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 35,101–35,200 of 51,399
Multiple path search for action tube detection in videos
Alwando, E. H. P., Chen, Y., & Fang, W. (2017) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2017.8297080 · Cited by 1
Cooney, M., & Bigün, J. (2017) · Hogskolan Ihalmstad (Halmstad University) · Cited by 5
Complexity and Accuracy of Hand-Crafted Detection Methods Compared to Convolutional Neural Networks
Tomaselli, V., Plebani, E., Strano, M., & Pau, D. P. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-68560-1_27 · Cited by 1
Improving robustness of stacked auto-encoder against evasion attack based on weight evenness
Luo, F., Chan, P. P. K., Lin, Z., & He, Z. (2017) · International Conference on Wavelet Analysis and Pattern Recognition · doi:10.1109/icwapr.2017.8076694 · Cited by 1
Torres, C., Bency, A. J., Fried, J., et al. (2017) · International Conference on Distributed Smart Cameras · doi:10.1145/3131885.3131928 · Cited by 1
Wu, X., Chen, X., & Zhou, J. (2017) · Communications in computer and information science · doi:10.1007/978-981-10-7299-4_2 · Cited by 1
MFRPN: Towards High-Quality Region Proposal Generation in Object Detection
Zhang, D., Zhang, H., Zeng, W., Han, Z., & Hu, X. (2017) · Communications in computer and information science · doi:10.1007/978-981-10-7305-2_6 · Cited by 1
Cyclist Detection, Tracking, and Trajectory Analysis in Urban Traffic Video Data
Shahraki, F. F. (2017) · Digital Scholarship - UNLV (University of Nevada Reno) · doi:10.34917/11156724 · Cited by 1
Optimal Transformation Estimation with Semantic Cues
Paudel, D. P., Habed, A., & Gool, L. V. (2017) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.499 · Cited by 2
Real-Time Road-Direction Point Detection in Complex Environment
Cai, H., Liu, E., Liu, H., & Wang, S. (2018) · IEICE Transactions on Information and Systems · doi:10.1587/transinf.2017edp7266 · Cited by 1
Indoor RGB-D Object Detection with the Guidance of Hand-Held Objects
Qiao, L., Zhu, Y., Li, R., et al. (2018) · Communications in computer and information science · doi:10.1007/978-981-10-8530-7_12 · Cited by 1
Aesthetic Intension Extraction in Architecture based on Deep Learning Framework
Park, J., Yoon, D., & Lee, W.-H. (2017) · Advanced science and technology letters · doi:10.14257/astl.2017.148.03 · Cited by 1
TransHist: Occlusion-robust shape detection in cluttered images
Han, C., Liu, X., Sinn, L. T., & Wong, T. (2018) · Computational Visual Media · doi:10.1007/s41095-018-0104-1 · Cited by 1
A Robust End-to-End Neural Network for Scene Text Detection
Yuan, Q., Li, H., Wang, Z., Fan, X., & Luo, Z. (2018) · Communications in computer and information science · doi:10.1007/978-981-10-8530-7_16 · Cited by 1
In-the-wild facial expression recognition in extreme poses
Yang, F. H., Zhang, Q., Zheng, C., & Qiu, G. (2018) · International Conference on Graphics and Image Processing (ICGIP) · doi:10.1117/12.2302626 · Cited by 3
Crowd scenes analysis using multiple sliding windows classifiers and Histogram of Oriented Gradient
Shalileh, S., & Shahdi, S. O. (2017) · Iranian Conference on Machine Vision and Image Processing · doi:10.1109/iranianmvip.2017.8342365 · Cited by 1
Semiautomatic training and evaluation of a learning-based vehicle make and model recognition system
Zwemer, M. H., Brouwers, G. M. Y. E., Wijnhoven, R. G. J., & de With, P. H. N. (2018) · Journal of Electronic Imaging · doi:10.1117/1.jei.27.5.051225 · Cited by 1
Border-oriented post-processing refinement on detected vehicle bounding box for ADAS
Chen, X., Zhang, Z., Li, M., & Li, D. (2018) · International Conference on Graphics and Image Processing (ICGIP) · doi:10.1117/12.2305330 · Cited by 1
Visualization of Real World Activity on Group Work
Deguchi, D., Kondo, K., & Shimada, A. (2018) · Lecture notes in computer science · doi:10.1007/978-3-319-91131-1_2 · Cited by 1
Sensing, Perception and Decision for Deep Learning Based Autonomous Driving
Yamashita, T. (2018) · Lecture notes in computer science · doi:10.1007/978-3-319-91131-1_12 · Cited by 1
Matching Low-Quality Photo to DSLR-Quality with Deep Convolutional Networks
Xia, W., Yang, C. G., Yang, Y., & Sun, W. (2018) · Lecture notes in computer science · doi:10.1007/978-3-319-94361-9_4 · Cited by 1
INVESTIGATION OF CONVOLUTIONAL NEURAL NETWORKS FOR VISUAL TRACKING OF PEDESTRIANS.
Jonkus, A., Tumas, P., & Serackis, A. (2018) · International Journal of Advanced Research · doi:10.21474/ijar01/7082 · Cited by 1
Improving detection speed in video by exploiting frame correlation
Mehta, R., & Amores, J. (2018) · Pattern Recognition Letters · doi:10.1016/j.patrec.2018.07.035 · Cited by 1
A Discriminative Feature Learning Based on Deep Residual Network for Face Verification
Zhang, T., Wang, R., & Ding, J. (2018) · Communications in computer and information science · doi:10.1007/978-981-13-1702-6_41 · Cited by 1
A Method of Aircraft Detection Using Fully Convolutional Network
Yu, D., Zhao, C., Xu, J., & Lin, Y. (2017) · International Conference on Computer Systems, Electronics and Control (ICCSEC) · doi:10.1109/iccsec.2017.8446851 · Cited by 1
Lao, M., Chen, X., Lin, F., Qin, G., Liu, W., & Zhou, Y. (2018) · International Conference on Control and Automation · doi:10.1109/icca.2018.8444232 · Cited by 3
Analysing object detectors from the perspective of co-occurring object categories
Nemes, C., & Jordán, S. (2018) · IEEE International Conference on Cognitive Infocommunications · doi:10.1109/coginfocom.2018.8639888 · Cited by 2
Pyramid Sub-Region Sensitive Network for Object Detection
Gong, T., Liu, B., Li, W., & Yu, N. (2018) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2018.8451801 · Cited by 1
Cox Processes for Counting by Detection
Rajan, P., Ma, Y., & Jedynak, B. (2018) · Journal of Mathematical Imaging and Vision · doi:10.1007/s10851-018-0838-5 · Cited by 1
A Hybrid Planning Strategy Through Learning from Vision for Target-Directed Navigation
Zhou, X., Weber, C., Bothe, C., & Wermter, S. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-01421-6_30 · Cited by 1
Interpretable Verification of Visually Similar Vehicle Images Using Convolutional Networks
Hong, L., Wang, W., Pang, Y., et al. (2018) · Communications in computer and information science · doi:10.1007/978-981-13-2922-7_13 · Cited by 1
Consecutive Feature Network for Object Detection
Huang, J., Lan, X., Li, S., et al. (2018) · IEEE International Conference on Mechatronics and Automation (ICMA) · doi:10.1109/icma.2018.8484571 · Cited by 1
A Multi-sensor Fusion Approach for Intention Detection
Singh, R. K., Varghese, R. J., Liu, J., Zhang, Z., & Lo, B. P. L. (2018) · Biosystems & biorobotics · doi:10.1007/978-3-030-01845-0_91 · Cited by 1
Towards Efficient Lesion Localization Based on Template Occlusion Strategy in Intelligent Diagnosis
Yan, H., Guo, K., Zhang, R., Li, J., & Liu, W. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-02698-1_5 · Cited by 1
A Local Top-Down Module for Object Detection with Multi-scale Features
Huang, S., Wang, L., Yang, P., & Deng, Q. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-03341-5_6 · Cited by 1
Marrying Stationary Low-Power Wireless Networks and Mobile Robots in a Hybrid Surveillance System
Ferrera, E., Ceriotti, M., Jungen, S., et al. (2018) · International Conference on Distributed Computing in Sensor Systems (DCOSS) · doi:10.1109/dcoss.2018.00029 · Cited by 1
Vehicle Detection Based on Separable Reverse Connected Network
Yang, E., Huang, L., & Hu, J. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-03341-5_12 · Cited by 1
Multi-flow Sub-network and Multiple Connections for Single Shot Detection
Li, Y., Zheng, H., & Chen, L. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-03335-4_15 · Cited by 1
Asymmetrical Reverse Connection and Smooth-NMS for Object Detection
Peng, J., Wang, Z., Lv, X., Wei, G., Fei, J., & Zhang, H. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-03341-5_21 · Cited by 1
Automatic Annotation of Object Instances by Region-Based Recurrent Neural Networks
Fîciu, I.-D., Stilpeanu, R., Ţoca, C., Petre, A. I., Pătraşcu, C., & Ciuc, M. (2018) · IEEE International Conference on Intelligent Computer Communication and Processing (ICCP) · doi:10.1109/iccp.2018.8516608 · Cited by 1
A New Monocular 3D Object Detection with Neural Network
Hong, W., Liu, Y., Zheng, Y., Wang, Y., & Shi, X. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-03341-5_15 · Cited by 1
Research on Real-Time Vehicle Detection Algorithm Based on Deep Learning
Yang, W. P., Zhang, J., Zhang, Z., & Wang, H. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-03341-5_11 · Cited by 1
Training accurate and compact one-stage object detection networks with heuristic knowledge
Jia, J., Zhou, L. J., Liu, J., & Chen, J. (2018) · Journal of Electronic Imaging · doi:10.1117/1.jei.27.6.063003 · Cited by 1
New Default Box Strategy of SSD for Small Target Detection
He, Y., Li, B., & Zhao, Y. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-04212-7_36 · Cited by 1
Yoon, Y.-S., Hwang, J., Jung, S.-U., & Park, J. (2018) · International Conference on Information and Communication Technology Convergence (ICTC) · doi:10.1109/ictc.2018.8539407 · Cited by 1
Densely Connected Single-Shot Detector
Xu, P., Zhao, X., & Huang, K. (2018) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2018.8545369 · Cited by 1
Basic Study on Viewpoints Classification Method using Car Distribution on the Road
Noda, M., Miyamoto, H., Tangsuksant, W., et al. (2018) · doi:10.1109/ict-robot.2018.8549907 · Cited by 1
Temporal relation algebra for audiovisual content analysis
Ibrahim, Z. A. A., Ferrané, I., & Joly, P. (2018) · Multimedia Tools and Applications · doi:10.1007/s11042-018-6771-1 · Cited by 1
Evaluation of real-time object detection model based on small targets
Qi, M., Zhu, B. B., Wang, H., Xiang, F., Chen, Z., & Xie, B. (2019) · International Symposium on Advanced Optical Manufacturing and Testing Technologies (AOMATT) · doi:10.1117/12.2505930 · Cited by 2
All-in-One Urban Mobility Mapping Application with Optional Routing Capabilities
Thompson, R. L., Stovall, J., Velasquez, D., et al. (2018) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata.2018.8622030 · Cited by 1
Character Recognition in Japanese Historical Documents via Adaptive Multi-Region Model
Wang, Y., & Kamata, S. (2018) · International Conference on Informatics, Electronics & Vision (ICIEV) · doi:10.1109/iciev.2018.8641033 · Cited by 2
Deep Activation Feature Maps for Visual Object Tracking
Li, Y., Miao, Z., & Wang, J. (2018) · doi:10.1145/3297067.3297088 · Cited by 1
Detection of the Information Hidden in Image by Convolutional Neural Networks
Zubov, I. G., Lysenko, N. V., & Labkov, G. M. (2019) · IEEE Conference of Russian Young Researchers in Electrical and Electronic Engineering · doi:10.1109/eiconrus.2019.8656886 · Cited by 1
Deep Counting Model Extensions with Segmentation for Person Detection
Ghosh, S. T., Amon, P., Hutter, A., & Kaup, A. (2019) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2019.8682662 · Cited by 1
A Multi-object Tracking Method Based on Bounding Box and Features
Liu, F., Jia, W., & Zhong, Y. (2019) · Advances in intelligent systems and computing · doi:10.1007/978-3-030-16621-2_20 · Cited by 1
Machine Vision in the Context of Robotics: A Systematic Literature Review
Ghofrani, J., Kirschne, R., Roßburg, D., Reichelt, D., & Dimter, T. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1905.03708 · Cited by 6
Mattela, G., Pal, C., Tripathi, M., Gavval, R., & Acharyya, A. (2019) · International Conference on Communication Systems & Networks (COMSNETS) · doi:10.1109/comsnets.2019.8711399 · Cited by 1
Examination of How to Estimate the Viewing Angle at Intersections
Goto, S., Murata, Y., & Atsumi, M. (2018) · Joint International Conference on Soft Computing and Intelligent Systems and International Symposium on Advanced Intelligent Systems (SCIS&ISIS) · doi:10.1109/scis-isis.2018.00121 · Cited by 1
Fast Object Detector Based on Convolutional Neural Networks
Piaskowski, K., & Belter, D. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-20805-9_15 · Cited by 2
Research on Fast Detection Method of Aircraft in Remote sensing image Based on Deep Learning
Zhang, Y., Liu, X., & Yang, H. (2018) · IEEE Information Technology and Mechatronics Engineering Conference (ITOEC) · doi:10.1109/itoec.2018.8740585 · Cited by 1
Robust Detection of Outdoor Urban Advertising Panels in Static Images
Morera, Á., Sánchez, Á., Sappa, A. D., & Vélez, J. F. (2019) · Communications in computer and information science · doi:10.1007/978-3-030-24299-2_21 · Cited by 1
An Action Recognition network for specific target based on rMC and RPN
Li, M., Feng, Y., Yin, Z., et al. (2019) · Journal of Physics Conference Series · doi:10.1088/1742-6596/1325/1/012073 · Cited by 1
A deep learning system that learns a discriminative model autonomously using difference images
Hamasaki, R., & Nakayama, K. (2019) · Genetic and Evolutionary Computation Conference Companion (GECCO Companion) · doi:10.1145/3319619.3326887 · Cited by 1
Motion Cue Based Instance-level Moving Object Detection
Huang, J., Zou, W., Zhu, Z. D., et al. (2019) · Chinese Control and Decision Conference (CCDC) · doi:10.1109/ccdc.2019.8832730 · Cited by 1
Universal Framework of Seals Erasing with Generative Adversarial Network
Chen, Z., Ding, Z., & Wang, S. (2019) · Communications in computer and information science · doi:10.1007/978-981-13-9917-6_27 · Cited by 1
Container number localization based on SSD algorithm
Ding, B., Guo, J., & Hu, J. (2019) · Youth Academic Annual Conference of Chinese Association of Automation (YAC) · doi:10.1109/yac.2019.8787699 · Cited by 1
Object Detection and Mapping During European Robotic Competitions - Lesson Learned
Majek, K., Będkowski, J., Pełka, M., Ratajczak, J., & Masłowski, A. (2019) · International Workshop on Robot Motion and Control · doi:10.1109/romoco.2019.8787341 · Cited by 1
da Costa, P. B., de Almeida, J. D. S., Teixeira, J. A. M., et al. (2019) · doi:10.5753/sbcas.2019.6258 · Cited by 1
Object Tracking by Multiple Correlation Filters Robust to Appearance Changes
Nishimura, H., Tasaka, K., Kawanishi, Y., & Murase, H. (2019) · The Journal of The Institute of Image Information and Television Engineers · doi:10.3169/itej.73.1004 · Cited by 1
Sparse 3D point clouds segmentation considering 2D image feature extraction with deep learning
Yu-sheng, L., Tian, Y., & Tian, J. (2019) · International Conference on Digital Image Processing · doi:10.1117/12.2539780 · Cited by 1
6D Pose Estimation for Industrial Applications
Cunico, F., Carletti, M., Cristani, M., Masci, F., & Conigliaro, D. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-30754-7_37 · Cited by 2
Densely convolutional and feature fused object detector
Guo, J., Yuan, C., Zhao, Z., Feng, P., Wang, T., & Duan, K. (2019) · Multimedia Tools and Applications · doi:10.1007/s11042-019-08119-6 · Cited by 1
Unmanned Boat Target Detection Based on Improved SSD
Yin, Y., Gui, F., & Chen, S. (2019) · Chinese Control and Decision Conference (CCDC) · doi:10.1109/ccdc.2019.8832423 · Cited by 1
Virtual multi-modal object detection and classification with deep convolutional neural networks
Mitsakos, N., & Papadakis, M. (2019) · Wavelets and Sparsity · doi:10.1117/12.2529233 · Cited by 1
Analysis of Object Detection Methods to Detect Traffic Flow
le Roux, J., & van der Haar, D. T. (2019) · doi:10.1109/icabcd.2019.8851054 · Cited by 1
41.4: Display Panel Defect Detection Algorithm Based On Group Convolutions
Ma, W., Shengsen, Z., & Zheng, Z. (2019) · SID Symposium Digest of Technical Papers · doi:10.1002/sdtp.13530 · Cited by 1
Application of Deep Object Detection in Underwater Acoustic Pulse Interception
Li, Y., Ma, X., Liu, Y., et al. (2019) · MTS/IEEE OCEANS Conference (OCEANS) · doi:10.1109/oceanse.2019.8867085 · Cited by 1
Development of a service robot for indoor operation using distributed computing
Mazumdar, A. P., Lee, K., Evran, E., et al. (2017) · Zeszyty Naukowe Instytutu Pojazdów / Politechnika Warszawska · Cited by 1
Gonçalves, C. L. A., Zampolo, R. F., Barros, F. J. B., Gomes, A. C., Carvalho, E. C., Ferreira, B. V., Rocha, R. D. L., Rodrigues, R. C., Dias, G., & Freitas, D. A. (2019) · SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI) · doi:10.5753/sibgrapi.est.2019.8336 · Cited by 1
Pixel2Field: Single Image Transformation to Physical Field of Sports Videos
Peng, L. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-33720-9_51 · Cited by 1
Transmission line image defect diagnosis based on YOLOv3 and SNIPER cascade lifting algorithm
Liu, G., Li, Z., Sun, X., et al. (2019) · IOP Conference Series Earth and Environmental Science · doi:10.1088/1755-1315/332/4/042032 · Cited by 1
Exploiting Structural Information in Camera Aided Radar Parameter Estimation
Mazher, K. U., Annaluru, S., Mezghani, A., et al. (2019) · IEEE Global Conference on Signal and Information Processing · doi:10.1109/globalsip45357.2019.9969383 · Cited by 1
An Industrial Defect Detection Platform Based on Rapid Iteration
Zhu, J., Cheng, D., & Kong, Q. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-34113-8_38 · Cited by 1
Multi-scale Feature and Spatial Relation Inference for Object Detection
Zhou, T., Miao, Z., & Wang, J. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-34120-6_54 · Cited by 2
CNN based Multi-View Object Detection and Association
Weber, M., Volkert, L., Hubschneider, C., & Zöllner, J. M. (2019) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc.2019.8917092 · Cited by 1
Picking Particles in Cryo-EM Micrographs without Knowing the Particle Size
Li, X., Lin, Y., Liu, Q., et al. (2019) · doi:10.1109/nysds.2019.8909792 · Cited by 1
Deep Learning-Based Algorithm for Object Identification in Multimedia
Ko, S.-K., Kim, B., & Kim, J. (2019) · Lecture notes in electrical engineering · doi:10.1007/978-981-13-9341-9_87 · Cited by 1
Adaptive Learning Methods for Autonomous Mobile Manipulation in RoboCup@Home
Memmesheimer, R., Seib, V., Evers, T., et al. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-35699-6_46 · Cited by 1
Reinforcing LiDAR-Based 3D Object Detection with RGB and 3D Information
Liu, W., & Zhou, Y. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-36711-4_18 · Cited by 1
IMDB-Attire: A Novel Dataset for Attire Detection and Localization
Yousuf, S. B., Sajid, H., Poon, S. K.-S., & Khushi, M. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-36711-4_46 · Cited by 1
Dr. Eureka: a humanoid robot manipulation case study
Lin, Y., Christmann, G. H. G., Grando, R. B., Guerra, R. D. S., & Baltes, J. (2019) · The Knowledge Engineering Review · doi:10.1017/s0269888919000213 · Cited by 1
Analysis of preceding researches and technologies for estimating occupants clothing insulation
Choi, E. J., Park, B. R., Choi, Y. J., & Moon, J. W. (2019) · KIEAE Journal · doi:10.12813/kieae.2019.19.6.101 · Cited by 1
SE block-based Single Shot Multibox Detector
Hou, L., & Xie, Y. (2019) · IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC) · doi:10.1109/icspcc46631.2019.8960892 · Cited by 1
Mehta, S., Meenpal, T., & Verma, A. (2019) · Innovations in Power and Advanced Computing Technologies (i-PACT) · doi:10.1109/i-pact44901.2019.8960223 · Cited by 1
Xing, Y. D., Tan, J. T. C., Wang, F., et al. (2019) · IEEE International Conference on Advanced Robotics and its Social Impacts (ARSO) · doi:10.1109/arso46408.2019.8948718 · Cited by 1
Target Classification System Based on Target Detection for Students' Classroom Assessment
Xu, Y., Teng, H., Ji, C., et al. (2019) · International Conference on Information Technology in Medicine and Education · doi:10.1109/itme.2019.00128 · Cited by 1
A Study on Improvement of Human Sensing System Reliability Using Thermal Image
Yang, S.-M., & Choe, J.-K. (2020) · The Journal of Korean Institute of Information Technology · doi:10.14801/jkiit.2020.18.1.35 · Cited by 1
Pose Detection of Object on Transmission Belt Based on R-SSD
Xu, Z., Niu, W., & Chen, M. (2019) · Chinese Automation Congress · doi:10.1109/cac48633.2019.8996345 · Cited by 1
Feyter, F. D., Hulens, D., Claes, B., & Goedemé, T. (2019) · International Conference on Machine Learning and Applications · doi:10.1109/icmla.2019.00323 · Cited by 2
ASAN: Self-Attending and Semantic Activating Network towards Better Object Detection
Zhu, X., Zhang, J., & Chen, G. (2020) · IEICE Transactions on Information and Systems · doi:10.1587/transinf.2019edp7164 · Cited by 1
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.