Park, Y., Lee, J., & Lee, S. (2026) · International Journal of Computer Vision · doi:10.1007/s11263-025-02688-w
“In modern object detection frameworks, both YOLO (Redmon et al., 2016) and SSD (Liu et al., 2016) architectures achieve efficient detection through their inherently low computational complexity.”
康雯婷 (2026) · Computer Science and Application · doi:10.12677/csa.2026.162037
Occlusion-Aware Lightweight Convolutional Neural Network for Traffic Sign Recognition
Xu, L., Wan, Y., Wu, X., Yao, C., Zou, K., Wang, X., Cao, Z., Wu, J., & Wang, D. (2025) · International Conference on Computer, Internet of Things and Control Engineering (CITCE) · doi:10.1109/citce67565.2025.11360023
“Two-stage detectors like Faster R-CNN exhibit higher accuracy but require substantial computational resources [9][10] .”
Mixing Real and Synthetic Data in Neural Network Training: A Case Study Regarding Runway Detection
Daniel, G. H., Cruz, J. E. C., & Maximo, M. R. O. A. (2026) · AIAA SciTech Forum · doi:10.2514/6.2026-1773
Advanced Crack Detection Algorithm for Mine Surfaces Utilizing YOLO-RD Framework
Dong, S., An, J., Yang, J., et al. (2025) · IEEE International Conference on Civil Aviation Safety and Information Technology (ICCASIT) · doi:10.1109/iccasit66611.2025.11348720
“The YOLO (You Only Look Once) algorithm series [1-8] is well-known for its exceptional speed in processing, as well as its remarkable accuracy.”
Improving Medical Image Segmentation with Semantic Mask-Guided Diffusion Models
Ribeiro, M. C., & de Aguiar, M. S. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-15984-7_4
AI-Driven Vehicular Violation Detection Algorithm for Runway Incursion Prevention
Niu, H., Chen, W., & Wang, Q. (2025) · IEEE International Conference on Civil Aviation Safety and Information Technology (ICCASIT) · doi:10.1109/iccasit66611.2025.11348859
“Among these, the YOLO series [6-12] has gained widespread adoption in industry due to its revolutionary real-time detection ___________________________________ 979-8-3315-0374-1/25/$31.00 ©2025 IEEE capabilities and remarkable balance between accuracy and speed.”
InfluentialSafety Helmet Detection Algorithm for Enriching Context and Capturing Multi-level Features
Qi, X., & Song, Y. (2025) · IEEE International Conference on Data Science and Computer Application (ICDSCA) · doi:10.1109/icdsca67083.2025.11349891
“Object detection algorithms represented by YOLO [1-5], SSD [6], and Cascade-RCNN [7] are the mainstream algorithms in the field of deep learning.”
Huang, X., Chen, J., Zhu, Z., Zhang, X., & Wang, P. (2026) · IEEE Signal Processing Letters · doi:10.1109/lsp.2026.3659427
Research on Bearing Defect Detection Algorithm Based on Improved YOLO
Lin, S. (2025) · IEEE International Conference on Civil Aviation Safety and Information Technology (ICCASIT) · doi:10.1109/iccasit66611.2025.11348686
“As a typical representative of one-stage detection, the YOLO algorithm stands out in terms of detection speed [3].”
A Novel Integration of YOLO and Fuzzy Logic for Real-Time, High-Precision Emotion Detection
Bhattacharjee, S. (2026) · Information systems engineering and management · doi:10.1007/978-3-032-07922-0_2
Megaweeds: an Experimental Study on Weed Detection with YOLOv7 Using a Novel Dataset
Wildeboer, S., Doornbos, J., Babur, Ö., & Bennin, K. E. (2026) · Lecture notes in civil engineering · doi:10.1007/978-3-032-15375-3_11 · Cited by 1
Shirzadifar, A., Hassan, I., Maambo, H. H., et al. (2026) · Lecture notes in civil engineering · doi:10.1007/978-3-032-15375-3_4
YOLO Based Safety System for a Drill Press
Abdelkader, A. B., Mohammad, A. A., Weaver, J. M. R., et al. (2025) · IEEE International Conference on Intelligent Reality (ICIR) · doi:10.1109/icir68135.2025.11361592
“The YOLO (You Only Look Once) framework, introduced in 2016 by Redmon et al. [15], made a major enhancement to object detection by considering the object detection problem as a single regression problem instead of the traditional way as a series of region proposals followed by classification.”
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.