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 38,201–38,300 of 51,399
You Only Look & Listen Once: Towards Fast and Accurate Visual GroundingPreprint
Deng, C., Wu, Q., Xu, G., Yu, Z., Xu, Y., Jia, K., & Tan, M. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1902.04213 · Cited by 1
A Hybrid SLAM and Object Recognition System for Pepper RobotPreprint
Ardón, P., Kushibar, K., & Peng, S. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1903.00675 · Cited by 3
Learning Condensed and Aligned Features for Unsupervised Domain Adaptation Using Label PropagationPreprint
Yoo, J., Park, C., Hong, Y., & Yoon, S. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1903.04860 · Cited by 1
A Capsule-unified Framework of Deep Neural Networks for Graphical ProgrammingPreprint
Li, Y., & Shan, C. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1903.04982 · Cited by 1
Semantic Comparison of State-of-the-Art Deep Learning Methods for Image Multi-Label Classification.Preprint
Kubany, A., Ishay, S. B., Ohayon, R., et al. (2019) · arXiv (Cornell University) · Cited by 1
Deep Learning Acceleration Techniques for Real Time Mobile Vision ApplicationsPreprint
Teyou, G. K. D. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1905.03418 · Cited by 1
Blocksworld Revisited: Learning and Reasoning to Generate Event-Sequences from Image PairsPreprint
Gokhale, T., Sampat, S. K., Fang, Z., Yang, Y., & Baral, C. R. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1905.12042 · Cited by 4
Vehicle Detection in Deep LearningPreprint
Xiao, Y. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1905.13390 · Cited by 11
Efficient architecture for deep neural networks with heterogeneous sensitivityPreprint
Cho, H., Jang, J., Lee, C., et al. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1810.05358 · Cited by 1
Hussain, K. F., Bassyouni, M. Y., & Gelenbe, E. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1906.08864 · Cited by 1
A Dataset for Developing and Benchmarking Active VisionPreprint
Ammirato, P., Poirson, P., Park, E., Košecká, J., & Berg, A. C. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1702.08272 · Cited by 1
Collaborative Deep Reinforcement Learning for Joint Object SearchPreprint
Kong, X., Xin, B., Wang, Y., et al. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1702.05573 · Cited by 1
Clouds of Oriented Gradients for 3D Detection of Objects, Surfaces, and Indoor Scene LayoutsPreprint
Ren, Z., & Sudderth, E. B. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1906.04725 · Cited by 1
Single Shot Scene Text RetrievalPreprint
Gómez, L., Mafla, A., Rusiñol, M., et al. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1808.09044 · Cited by 1
ShuffleDet: Real-Time Vehicle Detection Network in On-board Embedded UAV ImageryPreprint
Azimi, S. M. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1811.06318 · Cited by 1
Min-Entropy Latent Model for Weakly Supervised Object DetectionPreprint
Wan, F., Wei, P., Han, Z., Jiao, J., & Ye, Q. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1902.06057 · Cited by 5
Hierarchy Denoising Recursive Autoencoders for 3D Scene Layout PredictionPreprint
Shi, Y., Chang, A. X., Wu, Z., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1903.03757 · Cited by 1
Social Behavioral Phenotyping of Drosophila with a2D-3D Hybrid CNN FrameworkPreprint
Jiang, Z., Chazot, P. L., Celebi, M. E., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1903.11421 · Cited by 1
Semantic Image Retrieval by Uniting Deep Neural Networks and Cognitive ArchitecturesPreprint
Potapov, A. S., Zhdanov, I., Scherbakov, O., et al. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1806.06946 · Cited by 1
Unsupervised Domain Alignment to Mitigate Low Level Dataset BiasesPreprint
Sivamani, K. S. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1907.03644 · Cited by 1
He, D., Cai, D., Zhou, J., Luo, J., & Chen, S. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1907.03217 · Cited by 3
Self-supervised Training of Proposal-based Segmentation via Background PredictionPreprint
Katircioglu, I., Rhodin, H., Constantin, V., Spörri, J., Salzmann, M., & Fua, P. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1907.08051 · Cited by 4
Understanding Video Content: Efficient Hero Detection and Recognition for the Game "Honor of Kings"Preprint
Yao, W., Sun, Z., & Chen, X. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1907.07854 · Cited by 1
Image Matters: Scalable Detection of Offensive and Non-Compliant Content / Logo in Product ImagesPreprint
Gandhi, S., Kokkula, S., Chaudhuri, A., Magnani, A., Stanley, T., Ahmadi, B., Kandaswamy, V., Ovenc, O., & Mannor, S. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1905.02234 · Cited by 7
Aerial Object Detection using Learnable Bounding Boxes
Bhat, A. (2019) · RIT Scholar Works (Rochester Institute of Technology) · Cited by 2
Yang, X., Mirmehdi, M., & Burghardt, T. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1908.11240 · Cited by 1
STELA: A Real-Time Scene Text Detector with Learned AnchorPreprint
Deng, L., Gong, Y., Lu, X., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.07549 · Cited by 1
ASSD: Attentive Single Shot Multibox DetectorPreprint
Yi, J., Wu, P., & Metaxas, D. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.12456 · Cited by 1
Interpreting Undesirable Pixels for Image Classification on Black-Box ModelsPreprint
Kang, S.-H., Jung, H.-G., & Lee, S. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.12446 · Cited by 1
LIP: Learning Instance Propagation for Video Object SegmentationPreprint
Lyu, Y., Vosselman, G., Xia, G.-S., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1910.00032 · Cited by 1
PyTorchPipe: a framework for rapid prototyping of pipelines combining language and visionPreprint
Kornuta, T. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1910.08654 · Cited by 2
Kurnaz, F. C., Hocaog̃lu, B., Yılmaz, M. K., Sülo, İ., & Kalkan, S. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1910.11713 · Cited by 2
Xie, Q., Zhou, W., Qi, G.-J., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1910.11560 · Cited by 1
Xiao, L., Luo, C., Yu, T., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1910.11091 · Cited by 1
Leveraging Auxiliary Text for Deep Recognition of Unseen Visual RelationshipsPreprint
Kenigsfield, G. S., & El‐Yaniv, R. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1910.12324 · Cited by 1
Face Detection on Surveillance ImagesPreprint
Nouyed, M. I., & Guo, G. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1910.11121 · Cited by 1
OD-GCN: Object Detection Boosted by Knowledge GCNPreprint
Liu, Z., Jiang, Z., Feng, W., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1908.04385 · Cited by 1
Csönde, G., Sekimoto, Y., & Kashiyama, T. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1911.01672 · Cited by 2
Transfer Learning in Visual and Relational ReasoningPreprint
Jayram, T. S., Marois, V., Kornuta, T., Albouy, V., Sevgen, E., & Özcan, A. S. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1911.11938 · Cited by 4
Online deep transfer learning applied to building quality assessment robots
Liu, L. (2019) · DR-NTU (Nanyang Technological University) · doi:10.32657/10356/104468 · Cited by 2
Towards Understanding Residual and Dilated Dense Neural Networks via Convolutional Sparse CodingPreprint
Zhang, Z., & Zhang, S. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1912.02605 · Cited by 1
Continuous Speech Recognition using EEG and VideoPreprint
Krishna, G., Carnahan, M., Tran, C., & Tewfik, A. H. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1912.07730 · Cited by 1
Semantic Segmentation for Compound figuresPreprint
Jiang, W., Schwenker, E., Chan, M. K. Y., & Cossairt, O. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1912.07142 · Cited by 1
COMPUTER VISION BASED METHOD FOR AUTOMATIC REBAR DETECTION IN GROUND PENETRATING RADAR DATA
Asadi, P. (2019) · doi:10.23860/diss-asadi-pouria-2019 · Cited by 2
Deep Clustering with a Dynamic Autoencoder: From Reconstruction towards Centroids ConstructionPreprint
Mrabah, N., Khan, N., Ksantini, R., et al. (2023) · doi:10.32920/22734350.v1 · Cited by 1
Named Entity Recognition With Deep Learning
Yu, H. (2019) · Tuwhera (Auckland University of Technology) · Cited by 5
Multi-class analysis of urinary particles based on deep learningPreprint
Li, Q., Yu, Z., Qi, S., et al. (2020) · doi:10.22541/au.157878399.96593318 · Cited by 1
Dong, Z., Wu, J., Ren, T., Wang, Y., & Ge, M. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2001.02219 · Cited by 2
Dantas, D. O., Braun, C., Forte, K., Brito, F., Silva, A., Lins, S., Linder, N., & Junior, A. B. D. R. K. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2001.04944 · Cited by 1
Learning to adapt class-specific features across domains for semantic segmentationPreprint
Menta, M., Romero, A., & van de Weijer, J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2001.08311 · Cited by 1
Object Instance Mining for Weakly Supervised Object DetectionPreprint
Lin, C., Wang, S., Xu, D., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2002.01087 · Cited by 1
EHSOD: CAM-Guided End-to-end Hybrid-Supervised Object Detection with Cascade RefinementPreprint
Fang, L., Xu, H., Liu, Z., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2002.07421 · Cited by 1
No-regret Non-convex Online Meta-LearningPreprint
Zhuang, Z., Wang, Y., Yu, K., & Lu, S. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1910.10196 · Cited by 4
Deep Learning Based FDD Non-Stationary Massive MIMO Downlink Channel ReconstructionPreprint
Han, Y., Li, M., Jin, S., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2002.09858 · Cited by 1
Object 6D Pose Estimation with Non-local AttentionPreprint
Mei, J., Ding, H., & Jiang, X. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2002.08749 · Cited by 1
Applied Machine Vision and IoT
García, V. H. E., Sánchez, N., Rodrigo, J. A., Menéndez, J. M., & Mayordomo, J. M. L. (2020) · The Internet of Things · doi:10.1002/9781119545293.ch6 · Cited by 1
BiDet: An Efficient Binarized Object DetectorPreprint
Wang, Z., Wu, Z., Lu, J., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.03961 · Cited by 1
Belmonte-Hernández, A. (2019) · UPM Digital Archive (Technical University of Madrid) · doi:10.20868/upm.thesis.57985 · Cited by 2
BABO: Background Activation Black-Out for Efficient Object DetectionPreprint
Roh, B., Cho, H.-C., Ju, M.-H., & Pyo, S. H. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2002.01609 · Cited by 1
Weakly Supervised Dataset Collection for Robust Person DetectionPreprint
Minoguchi, M., Okayama, K., Satoh, Y., & Kataoka, H. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.12263 · Cited by 4
Unified Framework for Vision Inference on the EdgePreprint
Mohan, V. S. (2020) · doi:10.36227/techrxiv.11971383.v2 · Cited by 1
Pseudo-Labeling for Small Lesion Detection on Diabetic Retinopathy ImagesPreprint
Chen, Q., Liu, P., Ni, J., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.12040 · Cited by 1
Lightweight Mask R-CNN for Long-Range Wireless Power Transfer SystemsPreprint
Li, H., Wu, A., Wen, F., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2004.08761 · Cited by 1
MIDI-Sheet Music Alignment Using Bootleg Score SynthesisPreprint
Tanprasert, T., Jenrungrot, T., Müller, M., et al. (2019) · arXiv (Cornell University) · doi:10.5281/zenodo.3527747 · Cited by 1
Scope Head for Accurate Localization in Object DetectionPreprint
Zhan, G., Xu, D., Lu, G. S., Wu, W., Shen, C., & Ouyang, W. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2005.04854 · Cited by 1
Semantic Understanding for Augmented Reality and Its Applications
DeChicchis, J. (2020) · Cited by 6
Souto, Y. M., Pereira, R. S., Zorrilla, R., Chaves, A., Tsan, B., Rusu, F., Ogasawara, E., Ziviani, A., & Porto, F. A. M. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2005.11093 · Cited by 2
Minimizing Supervision in Multi-label CategorizationPreprint
Rajat, Varshney, M., Singh, P. P., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2005.12892 · Cited by 1
Phasic dopamine release identification using ensemble of AlexNetPreprint
Patarnello, L., Celin, M., & Nanni, L. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.02536 · Cited by 3
MFPP: Morphological Fragmental Perturbation Pyramid for Black-Box Model ExplanationsPreprint
Yang, Q., Zhu, X., Fwu, J.-K., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.02659 · Cited by 1
Hibikino-Musashi@Home 2019 Team Description PaperPreprint
Tanaka, Y., Ishida, Y., Abe, Y., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.01233 · Cited by 1
CoDeNet: Algorithm-hardware Co-design for Deformable ConvolutionPreprint
Dong, Z., Wang, D., Huang, Q., Gao, Y., Cai, Y., Wu, B., Keutzer, K., & Wawrzynek, J. (2020) · arXiv (Cornell University) · Cited by 1
Pixel Invisibility: Detecting Objects Invisible in Color ImagesPreprint
Wang, Y., & Wijesekera, D. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.08383 · Cited by 2
LabelEnc: A New Intermediate Supervision Method for Object DetectionPreprint
Miao, H., Liu, Y., Zhang, X., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.03282 · Cited by 1
Location-Aware Box Reasoning for Anchor-Based Single-Shot Object DetectionPreprint
Ma, W., Li, K., & Wang, G. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.06233 · Cited by 1
ESA-ReID: Entropy-Based Semantic Feature Alignment for Person re-IDPreprint
Tu, C., Yin, Z. Y., & Cai, L. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.04644 · Cited by 1
Uncertainty Quantification in Deep Residual Neural Networks
Wandzik, L., Garcia, R. V., & Krüger, J. (2020) · arXiv · doi:10.48550/arxiv.2007.04905 · Cited by 1
COBE: Contextualized Object Embeddings from Narrated Instructional VideoPreprint
Bertasius, G., & Torresani, L. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.07306 · Cited by 22
Tracking Passengers and Baggage Items using Multi-camera Systems at Security Checkpoints.Preprint
Siddique, A., & Medeiros, H. P. (2020) · arXiv (Cornell University) · Cited by 1
Liu, L., Bai, Y., & Li, Y. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.12326 · Cited by 1
Adma: A Flexible Loss Function for Neural NetworksPreprint
Shrivastava, A. D. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.12499 · Cited by 2
Dive Deeper Into Box for Object DetectionPreprint
Chen, R., Liu, Y., Zhang, M., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.14350 · Cited by 1
COCO-Search18: A Dataset for Predicting Goal-directed Attention ControlPreprint
Chen, Y., Yang, Z., Ahn, S., Samaras, D., Hoai, M., & Zelinsky, G. J. (2020) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2020.07.27.221499 · Cited by 1
Tam, L., Wang, X., Turkbey, E. B., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.15778 · Cited by 1
A Deep Representation Learning Framework for Medical Imaging Data Analysis
Xi, P. (2020) · Carleton University's Institutional Repository (MacOdrum Library, Carleton University) · doi:10.22215/etd/2020-14102 · Cited by 1
PAR: Personal Activity Radius Camera View for Contextual SensingPreprint
Echterhoff, J. M., & Wang, E. J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2008.07204 · Cited by 4
Freight Analysis Using YOLOv2Preprint
Kadam, S., Hatalge, A. D., Balip, A., & Powar, A. (2019) · SSRN Electronic Journal · doi:10.2139/ssrn.3420232 · Cited by 2
Towards Class-incremental Object Detection with Nearest Mean of ExemplarsPreprint
Ren, S., Yan, H., Xiong, N. N., & Guo, K. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2008.08336 · Cited by 1
Scene Text Detection with Selected AnchorPreprint
Zhu, A., Du, H., & Xiong, S. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2008.08523 · Cited by 1
Multi-Sensor Fusion for 3D Object Detection
Bhanushali, D. (2020) · RIT Scholar Works (Rochester Institute of Technology) · Cited by 1
Visible Feature Guidance for Crowd Pedestrian DetectionPreprint
Huang, Z., Yue, K., Deng, J., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2008.09993 · Cited by 1
Towards End-to-end Car License Plate Location and Recognition in Unconstrained ScenariosPreprint
Qin, S., & Liu, S. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2008.10916 · Cited by 1
Spatiotemporal Action Recognition in Restaurant VideosPreprint
Gupta, A., Desai, M., Liang, W., & Kannan, M. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2008.11149 · Cited by 1
Few-Shot Object Detection via Knowledge TransferPreprint
Kim, G., Jung, H.-G., & Lee, S. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2008.12496 · Cited by 1
Pogorelov, K. (2019) · NORA - Norwegian Open Research Archives · Cited by 1
Chiang, S.-H., Wang, T., & Chen, Y.-F. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2009.02711 · Cited by 1
Enabling Image Recognition on Constrained Devices Using Neural Network Pruning and a CycleGANPreprint
Lidfelt, A., Isaksson, D., Hedlund, L., Åberg, S., Borg, M., & Larsson, E. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2009.05300 · Cited by 1
RUHSNet: 3D Object Detection Using Lidar Data in Real TimePreprint
Sagar, A. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.01250 · Cited by 2
Curriculum Learning with Diversity for Supervised Computer Vision TasksPreprint
Soviany, P. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2009.10625 · Cited by 18
Embedded Systems and Computer Vision Techniques utilized in Spray Painting Robots: A ReviewPreprint
Shah, S., Pandey, S. V., Sorathiya, A., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.01131 · 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.