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 38,501–38,600 of 51,399
Intelligent Video Surveillance System with Abnormal Behavior Recognition and Metadata RetrievalPreprint
Kim, H., Shin, J., Park, S., et al. (2023) · Preprints.org · doi:10.20944/preprints202306.0147.v1 · Cited by 1
Deep Learning–Based Intelligent Measurement Methods and System for CmmPreprint
Cheng, Z., Sun, Y., Hu, K., et al. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4469728 · Cited by 1
A lightweight method for real-time monitoring of lump coal on mining conveyor beltsPreprint
Wu, L., Chen, L., Zhang, L., et al. (2023) · Research Square · doi:10.21203/rs.3.rs-3031808/v1 · Cited by 1
ACNN: Arbitrary Traces Attack based on LeakageArea DetectionPreprint
Xiao, C., & Tang, M. (2023) · Research Square · doi:10.21203/rs.3.rs-3036551/v1 · Cited by 1
Small Target Detection Model in Aerial Images Based on YOLOv7X+Preprint
Li, S., & Liu, W. (2023) · Research Square · doi:10.21203/rs.3.rs-3052166/v1 · Cited by 1
He, A., Zhang, A. A., Zhang, H., et al. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4500699 · Cited by 1
Boosting Infrared Target Detection: Unveiling the Power of ResNet-SA and Detection BlockPreprint
Lin, J. L., Li, S., Yang, X. D., Niu, S., Yan, B., & Fan, Y. (2023) · Research Square · doi:10.21203/rs.3.rs-3133773/v1 · Cited by 1
A Lightweight Gesture Recognition NetworkPreprint
Guo, G., Lei, X., & Li, B. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4505117 · Cited by 1
Technical Note: Using Computer Vision’s Pixel Segmentation to Detect Beef Cattle Feeding BehaviorPreprint
Pi, Y., Mendes, E. D. M., Tedeschi, L. O., et al. (2023) · Preprints.org · doi:10.20944/preprints202307.0705.v1 · Cited by 1
Efficient Deep Learning Models Based on Tension Techniques for Sign Language RecognitionPreprint
Attia, N. F., Ahmed, M. T. F. S., & Alshewimy, M. A. M. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4494547 · Cited by 1
OTLD:A four-stages visual system for perception of autonomous vehiclesPreprint
Xue, Q., Wang, X., Tu, G., & Wu, J. (2023) · Research Square · doi:10.21203/rs.3.rs-3132840/v1 · Cited by 2
A lightweight detection model for greenhouse-cultivated strawberries based on YOLOv5Preprint
Li, Y., & Xue, J. (2023) · Research Square · doi:10.21203/rs.3.rs-3178237/v1 · Cited by 1
Shafiei, A., Kameli, V., & Grailu, H. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4509042 · Cited by 1
Surface Defects Detection of Transparent Plastic Bottles Based on Improved Yolov5Preprint
Pei, J., Li, S., & Li, Y. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4524937 · Cited by 1
Bruce, D., Sanghvi, H. A., & Agarwal, A. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4517717 · Cited by 1
Deep Clustering with a Dynamic Autoencoder: From Reconstruction towards Centroids ConstructionPreprint
Mrabah, N., Khan, N., Ksantini, R., & Lachiri, Z. (2023) · doi:10.32920/22734350 · Cited by 1
Automotive air conditioning vent defect detection method based on improved yolov5Preprint
Zheng, G. F., Xu, H., Fu, Y., Kong, X. L., & Qiu, L. (2023) · Research Square · doi:10.21203/rs.3.rs-3220483/v1 · Cited by 1
Jain, A. (2023) · doi:10.36227/techrxiv.23916609.v1 · Cited by 1
Radar Target Classification Using Deep Learning
Kim, Y. (2023) · Wiley eBooks · doi:10.1002/9781119853923.ch16 · Cited by 3
Wang, Y., Jing, J., & Sheng, S. (2023) · Research Square · doi:10.21203/rs.3.rs-3312918/v1 · Cited by 1
Perception, Path Planning and Control Strategy for an Autonomous Electric Mini TractorPreprint
Wasnik, H., Salunkhe, S., Bhateshvar, Y. K., & Agrewale, M. R. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4566682 · Cited by 1
Class-Agnostic Counting and Localization with Feature Augmentation and Scale-Adaptive AggregationPreprint
Zhai, C., Du, Y., Wang, T., et al. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4552869 · Cited by 1
Automatic Tracking of NBA Statistics from a Live BroadcastPreprint
Veršnik, A., & Šajn, L. (2023) · Preprints.org · doi:10.20944/preprints202309.0648.v1 · Cited by 1
Şahin, Y. S., Başay, S., & Gençer, N. S. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4570966 · Cited by 2
A multimodal deep learning architecture for smoking detection with a small data approachPreprint
Lakatos, R., Pollner, P., Hajdú, A., & Joó, T. (2023) · medRxiv · doi:10.1101/2023.09.19.23295710 · Cited by 1
Fish Sonar Image Recognition Algorithm Based on Improved YOLOv5Preprint
Xing, B., Sun, M., Ding, M., et al. (2023) · Research Square · doi:10.21203/rs.3.rs-3369498/v1 · Cited by 1
Predictive Deep Learning Model for Neural Vessel OcclusionPreprint
Karlsberg, A., Kim, S., Zaghari, N., et al. (2023) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2023.09.27.559850 · Cited by 1
Fastest Moroccan License Plate Recognition Using a Lightweight Modified YOLOv5 ModelPreprint
Fadili, A., Aroussi, M. E., Saadane, R., et al. (2023) · Preprints.org · doi:10.20944/preprints202309.2107.v1 · Cited by 1
Nazar, T., & Kausar, S. H. (2023) · Research Square · doi:10.21203/rs.3.rs-3385141/v1 · Cited by 1
Diving Deep into Human Action Recognition in Aerial Videos: A SurveyPreprint
Kapoor, S., Sharma, A., & Verma, A. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4587787 · Cited by 1
Yang, M., Lv, R., Cao, Z., Wang, X., & Sheng, K. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4597443 · Cited by 2
Intelligent Weed Control for Precision Agriculture
Hu, K., & Wang, Z. (2023) · Springer eBooks · doi:10.1007/978-3-031-24861-0_194 · Cited by 1
MPQ-YOLO: Ultra Low Mixed-Precision Quantization of YOLO for Edge Devices DeploymentPreprint
Liu, X., Wang, T., Yang, J., et al. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4616035 · Cited by 1
Allak, A. S. H., Yi, J., SABBAGH, H. M., et al. (2023) · Preprints.org · doi:10.20944/preprints202311.0415.v1 · Cited by 1
SSIVD-Net: A Novel Salient Super Image Classification & Detection Technique for Weaponized ViolencePreprint
Aremu, T. (2023) · doi:10.36227/techrxiv.23898039.v2 · Cited by 1
Hv-Yolov8 by Hdpconv: Better Lightweight Detectors for Small Object DetectionPreprint
Wang, W., Meng, Y., Li, S., et al. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4632283 · Cited by 1
BreastCDNet: Breast Cancer Detection Neural Network, Classification and LocalizationPreprint
Mahichi, H., Ghods, V., Sohrabi, M. K., et al. (2023) · Research Square · doi:10.21203/rs.3.rs-3600120/v1 · Cited by 1
GAG-Net: Global Attention-Guided CNN Architecture for Accurate Ship DetectionPreprint
Feng, B., Huang, Y., Cao, M., et al. (2023) · Research Square · doi:10.21203/rs.3.rs-3612710/v1 · Cited by 1
Intasam, A., Piyawattanametha, N., Promworn, Y., Jiranantanakorn, T., Thawornwanchai, S., Thanasitthichai, S., Khwayotha, S., Juhong, A., & Piyawattanametha, W. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4635895 · Cited by 1
Multi-Yolov8: An Infrared Motion Object Detection Model Based on Yolov8 for Air VehiclePreprint
Sun, S., Mo, B., Xu, J., et al. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4648079 · Cited by 1
Liu, C., Li, K., Sui, X., Zhao, T., Zhang, T., Chen, Z., Wu, H., Li, C., Li, H., Yang, F., et al. (2023) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2023.12.11.571047 · Cited by 1
A Three-Stage Framework for Automatic Bengali License Plate Detection and Recognition SystemPreprint
Hasan, M. N., Islam, M. A., Nayeem, M. J., et al. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4648216 · Cited by 1
Mobile Robots Underwater Object Detection Using Deep LearningPreprint
Raisi, Z., & Nazarzehi, V. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4663189 · Cited by 1
Research on Meteorological Equipment Identification and Monitoring Algorithm Based on Yolov8Preprint
Wang, Z., Ye, R., Xu, Y., et al. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4665653 · Cited by 1
Unbiased Complete Estimation of Chloroplast Number in Plant Cells Using Deep Learning MethodsPreprint
Su, Q., Liu, L., Hu, Z., Wang, T., Wang, H., Guo, Q., Liao, X., Zhao, D., Yang, S., Liu, N., et al. (2023) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2023.12.17.572064 · Cited by 1
CMA-YOLO: A Wine Grape Detection Model Based on YOLOv5x Combining Mixed Attention MechanismPreprint
Lu, H., Zhang, X., Sun, J., & Wan, S. (2023) · Research Square · doi:10.21203/rs.3.rs-3754270/v1 · Cited by 2
Zeng, C., Hartmann, T., & Ma, L. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4677638 · Cited by 1
Improved YOLOv7-Based Multi-Target Tracking and Detection under Maritime Surveillance ScenarioPreprint
Zhu, J., Chang, H.-T., & Zhang, T. (2024) · Research Square · doi:10.21203/rs.3.rs-3823941/v1 · Cited by 1
Yologas: An Automatic Detection Method for Optical Gas ImagingPreprint
Wang, Q., Xing, M., Pan, X., et al. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4683447 · Cited by 1
Audio captioning and retrieval with improved cross-modal objectives
Koh, A. J. J. (2023) · DR-NTU (Nanyang Technological University) · doi:10.32657/10356/172437 · Cited by 1
Ultrasonic Image's Annotation Removal: A Self-supervised Noise2Noise ApproachPreprint
Zhang, Y., Jiang, N., Xie, Z., et al. (2024) · Research Square · doi:10.21203/rs.3.rs-3826717/v1 · Cited by 1
Improving the Perception of Objects under Foggy Conditions in the Surrounding EnvironmentPreprint
Chaar, M. M., Raiyn, J., & Weidl, G. (2024) · Research Square · doi:10.21203/rs.3.rs-3821656/v1 · Cited by 1
Performance Analysis of YOLO-NAS SOTA Models on CAL Tool DetectionPreprint
Raja, M. A., Loughran, R., & McCaffery, F. (2024) · doi:10.36227/techrxiv.170474405.56692658/v1 · Cited by 2
Robust Filter Pruning Guided by Deep Frequency-Features for Edge IntelligencePreprint
Qian, Y., Huang, W., Yu, Q., et al. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4691079 · Cited by 1
Research on Industrial Defect Detection Method Based on Improved YoloxPreprint
Pei, X., Su, S., Yuan, Y., Jiang, L., Chen, C., & Chu, C. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4697038 · Cited by 1
Srivast, D., Singh, V., Song, L., & Kochersberger, K. B. (2024) · Research Square · doi:10.21203/rs.3.rs-3865180/v1 · Cited by 3
Serverless Strategies and Tools in the Cloud Computing Continuum
Gallardo, S. R. (2023) · RiuNet (Universitat Politècnica de València) · doi:10.4995/thesis/10251/202013 · Cited by 4
Hrubý, R., Kvak, D., Dandár, J., et al. (2024) · medRxiv · doi:10.1101/2024.01.17.24301244 · Cited by 1
Towards Eliminating Recycling Confusion
Sarafraz, A., Alvarez, N., Toussaint, J., et al. (2024) · doi:10.1002/9781394214297.ch9 · Cited by 1
From Meteorology to Market: A Geo-Hierarchical Deep Learning Approach for Flood Risk PricingPreprint
Xu, Y., Tan, K. S., & Zhu, W. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4692475 · Cited by 2
A New Lightweight Network for Real-time Detection of Railway InfrastructurePreprint
Cheng, Y., & Cheng, R. (2024) · Research Square · doi:10.21203/rs.3.rs-3932509/v1 · Cited by 2
Misrachi, L., Covili, E., Mayard, H., et al. (2024) · medRxiv · doi:10.1101/2024.02.17.24301683 · Cited by 1
Using computer vision to detect and segment fire behavior classifications in UAS-captured imagesPreprint
Lawrence, B. L., & de Lemmus, E. (2024) · doi:10.31223/x5710x · Cited by 1
El-Sunais, Y., & Eberemu, N. C. (2024) · Preprints.org · doi:10.20944/preprints202402.1217.v1 · Cited by 1
Enhanced tooth segmentation algorithm for panoramic radiographs
Carneiro, J. A. (2023) · Digital Library of Theses and Dissertations (Universidade de São Paulo) · doi:10.11606/d.59.2023.tde-20022024-073306 · Cited by 4
Target detection of diamond nanostructures based on improved YOLOv8 modelingPreprint
Guo, F., Guo, X., Guo, L., et al. (2024) · Research Square · doi:10.21203/rs.3.rs-3963300/v1 · Cited by 1
LO-SLAM: Lunar Object-centric SLAM using Point Prompted SAM for Data AssociationPreprint
Tian, Y., Wan, X., Zhang, S., Zuo, J., Shao, Y., & Yang, M. (2024) · doi:10.36227/techrxiv.170975343.37379344/v1 · Cited by 1
Li, Y., GUO, G., Li, H., Da, T. E. N. G., & Guancheng, W. A. N. G. (2024) · Research Square · doi:10.21203/rs.3.rs-4006293/v1 · Cited by 1
A study on urban street garbage detection based onYOLOXPreprint
Li, L., Zhang, H., Lu, F., Wang, Z., & Huan, L. (2024) · Research Square · doi:10.21203/rs.3.rs-4002747/v1 · Cited by 2
Generalizable deep neural networks for image quality classification of cervical imagesPreprint
Ahmed, S. R., Befano, B., Egemen, D., et al. (2024) · Research Square · doi:10.21203/rs.3.rs-3845696/v1 · Cited by 1
The DCN-BiFPN Object Detection Algorithm based on YOLOv8Preprint
Yu, B., Li, S., Wang, W. J., et al. (2024) · Research Square · doi:10.21203/rs.3.rs-4019974/v1 · Cited by 1
Deep learning based genomic breeding of pest-resistant grapevinePreprint
Gan, Y., Liu, Z., Zhang, F., Xu, Q., Wang, X., Xue, H. F., Su, X., Ma, W., Long, Q.-M., Ma, A., et al. (2024) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2024.03.16.585323 · Cited by 1
A Novel Approach for Counting Wood Logs Using Cgans and Image Processing TechniquesPreprint
Mazzochin, J. V. C., Tiecker, G., Oliveira, G. A., et al. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4765248 · Cited by 1
Proceedings - 5th International Conference Business Meets Technology 2023
BMT Scientific Committee (2023) · doi:10.4995/bmt2023.2023.17398 · Cited by 1
Piva, A., Raimondi, L., Rasca, E., et al. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4768319 · Cited by 1
Swinvision: Detecting Small Objects in Low-Light EnvironmentsPreprint
Dai, T., Wang, Q., Shen, Y., et al. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4768710 · Cited by 1
Fd-Detr: Striking the Balance between Accuracy and Speed in Fall Detection ModelsPreprint
Zhu, Y., Zeng, B., Zheng, Y., & Hu, H. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4768681 · Cited by 1
Convolutional Neural Networks: An Introduction
Yi, B., Li, Y., & Lee, T. C. M. (2024) · Wiley eBooks · doi:10.1002/9781118445112.stat08393 · Cited by 1
Losada-del-Olmo, J. J., Gómez, Á. L. P., Ruiz, A., & López-de-Teruel, P. E. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4777359 · Cited by 1
Independently Keypoint Learning for Small Object Semantic CorrespondencePreprint
Jin, H., & Li, H. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4806466 · Cited by 1
Insect-Yolo: A New Method on Crop Insect DetectionPreprint
Wang, N., Fu, S., Rao, Q., et al. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4813498 · Cited by 1
Ye, W., Ren, J., Liang, J., Liu, W., Yi, H., Zhang, A. A., & Lu, C. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4819840 · Cited by 1
Ma, S., Chun, Q., Zhang, C., et al. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4833323 · Cited by 1
Data Rescue for Historical Document Tables Using Semi-Supervised LearningPreprint
Singh, L. G., & Middleton, S. E. (2024) · Research Square · doi:10.21203/rs.3.rs-4391424/v1 · Cited by 1
Zero/Few-Shot Pcb Anomaly Detection Approach Based on Differential ReconstructionPreprint
Yin, X., Wang, Y., Wang, S., et al. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4841941 · Cited by 1
A Measurement Model for Aquatic Animals Based on Instance Segmentation and 3D Point CloudPreprint
He, Z., Xu, X., Luo, J., et al. (2024) · Research Square · doi:10.21203/rs.3.rs-4437659/v1 · Cited by 1
Exploring Methods of Explainable AI: Data-driven Attribution of Climate Events
Landt-Hayen, M. (2023) · doi:10.21941/kcss/2023/5 · Cited by 3
Illumination-Guided Progressive Unsupervised Domain Adaptation for Low-Light Instance SegmentationPreprint
Zhang, Y., Guo, J., Yue, H., et al. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4871944 · Cited by 1
AW-YOLO: a multi-object detection network for autonomous driving under all weather conditionsPreprint
Yue, X., Gu, Q., Huang, S., Pan, J., Zhang, Y., & He, M. (2024) · Research Square · doi:10.21203/rs.3.rs-4524976/v1 · Cited by 1
Automatic ovarian follicle detection using object detection modelsPreprint
Hassan, M. H., Reiter, É., & Razzaq, M. (2024) · Research Square · doi:10.21203/rs.3.rs-4637709/v1 · Cited by 1
Yolosc-Sam: An Acceptable Extraction Method for Farmland Regions in Remote Sensing Images Using SamPreprint
Gao, R., Ji, Z., Zhang, Z., et al. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4879705 · Cited by 1
Aljagoub, D., Na, R., & Cheng, C. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4883405 · Cited by 1
CCD-YOLO: An Accurate and Fast Algorithm for Steel Surface Defect DetectionPreprint
Wang, D., & Wang, H. (2024) · Research Square · doi:10.21203/rs.3.rs-4580747/v1 · Cited by 2
A Survey on Artificial Neural Networks in Human-Robot InteractionPreprint
Świetlicka, A. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4884314 · Cited by 1
Balea, A. C. (2024) · Gredos (University of Salamanca) · doi:10.14201/gredos.158770 · Cited by 1
Transformer-Based Similarity Learning for Re-Identification of ChickensPreprint
Lamping, C., Kootstra, G., & Derks, M. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4886408 · Cited by 1
Seddik, E. H., Hewieg, M., & Afify, R. S. (2024) · Research Square · doi:10.21203/rs.3.rs-4573646/v1 · Cited by 1
wang, Y., Wang, W., Pan, X., Lu, K., Zhang, J., Chen, P., & Wang, B. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4897923 · 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.