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 45,301–45,400 of 51,399
Experimental Analysis of Fine-Tuned Drone Detection YOLO Models
Dogan, S., Walatkiewicz, J., Tout, S., et al. (2025) · doi:10.1109/satc65530.2025.11137294
Akashah, M. H. N., & Uchiyama, N. (2025) · IEEE International Conference on Real-time Computing and Robotics (RCAR) · doi:10.1109/rcar65431.2025.11139631
Privacy-Preserving Secure Framework for Intelligent Transportation Systems
Nagayoshi, Y., Ullah, S., Chen, B. K., Ibrahem, M. I., Fouda, M. M., & Abouyoussef, M. S. (2025) · IEEE International Conference on Secure IoT, Assured and Trusted Computing (SATC) · doi:10.1109/satc65530.2025.11136998
Kong, X., & Yamaguchi, M. (2025) · IEEE International Conference on Real-time Computing and Robotics (RCAR) · doi:10.1109/rcar65431.2025.11139630
“3 shows examples of bounding boxes obtained from color images using YOLO[32]. fundamental idea of this type of method is to determine whether a person has fallen by calculating the aspect ratio of the bounding box after detecting the person using an object detection algorithm[30].”
Integrating advanced robotics for precision agriculture and sustainability
Tanco, M. M., Barnech, G. T., Benavides, F., et al. (2025) · Agrociencia Uruguay · doi:10.31285/agro.29.1528
Research on Multimodal Non-Contact Magnetic Memory Method for Pipeline Defect Detection
孙, 亚. (2025) · Artificial Intelligence and Robotics Research · doi:10.12677/airr.2025.145102
Road Marking Line Recognition and Detection System Based on SDF-YOLOv8 in Foggy Weather
Li, S., Huang, M., You, D., et al. (2025) · doi:10.1109/iccnse66404.2025.11144186
“With the assistance of a single neural network,this technology can evaluate the boundary box and class probability of the target at one time, and directly optimize the detection performance [2] .”
An Improved YOLOv11-Based Algorithm for Impact Crater Detection
Zhang, T., Liang, J., & Tian, X. (2025) · IEEE International Conference on Image Processing and Computer Applications (ICIPCA) · doi:10.1109/icipca65645.2025.11138997
“The most successful CNN-based object detection model is the YOLO (You Only Look Once), known for its real-time processing abilities and high detection accuracy [3].”
Stern Target Detection Algorithm Based on Lightweight YOLO
Qi, R., Wang, X., Gan, X., et al. (2025) · International Conference on Electronic Technology and Information Science (ICETIS) · doi:10.1109/icetis66286.2025.11144281
“The YOLO series [6] adopts an end-to-end design, directly predicting object categories and locations across the entire image, offering higher detection speed and engineering applicability.”
Jiang, H., Fan, H., Fang, J., et al. (2025) · International Conference on Electronic Technology and Information Science (ICETIS) · doi:10.1109/icetis66286.2025.11144223
“In 2016, Redmon J et al. first proposed the first-generation YOLO, namely YOLOv1 [3] .”
Comprehensive Survey on Deep Learning-Based Advances in One-Stage Object Detection
Hmidani, O., & Alaoui, E. M. I. (2025) · International Conference on Circuit, Systems and Communication (ICCSC) · doi:10.1109/iccsc66714.2025.11135423 · Cited by 1
“One-stage detectors addressed this by collapsing the entire pipeline into a single network, enabling faster and more streamlined detection [1].”
InfluentialDynaLight-SLAM: A Visual SLAM of Dynamic Objects in Low-Light Conditions
Wu, P., Zhou, X., Zhou, X., et al. (2025) · doi:10.1109/ieeeconf65522.2025.11137240
“The You Only Look Once(YOLO) [1] models’ series is one of the most popular object detection algorithms in recent years.”
CP-YOLOv8s algorithm for tiny and extreme-type fabric defect detection
Guo, P., Liu, Y., Wu, Y., Wang, J., & Li, Y. (2025) · Textile Research Journal · doi:10.1177/00405175251362869 · Cited by 1
“7 The two-stage object detection algorithm first employs traditional image processing techniques or pretrained convolutional neural networks (CNNs) to generate candidate bounding boxes, which are subsequently refined through classification and bounding box regression.”
Sun, H., Wang, L., Liu, X., et al. (2025) · Signal Image and Video Processing · doi:10.1007/s11760-025-04566-x
“Single-stage detection methods [10–17], such as the YOLO [10–15] series, perform classification and localization directly using a single neural network.”
RTF-YOLO: an efficient object detection framework for autonomous vehicles
Sun, Y., Zhen, M., Ma, Y., Wang, H., Chen, G., & Gao, X. (2025) · Signal Image and Video Processing · doi:10.1007/s11760-025-04585-8
“Single-stage methods, such as the YOLO (You Only Look Once) [ 8–11 ] series and SSD [ 12 ], on the other hand, simplify the task of target detection into treating it as a regression task by simultaneously performing object detection and location estimation within a single neu - ral network, which…”
Ugalde, E. H. G., Rosas, M. Á. V., Tafolla, Y. E. S., et al. (2025) · TIES Revista de Tecnología e Innovación en Educación Superior · doi:10.22201/dgtic.26832968e.2025.13.55
Rangelov, D., Miltchev, R. I., & Genchev, E. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-05607-8_7
A Survey on Vehicle Damage Detection using Deep Learning Towards Intelligent Insurance
Tran, D.-H., Hoang, V.-D., Nguyen, D., Pham, T.-A., & Le, V.-T.-L. (2025) · Conference on Human System Interactions · doi:10.1109/hsi66212.2025.11142438 · Cited by 2
“Models such as YOLO (You Only Look Once) [2]–[4], [17]–[25] and DETR (DEtec-tion TRansformer) [1], [26]–[28] have been adapted for vehicle damage detection tasks, achieving notable performance.”
TODM: Task-Aware Object Detection Model for Small Remote Sensing Images
Wu, H., & Fan, D. (2025) · Asia-Pacific Conference on Communications Technology and Computer Science (ACCTCS) · doi:10.1109/acctcs66275.2025.00143
“For example, R-CNN introduced region proposals combined with convolutional features for object detection [1], while Faster R-CNN incorporated region proposal networks (RPNs) to improve detection speed and accuracy [2].”
A Real-Time Object Detection and Tracking Framework Based on RT-DETR and DeepSORT
Nguyen, D., Hoang, V.-D., Le, V.-T.-L., Pham, T.-C., Tran, Q.-K., & Luong, C. M. (2025) · Conference on Human System Interactions · doi:10.1109/hsi66212.2025.11142427 · Cited by 2
“Traditional object detection models such as SSD (Single Shot MultiBox Detector) [1], Faster R-CNN [2] and YOLO (You Only Look Once) [3]–[10] have demonstrated strong performance in real-time applications.”
Gu, T., Liu, Y., Zhang, H., Li, S., Wan, X., & Yu, K. (2025) · International Conference on Artificial Intelligence Technologies and Applications (ICAITA) · doi:10.1109/icaita67588.2025.11137874
“Joseph et al. [3] proposed the single-stage target detection model YOLO.”
Liu, J. (2025) · IEEE International Conference on Computing and Machine Intelligence (ICMI) · doi:10.1109/icmi65310.2025.11141220
Qin, Y., & Yu, M. (2025) · Asia-Pacific Conference on Communications Technology and Computer Science (ACCTCS) · doi:10.1109/acctcs66275.2025.00153
“In 2015, Joseph Redmon proposed the first single-stage object detection algorithm (You Only Look Once, YOLO) [7].”
Application of YOLOv8 Small Object Detection in Traffic Flow Congestion Prediction Models
Huang, Z., Xie, Z., Chen, G., et al. (2024) · doi:10.1109/icirdc65564.2024.00123
Khan, S. M., Makavi, S. A., Chohan, M. A., et al. (2025) · IEEE International Conference on Computing and Machine Intelligence (ICMI) · doi:10.1109/icmi65310.2025.11141246
Zhang, Q., Zhang, S., Qu, C., et al. (2025) · doi:10.1109/icaita67588.2025.11138006
“RT-DETR outperforms YOLO series models in real-time object detection [5] .”
A Defect Detection Approach for Hot-Rolled Steel Using an Improved YOLOv8
Li, Y., Jiang, Z., Yang, C., & Cui, F. (2025) · International Conference on Artificial Intelligence Technologies and Applications (ICAITA) · doi:10.1109/icaita67588.2025.11137950
“Surface defect detection methods can be broadly categorized into two types: one-stage algorithms like SSD [2] and YOLO [3] series, and two-stage algorithms such as R-CNN [4] , Fast R-CNN [5], and Faster R-CNN [6] .”
Integrating remote sensing and deep learning for mapping urban housing wealth patterns
Nyandwi, E., Gerke, M., Achanccaray, P., & Leßmann, C. (2025) · Geo-spatial Information Science · doi:10.1080/10095020.2025.2543496
“In particular, our preliminary experiment involved the single-stage detection YOLO model (Redmon et al. 2016), focusing on recent iterations, including YOLOv9 (Wang, Yeh, and Liao 2024) and YOLOv11 (Khanam and Hussain 2024).”
Research on The Vehicle Detection Technology Based on The Yolo Model
Cao, L. (2025) · ITM Web of Conferences · doi:10.1051/itmconf/20257803008
Shi, J. S., McRae‐Posani, B., Haque, S. S., Holodny, A. I., Shalu, H., & Stember, J. N. (2025) · American Journal of Neuroradiology · doi:10.3174/ajnr.a8998
Post-Earthquake Damage Detection of Reinforced Concrete Members Based on the Improved YOLO Model
Zixiao, C. H. E. N., Chenghao, S. O. N. G., & Hu, X. (2025) · Industrial Construction · doi:10.3724/j.gyjzg25071002
A Three-Stage Surface-Defect Detection Pipeline for Bridge Stay-Cable Sheaths
Yujing, L. I. U., Li, J., Yi, F. A. N., et al. (2025) · Industrial Construction · doi:10.3724/j.gyjzg25062002
Lin, Z., Zheng, W., & Wang, Y. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-04546-1_12
HCNQA: Enhancing 3D VQA with Hierarchical Concentration Narrowing Supervision
Zhou, S., Zhu, J., Huang, Q., Wang, F., Zhang, Y., & Zheng, F. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-04546-1_3
A Symmetry-Aware Multi-Attention Framework for Bird Nest Detection on Railway Catenary Systems
Shan, P., Feng, W., Lou, S.-T., Dauphin, G., & Bao, W. (2025) · Symmetry · doi:10.3390/sym17091505 · Cited by 1
Hui, Z., Li, P., Miao, S., Li, Y., Shen, L., & Shen, H. (2025) · Journal of Marine Science and Engineering · doi:10.3390/jmse13091739
A two-way feature fusion Ochotona curzoniae object detection model based on information interaction
Chen, H., & Zhang, Z. (2025) · Signal Image and Video Processing · doi:10.1007/s11760-025-04675-7
“For instance, Lin[6], Ghaisi[7], and Pang[8] utilized such approaches to capture multi-scale features, thereby improving detection performance across objects of varying sizes[9].”
Ren, W., Siha, A., Zhou, C., et al. (2025) · Signal Image and Video Processing · doi:10.1007/s11760-025-04640-4
“Object detection is a key task in computer vision with applications in autonomous driving and remote sensing [6].”
Liu, J., Li, B., Yang, X., Yang, N., Fei, H., Zhang, M., Li, F., & Ji, D. (2025) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2025.3609288 · Cited by 4
“A visual region set V , The representation of each visual region uses the YOLO [33] format, which is a quintuple, where v i represents the quintuple set of visual targets of the i -th image, which contains n v visual targets, v i,j represents the quintuple of the j -th visual target of the i -th…”
Low Power Approximate Attention guided ROI Module for Detection of UAV Images
Periyala, K. N., Chauhan, S. J., Rajput, A. P., et al. (2025) · doi:10.1109/sennet64220.2025.11136090
“Faster R-CNN [10] and YOLO [11] are some of the traditional deep learning algorithms.”
Guo, J., Guo, C., Liang, S., Li, Z., Wang, D., Lin, R., & Dang, Y. (2025) · IEEE/CIC International Conference on Communications in China (ICCC) · doi:10.1109/iccc65529.2025.11148883
“Classical object detection models, including the R-CNN [2], [3] and YOLO [4]–[6] series, have been widely applied in network O&M applications [7], [8].”
UAV detection using camera and radar
Andov, P., Sarjaš, A., & Gleich, D. (2025) · International Conference on Systems, Signals and Image Processing · doi:10.1109/iwssip66997.2025.11151948
“[1 ] The class probabilities for each object are also predicted by each grid cell, and final object detections are obtained using non-maximum suppression (NMS), which filters out redundant overlapping boxes based on their confidence scores.”
Improved Pipeline Disease Grading Detection Method for Visual Inspection of Sewer Pipeline Robots
Li, C., Li, S., Duan, X., et al. (2025) · IEEE International Conference on Multimedia and Expo workshops · doi:10.1109/icmew68306.2025.11152128
“YOLO (You Only Look Once) [22] algorithm is the pioneer of one-stage detector.”
Small Object Detection Algorithm for Road Images Based on Improved YOLOv11n
Peng, J., Tan, H., Jin, S., et al. (2025) · IEEE Conference on Industrial Electronics and Applications (ICIEA) · doi:10.1109/iciea65512.2025.11148962
“The second category is regression-based single-stage detectors, such as the YOLO [7] series and SSD algorithms [8].”
Xie, C., Zhuang, C., & Gao, P. (2025) · IEEE International Conference on Multimedia and Expo workshops · doi:10.1109/icmew68306.2025.11152067
“Note that we employ the referring segmentation model rather than traditional object detection models such as YOLO [19], since the former allows arbitrary referents while the latter only supports pre-defined classes.”
A Multi-element Anomaly Detection Approach for Complex Industrial Images
Jia, H., Yi, H., Zhang, H., Zhang, Y., & Liu, L. (2025) · IEEE International Conference on Multimedia and Expo workshops · doi:10.1109/icmew68306.2025.11152222
“The Single Shot MultiBox Detector (SSD) [15] and You Only Look Once (YOLO) series [16-18] further revolutionized the field by offering real-time detection capabilities with a single evaluation of the image, leading to widespread adoption in various industries.”
Lightweighting of Deep Learning Models with Application in Object Detection
Guo, J., Zhao, Z., Liu, Y., et al. (2025) · IEEE Conference on Industrial Electronics and Applications (ICIEA) · doi:10.1109/iciea65512.2025.11148973
“In contrast, single-stage detectors such as SSD [3] , the YOLO series(YOLO [4] - YOLOv4 [7] ) and EfficientNet [8] implement end-to-end regression to directly predict classification outcomes, prioritizing computational efficiency.”
Liao, Z., Hu, K., Wang, Y., et al. (2025) · IEEE Conference on Industrial Electronics and Applications (ICIEA) · doi:10.1109/iciea65512.2025.11148691
“Unlike two-stage methods, single-stage approaches, such as the YOLO series[9], predict bounding boxes and object categories simultaneously through a single forward pass, significantly enhancing detection speed, albeit at the cost of some precision.”
Wang, Z., Zheng, Z., Meng, J. H., & Xu, L. (2025) · Frontiers of Information Technology & Electronic Engineering · doi:10.1631/fitee.2400960 · Cited by 1
“Anchor-based detectors (Ren et al., 2015; Redmon et al., 2016; Lin TY et al., 2017) were proposed first which use predefined anchor boxes as references to locate and classify objects.”
Performance Analysis of Yolo Versions on Road Environment
Ikmel, G., Saleh, S., Heller, A., et al. (2025) · Revista de Gestão Social e Ambiental · doi:10.24857/rgsa.v19n9-002
Shi, Z., Chen, S., Ming, L., et al. (2025) · Radio Science · doi:10.1029/2026rs008649
FRFCNet: Feature Refinement and Flexible Concatenation for Object Detection
Zhang, T., Wu, Z., He, X., et al. (2025) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2025.3607701
MMW-Det: A Context-Aware Detection Method With Hybrid Attention for Noncooperative mmWave Screening
Zhang, Y.-Y., Pan, J., Liu, P., et al. (2025) · IEEE Sensors Journal · doi:10.1109/jsen.2025.3604828
“The two-stage model represented by Faster R-convolutional neural networks (CNN) [21], [22], [23] and the single-stage model represented by YOLO [24], [25], [26], [27], [28], [29] have been successively proposed and rapidly updated.”
Pradhan, H., Poudel, A., Shrestha, D., Rogers, A., Stewart, M., Jereb, A., Harper, J., Li, M., Zhang, W., Chen, J., et al. (2025) · The European Physical Journal E · doi:10.1140/epje/s10189-025-00521-3 · Cited by 1
“YOLO (You Only Look Once) [50], one of the most popular object detection frameworks, was selected in the current study.”
A YOLO-Based Algorithm for Detecting Key Components on Subway Train Roof
Liu, N., Zhang, J., Xing, Z. Y., et al. (2025) · Conference on Fully Actuated System Theory and Applications (FASTA) · doi:10.1109/fasta65681.2025.11138964
“YOLOv5s is a single-stage object detection algorithm in the YOLO series [14][15][16].”
An Improved YOLOv8 Algorithm for Infrared Recognition of Train Running Gear Components
Shi, C., Zhang, Y., Li, Q., et al. (2025) · Conference on Fully Actuated System Theory and Applications (FASTA) · doi:10.1109/fasta65681.2025.11138805
“YOLO (You Only Look Once) was proposed by R. Jo-seph et al. in 2015 and is the pioneer of single-stage object detection [3].”
Urban Intersection Collision Warning System Utilizing Traffic Surveillance Cameras
Guan, Y., Miraftabzadeh, S. M., Yaïci, W., & Zaninelli, D. (2025) · International Conference on Applying New Technology in Green Buildings (ATiGB) · doi:10.1109/atigb66719.2025.11142082
“The original YOLO achieved 45 FPS, while Fast YOLO reached 155 FPS on a Titan X GPU [19].”
FruCapsNet: A shuffled attention based capsule network for multi-fruit quality assessment
Gupta, S. K., Tripathi, A. K., & Singh, H. (2025) · Soft Computing · doi:10.1007/s00500-025-10863-x
“Mukhiddi - nov et al. ( 2022 ) introduced the improved YOLOv4 model for binary classification with five distinct categories of fruits or vegetables.”
InfluentialKD-LSRED: Knowledge Distillation for Lightweight Symbol Recognition in Engineering Diagrams
Ekeke, I., Moreno‐García, C. F., & Elyan, E. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-04630-7_28
Food Waste Detection in Canteen Plates with Visual Large Language Models
Calì, R., Ferreira, J., Cerqueira, P., et al. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-05179-0_3
Feature Interconnection for Fault Detection with Inaccurate Bounding Boxes
Pan, X., Liang, Q., Sun, G., Chen, S., & Wu, B. (2025) · Cluster Computing · doi:10.1007/s10586-025-05342-9
“In addition, existing object detectors mainly adopt IoU-based label assignment methods [12, 13], which also exhibit clear limitations when dealing with noisy bounding boxes.”
Sohn, T. S., Dillitzer, M., Bach, J., Corso, J. J., Brühl, T., Schwager, R., Eberhardt, T. D., & Sax, E. (2025) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw67362.2025.00371 · Cited by 5
“Recent advances in autonomous driving have increasingly integrated machine learning techniques to enhance perception, decision-making, and planning capabilities [10, 11, 23, 25, 48, 54].”
Automatic Explicit Content Detection in Anime: Comparison of DETR and YOLO
Suciati, A., Sari, D. K., & Yunus, A. P. (2025) · International Conference on Data Science and Its Applications (ICoDSA) · doi:10.1109/icodsa67155.2025.11157005
“Each grid cell predicts bounding boxes and class probabilities [19].”
Mallick, R., Dong, S., Ruiz, N., & Bargal, S. A. (2025) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw67362.2025.00160 · Cited by 3
“While robustness to occlusions for the task of object detection has been well-studied [35, 36], the final goal is to obtain a polygon that outlines non-occluded parts of objects.”
Maize Grain Classification Using Machine Learning
Macwan, S., Warrier, S., Dabhi, V. K., & Prajapati, H. B. (2025) · International Conference on Innovations in Intelligent Systems: Advancements in Computing, Communication, and Cybersecurity (ISAC3) · doi:10.1109/isac364032.2025.11156487
“Our comprehensive evaluation of state-of-the-art deep learning models—including EfficientNet [4], Inception-v3 [5], and MobileNet [6] architectures integrated with YOLO [7]-based detection—revealed significant limitations in achieving fine-grained classification necessary for agricultural quality…”
Multi-Spectral Imaging and Data Fusion for Real-Time Bleeding Detection
Rouhafzay, G., Rowlands, S., Valencia, A. J., et al. (2025) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw67362.2025.00441
“For liquid detection in both the thermal and IR modalities, we use two You Only Look Once (YOLO) [6] object detectors which undergo thorough training and fine-tuning using our specialized datasets for blood detection across different modalities.”
InfluentialReaction Rumble : A Facial Expression Recognition Application using CNN
Thopate, K., Joshi, H. J., Pise, G. S., Londhe, A. D., Ahire, L. K., & Pokale, T. (2025) · International Conference on Innovations in Intelligent Systems: Advancements in Computing, Communication, and Cybersecurity (ISAC3) · doi:10.1109/isac364032.2025.11156426
“The backbone is generating feature maps at different scales such that the network can detect objects of various sizes [9].”
Deep Learning-based Comorbidity Detection in Children: A Prophylactic Tool for Viral Diseases
Sridharan, J., & Sudha, N. (2025) · International Conference on Innovations in Intelligent Systems: Advancements in Computing, Communication, and Cybersecurity (ISAC3) · doi:10.1109/isac364032.2025.11156658
“The detector stage is based on the You Only Look Once (YOLO) approach [12].”
Evaluating the Impact of Image Augmentation on Deep Learning-Based Road Pothole Detection
Yusuf, F. M., Hamami, F., & Utama, N. I. (2025) · International Conference on Data Science and Its Applications (ICoDSA) · doi:10.1109/icodsa67155.2025.11157029
“One of the most widely used models is YOLO (You Only Look Once), which is popular for its fast speed and real-time object detection accuracy [4].”
Kapusta, J., Bauer, W., & Baranowski, J. (2025) · International Conference on Methods and Models in Automation and Robotics · doi:10.1109/mmar65820.2025.11150827
“Object detection, an established area within computer vision, has been extensively utilized for real-time surveillance and monitoring [5], [6]. analyze static architectural layouts for security purposes remains underexplored.”
Duarte, F. F., Lau, N., Pedrosa, E., Lopes, P., & Maurya, P. K. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-05176-9_12
Development of Artificial Intelligence-Based Product Size Detection System
Aharari, A., & Tanaka, S. (2025) · doi:10.3390/engproc2025108035
Kim, Y.-M., Oh, G., Youm, K., et al. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5460398
UAV-based multispectral imaging and deep learning for ink disease detection in chestnut forestsPreprint
Smith, K. N., Belcore, E., Balestra, M., et al. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5460401
Background-Aware Object Detection Network for Similar Object DistinguishingPreprint
Zhao, X., Ma, Y., Wu, J., Inthasone, S., Wang, H., Zeng, Y., & Huang, H. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5492556
Chen, L., Song, S., Wang, Y., Hu, Y., & Han, J. (2025) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2025.3608554 · Cited by 2
Análise Comparativa de Modelos de Detecção para Identificação de Ovelhas em Ambientes Naturais
Neto, J. D. S., Marques, J. V. M., Sarmento, J. L. R., & Silva, R. (2025) · Anais do Seminário Integrado de Software e Hardware (SEMISH) · doi:10.5753/semish.2025.8507
Deep Learning for Appearance Defect Inspection in Laptops: A Model Comparison
Santiago, J. P. O., Cabral, L., Sena, L., Neto, J. B. C., Nogueira, Y. L. B., & Machado, J. C. (2025) · Anais do Seminário Integrado de Software e Hardware (SEMISH) · doi:10.5753/semish.2025.7056
“YOLO [Redmon 2016] consists of a family of state-of-the-art detectors for real-time object detection, known for their strong performance while maintaining good accuracy in object detection.”
Mattos, S. L. R. R., Boldt, F. D. A., & Paixão, T. M. (2025) · Anais do Seminário Integrado de Software e Hardware (SEMISH) · doi:10.5753/semish.2025.7349
“The chosen model for this task is YOLOv8 [Jocher et al. 2023], a widely adopted variant of the YOLO ( You Only Look Once ) [Redmon 2016] family of architectures, recognized for balancing high accuracy with real-time detection capabilities.”
AeroYOLO: Efficient Multiscale and Attention-Augmented YOLOv8s for Robust Aerial Object Detection
Zhang, H. (2025) · IEEE Access · doi:10.1109/access.2025.3610617 · Cited by 3
YOLO-AFP: A More Robust Network for Aerial Object Detection
Li, X., Wang, Z., Chen, X., Li, W., Sun, K., Lai, Z., & Zhu, P. (2025) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2025.3610115
A Real-Time Defect Detection Algorithm for Photovoltaic Glass with High AccuracyPreprint
Fan, Y. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5494104
Enhancing Agricultural Disease Diagnosis: YOLO-Based Detection of Root Rot in Beans
Torres, R. C., & Borges, D. L. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-04968-1_21
VIGIA-E: Density-Aware Patch Selection for Edge-Based Small Object Detection with PTZ Cameras
Suárez–Ramírez, J., Sánchez-Cordero, K., & Monzón, N. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-04968-1_23
Synthetic Data for Robust Runway Detection
Chigot, E., Wilson, D. G., Ghrib, M., Jimenez, F., & Oberlin, T. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-04968-1_25
“One-stage detectors, such as YOLO [18] and SSD [15], prioritize speed over accuracy by directly predicting object location and class probabilities from the image.”
Multi-modal Human-Robot Collaboration in Production Lines Through Speech Commands and Gestures
Carletti, V., Greco, A., Longobardi, D., et al. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-05060-1_26
PLRF-NMS: A Piecewise Linear Rational Function in Non-Maximum Suppression
Persson, I., Ardö, H., & Nilsson, M. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-05060-1_29
Ding, K., Jian, S., & Jin, L. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-04624-6_13 · Cited by 1
Barodi, A., Benbrahim, M., & Zemmouri, A. (2025) · Vehicles · doi:10.3390/vehicles7030099
Rep-YOLOv8: an enhanced object detector with deep feature representation for autonomous driving
Sun, Y., Chen, G., Ma, Y., Wang, H., Zhen, M., & Gao, X. (2025) · The Journal of Supercomputing · doi:10.1007/s11227-025-07834-2 · Cited by 1
“CNN-based object detection techniques are primarily classified into two categories: two-stage detection algorithms, exemplified by the RCNN series [8], and one-stage detection algorithms, represented by YOLO [9].”
Research on Weed Object Detection in Sorghum Growth Environments
Qian, S., & Jiang, F. (2025) · IEEE International Conference on Electronic Information and Communication Technology (ICEICT) · doi:10.1109/iceict66683.2025.11160297
“In HGNetV2,the first stage is HGStem [5] (High-Resolution Stem Module), which enhances the Backbone for image feature extraction.”
Zhang, J., Zhao, P., Liu, L., Peng, B., Liu, Z., Wang, L., & Wei, Y. (2025) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2025.3611094 · Cited by 1
Jingxiong, C., Wu, Z., Lai, G., et al. (2025) · IEEE International Conference on Electronic Information and Communication Technology (ICEICT) · doi:10.1109/iceict66683.2025.11160228
“In recent years, with the rapid development of AI deep learning technology, Fast R-CNN [2] , Mask R-CNN [3] , SSD [4] , and YOLO [5-8] .”
Ding, H., & Du, S. (2025) · IEEE International Conference on Pattern Recognition and Machine Learning (PRML) · doi:10.1109/prml66062.2025.11160295
“In contrast, single-stage methods such as YOLO [5], SSD [6], and RetinaNet [7] directly regress object positions on feature maps, bypassing the region proposal step.”
Faster Container Code Detection and Recognition
Liu, A.-C., Hsieh, J.-W., & Chang, C. (2025) · International Conference on Computer Communication and the Internet (ICCCI) · doi:10.1109/iccci65070.2025.11158597
“In recent years, the advancements in convolutional neural networks (CNNs) models like VGG [12], SSD [13], and YOLO [14], [15], etc. have achieved excellent performance in object detection, classification, and related analysis tasks.”
Lightweight YOLOv8n Target Detection Network for Fog-Interference Resistance on Foggy Roads
Xiao, G., Zhang, D., Gao, Q., Huang, W., Peng, F., & Hai, Q. (2025) · IEEE International Conference on Electronic Information and Communication Technology (ICEICT) · doi:10.1109/iceict66683.2025.11160145
“Object detection algorithms based on the YOLO framework [1]-[8] have been widely used in general-purpose scenarios with weak noise interference by virtue of their efficient single-stage inference, and have shown significant advantages in real-time demanding tasks such as traffic monitoring and UAV…”
Deep Robust Object Detection Under High Illumination Conditions Using Modulo Images
Toscano-Palomino, L., Contreras, K., Monroy, B., et al. (2025) · doi:10.1109/stsiva66383.2025.11156687
“A representative example is You Only Look Once (YOLO), a real-time detection model trained to identify and classify objects within images using supervised learning [12].”
CDSNet: Crack detection and segmentation network for tunnelPreprint
Wu, X., & Zhang, H. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5497574
Lopes, M., & Miranda, B. (2025) · Simpósio Brasileiro de Testes de Software Sistemático e Automatizado (SAST) · doi:10.5753/sast.2025.14437
“To further refine the system, an object-detection model based on the YOLO architecture, initially proposed by Redmon et al. [11], was employed.”
Automated lesion detection in endoscopic imagery for small animal models – a pilot study
Eixelberger, T., Hackner, R., Fang, Q., Zohud, B. A., Stürzl, M., Naschberger, E., & Wittenberg, T. C. (2025) · Biomedizinische Technik/Biomedical Engineering · doi:10.1515/bmt-2025-0179
“Recent studies in automatic polyp detection indicate that the one stage YOLO ( ‘ you only look once ’ ) architecture by Redmon et al. [22] is capable of achieving both high performance scores and real-time inference.”
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.