You Only Look Once: Unified, Real-Time Object Detection
Open accessThe DOI matches its Crossref record; 53 of the 53 references it cites were found in a registry or an index; 8 of the 25 sources its claims cite were checked for support.
Abstract
We present YOLO, a new approach to object detection. Prior work on object detection repurposes classifiers to perform detection. Instead, we frame object detection as a regression problem to spatially separated bounding boxes and associated class probabilities. A single neural network predicts bounding boxes and class probabilities directly from full images in one evaluation. Since the whole detection pipeline is a single network, it can be optimized end-to-end directly on detection performance. Our unified architecture is extremely fast. Our base YOLO model processes images in real-time at 45 frames per second. A smaller version of the network, Fast YOLO, processes an astounding 155 frames per second while still achieving double the mAP of other real-time detectors. Compared to state-of-the-art detection systems, YOLO makes more localization errors but is less likely to predict false positives on background. Finally, YOLO learns very general representations of objects. It outperforms other detection methods, including DPM and R-CNN, when generalizing from natural images to other domains like artwork.
Overview
CoChat Summary
TL;DR
YOLO reframes object detection as a single regression problem, using one convolutional network to predict bounding boxes and class probabilities directly from full images. It achieves real-time detection speeds while remaining competitive with, and complementary to, slower region-based detectors.
Key findings
- YOLO runs at 45 FPS on a Titan X GPU, and Fast YOLO runs at 155 FPS; Fast YOLO reaches 52.7% mAP on PASCAL VOC 2007, more than double prior real-time detectors, while YOLO reaches 63.4% mAP.
- On PASCAL VOC 2012, YOLO scores 57.9% mAP; combining Fast R-CNN with YOLO raises Fast R-CNN from 71.8% to 75.0% mAP on VOC 2007, a 3.2% gain.
- YOLO makes fewer background false positives than Fast R-CNN: Fast R-CNN has 13.6% background false positives among top detections and is almost 3× more likely to predict background detections than YOLO.
- YOLO generalizes better to artwork: on Picasso, YOLO gets 53.3 AP versus R-CNN’s 10.4 AP and DPM’s 37.8 AP; on People-Art, YOLO gets 45 AP versus R-CNN’s 26 AP and DPM’s 32 AP.
Methods
- Detection is modeled as a single CNN regression: the image is divided into an S×S grid; for PASCAL VOC, S=7, B=2, C=20, producing a 7×7×30 tensor of bounding boxes, confidence scores, and class probabilities.
- The base network has 24 convolutional layers followed by 2 fully connected layers; Fast YOLO uses 9 convolutional layers. Convolutional layers are pretrained on ImageNet at 224×224, then detection training uses 448×448 input.
- Training uses PASCAL VOC 2007 and 2012 for about 135 epochs, batch size 64, momentum 0.9, decay 0.0005, sum-squared error with λ_coord=5 and λ_noobj=0.5, dropout, and data augmentation.
Limitations
- The paper states YOLO imposes strong spatial constraints because each grid cell predicts only two boxes and one class, limiting nearby objects and struggling with small objects in groups such as flocks of birds.
- The paper states YOLO struggles to generalize to objects in new or unusual aspect ratios or configurations, uses relatively coarse features due to downsampling, and its loss treats small and large box errors equally; its main error source is incorrect localization.
- The paper states YOLO still lags state-of-the-art detection accuracy and struggles to precisely localize some objects, especially small ones.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Figures





Verification
Claims the paper makes
6 Valid · 8 Not valid · 15 Not checked · 92 Own results and interpretations
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“While it is much faster than R-CNN, it still falls short of real-time and takes a significant accuracy hit from not having good proposals.”
What the sources say
- Could not verifycites [20] [20] K. Lenc and A. Vedaldi. R-cnn minus r. arXiv preprint arXiv:1506.06981 , 2015. 5, 6 - sourceExperimental — accuracy not yet measured
The ConvNet-based Object Detection section identifies R-CNN minus R as a method that uses predefined regions instead of region proposals. It gives no runtime measurement or assessment of whether the method achieves real-time detection; searches for real-time performance and speed did not establish that claim. (LLM, conf=0.76)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Could not verify
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“To avoid overfitting we use dropout and extensive data augmentation.”
What the sources say
- Partly supportedcites [18] [18] G. E. Hinton, N. Srivastava, A. Krizhevsky, I. Sutskever, and R. R. Salakhutdinov. Improving neural networks by preventing co-adaptation of feature detectors. arXiv preprint arXiv:1207.0580 , 2012. 4 - sourceExperimental — accuracy not yet measured
The paper states that dropout reduces overfitting (p. 1) and describes using dropout with data augmentation for its ImageNet model (H Models for ImageNet, p. 18). It does not establish that YOLO uses either technique or describe YOLO’s augmentation as extensive. (LLM, conf=0.88)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“However, only 30Hz DPM [31] actually runs in real-time.”
What the sources say
- Supportedcites [31] [31] M. A. Sadeghi and D. Forsyth. 30hz object detection with dpm v5. In Computer Vision-ECCV 2014 , pages 65-79. Springer, 2014. 5, 6 - source
The Introduction (p.1) states that 'except for certain objects including face, pedestrians and certain rigid objects, detectors do not currently run at video rate' and that the presented architecture detects the 20 PASCAL VOC categories simultaneously at 30Hz, i.e. at video/real-time rate. The Abstract (p.1) and Table 2 (Method) bound the comparison to other DPM speed-up efforts: reference DPM at 0.07Hz, the fastest GPU 'Vanilla DPM' at ~1Hz, FTVQ at 0.53s, and 'over an order of magnitude faster than the previous fastest DPM implementation', so none of the listed variants reaches real-time. Thus our copy supports both parts of the attribution: that this 30Hz DPM runs in real-time and that it is the only such DPM among the speed-up efforts compared. (LLM, conf=0.82)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“While it is much faster than R-CNN, it still falls short of real-time and takes a significant accuracy hit from not having good proposals.”
What the sources say
- Could not verifycites [20] [20] K. Lenc and A. Vedaldi. R-cnn minus r. arXiv preprint arXiv:1506.06981 , 2015. 5, 6 - sourceExperimental — accuracy not yet measured
The ConvNet-based Object Detection section identifies R-CNN minus R and says it uses predefined regions in an SPPnet system, but gives no speed comparison with R-CNN. A search for R-CNN minus R and speed found no passage in our copy establishing that it is much faster. (LLM, conf=0.73)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Could not verify
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“While it is much faster than R-CNN, it still falls short of real-time and takes a significant accuracy hit from not having good proposals.”
What the sources say
- Partly supportedcites [20] [20] K. Lenc and A. Vedaldi. R-cnn minus r. arXiv preprint arXiv:1506.06981 , 2015. 5, 6 - sourceExperimental — accuracy not yet measured
The “ConvNet-based Object Detection” section (page unavailable) says R-CNN minus R uses predefined regions instead of region proposals. It does not say that this causes a significant accuracy loss; the paper’s discussion of low accuracy concerns a different system, naïve Faster R-CNN. (LLM, conf=0.83)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
84 more claims
Create a free account to see all 121 claims and to verify the 2 references still open.
- Probably not a substantial claim. 17
- It may state two separate claims as one. 15
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“which was not thoroughly investigated in prevIoUs work such as YOLOv1 [20] and YOLOv2 [51] employing MSE/L2 loss (Mean Squared Error).”
From Object Detection in 20 Years: A Survey (2023) · cites this paper as [20]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“the YOLO series models v2-v5 [144-147] are some of the most advanced object detection methods based on DNN, which have good performance in terms of speed and precision.”
From A survey of model compression strategies for object detection (2023) · cites this paper as [144]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“As a typical and more widely used new form of applications [9], various deep learning-based intelligent services and applications have changed many aspects of people's lives due to the great advantages of Deep Learning (DL) in the fields of Computer Vision (CV) and Natural Language Processing (NLP) [10].”
From Convergence of Edge Computing and Deep Learning: A Comprehensive Survey (2020) · cites this paper as [9]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“A convolutional neural network predicts the bounding boxes as well as class probabilities for all the objects depicted in an image.”
From Object detection using YOLO: challenges, architectural successors, datasets and applications (2023) · cites this paper as [56]
The cited source says what the claim attributes to it.
In the citing paper
“Authors of YOLO [56] have reframed the problem of object detection as a regression problem instead of classification problem.”
From Object detection using YOLO: challenges, architectural successors, datasets and applications (2023) · cites this paper as [56]
6 more claims about this paper
Create a free account to see every claim other papers make about this one.
Citations
Cites
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2577031 · Cited by 73,472
Self-citationFaster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2015) · arXiv · doi:10.48550/arxiv.1506.01497 · Cited by 70,812
Self-citationGoing deeper with convolutions
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298594 · Cited by 48,562
ImageNet Large Scale Visual Recognition Challenge
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-015-0816-y · Cited by 39,380 · cited 1×
“We pretrain our convolutional layers on the ImageNet 1000-class competition dataset [29].”
MethodHistograms of Oriented Gradients for Human Detection
Dalal, N., & Triggs, B. (2005) · 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) · doi:10.1109/cvpr.2005.177 · Cited by 33,584 · cited 2×
“Detection pipelines generally start by extracting a set of robust features from input images (Haar [25], SIFT [23], HOG [4], convolutional features [6]).”
MethodRich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
Girshick, R., Donahue, J., Darrell, T., & Malik, J. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.81 · Cited by 32,684 · cited 2×
“Then, classifiers [35, 21, 13, 10] or localizers [1, 31] are used to identify objects in the feature space.”
MethodSelf-citationGirshick, R. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.169 · Cited by 28,105
Self-citationDelving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
He, K., Zhang, X., Ren, S., & Sun, J. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.123 · Cited by 19,741 · cited 1×
“Convolutional neural networks (CNNs) achieve impressive performance on classification tasks at real-time speeds [13].”
Object recognition from local scale-invariant features
Lowe, D. G. (1999) · Proceedings of the Seventh IEEE International Conference on Computer Vision · doi:10.1109/iccv.1999.790410 · Cited by 16,472 · cited 1×
“Detection pipelines generally start by extracting a set of robust features from input images (Haar [25], SIFT [23], HOG [4], convolutional features [6]).”
MethodRobust Real-Time Face Detection
Viola, P., & Jones, M. J. (2004) · International Journal of Computer Vision · doi:10.1023/b:visi.0000013087.49260.fb · Cited by 14,097 · cited 1×
“Detectors for single classes like faces or people can be highly optimized since they have to deal with much less variation [36].”
Background
Cited by
Items 47,001–47,100 of 51,399
Advanced Object Recognition System Using YOLO and LiDAR Simulation
Rongala, P., Singh, B., Kar, A., et al. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-14197-2_5
Zhou, S., Zhang, L., & Li, Y. (2025) · IEEE International Conference on Industrial Electronics for Sustainable Energy Systems (IESES) · doi:10.1109/ieses66335.2025.11359937
“Concurrently, real-time object detection networks such as YOLO have matured in automotive environments, providing robust multi-target perception [5] [6] [7].”
An End-to-End Wind Turbine Blades Surface Damage Detection Method
Tang, L., Zhang, S., Nian, J., et al. (2025) · IEEE International Conference on Industrial Electronics for Sustainable Energy Systems (IESES) · doi:10.1109/ieses66335.2025.11359844
“YOLOv1 [12], introduced in 2016, significantly improved detection speed but had limitations in detecting small and multi-scale objects.”
Using Deep Learning to Detect Pea Root Nodules Within a Complex Soil Media Background
Akinyemi, F., Beck, M., Bidinosti, C. P., et al. (2026) · Lecture notes in civil engineering · doi:10.1007/978-3-032-15375-3_8
Alhashimi, S. A., & Al-Azzawi, A. (2026) · Springer proceedings in mathematics & statistics · doi:10.1007/978-3-032-00914-2_30
Coffee Leaves Rust Detection Using YOLOv8
Patil, A., Kulkarni, A., Patil, V., Kour, N., Joshi, A. D., & Sawant, S. T. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-10250-8_26
Kharat, R., Thepade, S., Kothawade, A., et al. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-14197-2_26
Huaqing, L. I., Chen, X. Y., Chen, Y. H., Yang, K., Li, D., He, C., & Zhou, J. (2026) · Proceedings of the Institution of Mechanical Engineers Part J Journal of Engineering Tribology · doi:10.1177/13506501261417829
“The YOLO series 19 represents a prominent class of one-stage algorithms; by reformulating detection as a regression problem, these models achieve rapid inference speeds while maintaining competitive accuracy, rendering them ideal for real-time monitoring applications.”
Das, H. C., & Brahma, J. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-14038-8_35
Patil, R. S., & Patil, S. S. (2025) · International Conference for Advancement in Technology (ICONAT) · doi:10.1109/iconat66879.2025.11362689
“Among the DL models, YOLO (You Only Look Once) has gained widespread popularity due to its speed and efficiency in real-time object detection [7], [8].”
Shi, W., Liang, H., Qian, Y., et al. (2025) · IEEE International Conference on Industrial Electronics for Sustainable Energy Systems (IESES) · doi:10.1109/ieses66335.2025.11359817
“Recent advancements in artificial intelligence and computer vision have introduced deep learning-based object detection methods that offer high detection speed and accuracy [7], [8].”
HazSense: A Multimodal RGB-D Dataset for Real-World Hazard Detection
Brahma, S., & Sayed, K. (2025) · IEEE International Conference on Intelligent Reality (ICIR) · doi:10.1109/icir68135.2025.11361555
“These models struggled with small objects and showed poor performance on partially occluded instances [13], [14].”
Advance YOLO-Based Hybrid Architecture for Gesture Recognition
Thakkar, Y., Kothadiya, D., Chaudhari, A., et al. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-14038-8_37
A Review of Small Object Detection Based on Deep Learning
Peng, X., & Jiang, H. (2025) · International Conference on Big Data Analytics and Artificial Intelligence Application · doi:10.1145/3788108.3788510 · Cited by 3
“Deep learning models such as Faster R-CNN [1], YOLO [2] and SSD [3] have performed well in most object detection tasks.”
Improved YOLOv10 Algorithm for Remote Sensing Object Detection
Wang, B., Wu, H., & Wu, Y. (2025) · International Conference on Video, Signal and Image Processing (VSIP) · doi:10.1145/3784713.3784714
“In contrast, one-stage detection algorithms, such as YOLO (You Only Look Once) [13], complete both object localization and classification through a single network, offering a significant speed advantage, making them an effective solution to meet real-time detection demands.”
Elhanashi, A., & Saponara, S. (2026) · Springer eBooks · doi:10.1007/978-981-95-4846-0_3
Training and Fine-Tuning Object Detection Models
Elhanashi, A., & Saponara, S. (2026) · Springer eBooks · doi:10.1007/978-981-95-4846-0_7
Elhanashi, A., & Saponara, S. (2026) · Springer eBooks · doi:10.1007/978-981-95-4846-0_2
Enhanced Road Object Detection for ADAS Using YOLOv8 and Hyperparameter Evolution
Bouazizi, O., Azroumahli, C., & Mourabit, A. E. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-14964-0_33
MobiTest: A Testbed for Harnessing the Computing Power of Discarded Smartphones
Tripathi, P., Dhoriya, V., Sasidhar, K., et al. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-16632-6_8
Improved Single-Stage Facial Landmarks for Real-Time Driver Drowsiness Detection
Sharma, N., Banothu, S., Shah, M., & Singh, D. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-16632-6_12 · Cited by 1
Golder, S., Sultana, H., Noman, A. A., Khan, R., Bairagi, A. K., & Debnath, R. (2026) · Multimedia Tools and Applications · doi:10.1007/s11042-026-21350-2 · Cited by 2
DL-AAT: An Automatic Annotation Tool for Efficient Data Labeling in Vision-Based Systems
Yadav, K. S., Aktar, M., Singh, S., et al. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-15809-3_32
Enhancing Real-Time Driver Drowsiness Detection: A Comparative Evaluation of YOLOv5 and YOLOv8
Ennaama, S., Silkan, H., Bentajer, A., Tahiri, A., & Ennaama, F. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-14430-0_11
Introduction to Object Detection and Localization
Elhanashi, A., & Saponara, S. (2026) · Springer eBooks · doi:10.1007/978-981-95-4846-0_1 · Cited by 1
Enhancing Human-Robot Collaboration in Disassembly Processes Through Vision-Based Hardware Detection
Soufiane, A., Mohammed, T., Mohamed, H., et al. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-14964-0_28
Navhelp: A Navigation Help Model for Visually Impaired People Using Computer Vision
Kumari, N., Jain, B., & Kaur, N. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-08859-8_19
Automated Multi-Task Deep Learning Framework for Cervical Spine Fracture Segmentation
Gou, S., Luo, A., & Li, Y. (2025) · International Conference on Intelligent Medicine and Health (ICIMH) · doi:10.1145/3784929.3784933
Exploring Real‐Time Tracking of Vocal Fold Polyps in Video‐Stroboscopy Using Deep Learning
Kaza, S., Mohanty, A. S., Serpedin, A., Yau, J., Kim, Y. E., Kutler, R. B., Elemento, O., Sulica, L., Khosravi, P., & Rameau, A. (2026) · The Laryngoscope · doi:10.1002/lary.70396
“You Only Look Once (YOLO) was developed in 2015 and demonstrated better real-time performance than all previous algorithms in object detection [16].”
Face Recognition and Expression Analysis Using YOLO11 Architecture
Pattanshetty, V. I., Pattanshetty, V. I., Pattanshetty, V. I., et al. (2026) · Lecture notes in networks and systems · doi:10.1007/978-981-95-3495-1_16
Intelligent Recognition Method and System for Power Grid Flood based on Ground Monitoring Video
Dong, S., Yue, G., Zhang, S., et al. (2025) · International Conference on Electrical Engineering and Control Science (IC2ECS) · doi:10.1109/ic2ecs68700.2025.11362058
“A robust flood scene recognition module based on the YOLO framework[6] optimized for power grid environments, capable of detecting water accumulation and submerged infrastructure.”
Multi-view and spatial-correlation interaction for multi-scale object detection
Yang, Y., Zhu, Z., Li, Z., et al. (2026) · Multimedia Systems · doi:10.1007/s00530-025-02176-8
“Single-stage detectors, such as YOLO [ 10] and SSD [ 11–13 ], further revolutionized the field by elimi - nating the need for region proposals.”
Tang, D. (2025) · IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom) · doi:10.1109/trustcom66490.2025.00158
“YOLO [26] is a series of deep learning-based object detection models.”
Chang, L., Xu, B., Zhang, X., Wang, J., Shi, T., Guo, R., & Du, Y. (2026) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2026.113997
Liu, Z., Liu, Z., Chen, Q., et al. (2025) · International Conference on Sensing, Measurement & Data Analytics in the era of Artificial Intelligence (ICSMD) · doi:10.1109/icsmd67131.2025.11365340
“YOLO (You Only Look Once) series network is a classic and excellent model for object detection [17].”
Rethinking Adversarial Robustness: The Role of Input Transformations
NGUYEN, H. T.-M., Tran, K., Phan, Q. M., & Luong, N. H. (2025) · RIVF International Conference on Computing and Communication Technologies (RIVF) · doi:10.1109/rivf68649.2025.11365037
“Deep neural networks (DNNs) have demonstrated remarkable effectiveness in solving computer vision tasks (e.g., classification, segmentation) and have been widely deployed in real-world applications [1].”
A comparative study of deep learning-based models for broiler body segmentation
Akhtari, H., Navid, H., Ghaffarnezhad, A., & Shamshiri, R. R. (2026) · Signal Image and Video Processing · doi:10.1007/s11760-025-05088-2
“YOLOv8, an advanced one-stage object identification model [44], has been successfully applied in broiler segmentation [45, 46].”
Compression-Efficient Feature Extraction Method for a CMOS Image Sensor
Kuroda, K., Osuka, Y., Iegaki, R., Ujiie, R., Shima, H., Yoshida, K., & Okura, S. (2026) · Sensors · doi:10.3390/s26030962
“To achieve high accuracy in image recognition, Deep Neural Network (DNN) models [2–6] trained with large-scale datasets [7–11] are widely utilized.”
Tran, T. D., Danh, H. M., & Hoang, L. D. (2025) · RIVF International Conference on Computing and Communication Technologies (RIVF) · doi:10.1109/rivf68649.2025.11365135
“In parallel, one-stage methods such as YOLO [11] and SSD [12] approach the problem as regression tasks, significantly accelerating processing and making them suitable for real-time applications.”
Spatial Knowledge Graph Creation and Action Prediction with Neuro Symbolic AI
Paul, D., Bhakat, A., Panda, S., et al. (2025) · International Conference on Research in Computational Intelligence and Communication Networks (ICRCICN) · doi:10.1109/icrcicn68210.2025.11364870
“The YOLO architecture by Redmon et al. [1] enabled real-time object detection suitable for embedded driving systems.”
YOLOv5-Powered Smart Parking System with IoT-Based Real-Time Slot Monitoring
Nguyen, P. L., Phan, D. T., Nguyen, T. T., et al. (2025) · RIVF International Conference on Computing and Communication Technologies (RIVF) · doi:10.1109/rivf68649.2025.11365041
“…detectors, such as the YOLO family [7], treat object detection as a single regression problem, directly predicting bounding boxes and class probabilities from the full image in one pass, thereby eliminating the need for a separate proposal stage and achieving much faster inference times [7].”
SceneScribe: IoT-Enabled AI Audio Narration for the Visually Impaired
Nadesan, J., & Hajari, N. (2025) · Conference proceedings - Canadian Conference on Electrical and Computer Engineering · doi:10.1109/ccece64018.2025.11364359
“Deep learning algorithms such as You Only Look Once (YOLO) [4] and Single Shot multi-box Detector (SSD) [5] proved to be effecive in object recogniton and can be adapted for dynamic scene understanding [6].”
Kumar, A., Singh, K., & Ahuja, S. (2025) · International Conference on Internet of Everything, Microwave Engineering, Communication and Networks (IEMECON) · doi:10.1109/iemecon69302.2025.11365880
A Survey of Deep Learning Approaches in UAV-Based Forest Monitoring
Ton-That, M.-Q., Pham, T.-T., & Ly, Q. N. (2025) · RIVF International Conference on Computing and Communication Technologies (RIVF) · doi:10.1109/rivf68649.2025.11365027
A Robust Two-Tier Computer Vision System for Energy-Efficient Fire Detection
Chen, T., Li, L., Wang, R., Wang, P., Gao, Y., & Aibin, M. (2025) · Conference proceedings - Canadian Conference on Electrical and Computer Engineering · doi:10.1109/ccece64018.2025.11364433
“One-stage detectors such as YOLO [18] and SSD [19] directly predict object location and category in one pass.”
RoadTrack: Real-Time Distant Parking Detection via Visual Geometric Projection and Speed Estimation
Yi, K., Luo, L., Xie, C., Zhu, Y., & Tian, Y. (2026) · Signal Image and Video Processing · doi:10.1007/s11760-026-05148-1
“Among them, real-time object detectors based on the YOLO (You Only Look Once) series[1] have become mainstream solutions due to their high efficiency.”
EdgeFlame: A Physics-Inspired Framework for Zero-Shot Fire and Smoke Recognition
Lee, H., & Nadeem, M. (2025) · International Conference on Automation, Robotics and Computer Engineering (ICARCE) · doi:10.1109/icarce67182.2025.11362232 · Cited by 1
HSU-YOLO: High-Precision Small Object Detection for UAV Imagery
Sun, M., Liu, Y., Zhao, X., Wang, B., & Liu, D. (2025) · International Conference on Sensing, Measurement & Data Analytics in the era of Artificial Intelligence (ICSMD) · doi:10.1109/icsmd67131.2025.11365453
“Single-stage detectors like YOLO[6] convert detection into a regression task, eliminating proposal generation for faster speeds.”
Fruit Ripeness Detection: A Comparative Analysis of State-of-the-Art YOLO Models
Minh, P. Q., Tan, L. N., Tu, N. H., et al. (2025) · RIVF International Conference on Computing and Communication Technologies (RIVF) · doi:10.1109/rivf68649.2025.11365044
“Among these, real-time object detection architectures, most notably the you only look once (YOLO) family, have gained prominence in agriculture due to their balance between speed and accuracy [6], [7].”
Hai, N. C., Hai, L. H. S., Phuc, N. M., Tu, N. H., & Anh, N. T. (2025) · RIVF International Conference on Computing and Communication Technologies (RIVF) · doi:10.1109/rivf68649.2025.11365033 · Cited by 1
“Since 2016, you only look once (YOLO) has marked a turning point in object detection by processing entire images at once and formulating detection as a regression problem, significantly increasing speed compared to traditional methods [7].”
YOLO-TrOCR: A Proposed Model for Automated Ballot Counting
Thuan, L. D., Nghia, D. M., & Ngan, N. T. H. (2025) · RIVF International Conference on Computing and Communication Technologies (RIVF) · doi:10.1109/rivf68649.2025.11365040 · Cited by 2
“YOLO can achieve higher processing speed while maintaining high detection accuracy [22, 23].”
An Edge-Oriented Approach to PCB Defect Detection with YOLOv11n
Phuoc, V. N. D., Thanh, N. D., Mai, N. H., & Nguyen, T. T. K. (2025) · RIVF International Conference on Computing and Communication Technologies (RIVF) · doi:10.1109/rivf68649.2025.11365232
“However, AOI systems are costly, rely on design files, and adapt poorly to custom or small-batch PCBs [4], [5].”
Comparative Performance Analysis of YOLOv8 and YOLOv9 for Vehicle Detection and Distance Estimation
Othmen, S. B., Farhat, W., Faiedh, H., et al. (2025) · doi:10.1109/sta66620.2025.11364934
“This design significantly increases computing efficiency, making YOLO [11] an excellent choice for safety-critical use cases, including collision avoidance, autonomous driving, and advanced driver-assistance systems (ADAS) [13].”
InfluentialLin, Z., & Vong, C. (2025) · International Conference on Electrical, Control and Instrumentation Engineering (ICECIE) · doi:10.1109/icecie66637.2025.11363835
“Methods based on Convolutional Neural Networks (CNNs), represented by the YOLO series [7], excel in real-time performance, but their intrinsic local receptive fields limit the model’s ability to effectively model global contextual information, often struggling to differentiate between small objects…”
Mourning, C., & Naravara, G. (2026) · AIAA SciTech Forum · doi:10.2514/6.2026-2262
RT-DETR Enhanced with NAS: A Hybrid Spacecraft Detection Approach
Kamra, N., & Ulrich, S. (2026) · AIAA SciTech Forum · doi:10.2514/6.2026-2925
YOLD: You Only Look Denseness for Tiny Object Detection in Aerial Images
Gao, G., Shang, Y., Gao, J., Guo, H., Dong, Y., & Li, C. (2026) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2026.3660635 · Cited by 11
A computer vision application for automatic detection of defects in urban asphalt pavement in Brazil
Borges, M. A., & Spanhol, F. A. (2025) · doi:10.5753/ssv.2025.39495
“Like every member of the YOLO family [15], YOLOv5 is a one-stage detector: object localisation and classification are completed in a single forward pass, avoiding the proposal stages required by two-stage approaches.”
Exploring deep learning for sorting shredded end-of-life wind turbine blades
Linder, C., Rechsteiner, F., & Eiler, S. (2026) · Clean Technologies and Recycling · doi:10.3934/ctr.2026005
Recognition of Pitching Habits Using Multimodal Data of RGB Video and Skeleton
Hidaka, S., & Hotta, K. (2025) · International Symposium on Multimedia · doi:10.1109/ism66958.2025.00028
“The positional information of the target person is automatically obtained using the object detection model YOLO [7], and the detected bounding boxes are used as prompts for SAM to achieve accurate segmentation of pitcher.”
Box-guided class-contextual representation learning for self-visual lung nodule detection
Zhao, K., Zhang, L., Yi, L., et al. (2026) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2026.109731
Error-free and efficient prime editing in absence of maternal PolθPreprint
Kroll, F., Serafini, M., de Barbarin, L., Vargas, J. R. A., Dang, J. T.-M., Rosello, M., As, M., Cian, A. D., Concordet, J., Giovannangeli, C., et al. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.02.02.703001
Intelligent Accident Detection and Notification System for Smart Transportation
Ahmad, F., Chauhan, A., & Kumar, P. (2025) · IEEE Global Conference for Advancement in Technology (GCAT) · doi:10.1109/gcat66372.2025.11368482
“High detection accuracy is critical for this module, leading to the use of the You Only Look Once (YOLO) [14].”
Multi-Class Personal Protective Equipment Detection for Construction Safety Using YOLOv11
Mak, W. K., Man, Y. H. K., Wong, H. W., et al. (2026) · IGI Global eBooks · doi:10.4018/979-8-3373-9245-5.ch007
Detecção de Anomalias em Pavimentos Rodoviários com Inteligência Artificial: Uma Visão Geral
Bittencourt, P. M., de Oliveira, S. S. T., Pereira, L. A., et al. (2025) · doi:10.5753/erigo.2025.17149
Low Latency Crossing Pedestrian Detection by Dynamic Vision Sensor and RGB camera
Huang, B., Allebosch, G., Willems, T., et al. (2026) · Journal of Intelligent & Robotic Systems · doi:10.1007/s10846-026-02361-5
Collision Alert System: Computer Vision for Vehicle Safety
Kirthiga, N., Damodarreddy, K., Suresh Kumar, S., et al. (2026) · ITM Web of Conferences · doi:10.1051/itmconf/20268203021
An Improved Microaneurysms Detection for Diabetic Retinopathy Screening Using YOLO
Rahim, S. S., Deo, A., Mumtaz, R., & Palade, V. (2026) · Biomedicines · doi:10.3390/biomedicines14020359
“The You Only Look Once (YOLO) algorithm, introduced by Redmon et al. [32], refor-mulates object detection as a single regression task that simultaneously predicts bounding boxes and class probabilities for each grid cell in one forward pass of a convolutional network.”
Enhancing Object Detection in Autonomous Driving With Image Preprocessing and Lidar Camera Fusion
Devi, S., Vani, V., Reddy, R. R., et al. (2025) · International Conference on Computational Intelligence and Communication Networks · doi:10.1109/cicn67655.2025.11368283
“The effectiveness of these models improved substantially compared to the traditional methods, yet it diminished in the unfavorable weather conditions when sensor data was impaired[10],[11].”
AI-Powered Complaint Validation for Vehicle Obstruction in Smart Cities
Raghav, Gupta, D., & Kumar, M. (2025) · International Conference on Computational Intelligence and Communication Networks (CICN) · doi:10.1109/cicn67655.2025.11367831
“Redmon et al. [7] introduced earlier YOLO variants, which laid the groundwork for real-time object detection.”
Guerra, M. M., & Ribeiro, L. D. A. (2025) · Escola Regional de Informática de Goiás (ERI-GO) · doi:10.5753/erigo.2025.17153
An Integrated Framework for Border Surveillance Using Hybrid Detection Models and Transformers
Saxena, S., Kaur, H., Mishra, R., Patidar, R., Tahilramani, N., & Saxena, S. (2025) · International Conference on Computational Intelligence and Communication Networks (CICN) · doi:10.1109/cicn67655.2025.11368143
“Overview of models: YOLO was introduced as a real-time, single-stage detector [2] with higher mAP than two-stage models.”
SAM-Augmented Blending for Enhanced Microplastic Detection Using YOLO11
Shaad, M. R., Hemal, M. F. M., Rhythm, F. H., & Ovi, T. B. (2025) · International Conference on Sustainable Technologies for Industry 5.0 (STI) · doi:10.1109/sti69347.2025.11367502
“YOLO provides an efficient framework for microplastic detection by enabling fast and accurate localization of small, low-contrast particles in a single image pass, making it ideal for real-time applications like on-site water monitoring or drone-based inspection [10].”
Mussabek, M., Zumanov, Z., & Amirgaliyev, B. (2025) · International Conference on Information & Communication Technology and System (ICTS) · doi:10.1109/icts67612.2025.11369565
“BR24992852 “Intelligent models and methods of Smart City digital ecosystem for sustainable development and the citizens’ quality of life improvement”). frequent false positives or missed detections due to poor generalization outside of their training domain [5], [6].”
Real-Time Crop Disease Detection on Autonomous Drones Using NCNN-Optimized YOLO Models
Shaad, M. R., Haq, A. A., Rhythm, F. H., et al. (2025) · doi:10.1109/sti69347.2025.11367585
“…encompasses a diverse range of architectures, broadly categorized into two-stage detectors (e.g., Fast R-CNN [6]), which prioritize high accuracy at the expense of computational speed, and one-stage detectors (e.g., YOLO [7]), which achieve a more favorable balance between speed and accuracy.”
Lesion-guided attention mechanism for enhanced diabetic retinopathy image classification
Shao, Y. (2026) · Multimedia Tools and Applications · doi:10.1007/s11042-026-21344-0
“Among various image classification and detection algorithms, You Only Look Once (YOLO) [ 23] has garnered acclaim for its outstanding performance in real-time detection speed and accuracy.”
CDD-YOLO11: An Efficient and Robust YOLO11-Based Way for Container Defect Detection
Zhou, C., Ren, Z., Zhang, W., Liu, J., & Liu, F. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-5758-5_23
Autonomous Driving Test Scenario Generation and Integration Using UAV-Based Visual Data
Li, T. T., Carstens, B., & Liu-Henke, X. (2025) · IEEE International Symposium on Systems Engineering · doi:10.1109/isse65546.2025.11369991 · Cited by 2
“Common object detection frameworks include Faster R-CNN [26], YOLO [27], and SSD [28], among which YOLO is particularly prevalent in traffic-related applications due to its high speed and computational efficiency.”
Low-Cost Solar Powered Real Time AI-Driven Vehicle for Security Applications
Al-Nuaimi, M., Abdulwahid, O. S., & Al‐Greer, M. (2025) · IEEE International Symposium on Systems Engineering · doi:10.1109/isse65546.2025.11369974
“The object detection module is built upon the YOLOv5 (You Only Look Once, version 5) deep learning algorithm, which offers an effective balance between accuracy and computational speed in real-time embedded scenarios [11].”
Aparicio, E. H., Ramírez, C. E., & Hernández-Reyes, J. M. (2025) · International Conference in Software Engineering Research and Innovation (CONISOFT) · doi:10.1109/conisoft66928.2025.00032
Wu, J. (2025) · International Conference on Information Management and Engineering (ICIME) · doi:10.1109/icime66598.2025.00022
“From early two-stage detection methods such as Faster R-CNN [2], to later single-stage detection methods such as the YOLO series [3,4], and then to end-to-end detection methods based on Transformer architecture such as DETR [5] and RT-DETR [6], deep learning has provided more powerful feature…”
刘, 新. (2026) · Computer Science and Application · doi:10.12677/csa.2026.162048
Repeated pattern detection on fabric: A survey and novel approach
Ayyurek, E., Marcuzzo, M., Zangari, A., Giudice, L. D., Bigaglia, G., Pistellato, M., Albarelli, A., & Gasparetto, A. (2026) · PLoS ONE · doi:10.1371/journal.pone.0340797 · Cited by 1
“Architectures like Single-Shot object Detection (SSD) [14] and You Only Look Once (YOLO) [15] focused on further reducing inference time to allow for real-time usage.”
Multi-worm Tracking with Hierarchical Cues in Complex Microenvironments
Wang, L., Jin, Z., & Shen, Q. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-5758-5_7
FMA-Det: Inter-frame Motion-Aware Network for Anti-UAV Small Target Detection
Wei, Y., Jiang, Z., Zhang, J., Wang, G., & Wang, Y. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-5758-5_24
Zhang, M., Huang, N., He, Q., Song, W., Zhang, Y., & Mei, H. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-5758-5_18
Projection Mahjong: augmenting real-world Mahjong experience
Kato, T., & Hasegawa, T. (2026) · Multimedia Tools and Applications · doi:10.1007/s11042-026-21151-7
“These approaches typically employ object detection models such as SSD [ 21 ] or YOLO [ 22] to recognize Mahjong tile regions and their types, and their recognition performance has been evaluated.”
Roy, P. P., Munna, S. S., Karim, M. S. U., et al. (2025) · doi:10.1109/sti69347.2025.11367529
“…DeepSea-Net, is based on the You Only Look Once (YOLO) series of object detectors, which is known to be the best trade-off between detection performance and inference time, which is why it is especially appropriate in real-time scenarios as well as in detection training and validation tasks [7].”
Oriented Ship Detection in Bayer-Encoded Satellite Imagery
Khairunnisa, K., Kamirul, K., Rahayu, D. A., et al. (2025) · IEEE International Conference on Aerospace Electronics and Remote Sensing Technology (ICARES) · doi:10.1109/icares67579.2025.11371466
“Recent advances in one-stage detectors like YOLO [1], [2] have enabled accurate, real-time detection in complex aerial and satellite scenes.”
POMO-DETR: A Polarityaware Linear Attention Transformer for Road Defect Detection
Yang, J., Ying, C., & Luo, Y. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-5758-5_27
Sparse Self-attention-Guided Network for Multispectral Object Detection
Xiao, H., Ren, Z., & Cai, S. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-5758-5_2
Vision-Based 3D Baseball Swing Trajectory Reconstruction and Swing Performance Analysis
Lu, Y.-E., & Chu, W.-T. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-6960-1_46
Lu, C., Ye, X., Wu, J., & Wu, F. (2026) · Scientific Reports · doi:10.1038/s41598-026-39036-y
“Joseph Redmon 14 and others proposed the development of a single-phase object detection system named YOLOv1 in 2016.”
MEIG: An Interactive Attention-Based Generative Model for Multimodal Event Extraction
Ye, Q., Li, P., & Wang, Z. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-6603-4_23
Batista, J., Rios, T. N., Prazeres, C. V. S., Lemes, R. D. P., Peixoto, M., Figueiredo, G., Dur�ão, F. A., Almeida, E., Machado, I., Iwamoto, H. M., et al. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-15993-9_8
Detection and Segmentation of Date Fruit Bunch Stalk Using YOLOv8 and SAM Algorithms
Bouh, Y., Mouh, L. A. B., Reddate, O., et al. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-16281-6_7
Lira, P., Costa, K., Loss, S. M., et al. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-15993-9_17
Sensor Fusion for Enhanced Threat Detection and Tracking
White, A., Handley, J., & Yang, H. (2026) · IEEE Transactions on Nuclear Science · doi:10.1109/tns.2026.3660625
“To identify potential threat carriers, computer vision models, such as the Ultralytics deep learning model YOLOv8 [13], can be used on images taken during detection events.”
ANBI-UAV: A Framework for Automated Noise Barrier Inspection Using UAV Imagery in High-Speed Railway
Hua, Y., Liu, X., Chen, B., Yang, Y., Jiang, W., & Zhu, J. (2026) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2026.3662000
ADAS for Improving Road Safety
Jayakrishnan, P., Pugalaendhi, S. V., & Charan, S. S. (2026) · doi:10.1002/9781394336166.ch39
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.