You Only Look Once: Unified, Real-Time Object Detection
Open accessThe DOI matches its Crossref record; 53 of the 53 references it cites were found in a registry or an index; 8 of the 25 sources its claims cite were checked for support.
Abstract
We present YOLO, a new approach to object detection. Prior work on object detection repurposes classifiers to perform detection. Instead, we frame object detection as a regression problem to spatially separated bounding boxes and associated class probabilities. A single neural network predicts bounding boxes and class probabilities directly from full images in one evaluation. Since the whole detection pipeline is a single network, it can be optimized end-to-end directly on detection performance. Our unified architecture is extremely fast. Our base YOLO model processes images in real-time at 45 frames per second. A smaller version of the network, Fast YOLO, processes an astounding 155 frames per second while still achieving double the mAP of other real-time detectors. Compared to state-of-the-art detection systems, YOLO makes more localization errors but is less likely to predict false positives on background. Finally, YOLO learns very general representations of objects. It outperforms other detection methods, including DPM and R-CNN, when generalizing from natural images to other domains like artwork.
Overview
CoChat Summary
TL;DR
YOLO reframes object detection as a single regression problem, using one convolutional network to predict bounding boxes and class probabilities directly from full images. It achieves real-time detection speeds while remaining competitive with, and complementary to, slower region-based detectors.
Key findings
- YOLO runs at 45 FPS on a Titan X GPU, and Fast YOLO runs at 155 FPS; Fast YOLO reaches 52.7% mAP on PASCAL VOC 2007, more than double prior real-time detectors, while YOLO reaches 63.4% mAP.
- On PASCAL VOC 2012, YOLO scores 57.9% mAP; combining Fast R-CNN with YOLO raises Fast R-CNN from 71.8% to 75.0% mAP on VOC 2007, a 3.2% gain.
- YOLO makes fewer background false positives than Fast R-CNN: Fast R-CNN has 13.6% background false positives among top detections and is almost 3× more likely to predict background detections than YOLO.
- YOLO generalizes better to artwork: on Picasso, YOLO gets 53.3 AP versus R-CNN’s 10.4 AP and DPM’s 37.8 AP; on People-Art, YOLO gets 45 AP versus R-CNN’s 26 AP and DPM’s 32 AP.
Methods
- Detection is modeled as a single CNN regression: the image is divided into an S×S grid; for PASCAL VOC, S=7, B=2, C=20, producing a 7×7×30 tensor of bounding boxes, confidence scores, and class probabilities.
- The base network has 24 convolutional layers followed by 2 fully connected layers; Fast YOLO uses 9 convolutional layers. Convolutional layers are pretrained on ImageNet at 224×224, then detection training uses 448×448 input.
- Training uses PASCAL VOC 2007 and 2012 for about 135 epochs, batch size 64, momentum 0.9, decay 0.0005, sum-squared error with λ_coord=5 and λ_noobj=0.5, dropout, and data augmentation.
Limitations
- The paper states YOLO imposes strong spatial constraints because each grid cell predicts only two boxes and one class, limiting nearby objects and struggling with small objects in groups such as flocks of birds.
- The paper states YOLO struggles to generalize to objects in new or unusual aspect ratios or configurations, uses relatively coarse features due to downsampling, and its loss treats small and large box errors equally; its main error source is incorrect localization.
- The paper states YOLO still lags state-of-the-art detection accuracy and struggles to precisely localize some objects, especially small ones.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Figures





Verification
Claims the paper makes
6 Valid · 8 Not valid · 15 Not checked · 92 Own results and interpretations
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“While it is much faster than R-CNN, it still falls short of real-time and takes a significant accuracy hit from not having good proposals.”
What the sources say
- Could not verifycites [20] [20] K. Lenc and A. Vedaldi. R-cnn minus r. arXiv preprint arXiv:1506.06981 , 2015. 5, 6 - sourceExperimental — accuracy not yet measured
The ConvNet-based Object Detection section identifies R-CNN minus R as a method that uses predefined regions instead of region proposals. It gives no runtime measurement or assessment of whether the method achieves real-time detection; searches for real-time performance and speed did not establish that claim. (LLM, conf=0.76)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Could not verify
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“To avoid overfitting we use dropout and extensive data augmentation.”
What the sources say
- Partly supportedcites [18] [18] G. E. Hinton, N. Srivastava, A. Krizhevsky, I. Sutskever, and R. R. Salakhutdinov. Improving neural networks by preventing co-adaptation of feature detectors. arXiv preprint arXiv:1207.0580 , 2012. 4 - sourceExperimental — accuracy not yet measured
The paper states that dropout reduces overfitting (p. 1) and describes using dropout with data augmentation for its ImageNet model (H Models for ImageNet, p. 18). It does not establish that YOLO uses either technique or describe YOLO’s augmentation as extensive. (LLM, conf=0.88)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“However, only 30Hz DPM [31] actually runs in real-time.”
What the sources say
- Supportedcites [31] [31] M. A. Sadeghi and D. Forsyth. 30hz object detection with dpm v5. In Computer Vision-ECCV 2014 , pages 65-79. Springer, 2014. 5, 6 - source
The Introduction (p.1) states that 'except for certain objects including face, pedestrians and certain rigid objects, detectors do not currently run at video rate' and that the presented architecture detects the 20 PASCAL VOC categories simultaneously at 30Hz, i.e. at video/real-time rate. The Abstract (p.1) and Table 2 (Method) bound the comparison to other DPM speed-up efforts: reference DPM at 0.07Hz, the fastest GPU 'Vanilla DPM' at ~1Hz, FTVQ at 0.53s, and 'over an order of magnitude faster than the previous fastest DPM implementation', so none of the listed variants reaches real-time. Thus our copy supports both parts of the attribution: that this 30Hz DPM runs in real-time and that it is the only such DPM among the speed-up efforts compared. (LLM, conf=0.82)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“While it is much faster than R-CNN, it still falls short of real-time and takes a significant accuracy hit from not having good proposals.”
What the sources say
- Could not verifycites [20] [20] K. Lenc and A. Vedaldi. R-cnn minus r. arXiv preprint arXiv:1506.06981 , 2015. 5, 6 - sourceExperimental — accuracy not yet measured
The ConvNet-based Object Detection section identifies R-CNN minus R and says it uses predefined regions in an SPPnet system, but gives no speed comparison with R-CNN. A search for R-CNN minus R and speed found no passage in our copy establishing that it is much faster. (LLM, conf=0.73)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Could not verify
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“While it is much faster than R-CNN, it still falls short of real-time and takes a significant accuracy hit from not having good proposals.”
What the sources say
- Partly supportedcites [20] [20] K. Lenc and A. Vedaldi. R-cnn minus r. arXiv preprint arXiv:1506.06981 , 2015. 5, 6 - sourceExperimental — accuracy not yet measured
The “ConvNet-based Object Detection” section (page unavailable) says R-CNN minus R uses predefined regions instead of region proposals. It does not say that this causes a significant accuracy loss; the paper’s discussion of low accuracy concerns a different system, naïve Faster R-CNN. (LLM, conf=0.83)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
84 more claims
Create a free account to see all 121 claims and to verify the 2 references still open.
- Probably not a substantial claim. 17
- It may state two separate claims as one. 15
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“which was not thoroughly investigated in prevIoUs work such as YOLOv1 [20] and YOLOv2 [51] employing MSE/L2 loss (Mean Squared Error).”
From Object Detection in 20 Years: A Survey (2023) · cites this paper as [20]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“the YOLO series models v2-v5 [144-147] are some of the most advanced object detection methods based on DNN, which have good performance in terms of speed and precision.”
From A survey of model compression strategies for object detection (2023) · cites this paper as [144]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“As a typical and more widely used new form of applications [9], various deep learning-based intelligent services and applications have changed many aspects of people's lives due to the great advantages of Deep Learning (DL) in the fields of Computer Vision (CV) and Natural Language Processing (NLP) [10].”
From Convergence of Edge Computing and Deep Learning: A Comprehensive Survey (2020) · cites this paper as [9]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“A convolutional neural network predicts the bounding boxes as well as class probabilities for all the objects depicted in an image.”
From Object detection using YOLO: challenges, architectural successors, datasets and applications (2023) · cites this paper as [56]
The cited source says what the claim attributes to it.
In the citing paper
“Authors of YOLO [56] have reframed the problem of object detection as a regression problem instead of classification problem.”
From Object detection using YOLO: challenges, architectural successors, datasets and applications (2023) · cites this paper as [56]
6 more claims about this paper
Create a free account to see every claim other papers make about this one.
Citations
Cites
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2577031 · Cited by 73,472
Self-citationFaster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2015) · arXiv · doi:10.48550/arxiv.1506.01497 · Cited by 70,812
Self-citationGoing deeper with convolutions
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298594 · Cited by 48,562
ImageNet Large Scale Visual Recognition Challenge
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-015-0816-y · Cited by 39,380 · cited 1×
“We pretrain our convolutional layers on the ImageNet 1000-class competition dataset [29].”
MethodHistograms of Oriented Gradients for Human Detection
Dalal, N., & Triggs, B. (2005) · 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) · doi:10.1109/cvpr.2005.177 · Cited by 33,584 · cited 2×
“Detection pipelines generally start by extracting a set of robust features from input images (Haar [25], SIFT [23], HOG [4], convolutional features [6]).”
MethodRich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
Girshick, R., Donahue, J., Darrell, T., & Malik, J. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.81 · Cited by 32,684 · cited 2×
“Then, classifiers [35, 21, 13, 10] or localizers [1, 31] are used to identify objects in the feature space.”
MethodSelf-citationGirshick, R. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.169 · Cited by 28,105
Self-citationDelving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
He, K., Zhang, X., Ren, S., & Sun, J. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.123 · Cited by 19,741 · cited 1×
“Convolutional neural networks (CNNs) achieve impressive performance on classification tasks at real-time speeds [13].”
Object recognition from local scale-invariant features
Lowe, D. G. (1999) · Proceedings of the Seventh IEEE International Conference on Computer Vision · doi:10.1109/iccv.1999.790410 · Cited by 16,472 · cited 1×
“Detection pipelines generally start by extracting a set of robust features from input images (Haar [25], SIFT [23], HOG [4], convolutional features [6]).”
MethodRobust Real-Time Face Detection
Viola, P., & Jones, M. J. (2004) · International Journal of Computer Vision · doi:10.1023/b:visi.0000013087.49260.fb · Cited by 14,097 · cited 1×
“Detectors for single classes like faces or people can be highly optimized since they have to deal with much less variation [36].”
Background
Cited by
Items 32,801–32,900 of 51,399
ZoomCount: A Zooming Mechanism for Crowd Counting in Static ImagesPreprint
Sajid, U., Sajid, H., Wang, H., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2002.12256 · Cited by 2
Awalgaonkar, N. M., Zheng, H., & Gurciullo, C. S. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.01196 · Cited by 2
Machine Learning based Pallets Detection and Tracking in AGVsPreprint
Zhang, S., Xiang, J., & Han, W. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2004.08965 · Cited by 2
CatNet: Class Incremental 3D ConvNets for Lifelong Egocentric Gesture RecognitionPreprint
Wang, Z., She, Q., Chalasani, T., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2004.09215 · Cited by 2
MIDI Passage Retrieval Using Cell Phone Pictures of Sheet MusicPreprint
Yang, D., Tanprasert, T., Jenrungrot, T., Shan, M., & Tsai, T. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2004.10347 · Cited by 3
GraftNet: An Engineering Implementation of CNN for Fine-grained Multi-label TaskPreprint
Jia, C., Zhang, L., Huang, H., Cai, W., Hu, H., & Adivarekar, R. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2004.12709 · Cited by 1
Entity Candidate Network for Whole-Aware Named Entity RecognitionPreprint
He, W., Shao, Y., & Zhang, P. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2004.14145 · Cited by 2
Large Scale Font Independent Urdu Text Recognition SystemPreprint
Rehman, A. U., & Hussain, S. U. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2005.06752 · Cited by 9
Iteratively Optimized Patch Label Inference Network for Automatic Pavement Disease DetectionPreprint
Tang, W., Zhao, Q., Huang, S., et al. (2020) · arXiv (Cornell University) · Cited by 2
MAGNet: Multi-Region Attention-Assisted Grounding of Natural Language Queries at Phrase LevelPreprint
Shrestha, A., Pugdeethosapol, K., Fang, H., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.03776 · Cited by 2
Deep Learning Methods for Real-time Detection and Analysis of Wagner Ulcer Classification SystemPreprint
Han, A., Yongze, Z., Li, A., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.02322 · Cited by 2
A study of the effect of the illumination model on the generation of synthetic training datasetsPreprint
Zhang, X., Jia, N., & Ivrissimtzis, I. P. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.08819 · Cited by 3
Training Quantized Neural Networks with a Full-precision Auxiliary ModulePreprint
Zhuang, B., Liu, L., Tan, M., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1903.11236 · Cited by 2
Mask Data Priming Network for Automatic Check-OutPreprint
Xiao, Z. G., Zhao, J., & Sun, G. C. (2020) · Preprints.org · doi:10.20944/preprints202006.0170.v1 · Cited by 2
Hippo: Taming Hyper-parameter Optimization of Deep Learning with Stage TreesPreprint
Shin, A., Kim, D. Y., Jeong, J. S., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.11972 · Cited by 2
Expandable YOLO: 3D Object Detection from RGB-D ImagesPreprint
Takahashi, M., Moro, A., Ji, Y., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.14837 · Cited by 2
Deep Mixture Density Network for Probabilistic Object DetectionPreprint
He, Y., & Wang, J. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1911.10614 · Cited by 2
Understanding Object Detection Through An Adversarial LensPreprint
Chow, K.-H., Liu, L., Gürsoy, M. E., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.05828 · Cited by 2
Temporal Self-Ensembling Teacher for Semi-Supervised Object DetectionPreprint
Chen, C., Dong, S., Tian, Y., Cao, K., Liu, L., & Guo, Y. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.06144 · Cited by 2
AABO: Adaptive Anchor Box Optimization for Object Detection via Bayesian Sub-samplingPreprint
Ma, W., Tian, T., Xu, H., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.09336 · Cited by 2
Detection and Annotation of Plant Organs from Digitized Herbarium Scans using Deep LearningPreprint
Younis, S., Schmidt, M., Weiland, C., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.13106 · Cited by 2
SADet: Learning An Efficient and Accurate Pedestrian DetectorPreprint
Zhuang, C., Lei, Z., & Li, S. Z. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.13119 · Cited by 2
Vulnerability Under Adversarial Machine Learning: Bias or Variance?Preprint
Aboutalebi, H., Shafiee, M. J., Karg, M. E., Scharfenberger, C., & Wong, A. K. C. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2008.00138 · Cited by 3
Hinzmann, T., Stegemann, T., Cadena, C., & Siegwart, R. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2008.04197 · Cited by 6
Switching Loss for Generalized Nucleus Detection in HistopathologyPreprint
Anand, D., Patel, G., Dang, Y., & Sethi, A. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2008.03750 · Cited by 4
Weight Equalizing Shift Scaler-Coupled Post-training QuantizationPreprint
Oh, J.-H., Lee, S. J., Park, M.-J., Walagaurav, P., & Kwon, K. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2008.05767 · Cited by 3
Kasaei, H., Melsen, J., van Beers, F., Steenkist, C., & Voncina, K. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.08151 · Cited by 2
Towards Streaming Image UnderstandingPreprint
Li, M., Wang, Y.-X., & Ramanan, D. (2020) · arXiv.org · doi:10.48550/arxiv.2005.10420 · Cited by 5
A Survey of FPGA-Based Robotic ComputingPreprint
Wan, Z., Bo, Y., Li, T. Y., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2009.06034 · Cited by 2
Pest Animal's Detection and Habitat Identification in Low-resolution Airborne Thermal ImageryPreprint
Ulhaq, A., & Khan, A. A. (2020) · Preprints.org · doi:10.20944/preprints202009.0480.v2 · Cited by 1
Few-shot Object Detection with Self-adaptive Attention Network for Remote Sensing ImagesPreprint
Xiao, Z., Xue, W., & Zhong, P. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2009.12596 · Cited by 2
YOLOv2 for Pigs Detection in Industrial FarmingPreprint
Khan, A. Q., & Khan, S. H. (2020) · Preprints.org · doi:10.20944/preprints202009.0088.v1 · Cited by 1
CAPTION: Correction by Analyses, POS-Tagging and Interpretation of Objects using only NounsPreprint
Ferreira, L. A., Meneghetti, D. D. R., & Santos, P. E. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.00839 · Cited by 2
SwiftFace: Real-Time Face DetectionPreprint
Ramos, L., & Morales, B. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2009.13743 · Cited by 2
Task-Adaptive Feature Transformer for Few-Shot SegmentationPreprint
Seo, J. S., Park, Y.-H., Yoon, S. W., & Moon, J. J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.11437 · Cited by 4
UFO$^2$: A Unified Framework towards Omni-supervised Object DetectionPreprint
Ren, Z., Yu, Z., Yang, X., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.10804 · Cited by 2
Ma, X., Li, J., Kochenderfer, M. J., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2011.04251 · Cited by 2
Self-supervised Segmentation via Background InpaintingPreprint
Katircioglu, I., Rhodin, H., Constantin, V., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2011.05626 · Cited by 2
Probabilistic Radio-Visual Active Sensing for Search and TrackingPreprint
Varotto, L., Cenedese, A., & Cavallaro, A. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2011.10474 · Cited by 2
Yun, S., & Wong, A. M. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2011.14578 · Cited by 2
Movement Tracks for the Automatic Detection of Fish Behavior in VideosPreprint
McIntosh, D., Marques, T. P., Albu, A. B., Rountree, R. A., & Leo, F. C. D. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2011.14070 · Cited by 11
Xie, H., Hussein, M. E., Galstyan, A., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.00150 · Cited by 2
Domain Adaptive Object Detection via Feature Separation and AlignmentPreprint
Liang, C., Zhao, Z., Liu, J., & Zhang, J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.08689 · Cited by 5
ROBY: Evaluating the Robustness of a Deep Model by its Decision BoundariesPreprint
Chen, J., Wang, Z., Zheng, H., Xiao, J., & Ming, Z. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.10282 · Cited by 2
More Reliable AI Solution: Breast Ultrasound Diagnosis Using Multi-AI CombinationPreprint
Dai, J., Lei, S., Dong, L., Lin, X., Zhang, H., Sun, D., & Yuan, K. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2101.02639 · Cited by 9
Computer vision beyond the visible : image understanding through language
Aguilera, A. S. (2019) · UPCommons institutional repository (Universitat Politècnica de Catalunya) · doi:10.5821/dissertation-2117-166156 · Cited by 2
WITHDRAWN: Content piracy: A large scale logo dataset for classification through deep learning
Patalappa, K. K. J., & Chandramouli, S. M. (2021) · Materials Today Proceedings · doi:10.1016/j.matpr.2020.12.134 · Cited by 2
RetractedSafety Case Templates for Autonomous SystemsPreprint
Bloomfield, R., Fletcher, G., Khlaaf, H., Hinde, L., & Ryan, P. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2102.02625 · Cited by 29
MosaicOS: A Simple and Effective Use of Object-Centric Images for Long-Tailed Object DetectionPreprint
Zhang, C., Pan, T.-Y., Li, Y., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2102.08884 · Cited by 2
SiMaN: Sign-to-Magnitude Network BinarizationPreprint
Lin, M., Ji, R., Xu, Z., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2102.07981 · Cited by 2
Advances in Inference and Representation for Simultaneous Localization and MappingPreprint
Rosen, D. M., Doherty, K., Espinoza, A. T., & Leonard, J. J. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.05041 · Cited by 2
RPATTACK: Refined Patch Attack on General Object DetectorsPreprint
Huang, H., Wang, Y., Chen, Z., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.12469 · Cited by 2
Figure Extraction from Scanned Electronic Theses and Dissertations
Kahu, S. Y. (2020) · VTechWorks (Virginia Tech) · Cited by 2
Anchor-Free Person SearchPreprint
Yan, Y., Li, J., Qin, J., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.11617 · Cited by 2
Relation-aware Instance Refinement for Weakly Supervised Visual GroundingPreprint
Liu, Y., Wan, B., Ma, L., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.12989 · Cited by 2
Scoring Graspability based on Grasp Regression for Better Grasp PredictionPreprint
Depierre, A., Dellandréa, E., & Chen, L. (2021) · HAL Portal Artxiker (Hindustan Aeronautics Limited (India)) · Cited by 3
Few-Shot Learning for Video Object Detection in a Transfer-Learning Scheme.Preprint
Yu, Z., Wang, G., Lin, C., Raschka, S., & Luo, J. (2021) · arXiv (Cornell University) · Cited by 2
Being-ahead: Benchmarking and Exploring Accelerators for Hardware-Efficient AI DeploymentPreprint
Zhang, X.-F., Ye, H.-C., & Chen, D.-M. (2021) · arXiv.org · doi:10.48550/arxiv.2104.02251 · Cited by 3
A Structure-Aware Relation Network for Thoracic Diseases Detection and SegmentationPreprint
Lian, J., Liu, J., Zhang, S., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2104.10326 · Cited by 2
Gradient-based Adversarial Deep Modulation Classification with Data-driven SubsamplingPreprint
Yi, J., & Gamal, A. E. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2104.06375 · Cited by 6
Efficient Object Embedding for Spliced Image RetrievalPreprint
Chen, B.-C., Wu, Z., Davis, L. S., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1905.11903 · Cited by 2
RADDet: Range-Azimuth-Doppler based Radar Object Detection for Dynamic Road UsersPreprint
Zhang, A., Nowruzi, F. E., & Laganière, R. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2105.00363 · Cited by 2
Rapid Detection of Aircrafts in Satellite Imagery based on Deep Neural NetworksPreprint
Tahir, A., Adil, M. Z., & Ali, A. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2104.11677 · Cited by 8
Probabilistic Ranking-Aware Ensembles for Enhanced Object DetectionsPreprint
Mao, M., Zhang, B., Doermann, D., Guo, J., Han, S., Feng, Y., Wang, X., & Ding, E. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2105.03139 · Cited by 7
Improved detection of small objects in road network sequencesPreprint
García, I., Luque‐Baena, R. M., & López‐Rubio, E. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2105.08416 · Cited by 2
ICDAR 2021 Competition on Components Segmentation Task of Document PhotosPreprint
Lopes, C. A. M., Junior, R. B. D. N., Bezerra, B. L. D., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.08499 · Cited by 2
ACNet: Mask-Aware Attention with Dynamic Context Enhancement for Robust Acne DetectionPreprint
Min, K., Lee, G.-H., & Lee, S. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2105.14891 · Cited by 2
Xie, S., Hu, C., Bagavathiannan, M., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.08897 · Cited by 2
Semi-Supervised 3D Hand-Object Poses Estimation with Interactions in TimePreprint
Liu, S., Jiang, H., Xu, J., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.05266 · Cited by 2
Spectral Unsupervised Domain Adaptation for Visual RecognitionPreprint
Zhang, J., Huang, J., Tian, Z., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.06112 · Cited by 2
Learning to Track Object Position through OcclusionPreprint
Chakraborty, S., & Hebert, M. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.10766 · Cited by 3
Semantic Segmentation of Periocular Near-Infra-Red Eye Images Under Alcohol EffectsPreprint
Tapia, J. E., Droguett, E. L., Valenzuela, A., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.15828 · Cited by 2
Residual Error: a New Performance Measure for Adversarial RobustnessPreprint
Aboutalebi, H., Shafiee, M. J., Karg, M. E., Scharfenberger, C., & Wong, A. K. C. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.10212 · Cited by 2
AlterSGD: Finding Flat Minima for Continual Learning by Alternative TrainingPreprint
Huang, Z., Liang, M., Liang, S., & He, W. P. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2107.05804 · Cited by 10
Video Crowd Localization with Multi-focus Gaussian Neighbor Attention and a Large-Scale Benchmark.Preprint
Li, H., Liu, L., Yang, K., et al. (2021) · arXiv (Cornell University) · Cited by 2
Cell Detection from Imperfect Annotation by Pseudo Label Selection Using P-classificationPreprint
Fujii, K., Suehiro, D., Nishimura, K., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2107.09289 · Cited by 2
Discovering "Semantics" in Super-Resolution NetworksPreprint
Liu, Y., Liu, A., Gu, J., Zhang, Z., Wu, W., Qiao, Y., & Dong, C. (2021) · arXiv (Cornell University) · Cited by 8
Multilevel Knowledge Transfer for Cross-Domain Object DetectionPreprint
Csaba, B., Qi, X., Chaudhry, A., Dokania, P. K., & Torr, P. H. S. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2108.00977 · Cited by 10
Detection and Captioning with Unseen Object Classes.Preprint
Demirel, B., & Cinbiş, R. G. (2021) · arXiv (Cornell University) · Cited by 2
Audio-Visual Transformer Based Crowd CountingPreprint
Sajid, U., Chen, X., Sajid, H., Kim, T., & Wang, G. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2109.01926 · Cited by 2
Robust Privacy-Preserving Motion Detection and Object Tracking in Encrypted Streaming VideoPreprint
Tian, X., Zheng, P., & Huang, J. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2108.13141 · Cited by 2
MBDF-Net: Multi-Branch Deep Fusion Network for 3D Object DetectionPreprint
Tan, X., Chen, X., Zhang, G., Ding, J., & Lan, X. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2108.12863 · Cited by 2
Tattoos in forensics : retrieval, detection and synthesis
Xu, X. (2021) · DR-NTU (Nanyang Technological University) · doi:10.32657/10356/151535 · Cited by 3
Marginal MAP Estimation for Inverse RL under Occlusion with Observer NoisePreprint
Suresh, P. S., & Doshi, P. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2109.07788 · Cited by 3
ER-IQA: Boosting Perceptual Quality Assessment Using External Reference ImagesPreprint
Guo, J., Wang, W., Yang, W., Liao, Q., & Zhou, J. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2105.02464 · Cited by 3
A Survey of Fish Tracking Techniques Based on Computer VisionPreprint
Li, Z., Li, Z., Li, F., Yuan, M., Cen, C., Qi, Y., Guo, Q., & Li, Y. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2110.02551 · Cited by 7
FaPN: Feature-aligned Pyramid Network for Dense Image PredictionPreprint
Huang, S., Lu, Z., Cheng, R., & He, C. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2108.07058 · Cited by 8
A General Gaussian Heatmap Labeling for Arbitrary-Oriented Object Detection.Preprint
Huang, Z., Li, W., Xia, X., et al. (2021) · arXiv (Cornell University) · Cited by 2
Multi-source Few-shot Domain AdaptationPreprint
Yue, X., Zheng, Z., Reed, C., Das, H., Keutzer, K., & Sangiovanni-Vincentelli, A. L. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2109.12391 · Cited by 16
An Explainable approach to Deep Learning from CT-scans for Covid IdentificationPreprint
Soares, E. A., Angelov, P. P., & Zhang, Z. (2021) · doi:10.36227/techrxiv.15135846.v1 · Cited by 4
Yang, H., Li, C., Zhao, X., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2110.07723 · Cited by 2
ReCU: Reviving the Dead Weights in Binary Neural NetworksPreprint
Xu, Z., Lin, M., Liu, J., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.12369 · Cited by 2
DPNET: Dual-Path Network for Efficient Object Detectioj with Lightweight Self-AttentionPreprint
Shi, H., Zhou, Q., Ni, Y., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2111.00500 · Cited by 2
de Carvalho, O. L. F., Júnior, O. A. D. C., de Albuquerque, A. O., Santana, N. C., Borges, D. L., Gomes, R. A. T., & Guimarães, R. F. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2111.12122 · Cited by 2
Towards an Efficient Semantic Segmentation Method of ID Cards for Verification SystemsPreprint
Lara, R., Valenzuela, A., Schulz, D., Tapia, J. E., & Busch, C. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2111.12764 · Cited by 14
ROS integrated object detection for SLAM in unknown, low-visibility environments
Christie, B. D., Ennasr, O. N., & Glaspell, G. P. (2021) · doi:10.21079/11681/42385 · Cited by 2
Detection of E-scooter Riders in Naturalistic ScenesPreprint
Apurv, K., Tian, R., & Sherony, R. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2111.14060 · Cited by 16
Rethinking Query, Key, and Value Embedding in Vision Transformer under Tiny Model ConstraintsPreprint
Ahn, J., Hong, J., Ju, J., & Jung, H. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2111.10017 · Cited by 2
Head and Body: Unified Detector and Graph Network for Person Search in MediaPreprint
Shu, X., Tao, Y., Qiao, R., Ke, B., Wen, W., & Ren, B. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2111.13888 · Cited by 2
Metadata
- Authors
- Redmon, J., Divvala, S., Girshick, R., & Farhadi, A.
- Affiliations
- University of Washington (US)
- Meta (United States) (US)
- Venue
- 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2016-06
- Pages
- 779-788
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W1483870316
- Cited by
- 53,803
- References
- 42
- Citations by year
- 2026: 5347 · 2025: 8912 · 2024: 8953 · 2023: 8264 · 2022: 6785 · 2021: 5741 · 2020: 4223 · 2019: 3286 · 2018: 1560 · 2017: 635 · 2016: 90
- FWCI
- 644.23
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Zenodo (CERN European Organization for Nuclear Research) (cc-by)
- Funders
- National Science Foundation (1338054)
- Office of Naval Research (N00014-13-1-0720, N00014)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image and Video Retrieval Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Visual Attention and Saliency Detection
- Keywords
- object detection, YOLO, real-time detection, bounding box regression, end-to-end learning, false positive reduction, domain generalization
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol and qwen3.8-omni-flash).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.