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 32,701–32,800 of 51,399
Dual-Attention Network for Acute Pancreatitis Lesion Detection with CT Images
Zhang, J., & Zhang, D. (2021) · Lecture notes in electrical engineering · doi:10.1007/978-981-16-3880-0_25 · Cited by 2
da Silva, J. R., da Silva, Y. S., Santos, F. D. S., et al. (2021) · IEEE International Conference on Industry Applications · doi:10.1109/induscon51756.2021.9529913 · Cited by 2
Target Detection in Rural River Image Based on Yolo V5 Model with the Cross-Stitch Unit
Cai, Q., Zhong, S., & Chen, K. (2021) · International Conference on Image, Vision and Computing (ICIVC) · doi:10.1109/icivc52351.2021.9527005 · Cited by 2
A Vision System for Shot Tracking and Thrown Distance Measurement
Wen, H., Xiao, Z., Li, Y., et al. (2020) · International Conference on Information Science and Control Engineering · doi:10.1109/icisce50968.2020.00326 · Cited by 2
Deep Learning Based Formation Control of Drones
Kaboré, K., & Güler, S. (2021) · Studies in computational intelligence · doi:10.1007/978-3-030-77939-9_11 · Cited by 2
RBA-CenterNet: Feature Enhancement by Rotated Border Alignment for Oriented Object Detection
Liu, T., Wang, Y., Hou, S., Li, W., Guan, J., Zhou, S., & Qin, R. (2021) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn52387.2021.9534400 · Cited by 2
Cao, Y., Yang, Z. C., & Gao, C. (2021) · INTELIGENCIA ARTIFICIAL · doi:10.4114/intartif.vol24iss68pp21-32 · Cited by 2
Research on License Plate Detection and Recognition Based on Deep Learning
Gao, L., & Zhang, W. (2021) · International Conference on Computer Engineering and Artificial Intelligence (ICCEAI) · doi:10.1109/icceai52939.2021.00081 · Cited by 2
Ship Detection based on SAR Imaging Supervised by Noisy Ship Direction
Huang, J., Niu, Y., & Gan, W. (2021) · International Conference on Pattern Recognition and Artificial Intelligence (PRAI) · doi:10.1109/prai53619.2021.9551103 · Cited by 2
SOLOLaneNet: Instance Segmentation-Based Lane Detection Method using Locations
Zhang, H., Gu, Y., Wang, X., Wang, M., & Pan, J. (2021) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc48978.2021.9564795 · Cited by 3
Resource Constrained Neural Networks for Direction-of-Arrival Estimation in Micro-controllers
Sahoo, P., Rajoria, R., Chandhok, S., Darak, S. J., Pau, D. P., & Dabral, H.-D. (2021) · International Conference on AI-ML Systems (AIMLSystems) · doi:10.1145/3486001.3486230 · Cited by 3
Automatic Detection of Injection and Press Mold Parts on 2D Drawing Using Deep Neural Network
Lee, J., Kim, J., Park, J., et al. (2021) · International Conference on Control, Automation and Systems (ICCAS) · doi:10.23919/iccas52745.2021.9649875 · Cited by 2
Can DNN Detectors Compete Against Human Vision in Object Detection Task?
Li, Q., Zhang, J., Zhao, X., & Huang, K. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-88004-0_44 · Cited by 2
Pedestrian Detection Based on Improved YOLOv3 Algorithm
Li, A., Gao, X., & Chengming, Q. (2021) · Communications in computer and information science · doi:10.1007/978-981-16-7207-1_22 · Cited by 3
Compression of YOLOv3-spp Model Based on Channel and Layer Pruning
Lv, X., & Hu, Y. (2021) · Communications in computer and information science · doi:10.1007/978-981-16-7213-2_16 · Cited by 2
Dynamic Resource Allocation and Memory Management using Deep Convolutional Neural Network
Patil, D. R., & Purohit, R. (2019) · International Journal of Engineering and Advanced Technology · doi:10.35940/ijeat.a9961.129219 · Cited by 9
Unraveling Deep Learning Performance in Cross-Sensor Iris Recognition
Choudhary, M., Tiwari, V., & Venkanna, U. (2021) · Lecture notes in electrical engineering · doi:10.1007/978-981-16-3690-5_10 · Cited by 2
Fuhrmann, H., Boyko, A., Abdelpakey, M. H., & Shehata, M. (2021) · IEEE World Forum on Internet of Things (WF-IoT) · doi:10.1109/wf-iot51360.2021.9594927 · Cited by 3
Natural Scene Text Recognition Using Convolutional Recurrent Neural Network
Wang, Y., & Ha, J.-E. (2021) · International Conference on Computer Science & Education (ICCSE) · doi:10.1109/iccse51940.2021.9569296 · Cited by 2
Dual-det : a fast detector for oriented object detection in aerial images
Guan, Q., Qu, Z., Zhao, P., Zeng, M., & Liu, J. (2021) · International Journal of Remote Sensing · doi:10.1080/01431161.2021.1995071 · Cited by 4
A Face-Mask Detection System Based on Deep Learning Convolutional Neural Networks
Ndong, P. S. B., Adoni, W. Y. H., Nahhal, T., et al. (2021) · Advances in intelligent systems and computing · doi:10.1007/978-981-16-5559-3_23 · Cited by 2
Applying Multi-layers Feature Fusion in SSD for Detection of Small-Scale Objects
Imanov, E., & Shah, Z. (2022) · Lecture notes in networks and systems · doi:10.1007/978-3-030-92127-9_74 · Cited by 2
Rundo, F., Anfuso, I., Amore, M. G., Ortis, A., Messina, A. A., Sabrina Conoci, A., & Battiato, S. (2022) · Sensors · doi:10.3390/s22020674 · Cited by 2
Analysis and design of industrial safety automatic identification system based on Tiny-YOLOv3
Wu, P.-S., Lin, C.-Y., Cheng, T.-Y., et al. (2021) · IEEE International Future Energy Electronics Conference (IFEEC) · doi:10.1109/ifeec53238.2021.9661778 · Cited by 2
Detection Method of Apple Based on Improved Lightweight YOLOv5
Li, Z., Zhang, X., Feng, X., et al. (2022) · Communications in computer and information science · doi:10.1007/978-981-16-9247-5_22 · Cited by 2
Koruyucu Gözlük Kullanımının Görüntü İşleme Yöntemiyle Tespit Edilmesi
BAŞARAN, G., & Çağıl, G. (2021) · El-Cezeri Fen ve Mühendislik Dergisi · doi:10.31202/ecjse.945167 · Cited by 2
A MBGD enhancement method for imbalance smoothing
Ai, X., Sheng, V. S., & Li, C. (2022) · Multimedia Tools and Applications · doi:10.1007/s11042-022-12697-3 · Cited by 2
Canário, J. P., Ferreira, M. V., Freire, J., Carvalho, M. C., & Rios, R. A. (2022) · Multimedia Tools and Applications · doi:10.1007/s11042-022-12806-2 · Cited by 2
Monitoring Maritime Traffic with Ship Detection via YOLOv4
Verma, G., Gupta, A., Bansal, S., & Dhiman, H. (2022) · International Conference on Artificial Intelligence and Signal Processing (AISP) · doi:10.1109/aisp53593.2022.9760632 · Cited by 3
An Overview of Machine Learning Methods used in Fatigue Driving Detection
Dong, L., & Cai, J. (2022) · International Conference on Intelligent Information Technology (ICIIT) · doi:10.1145/3524889.3524900 · Cited by 2
Forest Fire Detection Algorithm Based on Aerial Image
Qi, M., & Chen, B. (2022) · Lecture notes in electrical engineering · doi:10.1007/978-981-16-9423-3_58 · Cited by 2
Human Fall Detection Model with Lightweight Network and Tracking in Video
Ren, X., Zhang, Y., & Yang, Y. (2021) · doi:10.1145/3507548.3507549 · Cited by 2
Conditional Context-Aware Feature Alignment for Domain Adaptive Detection Transformer
Chen, S. (2022) · Lecture notes in computer science · doi:10.1007/978-3-030-98358-1_22 · Cited by 2
Crack Detection with Multi-task Enhanced Faster R-CNN Model
Mao, Y., Ping, P., Chen, J., et al. (2020) · IEEE International Conference on Big Data Computing Service and Applications (BigDataService) · doi:10.1109/bigdataservice49289.2020.00044 · Cited by 2
Deep Learning Development Status in China
Center for Electronics and Information Studies, C. A. O. E. (2020) · Springer eBooks · doi:10.1007/978-981-15-4584-9_2 · Cited by 2
Ikeda, R., & Hidaka, A. (2022) · Communications in computer and information science · doi:10.1007/978-3-031-06381-7_15 · Cited by 2
Real-Time Detection of Face Mask and Social Distancing
Bag, V. V., Patil, M. B., Shinde, A., et al. (2022) · Smart innovation, systems and technologies · doi:10.1007/978-981-19-2719-5_33 · Cited by 2
Intelligent Feeding Algorithm for Recirculating Aquaculture System Based on Deep Learning
Yang, J., Yang, J., Wu, H., et al. (2022) · Lecture notes in electrical engineering · doi:10.1007/978-981-19-3927-3_39 · Cited by 2
A Self-attention Network for Face Detection Based on Unmanned Aerial Vehicles
Hua, S., Fan, H., Ding, N., Li, W., & Tang, Y. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-13822-5_39 · Cited by 2
Improved YOLOv4 Safety Helmet Detection Algorithm
Liu, Y., Zhang, D., Zhao, L. X., et al. (2022) · International Conference on Advances in Computer Technology, Information Science and Communications (CTISC) · doi:10.1109/ctisc54888.2022.9849797 · Cited by 2
Object Detection Using Microsoft HoloLens by a Single Forward Propagation CNN
Moezzi, R., Krčmařík, D., Cýrus, J., Bahri, H., & Kočí, J. (2022) · Proceedings in adaptation, learning and optimization · doi:10.1007/978-3-030-97196-0_42 · Cited by 2
MDS-Net: Multi-Scale Depth Stratification 3D Object Detection from Monocular Images
Xie, Z., Song, Y., Wu, J., Li, Z., Song, C., & Xu, Z. (2022) · Sensors · doi:10.3390/s22166197 · Cited by 7
Network Pruning by Feature Map Sharing with K-Means Clustering
Chiu, D.-Y., & Huang, S.-H. (2022) · IEEE International Conference on Consumer Electronics - Taiwan (ICCE-Taiwan) · doi:10.1109/icce-taiwan55306.2022.9869244 · Cited by 2
Deep-RIC: Plastic Waste Classification using Deep Learning and Resin Identification Codes (RIC)
Listyalina, L., Yudianingsih, Y., Soedjono, A. W., Utari, E. L., & Dharmawan, D. A. (2022) · Telematika · doi:10.31315/telematika.v19i2.7419 · Cited by 4
Single Camera Based Gait Analysis Method with Scaled and Image Coordinate Key-points
Xiang, T., Zhou, X.-H., Xie, X., Liu, S.-Q., Wang, C., Gui, M.-J., Li, H., & Hou, Z. (2022) · IEEE International Conference on Real-time Computing and Robotics (RCAR) · doi:10.1109/rcar54675.2022.9872256 · Cited by 2
Road object recognition method based on improved YOLOv3
Zhang, Y. (2022) · Academic Journal of Computing & Information Science · doi:10.25236/ajcis.2022.050501 · Cited by 2
Chang, J. S., Hwang, J., & Choi, M. (2022) · Transportation Research Record Journal of the Transportation Research Board · doi:10.1177/03611981221123809 · Cited by 3
Link-Aware Frame Selection for Efficient License Plate Recognition in Dynamic Edge Networks
Liu, J., Cong, R., Wang, X., & Zhou, Y. (2022) · Electronics · doi:10.3390/electronics11193186 · Cited by 2
Study of YOLOX Target Detection Method Based on Stand-Alone Self-Attention
Zeng, Y. (2022) · Academic Journal of Computing & Information Science · doi:10.25236/ajcis.2022.051205 · Cited by 1
Automatic Video Captioning using Deep Neural Network
Nguyen, T. (2017) · RIT Scholar Works (Rochester Institute of Technology) · Cited by 2
A vision based system for underwater dockingPreprint
Liu, S., Özay, M., Okatani, T., Xu, H., Sun, K., & Yang, L. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1712.04138 · Cited by 3
Temporally Identity-Aware SSD with Attentional LSTMPreprint
Chen, X., Yu, J., & Wu, Z. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1803.00197 · Cited by 2
Soft-PHOC Descriptor for End-to-End Word Spotting in Egocentric Scene ImagesPreprint
Bazazian, D., Karatzas, D., & Bagdanov, A. D. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1809.00854 · Cited by 2
Object Detection from Scratch with Deep SupervisionPreprint
Shen, Z., Liu, Z., Li, J., et al. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1809.09294 · Cited by 2
Real-time Face Detection and Recognition Based on Deep Learning
Wang, H. (2018) · Tuwhera (Auckland University of Technology) · Cited by 10
PartsNet: A Unified Deep Network for Automotive Engine Precision Parts Defect DetectionPreprint
Qu, Z., Shen, J., Li, R., Liu, J., & Guan, Q. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1810.12061 · Cited by 3
Three Dimensional Convolutional Neural Network Pruning with Regularization-Based MethodPreprint
Zhang, Y., Wang, H., Luo, Y., et al. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1811.07555 · Cited by 2
Mask-aware networks for crowd countingPreprint
Jiang, S., Lu, X., Lei, Y., et al. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1901.00039 · Cited by 2
A Single-shot Object Detector with Feature Aggragation and EnhancementPreprint
Li, W., & Liu, G. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1902.02923 · Cited by 2
Hernandez, V., Suzuki, T., & Venture, G. (2019) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/535492 · Cited by 2
GMC: Grid Based Motion Clustering in Dynamic EnvironmentPreprint
Zhang, H., Karunasekera, H., & Wang, H. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1902.09193 · Cited by 2
AdVersarial: Perceptual Ad Blocking meets Adversarial Machine LearningPreprint
Tramèr, F., Dupré, P., Rusak, G., et al. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1811.03194 · Cited by 2
FVNet: 3D Front-View Proposal Generation for Real-Time Object Detection from Point CloudsPreprint
Zhou, J. N., Tan, X., Shao, Z., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1903.10750 · Cited by 2
Object Localization with a Weakly Supervised CapsNetPreprint
Liu, W., Barsoum, E., & Owens, J. D. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1805.07706 · Cited by 2
StackNet: Stacking Parameters for Continual learningPreprint
Kim, J., Kim, J., & Kwak, N. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1809.02441 · Cited by 4
Generative Flow via Invertible nxn Convolution.Preprint
Truong, T.-D., Luu, K., Duong, C. N., Le, N., & Tran, M. (2019) · arXiv (Cornell University) · Cited by 2
Towards real-time object detection on edge with deep neural networks
Zhang, Z. (2018) · MOspace Institutional Repository (University of Missouri) · doi:10.32469/10355/67715 · Cited by 2
Instance-Level Salient Object SegmentationPreprint
Li, G., Xie, Y., Lin, L., & Yu, Y. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1704.03604 · Cited by 8
Focal Loss in 3D Object DetectionPreprint
Peng, Y., Tai, L., Wang, Y., et al. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1809.06065 · Cited by 2
Fast On-Line Kernel Density Estimation for Active Object LocalizationPreprint
Rhodes, A. D., Quinn, M. H., & Mitchell, M. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1611.05369 · Cited by 4
Large-Scale Object Detection of Images from Network Cameras in Variable Ambient Lighting ConditionsPreprint
Tung, C., Kelleher, M. R., Schlueter, R. J., et al. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1812.11901 · Cited by 2
Scaling Video Analytics Systems to Large Camera DeploymentsPreprint
Jain, S., Ananthanarayanan, G., Jiang, J., Shu, Y., & Gonzalez, J. E. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1809.02318 · Cited by 6
QANet -- Quality Assurance Network for Image SegmentationPreprint
Arbelle, A., Elul, E., & Raviv, T. R. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1904.08503 · Cited by 6
An evaluation of VGG16 and YOLO v3 on hand-drawn images
Hoang, L. (2019) · doi:10.15760/honors.703 · Cited by 2
Multi-Person Tracking By Multi-Scale Detection in Basketball ScenariosPreprint
Arbués-Sangüesa, A., Haro, G., & Ballester, C. (2019) · arXiv (Cornell University) · doi:10.21427/63bf-4y98 · Cited by 2
Delving Deep into Liver Focal Lesion Detection: A Preliminary StudyPreprint
Ma, J., Chen, Y., Chen, Y., Wan, F., Xue, S., Li, Z., & Feng, S. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1907.10346 · Cited by 4
Suchan, J., Bhatt, M., Varadarajan, S., Amirshahi, S. A., & Yu, S. X. (2018) · EasyChair preprint · doi:10.29007/v963 · Cited by 6
Object as DistributionPreprint
Ding, L., & Fridman, L. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1907.12929 · Cited by 10
Reprojection R-CNN: A Fast and Accurate Object Detector for 360° ImagesPreprint
Zhao, P., You, A., Zhang, Y., Liu, J., Bian, K., & Tong, Y. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1907.11830 · Cited by 3
Image Captioning with Unseen ObjectsPreprint
Demirel, B., Cinbiş, R. G., & İkizler-Cinbiş, N. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1908.00047 · Cited by 12
Dynamic Region Division for Adaptive Learning Pedestrian CountingPreprint
He, G., Ma, Z., Huang, B., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1908.03978 · Cited by 2
Feedbackward Decoding for Semantic SegmentationPreprint
Wang, B., Glossner, J., Iancu, D., & Gaydadjiev, G. N. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1908.08584 · Cited by 2
Understanding the Effects of Pre-Training for Object Detectors via EigenspectrumPreprint
Shinya, Y., Simo‐Serra, E., & Suzuki, T. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.04021 · Cited by 2
To What Extent Does Downsampling, Compression, and Data Scarcity Impact Renal Image Analysis?Preprint
Peng, C., Zhao, K., Wiliem, A., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.09945 · Cited by 2
Multi-modal Analysis for the Automatic Evaluation of Epilepsy
Ahmedt‐Aristizabal, D. (2019) · Queensland University of Technology · doi:10.5204/thesis.eprints.132537 · Cited by 2
Jin, C., Chen, S. Z., & He, H. H. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1910.07160 · Cited by 2
Grouping Capsules Based Different TypesPreprint
Ren, Q. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1911.04820 · Cited by 3
Hu, Y., Jin, Y., Li, R., & Zhang, X. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1911.06080 · Cited by 3
Instance-Invariant Adaptive Object Detection via Progressive DisentanglementPreprint
Wu, A., Han, Y., Zhu, L., & Yang, Y. (2019) · arXiv (Cornell University) · Cited by 2
Relation Graph Network for 3D Object Detection in Point CloudsPreprint
Feng, M., Gilani, S. Z., Wang, Y., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1912.00202 · Cited by 2
Vision: A Deep Learning Approach to provide walking assistance to the visually impairedPreprint
Thakurdesai, N., Tripathi, A., Butani, D., & Sankhe, S. R. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1911.08739 · Cited by 9
Liu, B., Zhang, J., Zhang, X., Zhang, W., Yu, C., & Zhou, Y. J. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1911.09299 · Cited by 10
Robustness-Driven Exploration with Probabilistic Metric Temporal LogicPreprint
Liu, X., Shi, P., Alqahtani, S., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1912.01704 · Cited by 2
Toward Filament Segmentation Using Deep Neural NetworksPreprint
Ahmadzadeh, A., Mahajan, S. S., Kempton, D., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1912.02743 · Cited by 2
Oriented Objects as pairs of Middle LinesPreprint
Wei, H., Zhang, Y., Chang, Z., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1912.10694 · Cited by 2
Scale Match for Tiny Person DetectionPreprint
Yu, X., Gong, Y., Jiang, N., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1912.10664 · Cited by 2
A Feasible Framework for Arbitrary-Shaped Scene Text RecognitionPreprint
Zhang, J., Wang, W., Huang, D., Liu, Q., & Wang, Y. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1912.04561 · Cited by 9
Small, Accurate, and Fast Vehicle Re-ID on the Edge: the SAFR ApproachPreprint
Suprem, A., Pu, C., & Ferreira, J. E. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2001.08895 · Cited by 5
Cooperative LIDAR Object Detection via Feature Sharing in Deep NetworksPreprint
Marvasti, E. E., Raftari, A., Marvasti, A. E., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2002.08440 · Cited by 2
Beyond Dropout: Feature Map Distortion to Regularize Deep Neural NetworksPreprint
Tang, Y., Wang, Y., Xu, Y., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2002.11022 · 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.