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 32,501–32,600 of 51,399
Pedestrian fall detection algorithm based on improved YOLOv5
Song, X., & Luo, Q. (2024) · International Conference on Computer Vision, Image and Deep Learning (CVIDL) · doi:10.1109/cvidl62147.2024.10603866 · Cited by 2
Grape Disease Detection Model Based on an Improved YOLOv8
Sheng, C., Yao, J., & Tian, Y. (2024) · International Conference on Computer Vision, Image and Deep Learning (CVIDL) · doi:10.1109/cvidl62147.2024.10604218 · Cited by 2
Wildlife Tracker using Deep Learning
Muhammed Hijas, H., Renjini, L., & Harikrishnan, S. R. (2024) · International Journal of Advanced Research in Science Communication and Technology · doi:10.48175/ijarsct-19253 · Cited by 2
Improved YOLOv8 Based Small Object Detection for Intelligent Robotic Arm in Complex Environments
Li, Z., & Ren, D. (2024) · IEEE Data Driven Control and Learning Systems Conference (DDCLS) · doi:10.1109/ddcls61622.2024.10606904 · Cited by 2
LSSAttn: Towards Dense and Accurate View Transformation for Multi-modal 3D Object Detection
Jiang, Q., & Sun, H. (2024) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra57147.2024.10610830 · Cited by 2
Improvement of YOLOv5s-Ghost model
Huang, Q., & Li, Z. (2024) · Journal of Physics Conference Series · doi:10.1088/1742-6596/2816/1/012081 · Cited by 2
Improved target detection algorithm based on YOLOv5s
Han, C., Chen, B., & Wu, H. (2024) · doi:10.1145/3674700.3674703 · Cited by 2
Research on Re-Identification of Amur Tigers and Bengal Tigers
Xia, Y., Hu, Y., Liu, W., & Que, T. (2024) · International Conference on Big Data and Privacy Computing (BDPC) · doi:10.1109/bdpc59998.2024.10649232 · Cited by 2
Design of Weed Detection Technique Using Yolo Models
Sreehari, M., & Jain, A. (2024) · Students Conference on Engineering and Systems · doi:10.1109/sces61914.2024.10652564 · Cited by 3
A Two-Stage Enhancement Method for Object Detection on Low-Resolution Images
Yuan, Z., Ling, M., Chang, K., Yin, M., Li, M., & Chen, B. (2024) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn60899.2024.10650286 · Cited by 2
Balakrishnan, M., & Rajagopal, R. (2024) · IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT) · doi:10.1109/conecct62155.2024.10677310 · Cited by 2
Object Detection Algorithm for UAV Aerial Image Based on Improved YOLOv8
Liu, Y., & Zhou, X. (2024) · International Conference on Electronic Communication and Artificial Intelligence (ICECAI) · doi:10.1109/icecai62591.2024.10675035 · Cited by 2
Crack Detection on Asphalt Road in Malaysia using UAV Images and YOLOv4
Mahmud, M. N., Osman, M. K., Ismail, A. P., Ahmad, F., Ahmad, K. A., Ibrahim, A., & Rabiani, A. H. (2024) · IEEE International Conference on Control System, Computing and Engineering · doi:10.1109/iccsce61582.2024.10696027 · Cited by 3
ORKA: An Ontology for Robotic Knowledge Acquisition
Adamik, M., Pernisch, R., Tiddi, I., & Stefan Schlobach, A. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-77792-9_19 · Cited by 6
Improved YOLOv8-based Vision Inspection Method for Weld Defect Classification
Wu, J., Zhao, J., Liang, M., & Cao, X. (2024) · International Conference on System Reliability and Safety Engineering (SRSE) · doi:10.1109/srse63568.2024.10772487 · Cited by 5
Point-Cloud Instance Segmentation for Spinning Laser Sensors
Casado-Coscolla, A., Sánchez-Belenguer, C., Wolfart, E., et al. (2024) · Journal of Imaging · doi:10.3390/jimaging10120325 · Cited by 2
Object Detection Approach Using YOLOv5 For Plant Species Identification
Clinton, B., Amperawan, A., & Dewi, T. (2024) · Jurnal Elektronika dan Telekomunikasi · doi:10.55981/jet.643 · Cited by 4
Bhatia, P. S., Reda, F. A., Harder, M., Zhan, Y., & Zhou, X. S. (2017) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2254647 · Cited by 2
Incomplete 3D motion trajectory segmentation and 2D-to-3D label transfer for dynamic scene analysis
Jiang, C., Paudel, D. P., Fougerolle, Y. D., et al. (2017) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2017.8202214 · Cited by 2
Enabling ∼100fps detection on a landing unmanned aircraft for its on-ground vision-based recovery
Cao, Z., Zhao, K., Fang, Q., et al. (2017) · International Conference on Advanced Robotics (ICAR) · doi:10.1109/icar.2017.8023640 · Cited by 2
Improving Object Detection with Convolutional Neural Network via Iterative Mechanism
Qiu, X., & Yuan, C. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-70090-8_15 · Cited by 3
Image set-based classification using collaborative exemplars representation
Xu, Z. J., Cai, G., Wen, Y., et al. (2017) · Signal Image and Video Processing · doi:10.1007/s11760-017-1198-0 · Cited by 2
A judgment framework for roller skating using faster R-CNN
Bu, Q., Lan, S., Gu, C., et al. (2017) · doi:10.1109/fads.2017.8253193 · Cited by 2
Merging recovery feature network to faster RCNN for low-resolution images detection
Zhang, R., & Yang, Y. (2017) · IEEE Global Conference on Signal and Information Processing · doi:10.1109/globalsip.2017.8309157 · Cited by 2
Large Scale Deep Network Architecture of CNN for Unconstraint Visual Activity Analytics
Kumar, N. (2018) · Advances in intelligent systems and computing · doi:10.1007/978-3-319-76348-4_25 · Cited by 2
Matsuda, H., & MAKANAE, K. (2017) · Journal of Japan Society of Civil Engineers Ser F3 (Civil Engineering Informatics) · doi:10.2208/jscejcei.73.i_347 · Cited by 2
Image Multi-human Behavior Analysis Based on Low Rank Texture Direction
Li, M., & Zhang, G. (2018) · Journal of Signal Processing Systems · doi:10.1007/s11265-018-1344-0 · Cited by 2
End-to-end learning via a convolutional neural network for cancer cell line classification
Akogo, D., & Palmer, X. (2019) · Journal of Industry-University Collaboration · doi:10.1108/jiuc-02-2019-002 · Cited by 2
Wang, H., Owens, H., Smith, J. M., et al. (2018) · Cited by 2
Combining HWEBING and HOG‐MLBP features for pedestrian detection
Ling, X., Zhang, Y., Zhang, J., Wang, Q., & Li, Y. (2018) · The Journal of Engineering · doi:10.1049/joe.2018.8308 · Cited by 2
Chen, X., Lin, F., Hamid, M. R. A., Teo, R., & Phang, S. K. (2018) · International Conference on Control and Automation · doi:10.1109/icca.2018.8444340 · Cited by 2
MASON: A Model AgnoStic ObjectNess Framework
Joseph, K. J., Patel, R., Srivastava, A. K., Gupta, U., & Balasubramanian, V. N. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-11021-5_40 · Cited by 2
Statistic Experience Based Adaptive One-Shot Detector (EAO) for Camera Sensing System
Zhu, X., Ding, B., Meng, Q., Gu, L., & Yang, Y. (2018) · Sensors · doi:10.3390/s18093041 · Cited by 2
Fast-Tracking Application for Traffic Signs Recognition
Ouadrhiri, A. A. E., Burian, J., Andaloussi, S. J., et al. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-00692-1_34 · Cited by 2
Improved Local Texture Features for Pedestrian Detection
Ling, X., Zhang, Y., Wang, Q., & Li, Y. (2018) · International Conference on Image, Vision and Computing (ICIVC) · doi:10.1109/icivc.2018.8492888 · Cited by 2
Motorbike Detection in Urban Environment
Huynh, C. K., Dang, T. K., & Le, T. S. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-03192-3_22 · Cited by 2
UAV-Vision Based Real-Time Power Line Components Identification
安, 站. (2018) · Artificial Intelligence and Robotics Research · doi:10.12677/airr.2018.74020 · Cited by 2
Fully Convolutional Network With Densely Feature Fusion Models for Object Detection
Huang, S., Liy, X., Jiang, Z., Guo, X., & Men, A. (2018) · IEEE International Conference on Multimedia & Expo Workshops (ICMEW) · doi:10.1109/icmew.2018.8551503 · Cited by 2
GBCNN: A Full GPU-Based Batch Multi-Task Cascaded Convolutional Networks
Li, S., Dou, Y., Xu, J., Yang, K., & Li, R. (2019) · IEEE Access · doi:10.1109/access.2019.2894589 · Cited by 2
Deep Neural Networks with Mixture of Experts Layers for Complex Event Recognition from Images
Li, M., & Kamata, S. (2018) · Joint International Conference on Informatics, Electronics & Vision and International Conference on Imaging, Vision & Pattern Recognition (ICIEV & icIVPR) · doi:10.1109/iciev.2018.8641027 · Cited by 2
Game Robot's Vision Based on Faster RCNN
Liu, S., Zheng, B., Zhao, Y., et al. (2018) · Chinese Automation Congress · doi:10.1109/cac.2018.8623107 · Cited by 2
3D Pose Estimation for Robotic Grasping Using Deep Convolution Neural Network
Wang, Y., Xu, Y., Zhang, X., et al. (2018) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio.2018.8664818 · Cited by 2
Real Time Object Detection Can be Embedded on Low Powered Devices
Pal, J. B., & Agarwal, S. (2019) · International Journal of Computer Sciences and Engineering · doi:10.26438/ijcse/v7i2.10051009 · Cited by 2
Logo and Brand Recognition from Imbalanced Dataset Using MiniGoogLeNet and MiniVGGNet Models
Sarwo, S., Heryadi, Y., Budiharto, W., et al. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-14799-0_33 · Cited by 2
Neural Network Components for Evolved Vision Systems
Kyle-Davidson, C., & Clark, A. F. (2018) · Computer Science and Electronic Engineering Conference · doi:10.1109/ceec.2018.8674219 · Cited by 2
Foreground Feature Enhancement for Object Detection
Jiang, S., Xu, T., Li, J., Shen, Z., & Guo, J. (2019) · IEEE Access · doi:10.1109/access.2019.2908630 · Cited by 2
Sign Recognition - How well does Single Shot Multibox Detector sum up? A Quantitative Study
Manikandan, R. (2018) · IEEE Applied Imagery Pattern Recognition Workshop · doi:10.1109/aipr.2018.8707409 · Cited by 3
Lu, Q., Jiang, Z., Men, A., & Tang, P. (2019) · IET Computer Vision · doi:10.1049/iet-cvi.2018.5601 · Cited by 2
Node Detection and Tracking in Smart Cities Based on Internet of Things and Machine Learning
Teimoor, R. A., & Darwesh, A. M. (2019) · UHD Journal of Science and Technology · doi:10.21928/uhdjst.v3n1y2019.pp30-38 · Cited by 2
A Target Detection System for Mobile Robot Based On Single Shot Multibox Detector Neural Network
Du, Y., Gao, M., Yang, Y., et al. (2018) · IEEE International Conference on Control Science and Systems Engineering (ICCSSE) · doi:10.1109/ccsse.2018.8724782 · Cited by 2
Real Time Object Detection Based on YOLO with Feature Filter Bank
Haque, M. F., Lim, H.-Y., & Kang, D.-S. (2019) · The Journal of Korean Institute of Information Technology · doi:10.14801/jkiit.2019.17.5.91 · Cited by 2
DiagonalNet: Confidence diagonal lines for the UAV detection
Hu, Q., Duan, Q., Mao, Y., Zhou, X., & Zhou, G. (2019) · IEEJ Transactions on Electrical and Electronic Engineering · doi:10.1002/tee.22938 · Cited by 3
Towards an Adaptive Multi-Modal Traffic Analytics Framework at the Edge
Pettet, G., Sahoo, S. K., & Dubey, A. K. (2019) · IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops) · doi:10.1109/percomw.2019.8730577 · Cited by 2
Human Body Tracking Method Based on Deep Learning Object Detection
Yuan, Z. (2019) · doi:10.1145/3339363.3339390 · Cited by 3
Deep Learning Models for Content-Based Retrieval of Construction Visual Data
Nath, N. D., & Behzadan, A. H. (2019) · ASCE International Conference on Computing in Civil Engineering (i3CE) · doi:10.1061/9780784482438.009 · Cited by 5
Automatic localization of phoenix by satellite image analysis
Cousin, R., & Ferry, M. (2019) · Arab Journal Of Plant Protection · doi:10.22268/ajpp-037.2.083088 · Cited by 2
RGB-D Indoor Mapping Using Deep Features
Güçlü, O., Çağlayan, A., & Can, A. B. (2019) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2019.00164 · Cited by 5
Zhang, Y., Wang, J., Miao, Z., et al. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-26766-7_62 · Cited by 2
Space-Time Slicing: Visualizing Object Detector Performance in Driving Video Sequences
Lee, T., & Wittenburg, K. B. (2019) · IEEE Pacific Visualization Symposium · doi:10.1109/pacificvis.2019.00045 · Cited by 2
Visualization of the Image Geometric Transformation Group Based on Riemannian Manifold
Liu, T., Shi, Z., & Liu, Y. (2019) · IEEE Access · doi:10.1109/access.2019.2932412 · Cited by 2
A Vision-based Unmanned Aircraft System for Autonomous Grasp & Transport
Liu, X., He, Y., Chen, B., et al. (2019) · International Conference on Unmanned Aircraft Systems (ICUAS) · doi:10.1109/icuas.2019.8798329 · Cited by 2
¿Es posible entrenar modelos de aprendizaje profundo con datos sintéticos?
Vállez, N., Mata, A. V., Cotorro, J. J., & Déniz, Ó. (2019) · Jornadas de Automática · doi:10.17979/spudc.9788497497169.859 · Cited by 2
GMC: Grid Based Motion Clustering in Dynamic Environment
Zhang, H., Karunasekera, H., Zhou, H., & Wang, H. (2019) · Advances in intelligent systems and computing · doi:10.1007/978-3-030-29513-4_93 · Cited by 4
Automated Mapping Of Accessibility Signs With Deep Learning From Ground-level Imagery and Open Data
Nassar, A., & Lefèvre, S. (2019) · Joint Urban Remote Sensing Event (JURSE) · doi:10.1109/jurse.2019.8808961 · Cited by 4
Analysis of loss functions for fast single-class classification
Keren, G., Sabato, S., & Schuller, B. W. (2019) · Knowledge and Information Systems · doi:10.1007/s10115-019-01395-6 · Cited by 3
A Reinforcement Learning Approach for Sequential Spatial Transformer Networks
Azimi, F., Raue, F., Hees, J., & Dengel, A. R. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-30487-4_45 · Cited by 3
3D Object Detection Based on Vanishing Point and Prior Orientation
Gao, Y., Zhao, H., Fang, Z., Huang, B., & Zhong, C. (2019) · Wuhan University Journal of Natural Sciences · doi:10.1007/s11859-019-1408-4 · Cited by 2
Residual Learning for FC Kernels of Convolutional Network
Alexeev, A., Matveev, Y. N., Matveev, A., & Pavlenko, D. V. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-30484-3_30 · Cited by 3
Drift Compensation of Mono-Visual Odometry and Vehicle Localization Using Public Road Sign Database
Jang, C., & Kim, Y. (2019) · International Journal of Automotive Technology · doi:10.1007/s12239-019-0116-6 · Cited by 2
Real-time Ball Detection for Robocup Soccer Using Convolutional Neural Networks
de Abreu, L. R., & Bianchi, R. A. C. (2019) · Workshop of Computer Vision (WVC) · doi:10.5753/wvc.2019.7636 · Cited by 2
Accurate Single-Stream Action Detection in Real-Time
Liu, Y., Yang, F., & Ginhac, D. (2019) · International Conference on Distributed Smart Cameras · doi:10.1145/3349801.3349821 · Cited by 2
Text Attention and Focal Negative Loss for Scene Text Detection
Huang, R., & Xu, B. (2019) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2019.8851959 · Cited by 2
Strong-Background Restrained Cross Entropy Loss for Scene Text Detection
Huang, R., & Xu, B. (2019) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2019.8852198 · Cited by 2
On Class Imbalance and Background Filtering in Visual Relationship Detection
Sarullo, A., & Mu, T. (2019) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2019.8851814 · Cited by 3
CSSD: Cascade Single Shot Face Detector
Wang, S., Xu, T., Li, W., & Sun, H. (2019) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2019.8851713 · Cited by 3
Towards Optimal Incentive-Driven Verification in Social Sensing Based Smart City Applications
Vance, N., Zhang, D., Zhang, Y., et al. (2019) · IEEE International Conference on High Performance Computing and Communications; IEEE International Conference on Smart City; IEEE International Conference on Data Science and Systems (HPCC/SmartCity/DSS) · doi:10.1109/hpcc/smartcity/dss.2019.00379 · Cited by 2
Deep Learning-based Overlapping-Pig Separation by Balancing Accuracy and Execution Time
Lee, H., Sa, J., Chung, Y., et al. (2019) · Computer Science Research Notes · doi:10.24132/csrn.2019.2901.1.3 · Cited by 2
6D Object Pose Estimation for Robot Programming by Demonstration
Ghahramani, M., Vakanski, A., & Janabi‐Sharifi, F. (2019) · Springer proceedings in physics · doi:10.1007/978-981-32-9632-9_11 · Cited by 2
Machine Learning Based User Interface Generation
Mistry, M., Apte, A., Ghodake, V., et al. (2019) · Advances in intelligent systems and computing · doi:10.1007/978-3-030-30465-2_50 · Cited by 2
Exploring 3 R’s of Long-term Tracking: Re-detection, Recovery and Reliability
Karthik, S., Moudgil, A., & Gandhi, V. (2020) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv45572.2020.9093465 · Cited by 3
Video Surveillance System with a Deep Learning Approach
Lestari, P., Manik, D. H. D., Sihotang, N. L. B., & Husein, A. M. (2019) · SinkrOn · doi:10.33395/sinkron.v4i1.10247 · Cited by 2
StreetOCRCorrect: An Interactive Framework for OCR Corrections in Chaotic Indian Street Videos
Singh, P., Patwa, B., Saluja, R., et al. (2019) · doi:10.1109/icdarw.2019.10036 · Cited by 2
A Cloud-Based Machine Vision Approach for Utilization Prediction of Manual Machine Tools
Parto, M., Han, D., Rauby, P., Ye, C., Zhou, Y., Chau, D. H., & Kurfess, T. R. (2019) · Smart and Sustainable Manufacturing Systems · doi:10.1520/ssms20190019 · Cited by 3
Web Page Information Extraction System by Using Deep Learning
Pakyürek, M., Sezgin, M. S., & Kulaç, S. (2019) · doi:10.1109/ubmk.2019.8907083 · Cited by 2
Hybrid Multiple Object Tracking System Design for Real-Time Application
Woo, Y., Choi, K., & Lee, J. (2019) · The Journal of Korean Institute of Information Technology · doi:10.14801/jkiit.2019.17.11.1 · Cited by 2
Recognition & Evaluation of Additional Traffic Signs on the example of ’80 km/h when wet’
Weber, T., Erçelik, E., Ebert, M., et al. (2019) · IEEE Intelligent Transportation Systems Conference (ITSC) · doi:10.1109/itsc.2019.8916950 · Cited by 2
Generic Object Detection and Tracking for Accelerating Video Analysis within VICTORIA
Schreiber, D., Boyer, M., Gemeiner, P., et al. (2019) · International Conference on Speech Technology and Human-Computer Dialogue (SpeD) · doi:10.1109/sped.2019.8906552 · Cited by 2
LIP: Learning Instance Propagation for Video Object Segmentation
Lyu, Y., Vosselman, G., Xia, G.-S., & Yang, M. Y. (2019) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2019.00335 · Cited by 4
A Natural Scene Text Extraction Approach Based on Generative Adversarial Learning
Xu, H., Su, X., Liu, T., Guo, P., Gao, G., & Bao, F. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-36708-4_6 · Cited by 3
Steijn, W. M. P., van der Beek, D., Groeneweg, J., Jansen, A., Oldenhof, W. A., & Raben, I. (2019) · International Journal of Occupational Safety and Ergonomics · doi:10.1080/10803548.2019.1699335 · Cited by 3
PataNET: A Convolutional Neural Networks to Identify Plant from Leaf Images
Islam, M. M., Rabby, A. S. A., Arfin, M. H. R., & Hossain, S. A. (2019) · International Conference on Computing, Communication and Networking Technologies (ICCCNT) · doi:10.1109/icccnt45670.2019.8944667 · Cited by 3
Tang, D., Kong, H., Meng, X., et al. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-37731-1_44 · Cited by 2
Person Search via Deep Integrated Networks
Chen, J.-C., Wu, C.-F., Chen, C.-H., et al. (2019) · Applied Sciences · doi:10.3390/app10010188 · Cited by 2
XD-STOD: Cross-Domain Superresolution for Tiny Object Detection
Fromm, M., Berrendorf, M., Faerman, E., et al. (2019) · IEEE ... International Conference on Data Mining workshops · doi:10.1109/icdmw.2019.00031 · Cited by 2
Real-time Pedestrian Dynamic-load Localization using Vision-based Motion Sensing
Lim, J., & Yoon, H. (2019) · Korean Society of Hazard Mitigation · doi:10.9798/kosham.2019.19.7.323 · Cited by 2
Visual Locating of Reactor in an Industrial Environment Using the Composite Method
Cao, C., Ouyang, Q., Hou, J., & Zhao, L. (2020) · Sensors · doi:10.3390/s20020504 · Cited by 2
Old Man Fall Detection Based on Surveillance Video Object Tracking
Qiu, Z., Liang, X., Chen, Q., Huang, X., & Wang, Y. (2020) · Communications in computer and information science · doi:10.1007/978-981-15-2767-8_15 · Cited by 2
Optimizing Deep Learning Based Semantic Video Segmentation on Embedded GPUs
Baba, F., Kenjić, D., Bjelica, M. Z., et al. (2019) · International Conference on Consumer Electronics · doi:10.1109/icce-berlin47944.2019.8966156 · Cited by 2
Human Bone Localization in Ultrasound Image Using YOLOv3 CNN Architecture
Lazuardi, R. A. F., Karlita, T., Yuniarno, E. M., et al. (2019) · International Conference on Computer Engineering, Network, and Intelligent Multimedia (CENIM) · doi:10.1109/cenim48368.2019.8973372 · Cited by 2
Pelican Crossing Adaptive Time Arrangement using Convolutional Neural Network
Resha, R. P., Rachmadi, R. F., Nugroho, S. M. S., et al. (2019) · International Conference on Computer Engineering, Network, and Intelligent Multimedia (CENIM) · doi:10.1109/cenim48368.2019.8973343 · Cited by 2
Metadata
- Authors
- Redmon, J., Divvala, S., Girshick, R., & Farhadi, A.
- Affiliations
- University of Washington (US)
- Meta (United States) (US)
- Venue
- 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2016-06
- Pages
- 779-788
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W1483870316
- Cited by
- 53,803
- References
- 42
- Citations by year
- 2026: 5347 · 2025: 8912 · 2024: 8953 · 2023: 8264 · 2022: 6785 · 2021: 5741 · 2020: 4223 · 2019: 3286 · 2018: 1560 · 2017: 635 · 2016: 90
- FWCI
- 644.23
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Zenodo (CERN European Organization for Nuclear Research) (cc-by)
- Funders
- National Science Foundation (1338054)
- Office of Naval Research (N00014-13-1-0720, N00014)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image and Video Retrieval Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Visual Attention and Saliency Detection
- Keywords
- object detection, YOLO, real-time detection, bounding box regression, end-to-end learning, false positive reduction, domain generalization
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol and qwen3.8-omni-flash).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.