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 44,801–44,900 of 51,399
A Framework for Traffic Sign Recognition and Localization Based on Vehicle Trajectory and VideoPreprint
Li, L., Li, B., Cai, Z., & Cao, W. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5340160
Privacy Preserving Data Sharing for Connected Autonomous Vehicles Leveraging Edge Computing
Bai, T. (2025) · University of North Texas Digital Library (University of North Texas) · doi:10.12794/metadc2443147
COMPARATIVE ANALYSIS OF STATE-OF-THE-ART NEURAL NETWORKS FOR ART OBJECT RECOGNITION
Kozhagulov, Y. T., Maksutova, А. А., Zhexebay, D., et al. (2025) · Herald of Kazakh-British technical university · doi:10.55452/1998-6688-2025-22-2-67-75
A comprehensive review on ai-based farming robots
Mali, R., Phulwale, V., Phad, A., et al. (2024) · KT Journal of Mechanical Engineering · doi:10.64188/3048956325004
Lee, K., Hong, C., Yang, W.-H., Shim, Y.-D., & Lee, E. (2025) · International Journal of Precision Engineering and Manufacturing-Smart Technology · doi:10.57062/ijpem-st.2025.00045
Hyun, Y., Nam, E., & Yoo, Y. (2025) · International Journal of Precision Engineering and Manufacturing-Smart Technology · doi:10.57062/ijpem-st.2025.00052 · Cited by 1
Robust and Secure Hashing Towards Pirated Neural Network Model Detection
Xiong, C., Qin, C., Qian, Z., Li, X., & Zhang, X. (2025) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3747297
“…of proposed method in real-world applications, we utilize 12 SOTA and mainstream models, i.e., SAM-Med2D [6] (trained by SA-Med2D-20M dataset), YoloV8, 9, 10, 11 [21, 22] (trained by COCO and ImageNet dataset), and DARL [11] (trained by XCAD dataset), to compose a model dataset for testing.”
Lewis, J. R., Pathan, S., Kumar, P., & Dias, C. C. (2025) · IEEE Access · doi:10.1109/access.2025.3586736 · Cited by 1
YOLO-KAN: Exploring the Adaptability of Kolmogorov-Arnold Networks in the YOLO Model
Zhao, X., Lee, J., & Amjad, T. (2025) · IEEE Conference on Artificial Intelligence (CAI) · doi:10.1109/cai64502.2025.00144
“Unlike traditional object detection approaches that focus more on accuracy [2]–[4], the YOLO series models (You Only Look Once) simultaneously emphasize speed and accuracy [5], aiming to meet the real-time requirements of industrial applications such as autonomous driving and robotics.”
Early Diagnosis of Lung Adenocarcinoma Leveraging YOLO Architectures
Bhattacharjee, V., Kamalashree, S., & Ghanta, S. (2025) · IEEE Conference on Artificial Intelligence (CAI) · doi:10.1109/cai64502.2025.00083
“However, the second category includes SSD [19] and YOLO algorithms [20], which employ a neural network where an input is passed through a neural network without any updates to network’s weights.”
Standardized AI-Driven UAV Water Rescue System for Safe and Reliable Autonomous Operations
Hsu, U.-K., Ye, Y., Hsu, S.-Y., et al. (2025) · IEEE Conference on Artificial Intelligence (CAI) · doi:10.1109/cai64502.2025.00230
“The YOLOv3 model, proposed by Redmon and Farhadi [3], features a highly efficient single-stage detection architecture that enables real-time, high-accuracy object detection [4].”
Preaftrack: multi-object tracking based on adaptive feature matching from detection results
Zhang, M., Hou, C., Pang, Y., Shi, J., Zhang, Y., & Huang, X. (2025) · The Journal of Supercomputing · doi:10.1007/s11227-025-07466-6
“The YOLO series [20–23] has been widely adopted in MOT due to its balanced speed-accuracy trade-off.”
Natural Occlusion-Based Backdoor Attacks: A Novel Approach to Compromising Pedestrian Detectors
Li, Q., Wu, Y., Li, Q., Cui, X., Chen, Y., Chang, X., Liu, J., & Niu, W. (2025) · Sensors · doi:10.3390/s25134203 · Cited by 1
“Notable examples in this category include Fast R-CNN [35], Cascade R-CNN [36], and Mask R-CNN [34] [38], SSD [39], and RetinaNet [37].”
Helmet Detection in Mines Using Two-Branch YOLOv5 Network with Adaptive Weight Adjustment
Sui, Z., Pei, M., & Nie, Z. (2024) · International Conference on Sensors, Signal and Image Processing (SSIP) · doi:10.1145/3725949.3725950
Cross-Filter Structured Pruning for Efficient Sparse CNN Acceleration
Pham, N.-S., Shin, S., Xu, L., Shi, W. L., & Suh, T. (2025) · IEEE Access · doi:10.1109/access.2025.3587027 · Cited by 2
Toward Real-Time Maritime Surveillance: Deep Learning and Feature Fusion for Ship Detection
Ameenulhakeem, D. W. O., & Ocan, O. N. (2025) · IEEE International Conference on Soft Computing and Measurements (SCM) · doi:10.1109/scm66446.2025.11060412
“…the effectiveness of these features when adapted for this domain, with enhancements aimed at reducing noise caused by visual distractions [27] and in terms of network architecture, a deep neural network with Dropout techniques was employed, following an approach similar to ResNet [28],…”
Ando, S., Watanabe, N., Sekine, C., Sekiguchi, S., & Fuchiwaki, O. (2025) · Advanced Intelligent Discovery · doi:10.1002/aidi.202500068
Enhancing Daytime Train Image Detection with YOLOv8 through Data Augmentation Techniques
Inoue, Y., Sultana, R., Nishino, Y., et al. (2024) · Artificial Intelligence and Cloud Computing Conference (AICCC) · doi:10.1145/3719384.3719411
Self-similarity Enhancement Via Shape-embedding For Few-shot Counting
Xie, G., Yi, C., Zhan, J., et al. (2024) · Artificial Intelligence and Cloud Computing Conference (AICCC) · doi:10.1145/3719384.3719429
Adaptive Retraining Techniques for Foreign Object Detection in Industrial Environments
Purayil, S. V., Popa, M. C., Winands, M. H. M., & Mihaľák, M. (2025) · doi:10.1109/cism64958.2025.11060857
Romanenko, D. S., & Belyaev, S. A. (2025) · doi:10.1109/scm66446.2025.11060416
“Modern approaches use neural networks [4], such as convolutional and recurrent neural networks, and their combinations (e.g., LSTM for tracking temporal sequences).”
Object Distance Estimation System with Deep Neural Networks
Caraíba, A. F. D. S., & Cardoso, Á. A. (2025) · Brazilian Conference on Robotics (CROS) · doi:10.1109/cros66186.2025.11066153 · Cited by 1
“Some popular object detection algorithms are YOLO [6], R-CNN [7], and MobileNet [8].”
Fast and Accurate Vision-based Flying Object Detection and Tracking for Pursuing Intruder UAVs
Nascimento, A. M., Garcia, W., Sales, A., et al. (2025) · doi:10.1109/cros66186.2025.11064861
“…we leveraged an existing CNN architecture and based our detector on the YOLOv8 object detection CNN, which was modified for detecting a single class of objects and is able to perform fast and accurate segmentation, pose/keypoint estimation, and classification without sacrificing accuracy [15]–[17].”
Cross-Device Transfer Learning for Kayser-Fleischer Ring Detection: From Slit-Lamp to Smartphone
Wang, J., Wang, X., Sun, Y., Yang, X., Han, Y., Lin, N., & Yao, Z. (2024) · International Conference on Health Big Data and Intelligent Healthcare (ICHIH) · doi:10.1109/ichih63459.2024.11064874
A YOLO-based Method for Detecting Bone-Irregular in Chest X-rays
Shang, S. (2024) · International Conference on Health Big Data and Intelligent Healthcare (ICHIH) · doi:10.1109/ichih63459.2024.11064826
Elsoin, M. D., Weking, A. N., & Watomakin, D. B. (2025) · Journal of Innovative and Creativity (Joecy) · doi:10.31004/joecy.v5i2.1772
Tan, L., Liao, X., Zheng, A., et al. (2025) · doi:10.1109/cisce65916.2025.11065589
A Utility Pole Detection Model Based on YOLOv8s
Qu, J., Sun, J., Zhang, L., Zhang, C., & Peng, D. (2025) · International Conference on Communications, Information System and Computer Engineering (CISCE) · doi:10.1109/cisce65916.2025.11065156
“…Faster R-CNN[1] (Faster Region-based Convolutional Neural Network), which are renowned for their precision in detection; the subsequent category includes single-stage detection frameworks, typified by the YOLO[2] (You Only Look Once) series, which are celebrated for their expediency in detection.”
Cariño, C. J. R., & Balintec, E. P. (2025) · Cognitive Models and Artificial Intelligence Conference (AICCONF) · doi:10.1109/aicconf64766.2025.11064286
“The images were manually annotated with bounding boxes around banana trunks following standardized annotation protocols established by [26] and [27] for agricultural object detection.”
A Hybrid Deep Learning-Based Approach in Agricultural Sustainability: Apple Orchard Study
Mavaddat, A., Andrade, F. A. A., Hjelmervik, K. T., Johannessen, E. A., & Hovden, C. (2025) · Cognitive Models and Artificial Intelligence Conference (AICCONF) · doi:10.1109/aicconf64766.2025.11064103
“Additionally, three different YOLO versions (YOLOv5 [1], YOLOv7 [2], and YOLOv8 [3]) were applied to the sub-datasets to find the best model performance.”
Dinh, T. Q. K., Thirion‐Moreau, N., Nguyễn, T. P., Simon, J., & Escoubas, L. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5347102
Effective Small Sample-Size Learning for High-Dimensional Deep Neural NetworksPreprint
Ijaz, Y., Coleman, S., Kerr, D., Siddique, N. H., McAteer, C., Baker, B., & Nguyen, K. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5344815
Enhancing Pedestrian Detection with Explainable AI and Deep Learning
Benfaress, I., Bouhoute, A., & Zinedine, A. (2025) · Lecture notes in networks and systems · doi:10.1007/978-3-031-95326-2_27
Frequency-Aware Networks to Robust Low-Voltage Meter Detection in High-light Environments
Huang, Z., Li, H., Lu, J., et al. (2025) · doi:10.1109/cisce65916.2025.11065030
“One-stage detectors such as YOLO [4] , RetinaNet [5] , and EfficientDet [6] offer faster inference and are widely used in real-time industrial applications.”
Human Interfaces with Machine Learning Recognition Systems
Clarkson, C. (2025) · Cronfa (Swansea University) · doi:10.23889/suthesis.69942
Kim, G., Han, W.-H., & Hong, D.-G. (2025) · Metallurgical and Materials Transactions B · doi:10.1007/s11663-025-03676-8
“[12,13] To accurately detect the boundaries of the steel skull, the contour points of the skull were manually labeled and provided to the model.”
Detecting Objects in Photos and Videos Obtained by Aerial Reconnaissance from UAVs
Krytskyi, D., ТКАЧОВ, І., Pyvovar, M., et al. (2025) · Lecture notes in networks and systems · doi:10.1007/978-3-031-94845-9_23
Unveiling YOLO Variants: Comparative Study for Enhanced Object Detection
Anusha, N., Reddy, J. A., & Vaishnavi, K. (2025) · Lecture notes in networks and systems · doi:10.1007/978-981-96-5223-5_37
Zaidi, I., Brahimi, S., & Boulehouache, S. (2025) · Information systems engineering and management · doi:10.1007/978-3-031-90758-6_25
Automated Weed Detection in Agriculture: A Performance Evaluation of YOLOv8 and InceptionV3 Models
Gattal, A., Nait-Hamoud, M.-C., Gattal, M.-F., Hadji, H., & Cheriet, M. (2025) · Information systems engineering and management · doi:10.1007/978-3-031-90758-6_7
Unsupervised Insulator Defect Detection Method Based on Masked Autoencoder
Song, Y., & Xiong, W. (2025) · Sensors · doi:10.3390/s25144271
“Object detection frameworks, including YOLO [17] and Faster R-CNN [18], facilitate simultaneous defect localization and classification, while semantic segmentation models such as U-Net [19] and DeepLab [20] allow for pixel-level defect annotation.”
Íñiguez, R., Poblete-Echeverría, C., Barrio, I., et al. (2025) · Agriculture · doi:10.3390/agriculture15141495
Overview of Remote Sensing Monitoring Applications Based on YOLOv12
Zuo, T., Wu, B., Gao, X., et al. (2025) · International Conference on Geology, Mapping and Remote Sensing (ICGMRS) · doi:10.1109/icgmrs66001.2025.11065869
“Accurately identifying land use status is of great significance for urban planning, resource management, and ecological protection [21, 23, 24, 25, 29, 30].”
Aerial Image Detection Based on DCB-YOLOv8-SOD: An Improved Object Detection Model
Gao, Y., He, X., He, W., & Ma, Q. (2025) · International Symposium on Computer Technology and Information Science (ISCTIS) · doi:10.1109/isctis65944.2025.11065191
“Currently, the primary method for processing images involves using deep learning techniques to recognize and analyze images, including algorithms from the YOLO [3] series.”
Multi-Vehicle Detection Method Based on YOLOv8 for Severe Weather Conditions
Zhi, Z., Zhao, M., Gao, H., et al. (2025) · International Symposium on Computer Technology and Information Science (ISCTIS) · doi:10.1109/isctis65944.2025.11065386
“In recent years, deep learning-based object detection methods, represented by algorithms such as YOLO [1], SSD [2] , and RetinaNet [3], have achieved remarkable progress and widespread adoption across industries.”
Camera Trap Data Analysis for Grevy's Zebra Monitoring
Ruto, V., Njathi, Y., Ligawa, T., & Maina, C. W. (2025) · IST-Africa Conference (IST-Africa) · doi:10.23919/ist-africa67297.2025.11060060
“This paper focuses on the application of MegaDetector [6], a pre-trained animal detection model based on YOLO (You Only Look Once) [7] object detection model, a real-time convolutional neural network (CNN) architecture and EfficientNet [8] classification model, to the problem of identifying and…”
Anima Network:A Micro Doppler Radar Based Animal Classification SystemPreprint
buyukakkaslar, M. T., Yüce, M. F., Ertürk, M. A., et al. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5348263
An Rgbd Fused Real Time Defect Detection and Size Estimation Method for Sewer RobotsPreprint
Shen, W., ZHANG, J., Wei-ming, J., & Song, A. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5348408
Shteriyanov, V., Джусупова, Р., Bosch, J., et al. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5348483
Fault Identification of Railway Signaling Lightning Protection Modules Based on Improved YOLOv8
Chen, H., Yang, S., Liu, S., et al. (2025) · doi:10.1109/ddcls66240.2025.11065786
“In contrast, single-stage YOLO (You Only Look Once) detectors excel with efficient architectures and rapid processing, ideal for time-sensitive railway scenarios [5,6,7].”
EHS-YOLO Model for Saccharomyces Cerevisiae Cell Detection
Jian, Z., & Xie, L. (2025) · doi:10.1109/ddcls66240.2025.11065122
“To overcome this limitation, the You Only Look Once (YOLO) [15] model was proposed, which for the first time applied a single convolutional neural network to the entire image, achieving end-to-end training and greatly increasing detection speed.”
Zhang, M., Cui, H., Li, Z., Qiao, W., Chi, R., & Yao, W. (2025) · IEEE Data Driven Control and Learning Systems Conference (DDCLS) · doi:10.1109/ddcls66240.2025.11065800
“Since the emergence of deep learning, object detection frameworks have evolved from the RCNN series (R-CNN[6], Fast R-CNN[7], Faster R-CNN[8]) to representative architectures like the YOLO (You Only Look Once)[9] series and SSD (Single Shot MultiBox Detector)[10].”
Steel Smoke Detection Method Based on Improved AFPN with Attention Mechanism
Li, J., Zhou, F., Han, Z., et al. (2025) · doi:10.1109/ddcls66240.2025.11066036
“Single-stage methods treat object detection as a regression problem, and while they are fast, they are not very accurate [2, 3].”
Multiple-category, Multiple-instance Segmentation from RGB-D Data for Industrial Bin-picking
Xiao, L., & Liu, S. T. (2025) · doi:10.1109/ddcls66240.2025.11065770
“In the field of image processing, convolutional neural networks (CNNs) have demonstrated excellent performance in object detection [5], [6] and instance segmentation [7].”
Wei, Y., Huang, B., Zhao, B., et al. (2025) · International Journal of Computer Assisted Radiology and Surgery · doi:10.1007/s11548-025-03477-z
“The pipeline begins with initial marker localization, leveraging a YOLO-based network [11], a contemporary object detection model chosen for its balance of detection accuracy and computational efficiency, to identify marker regions within camera frames.”
Kim, J., & Choi, D. (2025) · Journal of Advances in Military Studies · doi:10.37944/jams.v8i1.277
MSMD-YOLO: An Object Detection Network for Visually Impaired People with FPGA Acceleration
Duan, Z., Ruan, Q., Zhang, J., & Chen, W. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-9952-0_15
LPI-YOLO: Lightweight Polyp Detection in Intestinal Endoscopy Based on Improved YOLOv8
Qi, X., & Zhou, J. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-9952-0_38
Defensive Strategies Against Object Detection-Based CAPTCHA Attacks
Dayanand, Jeberson, W., & Jeberson, K. (2025) · Smart innovation, systems and technologies · doi:10.1007/978-981-96-2182-8_42
Selective Scale Context Awareness Network for Object Counting in Intelligent Transportation System
Hu, X., Lin, C., & Yuan, X. (2025) · Journal of Transportation Engineering Part A Systems · doi:10.1061/jtepbs.teeng-8944
License Plate Recognition for Car Management Systems
Quang, P. X., & Trung, H. D. (2025) · Lecture notes in networks and systems · doi:10.1007/978-3-031-78934-2_6
Qin, L., & Song, W. (2025) · Sensors · doi:10.3390/s25144387
“This version demonstrates superior performance in achieving an optimal balance between processing speed and detection accuracy when compared to its predecessors [17–22].”
A Review of Vision-Based Tracking Methods: Temporal and Spatial Features
Bayat, M. H., Tarvirdizadeh, B., & Shahbazi, M. (2025) · Archives de l'Institut d'Hessarek. · doi:10.61186/jsdp.22.1.83
Basketball Small Object Detection Algorithm Based on Improved YOLO v7
Wang, L., Lu, Z., Lin, X., Ji, Q., Zhong, H., & Zang, P. (2025) · International Conference on Computer and Communication Systems (ICCCS) · doi:10.1109/icccs65393.2025.11069919
“Unlike two-stage methods, single-stage object detection methods, including YOLO [10], [11], SSD [12], CornerNet [13], and CenterNet [14], directly predict object classifications and positions without generating candidate regions, making them more suitable for low-latency, real-time scenarios.”
Improved Lightweight SSD Target Detection Algorithm for Vehicle Vision System
Wang, Y., Zhang, Y., & Zhu, B. (2025) · Smart innovation, systems and technologies · doi:10.1007/978-3-031-87154-2_15
Detection of PCB Surface Defects in Improved YOLOv8s
Zhu, B., Zhang, Y., & Wang, Y. (2025) · Smart innovation, systems and technologies · doi:10.1007/978-3-031-87154-2_14 · Cited by 1
Improved Lightweight Steel Surface Defect Detection Algorithm of YOLOv8
Zhang, L., & Zhou, Z. (2025) · International Conference on Computer, Control and Robotics (ICCCR) · doi:10.1109/icccr65461.2025.11072579
“Mainstream algorithms for deep learning based target detection are mainly two-stage algorithms such as Faster-RCNN [6] and one-stage algorithms such as YOLO [7] and SSD [8] .”
FOADA: Toward Robust Open-World Mobile App Fingerprinting
Gong, J., Meng, G., Cai, W., Liang, S., Wang, T., & Chang, E. (2025) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2025.3589008 · Cited by 1
UAV Detection in Multi-Motion Targets Environment Based on CA-YOLOv5-FE Network
Jin, D., Wang, X., He, F., & Ma, J. (2025) · International Conference on Computer, Control and Robotics (ICCCR) · doi:10.1109/icccr65461.2025.11072585
“In 2016, Redmon et al. [11] proposed You Only Look Once (YOLO) algorithm, the most obvious difference between this type of one-stage approach and the previous two-stage approach is that YOLO discards the candidate box extraction.”
Research on Target Detection of Fruit and Vegetable Diseases Based on Td-Fd-YOLOv8 Algorithm
Zheng, Y., Qi, W., Dong, Y., & Chen, F. (2025) · International Conference on Computer and Communication Systems (ICCCS) · doi:10.1109/icccs65393.2025.11069786
LPT: Lightweight Pooling Transformer for Object Detection
Wang, G., Zhu, B., Yao, J., & Li, K. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-9946-9_2
MTS-Net: research on multi-modal, multi-task, multi-stage tumor segmentation model for PET/CT
Zheng, Y., Sun, Z., Chen, S., et al. (2025) · Applied Intelligence · doi:10.1007/s10489-025-06759-w
“YOLO [18], originally proposed for real-time object detection, has been extended to medical imaging tasks.”
A Multi-scale Feature Fusion Method for Small Target Detection in High-Altitude Aerial Photography
Wang, Y., Zhu, Y., Wang, D., Li, M., & Jie, Y. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-9949-0_4
VSS-Pose: Multi-person 2D Pose Estimation with Selective State Space and Sampling Innovations
Li, Y., Chen, D., Liu, N., Ma, Z., & Tan, B. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-9949-0_19
GAHL: Gradient-Adaptive Hyperbolic Loss for Tiny Object Detection
Liu, T., & Cui, Z. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-9949-0_25
Bayraktar, M., Zalluhoğlu, C., Aldemir, A., et al. (2026) · Journal of Performance of Constructed Facilities · doi:10.1061/jpcfev.cfeng-5371
Raisi, Z., Nazarzehi, V., Sarani, E., & Damani, R. (2025) · SN Computer Science · doi:10.1007/s42979-025-04196-7 · Cited by 1
“In order to better assist researchers, we provide annotations in different formats of scene text detection communities, including ICDAR ".txt" [70, 83, 84] file for each image, Microsoft COCO [95] ".json" file, and YOLO [46] format including rectangular and rotated rectangular bounding boxes.”
Xu, X., Li, F., Yang, C., et al. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5352144
Deng, L., Cheng, Y., & Wu, J. (2025) · Acta Astronautica · doi:10.1016/j.actaastro.2025.07.017
Gimbal Camera-Based Flight Guidance for Striking Illegal Drones
Lee, H., & Lee, K. (2025) · Lecture notes in networks and systems · doi:10.1007/978-3-031-92011-0_15
Research on Real-Time Instance Segmentation Based on Multi-Scale Context Information Fusion
Wen, E., Li, Q., Li, Q., & Huang, H. (2025) · International Conference on Neural Networks, Information and Communication Engineering (NNICE) · doi:10.1109/nnice64954.2025.11063877
Pedestrian Detection Combining DLA-34 and Attention Mechanism
Qiu, Z., & Qian, S. (2025) · International Conference on Neural Networks, Information and Communication Engineering (NNICE) · doi:10.1109/nnice64954.2025.11064667
D2SO: Detecting Distant and Small Objects for Vision-Based Vehicle Autonomous Systems
Zhang, H., Lucero, H. R., Sha, K., Fan, H., Fu, S., & Feng, Y. (2025) · IEEE International Conference on Mobility, Operations, Services and Technologies (MOST) · doi:10.1109/most65065.2025.00013
“Detection models such as Faster R-CNN [8], YOLO [9], and SSD [10] detect medium-to-large-sized objects.”
Sound: Unknown Object Detection for Autonomous Driving
Chen, D., Ma, X., He, Y., Feng, W., Yang, Q. K., Fu, S., & Tsao, T. (2025) · IEEE International Conference on Mobility, Operations, Services and Technologies (MOST) · doi:10.1109/most65065.2025.00020
“We have witnessed great advancements in the field of known-set object detection, with models like AlexNet [37], ResNet [1], DenseNet [38], and the YOLO series, spanning from YOLOv1 [39] the latest YOLOv8 [40].”
Investigating the Transferability of TOG Adversarial Attacks in YOLO Models in the Maritime Domain
Manasut, P., Ibtasham, M. S., Yaradanakul, Z., Azimi, S., Lafond, S., & Iancu, B. (2025) · IEEE Access · doi:10.1109/access.2025.3589512
Cheng, B., Wang, B., Wang, Q., et al. (2025) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2025.3589361
Semantic Odor Source Localization via Visual and Olfactory Integrated Navigation
Wang, L., Hassan, S., & Mahmud, K. R. (2025) · International Conference on Artificial Intelligence, Robotics and Control (AIRC) · doi:10.1109/airc64931.2025.11077500 · Cited by 2
“Instead of relying on a pre-trained computer vision model (e.g., YOLO [13]), we directly input the captured images into the LLM.”
Comprehensive Weather-Affected Automobile Vision Algorithm based on SURF and Optical Flow
Verma, A., Warnekar, H. A., & Ghanekar, U. (2025) · International Conference on Inventive Computing and Informatics (ICICI) · doi:10.1109/icici65870.2025.11069973
“Despite their success, deep learning methods required large, diverse datasets and substantial computational resources, struggled in poor visibility conditions caused by adverse weather [2] pose challenges for real-time applications and edge devices.”
Expand to Detect: Enlarging Bounding Box Annotations for Small Object Detection
Uğur, M., & Ekenel, H. K. (2025) · IEEE International Conference on Digital Signal Processing (DSP) · doi:10.1109/dsp65409.2025.11075181
“Although modern deep learning techniques, such as DETR [3] and YOLO [4], have achieved impressive re-sults on ground-based datasets such as MS COCO [5], their performance often degrades when applied to aerial datasets like VisDrone [6] due to the challenges inherent in aerial images [7].”
A Situation-Aware Cloud-Edge Architecture for Cultural Heritage Management
Aliberti, L., D’Aniello, G., Santo, M. D., et al. (2025) · IEEE Conference on Cognitive and Computational Aspects of Situation Management (CogSIMA) · doi:10.1109/cogsima64436.2025.11079541
“…on drones [15] [16], cameras, or in low-power gateways, the perception and comprehension phases can be implemented through object detection techniques such as small Yolo [17] [18], in its various and most recent versions, due to their great speed and excellent performance in many situations.”
From Vision to Sound: Enhanced Object Localization for Visually Impaired and Blind
Kuzdeuov, A., Nurgaliyev, S., Akhmetov, T., Ezhov, V., Moger, G. D., & Varol, H. A. (2025) · International Conference on Control, Automation and Robotics (ICCAR) · doi:10.1109/iccar64901.2025.11073053
“The You Only Look Once (YOLO) [9] and Single Shot Detector (SSD) [10] object detection models are frequently utilized in visual assistant systems.”
Context-Aware Worker Assistance System in Augmented Reality using Semantically Zoomable Digital Twin
Walunj, S., Pahlevannejad, P., Karnoub, A., Plociennik, C., & Ruskowski, M. (2025) · IEEE Conference on Cognitive and Computational Aspects of Situation Management (CogSIMA) · doi:10.1109/cogsima64436.2025.11079486 · Cited by 1
“Yolo object detection [22] models are the state of the art models and widely trained on custom datasets for multi-class object detection [23] [24].”
Łącki, M., & Ratuszniak, P. (2025) · IEEE EUROCON - International Conference on Smart Technologies (EUROCON) · doi:10.1109/eurocon64445.2025.11073461
“The YOLO (You Only Look Once) algorithm is also widely used solution for real-time object detection and classification [15].”
Underwater Acoustic Target Detection Network Based on Comprehensive Feature Extraction
Sun, D., Wang, K., Liu, P., & Zhang, C. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-7188-5_21
Accurate detection of brain tumors in MRI images using the YOLO algorithm
Solatinia, B., & Yahyapour, A. (2025) · The Neuroscience Journal of Shefaye Khatam · doi:10.61186/shefa.13.2.11
Symmetric Kernel Attention: Making Transformer Suitable for Object Detection
Zhang, X., Li, Z., Guo, Z., Fang, X., & Qiao, Y. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-6957-8_2
Animal Protection System Cats and Dogs Approaching The Substance With The Mini Computer
Ramadhani, S. A., Anandika, A., Syahputra, R., et al. (2025) · CHIPSET · doi:10.25077/chipset.6.01.18-29.2025
“The obtained YOLO model was later used to recognize objects from video and real-time webcam, the accuracy of identification of pizza objects on video was 99% [25].”
TDENet: Three-branch distillation enhancement network for foggy scene object detection
Shi, Y., Guo, J., Wang, X., & Wang, Y. (2025) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2025.104534 · Cited by 2
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.