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 19,501–19,600 of 51,400
Improved YOLO Algorithm Based on Multi-Scale Object Detection in Haze Weather Scenarios
Shi, J., Ruan, S., Tao, Y., Rui, Y., Deng, J. M., Liao, P., & Mei, P. (2025) · CHAIN · doi:10.23919/chain.2025.000008 · Cited by 8
Tian, T., Lu, D., Kong, F., Ma, Y., Li, J., & Du, X. (2025) · Engineering Structures · doi:10.1016/j.engstruct.2025.120581 · Cited by 8
MB-YOLO: a deep learning-based network for detecting cracks in highway tunnel linings
Lu, G., Kou, L., Yan, W. S., et al. (2025) · Measurement Science and Technology · doi:10.1088/1361-6501/addbfd · Cited by 7
“Mainstream target detection algorithms include single-stage detection meth-ods represented by the You Only Look Once (YOLO) [12] series and single shot detection [13], as well as two-stage detection algorithms represented by region-based convolutional neural network (R-CNN) [14] and the Faster…”
Implications of Artificial Intelligence for Assessing the Built Environment
Moradi, F., & Biloria, N. M. (2025) · Journal of Urban Technology · doi:10.1080/10630732.2025.2468142 · Cited by 9
Zhang, K., Mao, B., Liu, H., & Zhang, Y. (2025) · Measurement · doi:10.1016/j.measurement.2025.117948 · Cited by 12
GA-DETR: a lightweight and efficient infrared target detection method for UAVs
Wu, P., Yao, T., He, W., & Zhang, L. (2025) · The Journal of Supercomputing · doi:10.1007/s11227-025-07247-1 · Cited by 7
“In contrast, one-stage detection algorithms, such as single shot multi-box detector (SSD) [5], EfficientDet [6], and the YOLO [7] series, directly predict the class and bounding box of the target, omitting the region generation step, thus significantly improving detection speed.”
Surface Defect Detection of Ultrathin Fiberboard Based on Improved YOLOv8x
Long, Y., & Lin, W. (2025) · Journal of Nondestructive Evaluation · doi:10.1007/s10921-025-01196-8 · Cited by 8
“The YOLO (You Only Look Once) [17] algorithm is a single-stage, high-precision object detection method.”
Das, M., Ferreira, G., & Chen, C. J. (2025) · Smart Agricultural Technology · doi:10.1016/j.atech.2025.101054 · Cited by 10
Improved UAV Target Detection Model for RT-DETR
He, Y. J., Pang, Y., Ou, G., et al. (2025) · IEEE Access · doi:10.1109/access.2025.3575189 · Cited by 7
Dittakan, K., Thaenthong, J., & Prasomkit, T. (2025) · IEEE Access · doi:10.1109/access.2025.3575811 · Cited by 10
MOSE: A Novel Orchestration Framework for Stateful Microservice Migration at the Edge
Calagna, A., Yu, Y., Giaccone, P., et al. (2025) · IEEE Transactions on Network and Service Management · doi:10.1109/tnsm.2025.3579051 · Cited by 7
“Ultralytics is a renown off-the-shelf solution that integrates (i) YOLOv8 [51], a widely used collection of pre-trained real-time object detection and image segmentation models, and (ii) BoT-SORT [52], a cutting-edge multi-object tracking algorithm that, leveraging motion modeling and…”
Individual tree extraction through 3D promptable segmentation networks
Xiu, T., Qi, H., Xu, J., & Liang, X. (2025) · Methods in Ecology and Evolution · doi:10.1111/2041-210x.70057 · Cited by 11
“Another strand of literature applied the YOLO model (Redmon et al., 2016 ) to detect the individual tree crowns (ITCs), thereafter leveraging the areas of ITC segments for tree extraction (Straker et al., 2023 ; Sun et al., 2022 ).”
SR-DETR: Target Detection in Maritime Rescue from UAV Imagery
Liu, Y., & Wei, Y. (2025) · Remote Sensing · doi:10.3390/rs17122026 · Cited by 10
Alam, F., Ullah, A., Shah, D., Ali, S., & Tahir, M. (2025) · International Journal of Intelligent Systems · doi:10.1155/int/3164952 · Cited by 14
Att-YOLO: A Real-Time Rock Core Classification and Localization Deep Learning Model
Yu, S., & Wong, L. N. Y. (2025) · Rock Mechanics and Rock Engineering · doi:10.1007/s00603-025-04641-2 · Cited by 8
“You Only Look Once (YOLO) is a state-of-the-art single-stage object detection algorithm in computer vision, proposed by Redmon et al. (2016).”
Enhanced YOLOv10 for small object detection with context-aware and adaptive modules
Wang, J., Su, J., Wen, Z., & Sun, Y. (2025) · International Journal of Multimedia Information Retrieval · doi:10.1007/s13735-025-00373-9 · Cited by 8
“In the field of object detection, YOLO [1] series models are widely recognized for their efficient real-time performance and accuracy.”
RST-YOLOv8: An Improved Chip Surface Defect Detection Model Based on YOLOv8
Tang, W., Deng, Y., & Luo, X. (2025) · Sensors · doi:10.3390/s25133859 · Cited by 9
“One-stage models are characterized by fast detection speeds but lower accuracy, with representative algorithms including the YOLO [3–9] series and SSD [10].”
Wang, Y., Wu, T., Guo, L., & Mo, Y. (2025) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2025.3582861 · Cited by 12
A lightweight adaptive feature selection network for enhanced small object detection in UAV imagery
Yu, J., Wu, J., & Tang, Y. (2025) · The Visual Computer · doi:10.1007/s00371-025-04057-7 · Cited by 8
Choudhary, S., Saurav, S., Gidde, P., Saini, R., & Singh, S. K. (2025) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2025.110476 · Cited by 8
MCDet: Target-Aware Fusion for RGB-T Fire Detection
Xu, Y., Wang, H., Bi, Y., Nie, G., & Wang, X. (2025) · Forests · doi:10.3390/f16071088 · Cited by 8
Yao, Y., Liu, C., Li, J., & Wu, J. (2025) · Measurement · doi:10.1016/j.measurement.2025.118213 · Cited by 8
The Lightweight Method of Ground Penetrating Radar (GPR) Hidden Defect Detection Based on SESM-YOLO
Yan, Y. J., Jiao, G., Cui, M., & Ni, L. (2025) · Buildings · doi:10.3390/buildings15132345 · Cited by 10
Damage detection in aircraft engine borescope inspection using deep learning
Uzun, I., Tolun, M. R., Sarı, F., & Alpaslan, F. N. (2025) · Neural Computing and Applications · doi:10.1007/s00521-025-11443-8 · Cited by 11
“Using open source labelImg software [25] (Windows version), images were labeled in Pascal Voc format (xml) [5] as well as YOLO (txt) [17] format by the aeronautical engineer.”
Raza, N., Habib, M. A., Imran, H. M., Qayum, M. A., Perveen, S., Jabbar, S., Sarwar, S., & Ahmad, M. (2025) · IEEE Access · doi:10.1109/access.2025.3588376 · Cited by 9
Wennmann, M., Kächele, J., von Salomon, A., Nonnenmacher, T., Bujotzek, M., Xiao, S., Mora, A. M., Hielscher, T., Hajiyianni, M., Menis, E., et al. (2025) · Academic Radiology · doi:10.1016/j.acra.2025.06.034 · Cited by 8
Aussel, B., Rüsch, O., Gundlach, B., Bickel, V., Kruk, S., & Sefton‐Nash, E. (2025) · Journal of Geophysical Research Planets · doi:10.1029/2025je008981 · Cited by 8
Cooperative Mapping, Localization, and Beam Management via Multi-Modal SLAM in ISAC Systems
Que, H., Yang, J., Du, T., et al. (2025) · IEEE Transactions on Communications · doi:10.1109/tcomm.2025.3588548 · Cited by 7
“…θ j,l ( t ) , φ j,l ( t ) for the NLoS path and the path gain g j,l ( t ) are given by tan θ j,l ( t ) = x UEY ,j ( t ) − x VAY ,l x UEX ,j ( t ) − x VAX ,l , (4a) with γ j,l ( t ) = ( π − | θ j,l ( t ) − φ j,l ( t ) | ) / 2 being the reflection angle and ε the dielectric constant of the wall.”
A robotic grasping method of box-shaped objects based on Dual-Stream You Only Look Once framework
Deng, H., Shi, J., Cui, J., Bai, S., & Zuo, X. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.111559 · Cited by 8
How sentiment volatility of influencer product recommendation posts affects customer engagement
Zhang, M., Xie, K., Cai, S., & Wang, Y. (2025) · Journal of Business Research · doi:10.1016/j.jbusres.2025.115597 · Cited by 9
Yang, X., Wang, H., Zhou, Q. T., Lü, L., Zhang, L., Sun, C., & Wu, G. (2025) · Algorithms · doi:10.3390/a18070433 · Cited by 11
Bai, Z., Zou, D., Liu, T., Li, K., Luo, W., Liao, H., & Zhou, A. (2025) · Construction and Building Materials · doi:10.1016/j.conbuildmat.2025.142718 · Cited by 8
Utilizing information technology to address challenges in Hajj and Umrah: A narrative review
Abdoh, E. S. (2025) · Journal of Information Studies & Technology (JIS&T) · doi:10.5339/jist.2025.12 · Cited by 10
An Overview on Machine Learning Techniques for Detection and Classification of Fish in Aquaculture
Raghavendra, C. G., George, A. A., & Niranjanamurthy, M. (2025) · International Conference on Intelligent Sustainable Systems (ICISS) · doi:10.1109/iciss63372.2025.11076412 · Cited by 7
Evaluating YOLO for dental caries diagnosis: a systematic review and meta-analysis
Lam, Q. T., Minh, L. H. N., Lee, I., & Le, N. Q. K. (2025) · Evidence-Based Dentistry · doi:10.1038/s41432-025-01180-1 · Cited by 13
“It is designed to determine the entire image in order to encode contextual information, including the object ’ s features and division 17 .”
Dang, Y., Wang, H., & Fan, Y. (2025) · Journal of Real-Time Image Processing · doi:10.1007/s11554-025-01739-2 · Cited by 8
“Rep-resentative algorithms include SSD [8], RetinaNet [9], and the YOLO series [10–13].”
Barefoot Footprint Detection Algorithm Based on YOLOv8-StarNet
Shen, Y., Jiang, X., Zhao, Y., & Xie, W. (2025) · Sensors · doi:10.3390/s25154578 · Cited by 8
“Through continuous iteration and development, YOLO has been applied to numerous visual tasks, from the initial YOLOv1 [20] to YOLOv8, with its architecture and performance continuously improving.”
Object detection-based deep autoencoder hashing image retrieval
Erkan, U., Yılmaz, A., Toktaş, A., et al. (2025) · Signal Processing Image Communication · doi:10.1016/j.image.2025.117384 · Cited by 7
A review on computer-aided diagnostic system to classify the disorders of the gastrointestinal tract
Ramzan, M. R., Raza, M., Khan, Z. F., Khan, M. A., Bačanin-Džakula, N., Damaševičius, R., Jeon, S., & Nam, Y. (2025) · European journal of medical research · doi:10.1186/s40001-025-02718-w · Cited by 11
“A high-sensitivity algo-rithm utilizes to identify the real-time pattern from the images is known as you only look once (YOLO) to detect and pinpoint polyps [85].”
Fusion-Solar-Net for solar panel fault detection
Rohith, G., Rajalakshmi, R., Manish, D. S., & Arunagirinathan, R. N. (2025) · Results in Engineering · doi:10.1016/j.rineng.2025.106513 · Cited by 18
Saket, O., Aicha, A. B., & Fathallah, H. (2025) · Applied Intelligence · doi:10.1007/s10489-025-06797-4 · Cited by 9
“Then, I3D [66] is chosen for their ability to handle temporal information, while MobileNet [ 67] and YOLO [68], are utilized for their computational efficiency in real-time object detec - tion.”
Chaman, M., Maliki, A. E., Dahou, H., et al. (2025) · Engineering Technology & Applied Science Research · doi:10.48084/etasr.11320 · Cited by 7
Chen, H., Zhang, L., Yan, S., Li, X., & Wang, D. (2025) · Landslides · doi:10.1007/s10346-025-02596-7 · Cited by 7
“Major single-stage models include the SSD (Single Shot MultiBox Detector, Liu et al. 2016) and the YOLO (You Only Look Once, Redmon et al. 2016) series of network models.”
Feature Hallucination for Self-supervised Action Recognition
Wang, L., & Koniusz, P. (2025) · International Journal of Computer Vision · doi:10.1007/s11263-025-02513-4 · Cited by 12
“…deep learning-based object detection methods include Region-based Convolutional Neural Networks (R-CNN) [54], its faster variants [53, 120], mask-based extensions [58], and the YOLO family [119], including YOLO v2 and YOLO v3, which prioritize efficiency by using a single network architecture.”
Balancing complexity and accuracy for defect detection on filters with an improved RT-DETR
Zhang, M., Wei, X., Liu, G., et al. (2025) · Scientific Reports · doi:10.1038/s41598-025-13960-x · Cited by 7
A weld defect detection algorithm designed based on YOLOv9
Liu, L., Zhang, M., Zhou, X., et al. (2025) · Measurement · doi:10.1016/j.measurement.2025.118630 · Cited by 7
Test-Time Backdoor Detection for Object Detection Models
Zhang, H., Wang, Y., Yan, S., Zhu, C., Zhou, Z., Hou, L., Hu, S., Li, M., Zhang, Y., & Zhang, L. Y. (2025) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52734.2025.02270 · Cited by 40
Li, F., Lu, Y., Ma, Q., Yin, S., & Zhao, R. (2025) · Frontiers in Plant Science · doi:10.3389/fpls.2025.1620339 · Cited by 17
Rampavan, M., & Ijjina, E. P. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.111932 · Cited by 8
Zhou, H., Geng, Z., Sun, M., Wu, L., & He, Y. L. (2025) · Sensors · doi:10.3390/s25164938 · Cited by 8
“Models like CornerNet [5], Ex-tremeNet [6], CenterNet [7], Objects as Points [8], FCOS [9], and FoveaBox [10] demonstrate superior efficiency and accuracy by eliminating redundant computations.”
Zhou, W., Wang, J., Meng, X., Wang, J., Song, Y., & Liu, Z. (2025) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2025.104560 · Cited by 16
Jiang, H., Li, X., Liu, Z., Luo, S., Huang, J., Chen, C., Chen, R., & Li, F. (2025) · Micromachines · doi:10.3390/mi16080957 · Cited by 8
“To solve this problem, a deep learning approach was employed with the open-source YOLOv8 convolutional neural network for the semantic segmentation of cell images [60,61], see Figure 1.”
Cheng, J., Li, Y., Zhao, Z., Li, D., Zhong, L., Ding, S., & Yan, X. (2025) · Measurement Science and Technology · doi:10.1088/1361-6501/adfb9f · Cited by 10
“Among them, the YOLO series (Redmon [21]) and SSD [22] have become mainstream solutions for real-time detection due to their efficient architectures.”
Automated seed counting using image processing and deep learning
Zu, Q., Liu, T., Zhu, W., et al. (2025) · Frontiers in Plant Science · doi:10.3389/fpls.2025.1659781 · Cited by 7
Wang, Z., Hu, S., Wang, X., Gao, Y., Zhang, W., Chen, Y., Lin, H., Gao, T., Chen, J., Gong, X., et al. (2025) · Applied Sciences · doi:10.3390/app15179501 · Cited by 16
YOLOv8-DPE: a novel lightweight object detection network for weld defect detection
Yang, L., Gu, Y., & Feng, H. (2025) · Welding in the World · doi:10.1007/s40194-025-02147-7 · Cited by 8
SMI-YOLOv8: Intelligent detection of tunnel lining cracks via multiscale feature attention fusion
Dang, D., Gong, L., Jin, C., Cui, X., Yang, T., & Qin, J. (2025) · Measurement · doi:10.1016/j.measurement.2025.118833 · Cited by 12
Wang, Z., Sun, H., Calautit, J. K., Yang, M., Chen, J., Guan, R., & Darkwa, J. (2025) · Building Simulation · doi:10.1007/s12273-025-1335-6 · Cited by 11
“However, while Faster R-CNN was highly effective when introduced in 2015, newer algorithms such as YOLO offer improved speed and efficiency (Redmon et al. 2016).”
FEFM-YOLO11: Underwater Object Detection Algorithm Based on Improved YOLO11
Wang, Q., & Liu, Z. (2025) · Neural Processing Letters · doi:10.1007/s11063-025-11805-2 · Cited by 7
Deep learning-based kiwifruit flower recognition method to facilitate automated pollination
Li, X., Du, J., Chen, X., Shi, F., & Li, S. (2025) · Applied Soft Computing · doi:10.1016/j.asoc.2025.113855 · Cited by 9
Strawberry ripeness detection in complex environment based on improved RT‐DETR
Yang, G., Wu, Y., Weng, D., & Zeng, L. (2025) · Agronomy Journal · doi:10.1002/agj2.70162 · Cited by 10
Current Trends in Wildfire Detection, Monitoring and Surveillance
Bugarić, M., Krstinić, D., Šerić, L., & Stipaničev, D. (2025) · Fire · doi:10.3390/fire8090356 · Cited by 15
“A wide group of wildfire detection methods is based on the You Only Look Once (YOLO) algorithm and its variants [53].”
Feng, R., Zhu, H., Sze, N. N., et al. (2025) · Transportation Letters · doi:10.1080/19427867.2025.2559276 · Cited by 7
“The YOLO series (Redmon and Farhadi 2017; Redmon et al. 2016) and the R-CNN series (Ren et al. 2016) are two well-known methodologies in the field of convolutional neural networks (CNN) for object detection.”
Zulueta-Coarasa, T., Jug, F., Mathur, A., Moore, J., Muñoz‐Barrutia, A., Anita, L., Babalola, K., Bankhead, P., Paul‐Gilloteaux, P., Gogoberidze, N., et al. (2025) · Nature Methods · doi:10.1038/s41592-025-02835-8 · Cited by 18
Opentad: a Unified Framework and Comprehensive Study of Temporal Action Detection
Liu, S., Zhao, C., Zohra, F., Soldan, M., Pardo, A., Xu, M., Alssum, L., Ramazanova, M., Alcázar, J. L., Cioppa, A., et al. (2025) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw67362.2025.00247 · Cited by 19
Granulocyte abundance and maturation state at diagnosis predicts treatment-free remission in CML
Purhonen, M., Tatun, M., Luukkainen, K., Hung, K., Sundquist, H., Tafjord, O., Söderlund, S., Awad, S. A., Døhlen, A., Heikkinen, J., et al. (2025) · Leukemia · doi:10.1038/s41375-025-02769-2 · Cited by 10
“Computer vision algorithms utilize various Convolutional Neural Network (CNN) architectures [24, 25], as well as the Vision Transformer (ViT) [26] architecture.”
Enhancing YOLO-Based SAR Ship Detection with Attention Mechanisms
Rocha, R. D. L., & de Figueiredo, F. A. P. (2025) · Remote Sensing · doi:10.3390/rs17183170 · Cited by 16
A systematic review of deep learning-based object detection methods for crop grading
Zhu, X., Ren, L., Yang, M., Zhang, Y., Zhang, C., Cui, J., & Liu, J. (2025) · CABI Agriculture and Bioscience · doi:10.1079/ab.2025.0060 · Cited by 8
UAV-Based Transport Management for Smart Cities Using Machine Learning
Balivada, S., Gao, J. Z., Sha, Y., et al. (2025) · Smart Cities · doi:10.3390/smartcities8050154 · Cited by 7
“Furthermore, This research focused on employing these traditional models to effectively identify livestock and wild animal detection using Faster RCNN and Unet [5,6] and monitor obstacles in urban scenarios.”
Dong, T., Wang, T., Han, Y., Li, D., Guo Zhang, A., & Peng, Y. (2025) · Remote Sensing · doi:10.3390/rs17193301 · Cited by 11
Cherry-YOLO: enhanced real-time detection of Cherry ripeness and defects with optimised YOLOv8
Luan, F., Fan, K., Xu, X., et al. (2025) · Computing · doi:10.1007/s00607-025-01558-0 · Cited by 7
“Two-stage detectors like Faster R-CNN [ 15 ] offer high accuracy but are computationally demanding, while single-stage detectors such as YOLO [ 16] and SSD [ 17 ] offer real-time speed with competitive accuracy.”
Gonzalez-Mohino, M. B., Ruiz-Santaquiteria, J., Cristóbal, G., Perona, E., Salido, J., & Bueno, G. (2025) · Aquatic Ecology · doi:10.1007/s10452-025-10227-5 · Cited by 9
“In the study by Park et al. (2022), deep learning algorithms were applied for algae detection using the You Only Look Once (YOLO) architecture (Redmon 2016) to detect and classify 30 algal genera using 437 images.”
Crack Segmentation Using U-Net and Transformer Combined Model
Noh, J.-H., Jang, J., Jo, J., et al. (2025) · Applied Sciences · doi:10.3390/app151910737 · Cited by 7
CottonSim: A vision-guided autonomous robotic system for cotton harvesting in Gazebo simulation
Thayananthan, T., Zhang, X., Huang, Y., Chen, J., Wijewardane, N. K., Martins, V. S., Chesser, G. D., & Goodin, C. T. (2025) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2025.110963 · Cited by 8
“Cotton boll detection and scene segmentation using YOLOv8 You Only Look Once (YOLO), as one of the most popular deep learning models first introduced in 2016 (Redmon et al., 2016), revolutionized the field of computer vision.”
Expert-Guided Explainable Few-Shot Learning for Medical Image Diagnosis
Uddin, I. I., Wang, L., & Santosh, K. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-08009-7_10 · Cited by 24
Zhao, X., Zhang, H., Li, C., Wang, K., & Zhang, Z. (2025) · Remote Sensing · doi:10.3390/rs17203411 · Cited by 20
ADG-YOLO: A Lightweight and Efficient Framework for Real-Time UAV Target Detection and Ranging
Wang, H., Dang, Z., Cui, M., Shi, H., Qu, Y., Ye, H., Zhao, J., & Wu, D. (2025) · Drones · doi:10.3390/drones9100707 · Cited by 8
Real-Time Object Detection and Classification using YOLO for Edge FPGAs
Amin, R. A., & Obermaisser, R. (2025) · International Symposium ELMAR (ELMAR) · doi:10.1109/elmar66948.2025.11193980 · Cited by 12
“However, both approaches face limitations in detecting small or densely packed objects [1], which are often encountered in real-world scenes. contrast, the YOLO family of algorithms has demonstrated high performance in real-time applications, offering a good balance between speed and accuracy [2].”
A YOLO-based substation defect detection model with enhanced feature extraction and fusion
Cheng, W., Liu, Z., Du, J., Yang, W., & Wang, T. (2025) · Electric Power Systems Research · doi:10.1016/j.epsr.2025.112354 · Cited by 9
An efficient and lightweight algorithm for detecting surface defects of steel based on SCCI-YOLO
Zhou, H., Zou, H., & Hu, G. (2025) · Scientific Reports · doi:10.1038/s41598-025-20154-y · Cited by 7
Zhang, X., Chen, M., & Huang, Y. (2025) · Sustainable Cities and Society · doi:10.1016/j.scs.2025.106906 · Cited by 11
Fixing Background Misclassification in Few-Shot Object Detection via Product of Experts
Ong, D. S., Liu, Y., Shang, C., Ding, G., Shen, Q., & Han, J. (2025) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2025.3622983 · Cited by 8
“While the majority of FSOD research has been developed on two-stage architectures, particularly Faster R-CNN [47], a few studies have explored the feasibility of one-stage detectors such as YOLO [46] and DETR [3].”
Gu, Y., Chen, L., & Su, T. (2025) · World Electric Vehicle Journal · doi:10.3390/wevj16110591 · Cited by 9
Fpa-yolov8s: an efficient small object detection algorithm for drone aerial imagery
Nan, H., & Cheng, L. (2025) · Pattern Analysis and Applications · doi:10.1007/s10044-025-01566-y · Cited by 10
“The initial YOLOv1 model, proposed by Redmon et al. [ 7 ], utilized convolutional neural networks (CNNs) to extract features, enabling the identification of object categories and locations.”
Katsamenis, I., Bakalos, N., Lappas, A. S., Protopapadakis, E. E., Montoliu, C. M.-P., Doulamis, A. D., Doulamis, N. D., Rallis, I., & Kalogeras, D. (2025) · Sensors · doi:10.3390/s25216653 · Cited by 9
“This study focuses on comparing three recent generations of the YOLO (You Only Look Once) family [14], and in particular YOLOv8, YOLOv11, and YOLOv12, across their various scales (nano, small, medium, and large) to determine the most effective architecture for detecting the road elements that were…”
PSDD: A Benchmark PolSAR Dataset for CNN Performance Evaluation of Ship Detection
Gao, G., Yang, G., Zhang, C., Bai, Q., Li, C., Zhang, L., & Duan, D. (2025) · IEEE Aerospace and Electronic Systems Magazine · doi:10.1109/maes.2025.3628216 · Cited by 13
“…of 10 commonly used CNN detectors was considered: Faster R-CNN [57], Mask R-CNN [58], region-based fully convolutional network (R-FCN) [59], Retina-Net [60], SSD512 [61], receptive field block network (RFBNet) [62], You Only Look Once (YOLOv3) [63], YOLOv4 [64], CenterNet [65], and EfficientNet [66].”
Smoke Detection on the Edge: A Comparative Study of YOLO Algorithm Variants
Polenakis, I., Sarantidis, C., Karydis, I., & Avlonitis, M. (2025) · Signals · doi:10.3390/signals6040060 · Cited by 6
Niu, J., Li, M., Lin, H., Liu, Y., Liu, Z., Li, H., & Niu, S. (2025) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2025.3630098 · Cited by 9
Shi, Y., Zhan, X., Li, Y., Wu, Z., Zhang, W., & Li, H. (2025) · Measurement · doi:10.1016/j.measurement.2025.119602 · Cited by 11
Key technologies and latest research progress of automated robotic welding: a review
Li, Y., Xu, Y., Wang, X., Ma, X., Wang, Q., & Zhang, H. (2025) · Journal of Intelligent Manufacturing · doi:10.1007/s10845-025-02700-7 · Cited by 11
Unifying ground and air: a comprehensive review of deep learning-enabled CAVs and UAVs
Zia, M. U., Xiang, W., Huang, T., Ahmad, J., Chattha, J. N., Naqvi, I. H., & Butt, F. A. (2025) · Artificial Intelligence Review · doi:10.1007/s10462-025-11425-1 · Cited by 14
RMH-YOLO: A Refined Multi-Scale Architecture for Small-Target Detection in UAV Aerial Imagery
Yang, F., He, M., Liu, J., et al. (2025) · Sensors · doi:10.3390/s25227088 · Cited by 7
“Representative models include SSD [15], RetinaNet [16], and the YOLO family [17].”
HF-D-FINE: High-resolution features enhanced D-FINE for tiny object detection in UAV image
Hu, Q., & Wang, L. (2025) · Image and Vision Computing · doi:10.1016/j.imavis.2025.105834 · Cited by 9
Enhancing object detection in remote sensing images with improved YOLOv8 model
Hu, Z., Chen, W., Yang, D., Wang, Z., & Wang, P. (2025) · Scientific Reports · doi:10.1038/s41598-025-26536-6 · Cited by 17
Frontiers and advances of deep learning-based fruit and vegetable image analysis
Ma, J., Wan, Y., Min, W., Ma, Z., Tan, L., & Jiang, S. (2025) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2025.111256 · Cited by 12
Fine-Grained Interpretation of Remote Sensing Image: A Review
Wang, D., Yan, Z., & Liu, P. (2025) · Remote Sensing · doi:10.3390/rs17233887 · Cited by 15
Schmid, P. E., Hirschberg, J., Spielmann, R., & Aaron, J. (2025) · Natural hazards and earth system sciences · doi:10.5194/nhess-25-4863-2025 · Cited by 5
“…velocities (cid:58)(cid:58)(cid:58) are (cid:58)(cid:58)(cid:58)(cid:58)(cid:58)(cid:58)(cid:58)(cid:58) restricted (cid:58)(cid:58) to (cid:58)(cid:58) the (cid:58)(cid:58)(cid:58)(cid:58)(cid:58)(cid:58)(cid:58) LiDAR field of viewof the LiDAR sensors”
Hybrid Multi-Scale Neural Network with Attention-Based Fusion for Fruit Crop Disease Identification
Seilov, S., Nurzhaubayev, A., Baideldinov, M., Zhursinbek, B., Ashimgaliyev, M., & Zhumadillayeva, А. (2025) · Journal of Imaging · doi:10.3390/jimaging11120440 · Cited by 9
“While multilevel feature fusion allows the model to maintain both fine-grained features and high-level semantic information, multiscale approaches help in the capturing of lesions and disease symptoms at different sizes and shapes [33,43–45].”
Chen, H., Tang, X., Xiang, Q., Shi, Z., Liu, J., Dai, L., Ye, S., Xiao, Z., & Zhang, L. (2025) · Journal of Real-Time Image Processing · doi:10.1007/s11554-025-01726-7 · Cited by 8
“In contrast, one-stage detectors like YOLO and SSD use end-to-end architectures that simultaneously perform target localization and classification [22–24], making them more suitable for real-time surface applications such as vessel surveillance and unmanned surface vehicle navigation, where low…”
Nguyen, T., & Tran, M. K. P. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-4963-4_8 · Cited by 8
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.