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 33,801–33,900 of 51,399
Yolo-tir: an improved YOLOv5 model for vehicle and pedestrian in thermal infrared images
Yao, S., Yu, K., Li, L., Zhang, K., & Liu, Y. (2025) · Soft Computing · doi:10.1007/s00500-025-10641-9 · Cited by 2
A video dataset for hadal snailfish along with the benchmark
Zhang, J., & Wang, Y. (2025) · Deep Sea Research Part I Oceanographic Research Papers · doi:10.1016/j.dsr.2025.104517 · Cited by 1
Wang, R., Wang, H., & Shi, H. (2025) · International Conference on Algorithms, Software Engineering and Network Security (ASENS) · doi:10.1109/asens64990.2025.11011055 · Cited by 1
Zhao, K., Liu, T., Xia, X., & Zhao, Y. (2025) · Sensors · doi:10.3390/s25113373 · Cited by 1
“YOLOv1, proposed by Redmon in 2016 [21], significantly improved detection speed by transforming the object detection task into a regression problem.”
SegAttnDetec: A Segmentation-Aware Attention-Based Object Detector
Sundaralingam, H., Suresh, T., & Akilan, T. (2025) · Procedia Computer Science · doi:10.1016/j.procs.2025.03.274 · Cited by 1
Smart Traffic Management System Emergency Vehicle
R, S. G. K., Prajwal, N., Pramod, B. V. N., et al. (2025) · doi:10.38124/ijisrt/25may1592 · Cited by 1
Lrt-detr: a lightweighted RT-DETR with RepFormer and SimpleUpsample for fast object detection
Li, A., Cheng, K., Hua, X., & Wang, Y. (2025) · Signal Image and Video Processing · doi:10.1007/s11760-025-04112-9 · Cited by 1
“The early deep learning methods for object detection, such as SSD [2] and YOLO [3] series, are based on CNN architecture.”
Leveraging Temporal Gaze Patterns for Intelligent Segmentation in Mobile Eye-Tracking
Wang, S., Chen, Y., Wu, S., Kiefer, P., & Raubal, M. (2025) · Proceedings of the ACM on Computer Graphics and Interactive Techniques · doi:10.1145/3729412 · Cited by 1
A Comparative Study of YOLOv5 and YOLOv8 for Helmet Detection Inside ATMs
Sharma, P. K., Lakshmipriya, B., Poonguzhali, N., et al. (2025) · doi:10.1109/incacct65424.2025.11011332 · Cited by 1
“Family of you look only once (YOLO) architectures are the prominent single stage detectors predict directly categorize the object classes and bounding box and are hence faster than the two stage detectors [10].”
Zhang, S., He, S., Wu, J., Wang, D., Zeng, P., & Lyu, G. (2025) · Computerized Medical Imaging and Graphics · doi:10.1016/j.compmedimag.2025.102582 · Cited by 1
Gas sensors and real-time video for accurate classroom occupancy detection
Challa, K., AlHmoud, I. W., Jaiswal, C., et al. (2025) · MethodsX · doi:10.1016/j.mex.2025.103386 · Cited by 1
Towards high-accuracy digital detection in meter images: The ASS-YOLO algorithm and Dig21000 dataset
Xie, W., Guo, Y., Wu, Z., et al. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.130606 · Cited by 1
Tseng, Y.-S., Su, Y.-F., & Lin, D.-T. (2025) · Multimedia Tools and Applications · doi:10.1007/s11042-025-20910-2 · Cited by 5
Zocco, F., Lake, D. R., McLoone, S., & Rahimifard, S. (2025) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2025.3574911 · Cited by 8
MPA-Det: multi-path aggregation-based object detection framework for aerial visual computing
Lei, Y., Jin, K., Qiu, Z., Sun, Y., Bai, H., & He, W. (2025) · The Visual Computer · doi:10.1007/s00371-025-03933-6 · Cited by 2
“Single shot detectors, such as YOLO (You Only Look Once) [23] and SSD (Single Shot Multi-Box Detector) [24], have elevated object detection to new levels of efficiency by directly predicting object bounding boxes and class probabilities across the entire image, bypassing the explicit region proposal…”
Li, D., Peng, X., Ye, Z., Cao, H., Wang, B., Zhao, X., & Shi, F. (2025) · Nanomaterials · doi:10.3390/nano15110821 · Cited by 3
“In 2015, Redmon et al. dropped the You Only Look Once (YOLO) algorithm, marking a pivotal breakthrough in the field of object detection [14].”
Yan, B., Zhang, Y., & He, Q. (2025) · Journal of Imaging Informatics in Medicine · doi:10.1007/s10278-025-01512-8 · Cited by 2
Kashkoush, A. I., Davison, M. A., Achey, R. L., et al. (2025) · Neurosurgery · doi:10.1227/neu.0000000000003534 · Cited by 1
Optimizing YOLOv7 Versus YOLOv8: A Comparative Study on Fruit Detection Performance
Saeleung, P., Chotikawanid, P., Pianroj, Y., Jumrat, S., Punvichai, T., & Muangprathub, J. (2025) · Lecture notes in networks and systems · doi:10.1007/978-981-96-1747-0_33 · Cited by 2
TRYOLO: A Transformer-Based Real-Time Object Detection Model for UAV Images
Dewangan, B., Srinivas, M., & Subramanyam, R. B. V. (2025) · Communications in computer and information science · doi:10.1007/978-3-031-94263-1_3 · Cited by 1
Anchor-Free SNR-Aware Signal Detector for Wideband Signal Detection Framework
Li, C., Xiang, X., Hu, M., Wang, R., & Qi, Y. (2025) · Electronics · doi:10.3390/electronics14112260 · Cited by 2
An Improved YOLOv10 Algorithm for Kitchen Hygiene and Safety Monitoring
Liu, S., Huang, G., & Dai, Z. (2025) · doi:10.1109/iscait64916.2025.11010788 · Cited by 1
Enhancing Bee Mite Detection with YOLO: The Role of Data Augmentation and Stratified Sampling
Lee, H., Shin, J.-Y., Kim, S.-B., Kim, M.-J., Kim, M. S., Lee, H., & Mo, C. (2025) · Agriculture · doi:10.3390/agriculture15111221 · Cited by 4
DAT-YOLO: Small Object Detection Model from the Perspective of Drones
Li, W., Zhang, K., Li, P., & Yan, K. (2025) · International Conference on Generative Artificial Intelligence and Information Security (GAIIS) · doi:10.1145/3728725.3728810 · Cited by 2
Improved YOLOv5 network for recognizing fuzzy image detection
Zhang, Y., & Zhao, T. (2025) · Journal of the Chinese Institute of Engineers · doi:10.1080/02533839.2025.2511262 · Cited by 1
“(J. S. D. Redmon, Girshick, and Farhadi 2016) proposed the first version of YOLO.”
Human-Centric Depth Estimation: A Hybrid Approach with Minimal Data
Kim, Y., Ahn, H., Kim, T., Ahn, B., & Choi, D. (2025) · Electronics · doi:10.3390/electronics14112283 · Cited by 1
MFVL-YOLO: small object detection algorithm for aerial remote sensing images
Wang, F., jin, J., Xiao, C., Wang, C., & Neha, N. (2025) · Physica Scripta · doi:10.1088/1402-4896/ade1b6 · Cited by 1
Liu, Y., Shi, Z.-H., Jin, Y., Yang, C., & Liu, C. (2025) · Artificial Intelligence in Medical Imaging · doi:10.35711/aimi.v6.i1.106928 · Cited by 1
Nasri, M., Yin, S., & Wang, Y. (2025) · ASCE International Conference on Transportation and Development (ICTD) · doi:10.1061/9780784486191.013 · Cited by 1
Mitra, R., Sourav, M. A. A., Kim, S., Gülmezoğlu, B., & Ceylan, H. (2025) · ASCE International Conference on Transportation and Development (ICTD) · doi:10.1061/9780784486191.027 · Cited by 5
Bhattacharjya, U., Sarma, K. K., Kakati, A., Medhi, J. P., Barman, G., & Choudhury, B. K. (2025) · IEEE Sensors Letters · doi:10.1109/lsens.2025.3576896 · Cited by 2
Xu, S. (2025) · Advances in transdisciplinary engineering · doi:10.3233/atde250255 · Cited by 1
A Deep Learning based Approach for Automated Defect Detection of Fabrics in Garment Production Line
Zarif, S. A. A. M., Deori, P. J., Muna, U. M., et al. (2024) · International Conference on Computing Advancements (ICCA) · doi:10.1145/3723178.3723196 · Cited by 1
An Improved Lightweight Pest Detection Method Based on YOLOv8
Zhang, L., & Du, X. (2025) · Journal of Electronic Research and Application · doi:10.26689/jera.v9i3.10810 · Cited by 1
Ye, W., Ren, J., Liang, J., Liu, W., Yi, H., Zhang, A. A., & Lu, C. (2025) · Structural Health Monitoring · doi:10.1177/14759217251338866 · Cited by 2
“One-stage algorithms, like single-shot multibox detector, 22 and you only look once (YOLO) series algorithms, 23,24 directly extract features within the network to predict object classification and location.”
Enhanced multi-object tracking via appearance feature gating using UMAP
Arioka, K., & Sawada, Y. (2025) · SICE Journal of Control Measurement and System Integration · doi:10.1080/18824889.2025.2507984 · Cited by 1
“…the observation noise, with detailed definitions provided in [15]; τ is a multiplier coefficient controlling the effect of the confidence score, determined experimentally; b i ( i = 1, . . . , 8 ) are positive constants; and μ [ k ] is the confidence score [6], treated as a known value in the EKF.”
An Improved RT-DETR Object Detection Method for Substation Equipment
Zhu, J., & Tang, H. (2025) · International Conference on Advanced Algorithms and Control Engineering (ICAACE) · doi:10.1109/icaace65325.2025.11019525 · Cited by 1
CM -YOLO: A Highly Accurate YOLOv5 S-Based Model for Steel Surface Defect Detection
Li, L.-H., Ma, Y., & Su, L. (2025) · International Conference on Advanced Algorithms and Control Engineering (ICAACE) · doi:10.1109/icaace65325.2025.11018999 · Cited by 1
RML++: Regroup Median Loss for Combating Label Noise
Li, F., Li, K., Wang, Q., Han, B., Tian, J., & Zhou, J. (2025) · International Journal of Computer Vision · doi:10.1007/s11263-025-02494-4 · Cited by 13
“DNNs have been successfully applied in various practical tasks, e.g., image classification (Krizhevsky et al., 2012; Szegedy et al., 2015; Zhang et al., 2015), object detection (Girshick, 2015; Redmon et al., 2016), and image semantic segmentation (He et al., 2017; Zhang et al., 2018).”
Detecção Automática de Macrófagos em Esfregaço de Medula Óssea Canina com Deep Learning
Araújo, R. L., Dias, V. B. L., Borges, A. L., et al. (2025) · doi:10.5753/sbcas.2025.7650 · Cited by 1
Fontainha, T. C., Henriques, F. D. R., Lima, A. A. D., et al. (2025) · doi:10.5753/sbcas.2025.7629 · Cited by 1
Fast and Accurate Bangladeshi License Plate Identification using YOLO
Biswas, S., Islam, A., & Talukder, K. H. (2024) · International Conference on Computer and Information Technology (ICCIT) · doi:10.1109/iccit64611.2024.11022467 · Cited by 1
Smart Warehouse Monitoring System for Collaborative Character Recognition Platform Research
Liu, X., Tang, Z., Wang, W., et al. (2024) · Asian Conference on Artificial Intelligence Technology (ACAIT) · doi:10.1109/acait63902.2024.11022106 · Cited by 1
Performance Comparison of YOLO Setups for Agriculture Machine Surrounding Monitoring
Tarasiuk, K., Mystkowski, A., Ostaszewski, M., Majka, A. R., & Czarnigowski, J. A. (2025) · International Carpathian Control Conference · doi:10.1109/iccc65605.2025.11022828 · Cited by 3
“Notable examples of such approaches include YOLO [10] and Single Shot Multi-Box Detector (SSD) [11] networks.”
Tamezheneal, R., Nithyasree, M., Thenmozhi, A., Sathiyaprasad, B., Krishnaja, S., & Menaka, D. (2025) · doi:10.1109/iccct63501.2025.11020247 · Cited by 1
ANALYTICAL REVIEW OF NEURAL NETWORK ALGORITHMS FOR FIRE DETECTION IN EMERGENCY SITUATIONS
Zorin, V. A., & Meshcheryakov, R. V. (2025) · Bulletin of the South Ural State University series Mathematics Mechanics Physics · doi:10.14529/mmph250203 · Cited by 1
SDRT-DETR: A Novel Space Dim Target Detection Model Based on Real-Time Deformable Transformer
Chen, H., Yu, H., Wu, P., et al. (2024) · Asian Conference on Artificial Intelligence Technology (ACAIT) · doi:10.1109/acait63902.2024.11021797 · Cited by 1
Time series identification, classification, and display methods for periodic flow patterns
Fang, J., Li, R., Zhang, T., et al. (2025) · Flow Measurement and Instrumentation · doi:10.1016/j.flowmeasinst.2025.102977 · Cited by 1
Towards Reliable Tracking: An Uncertainty-Aware Siamese Tracker
Ma, J., Lan, X., Liang, Q., Li, G., Mo, Z., & Zhong, B. (2025) · IEEE Transactions on Emerging Topics in Computational Intelligence · doi:10.1109/tetci.2025.3575412 · Cited by 6
“Inspired by the excellent anchor-free detectors [26], [27], [28], [29], anchor-free methods have drawn significant attention due to their flexibility and efficiency in the tracking tasks.”
Hybrid Tunnel Entrance Detection via Multiple Morphological Component-Based Texture Enhancement
Huang, H., Chen, J., Chen, T., Li, J., & Plaza, A. (2025) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2025.3577214 · Cited by 1
AI-Assisted Robotic Eggplant Harvester with a Four Degree of Freedom Robotic Arm
Alwis, H., Madhuwantha, M. H. S. N., Sahib, M., et al. (2025) · International Research Conference on Smart Computing and Systems Engineering (SCSE) · doi:10.1109/scse65633.2025.11031024 · Cited by 1
A Lightweight Network for Vehicle and Pedestrian Object Detection in Autonomous Driving Scenarios
Zhu, Y., Zhang, Y., & Sun, K. (2025) · International Journal of Image and Graphics · doi:10.1142/s0219467827500434 · Cited by 1
基于YOLO提示与ICT-ViT的印刷电路板缺陷高效分割技术研究
Tieqiang, 孙. S., Hongjian, 于. Y., Can, 张. Z., Yidong, 袁. Y., & Aoran, 孙. S. (2025) · Laser & Optoelectronics Progress · doi:10.3788/lop242339 · Cited by 1
An efficient improved YOLOv10 algorithm for detecting electric bikes in elevators
Li, T., Lei, L., Wang, Z., et al. (2025) · Electronic Research Archive · doi:10.3934/era.2025163 · Cited by 1
Exponential data augmentation methods for improving YOLO performance in computer vision tasks
Myshkovskyi, Y., & Nazarkevych, M. (2025) · Vìsnik Nacìonalʹnogo unìversitetu Lʹvìvsʹka polìtehnìka Serìâ Ìnformacìjnì sistemi ta merežì · doi:10.23939/sisn2025.17.189 · Cited by 1
“According to [8] and [11], one of the key metrics for evaluating pattern recognition systems is Accuracy, which shows the ratio of correctly identified examples to their total number.”
Real-Time Polyp Detection: A Speed and Performance Analysis of YOLOv5 and YOLOv6
Demirel, S., Çelikten, A., Akpulat, A., et al. (2025) · Osmaniye Korkut Ata Üniversitesi Fen Bilimleri Enstitüsü Dergisi · doi:10.47495/okufbed.1544536 · Cited by 1
Efficient Drone Detection Method Based on YOLOv8s Improvement
Su, B., Zhang, J., & Lin, Y. (2025) · Computing and Informatics · doi:10.31577/cai_2025_2_445 · Cited by 3
Comparative Study of YOLO Versions for Airplane Detection in Remote Sensing Satellite Images
Rashad, R. A., Mahmoud, T. A., Sanad, I. S., & Hanafy, M. E. (2025) · doi:10.1109/iceeng64546.2025.11031270 · Cited by 1
“The YOLO framework was originally proposed by Redmon et al. in their seminal 2016 CVPR publication [10], establishing the first fully differentiable pipeline capable of real-time object detection.”
Advancing Traffic Sign Recognition: Real-Time Detection and Optimization with YOLOv8
Appavu, N. (2025) · International Conference on Distributed Computing and Electrical Circuits and Electronics (ICDCECE) · doi:10.1109/icdcece65353.2025.11035771 · Cited by 1
“By doing away with intricate pipelines, YOLOv1 [11] transformed real-time detection, and YOLOv4 [12] maximized effectiveness and precision for embedded systems.”
Ancient character detection based on fine-grained density map
Yue, M., Shi, D., Diao, X., Guo, S., Li, C., & Xu, H. (2025) · npj Heritage Science · doi:10.1038/s40494-025-01791-y · Cited by 9
Improving Long-Tailed Object Detection with Balanced Group Softmax and Metric Learning
Gaba, S. (2025) · IEEE International Conference on Semantic Computing (ICSC) · doi:10.1109/icsc64641.2025.00051 · Cited by 1
DScanNet: Packaging Defect Detection Algorithm Based on Selective State Space Models
Luo, Y., Du, Y., Wang, Z., et al. (2025) · Algorithms · doi:10.3390/a18060370 · Cited by 1
Simulated Object Detection in Underwater Environments
Morgan, P., White, L. G., Jensen, D. H., & Whitaker, B. M. (2025) · Intermountain Engineering, Technology and Computing (IETC) · doi:10.1109/ietc64455.2025.11039487 · Cited by 1
“YOLO was first developed by Joseph Redmond in 2015 [20].”
A Cloud-Edge Collaborative Framework for Object Detection Using Kubeedge
Qing, C., Zhang, L., Gao, Y., & Zhang, W. (2025) · International Conference on Cloud Computing and Big Data Analytics (ICCCBDA) · doi:10.1109/icccbda64898.2025.11030479 · Cited by 1
Diffusion Based Ambiguous Image Segmentation
Christensen, J. L., Hannemose, M. R., Dahl, A. B., & Dahl, V. A. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-95911-0_14 · Cited by 1
“The ability of convolutional neural networks (CNNs) and their variants to learn complex patterns has led to breakthroughs across diverse applications, from object detection to semantic segmentation [19,14,18,22].”
Zeng, D., Wang, H., & Chen, J. (2025) · Journal of Building Engineering · doi:10.1016/j.jobe.2025.113202 · Cited by 1
Eikd: method of extracting important information from feature map for knowledge distillation
Zhang, B., Zhang, W., Zhou, L., Guo, Y., Wang, J., & Zhu, J. (2025) · International Journal of Machine Learning and Cybernetics · doi:10.1007/s13042-025-02716-8 · Cited by 1
“In recent years, deep neural networks have been widely used in various fields such as object detection [1], natural language processing [2], image classification [3], and speech recognition due to their high performance on large-scale datasets and their excellent ability to learn complex features…”
Intersection User Class Detection Using UAV Images and YOLO-Based Algorithms in Smart Cities
Doğan, E., Ayan, E., Korkmaz, E., et al. (2025) · Smart City Symposium Prague (SCSP) · doi:10.1109/scsp65598.2025.11037712 · Cited by 1
Improved RT-DETR for Road Defect Detection
Xia, Y., Hu, S., & Wu, T. (2025) · doi:10.1109/ainit65432.2025.11035660 · Cited by 1
Lin, J., Zhou, Z., Qiu, Q., Liu, R., Shen, J., & Zhang, Y. (2025) · International Conference on Computer Supported Cooperative Work in Design (CSCWD) · doi:10.1109/cscwd64889.2025.11033611 · Cited by 2
GMD-YOLOv5s: An Improved Steel Surface Defect Detection Algorithm Based on YOLOv5s
Su, Z., Li, A., Yang, Z., & Li, M. (2025) · International Conference on Computer Supported Cooperative Work in Design (CSCWD) · doi:10.1109/cscwd64889.2025.11033517 · Cited by 2
Boosting Open-Vocabulary Object Detection by Handling Background Samples
Zeng, R., Zhang, L., Yang, X., & Liu, Z. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-6975-2_19 · Cited by 4
Dynamic Video Prompting Network for Thyroid Nodule Detection in Ultrasound Videos
Yin, L., Li, Y., & Luo, H. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-6972-1_4 · Cited by 1
An Improved YOLOv8n-Based Approach for Citrus Leaf Disease Detection
Tang, Y., Zhang, Q., Wang, Y., & Lv, W. (2025) · International Conference on Information Science, Electrical and Automation Engineering (ISEAE) · doi:10.1109/iseae64934.2025.11042097 · Cited by 2
Design of Collision Warning System Based on the Fusion of In-vehicle and Out-of-vehicle Information
Lu, M., Zhong, Z., & Zhang, Y. (2025) · International Conference on Advanced Electronic Materials, Computers and Software Engineering (AEMCSE) · doi:10.1109/aemcse65292.2025.11042337 · Cited by 1
Dynamic Latent Feature Guidance for Few-Shot Object Detection
Yao, X., Liu, J., Li, Q., et al. (2025) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2025.3575898 · Cited by 1
Leveraging CNNs and Transformers: The Hybrid Model for Brain Tumor Detection and Segmentation
Pasunoori, K. C., Prasad, C. R., & Kumar, K. (2025) · International Conference on Signal Processing, Computing and Control (ISPCC) · doi:10.1109/ispcc66872.2025.11039415 · Cited by 1
Coarse-Fine Tracker: A Robust MOT Framework for Satellite Videos via Tracking Any Point
Shi, H., Liu, X., Qi, X., Zhu, E., Jia, J., & Wang, L. (2025) · Remote Sensing · doi:10.3390/rs17132167 · Cited by 1
REAL-TIME VIDEO PROCESSING: COMPARATIVE ANALYSIS OF YOLO AND SSD ARCHITECTURES
Mihaylov, A., & Евдокимова, С. (2025) · All-Russian Scientific and Practical Conference "Actual Problems of Automation, Robotics, and Management in Technical, Organizational, and Economic Systems" · doi:10.58168/aiarmtoes2025_217-223 · Cited by 1
Zeng, Y. C., Luo, A., Zhan, K., Li, J., Zhang, Y., & Hu, K. (2025) · International Conference on Multimedia Retrieval · doi:10.1145/3731715.3733404 · Cited by 3
“Current RSOD methodologies primarily utilize two frameworks: one-stage [1, 15, 29, 30] and two-stage [13, 31].”
Spatially-Aware Entity Relation Exploration for Remote Sensing Image-Text Retrieval
Shui, J., Ding, S., Ge, M., & Li, M. (2025) · International Conference on Multimedia Retrieval · doi:10.1145/3731715.3733434 · Cited by 3
“In order to obtain more accurate entity information, we choose to use YOLO[30] pre-trained on DOTA[35] dataset as our local feature extractor, so as to have more accurate capture of remote sensing entity features.”
Bidirectional Segmentation-Aware Network for One-Shot Object Detection
Zhang, W., Chen, Z., Su, Y., Xiang, Z., Shan, H., & Liu, E. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.130761 · Cited by 1
ZoomHead: A Flexible and Lightweight Detection Head Structure Design for Slender Cracks
Li, H., Yang, F., Huo, J., Gao, Q., Deng, S., & Guo, C. (2025) · Sensors · doi:10.3390/s25133990 · Cited by 2
“Representative algorithms include SSD [13] and YOLO [14].”
Aphelios: A Selective Lock-step Neural Processing Unit Design
Sun, W., Gan, Y., Hao, Y., & Han, Y. (2025) · ACM Great Lakes Symposium on VLSI (GLSVLSI) · doi:10.1145/3716368.3735205 · Cited by 3
Spectrogram-Based Spectrum Prediction for AI-managed Cognitive-Radio Edge Devices
Rojas, A., Liñán-Cembrano, G., Doleček, G. J., et al. (2025) · IEEE International Symposium on Circuits and Systems proceedings · doi:10.1109/iscas56072.2025.11043580 · Cited by 1
A Fast and Lightweight Method for Detecting Damaged Buildings After Earthquakes
Yang, D., & Feng, Z. (2025) · Journal of Intelligent & Fuzzy Systems · doi:10.1177/18758967251348745 · Cited by 1
“Since the release of the first YOLO model in 2016 (Redmon et al., 2016), the YOLO models have undergone multiple optimizations and iterations, evolving into numerous variants to meet the specific needs of different tasks.”
Deep learning to classify the ripeness of coffee fruit in the mechanized harvesting process
Zanella, M. A., Barrio-Conde, M., Gil, J., et al. (2025) · Scientia Agricola · doi:10.1590/1678-992x-2024-0156 · Cited by 1
Catheter detection and segmentation in X-ray images via multi-task learning
Lin, X., Ma, Y., Koland, E., Howell, S., Rinaldi, C. A., & Rhode, K. (2025) · International Journal of Computer Assisted Radiology and Surgery · doi:10.1007/s11548-025-03461-7 · Cited by 3
An Interpretability Method for Broken Wire Detection
Wu, H., Liu, S., Xu, Z., Ji, Z., Qian, M., Yuan, X., & Wang, Y. (2025) · Sensors · doi:10.3390/s25134002 · Cited by 1
“One-stage detectors, such as the YOLO series [10], SSD [11], etc., combine candidate region generation and object classification and localization in one stage, directly predicting the target location and accumulating chants from input images.”
Improving Elevator Control Algorithms by Integrating with Computer Vision
Diep, V. T., Phat, N. D., & Hung, P. D. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-97000-9_15 · Cited by 1
YOLOv8n-PP: a lightweight pose recognition algorithm for photovoltaic array cleaning robot
Luo, J., Wang, G., Lei, Y., Wang, D., & Zhang, H. (2025) · Journal of Real-Time Image Processing · doi:10.1007/s11554-025-01713-y · Cited by 4
“We compared five mainstream object detection models: YOLOv5s [33], YOLOv7 [43], YOLOv8s, YOLOv8n, and YOLOv8n-PP, using seven evaluation metrics: Precision, Recall, AP 50 , F1, GFLOPs, AP, and FPS.”
InfluentialXia, R., Fang, H., & Zhang, C. (2025) · SAE International Journal of Transportation Safety · doi:10.4271/09-13-02-0008 · Cited by 1
Bin Picking by Robot Arm Based on Object Position and Pose Recognition
Matsumoto, K., Suzuki, H., Kitajima, T., et al. (2025) · Journal of Signal Processing · doi:10.2299/jsp.29.131 · Cited by 1
Zhu, J., & Gao, N. (2025) · Electronics · doi:10.3390/electronics14132612 · Cited by 1
Extending YOLO for Feature-Based Classification Through Numerical-to-Image Transformation
Khunsongkiet, P., & Mahanan, W. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-8889-0_40 · Cited by 1
Semi-Supervised Maritime Object Detection: A Data-Centric Perspective
Wu, M., Zhang, W., Min, R., Zhang, L., Xu, Y., Qin, Y., & Yu, J. J. (2025) · Journal of Marine Science and Engineering · doi:10.3390/jmse13071242 · Cited by 2
Yang, T., Wang, S., Tong, Y., Zou, M., Shang, X., Ma, W., & Zhang, Z. (2025) · Machine Intelligence Research · doi:10.1007/s11633-025-1561-5 · Cited by 1
Influence of simulated traffic on foundation pit deformation via machine vision technology
Wu, X., Sun, M.-M., Xie, Z., et al. (2025) · Scientific Reports · doi:10.1038/s41598-025-05699-2 · Cited by 1
“The YOLO model, the pioneer in single-stage detectors, has seen significant enhancements in accuracy and speed with its latest version 33 .”
Dai, Z., Sun, H., Zhao, L., Qin, X., Wei, L., Liang, X., Chen, T., & Jia, J. (2025) · Rock Mechanics and Rock Engineering · doi:10.1007/s00603-025-04726-y · Cited by 1
“Specifically, target detection can be divided into two main categories: you only look once (YOLO) (Redmon et al. 2016) and region-based convolutional neural network (R-CNN) (Girshick et al. 2013).”
Tan, T. J., Su, Z., Chow, J. K., Leung, T. L., Tan, P. S., Leung, M. L., Wu, W., Yang, H., Gu, D., & Wang, Y.-H. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.111534 · Cited by 3
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.