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 38,701–38,800 of 51,399
The Research of the Real-time Detection and Recognition of Targets in Streetscape VideosPreprint
Jian-min, L. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1806.04070
Querying Videos Using DNN Generated Labels
Wu, Y., Drucker, S. M., Philipose, M., & Ravindranath, L. (2018) · Workshop on Human-In-the-Loop Data Analytics (HILDA) · doi:10.1145/3209900.3209909
Searching and Matching Texture-free 3D Shapes in Images
Liao, S., Gavves, E., & Snoek, C. G. M. (2018) · International Conference on Multimedia Retrieval · doi:10.1145/3206025.3206057
Occlusion-aware pedestrian detection
Apostolopoulos, C., Nasrollahi, K., Yang, M., Jahromi, M. N. S., & Moeslund, T. B. (2019) · International Conference on Machine Vision · doi:10.1117/12.2523107
The implementation of an object detection algorithm on the FT processor
Li, B., Chen, S., & Yang, C. (2018) · MATEC Web of Conferences · doi:10.1051/matecconf/201817303081
CVTron Web: A Versatile Framework for Online Computer Vision Services
Chen, Y., & Yao, X. (2018) · Lecture notes in computer science · doi:10.1007/978-3-319-94472-2_5
Active query-driven visual search using probabilistic bisection and convolutional neural networksPreprint
Tsiligkaridis, A., & Tsiligkaridis, T. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1806.11223
A New TV World for Kids - When ZUI Meets Deep Learning
Wang, H., Fu, Y., Li, Y., et al. (2018) · IEEE Conference on Multimedia Information Processing and Retrieval (MIPR) · doi:10.1109/mipr.2018.00029
Pruning channels and fully convolutional deep learning based target detection
Xu, Z., Zhu, S., & Lu, B. (2018) · Chinese Control and Decision Conference (CCDC) · doi:10.1109/ccdc.2018.8407410 · Cited by 1
Pedestrian Detection with D-CNN
Gao, Z., Chen, W., Cao, G., & Chen, P. (2018) · Communications in computer and information science · doi:10.1007/978-981-13-1026-3_13
Constrained Neural Network and Its Application in Target Direction Estimation
刘, 进. (2018) · Geomatics Science and Technology · doi:10.12677/gst.2018.63017
Detection of images with animals in raw camera-trap data
TEKELİ, U., & Baştanlar, Y. (2018) · Signal Processing and Communications Applications Conference (SIU) · doi:10.1109/siu.2018.8404214
An Effective Framework for Person Re-Identification in Video Surveillance
Wang, J., Miao, Z., Zhang, Y., et al. (2018) · International Conference on Multimedia Systems and Signal Processing (ICMSSP) · doi:10.1145/3220162.3220179
Dimensionality Deduction for Action Proposals: To Extract or to Select?
Jiang, J., Wang, H., Xie, L., Zhang, J., & Deng, C. (2018) · Lecture notes in computer science · doi:10.1007/978-3-319-95957-3_37
Weakly-Supervised Object Localization by Cutting Background with Deep Reinforcement Learning
Wu, Z., & Zhang, Z. (2018) · Lecture notes in computer science · doi:10.1007/978-3-319-97310-4_24
An Accurate Method Based on Deep Learning Architectures for Real-world Object Detection
Yang, L., Pan, X., Zhang, J., et al. (2018) · DEStech Transactions on Computer Science and Engineering · doi:10.12783/dtcse/cnai2018/24183
Impact of Shifting Time-Window Post-Processing on the Quality of Face Detection Algorithms
Blokus, A., & Krawczyk, H. (2018) · Conference on Human System Interactions · doi:10.1109/hsi.2018.8431293
A Multi-view Images Generation Method for Object Recognition
Jin, Z., Cui, G., Chen, G., & Chen, X. (2018) · Lecture notes in computer science · doi:10.1007/978-3-319-97589-4_26
Complex Water Surface Segmentation with RGBP-FCN
Liu, S., Chen, Q., Yue, Z., et al. (2018) · Lecture notes in computer science · doi:10.1007/978-3-319-97589-4_31
Semantic Web Technology as a Tool for Integrating Training and Job Market Supply Chains
Malandrino, O., & Sessa, M. R. (2018) · IEEE International Conference on Advanced Learning Technologies (ICALT) · doi:10.1109/icalt.2018.00088
Tracking System for Driving Assistance with the Faster R-CNN
Yang, K., Zhang, C., & Wu, M. (2018) · Advances in intelligent systems and computing · doi:10.1007/978-981-13-0344-9_31
Dynamic saliency detection via CNN and spatial-temporal fusion
Zhang, Q., & Xu, D. (2018) · International Conference on Digital Image Processing · doi:10.1117/12.2503058
A pedestrian detection algorithm based on deep deconvolution networks in complex scenes
Sun, Y., Liu, Z., & Zhang, M. (2018) · International Conference on Digital Image Processing · doi:10.1117/12.2502815
Real-time pedestrian detection for driver assistance systems based on deep learning
Gong, Z., Tao, W., & Wang, X. (2018) · International Conference on Digital Image Processing · doi:10.1117/12.2503047
Domain Adaptation Tracker With Global and Local Searching
Zhao, F., Zhang, T., Wu, Y., Wang, J., & Tang, M. (2018) · IEEE Access · doi:10.1109/access.2018.2862878
Dynamic Detection-Tracking Switching
Bruno, A., Park, J., Hwang, S., & Kim, M. (2018) · International Conference on Ubiquitous and Future Networks · doi:10.1109/icufn.2018.8436727 · Cited by 2
Scene text detection for augmented reality: character bigram approach to reduce false positive rate
Gubbi, S., & Amrutur, B. S. (2018) · CSI Transactions on ICT · doi:10.1007/s40012-018-0203-2
A Scene-Assisted Air-to-Ground Object Detection Method
Liu, X., Yang, D., Chen, J., et al. (2018) · Journal of Physics Conference Series · doi:10.1088/1742-6596/1069/1/012002
Accuracy Improvement of Functional Attribute Recognition by Dense CRF Considering Object Shape
Iizuka, M., Akizuki, S., & Hashimoto, M. (2018) · IEEJ Transactions on Electronics Information and Systems · doi:10.1541/ieejeiss.138.1088
A Study On The Use of Deep Learning for Automatic Audience Counting
Florentino, C. S., & Costa, R. E. O. (2018) · Brazilian Symposium on Multimedia and the Web · doi:10.1145/3243082.3243110
Fusing Object Context to Detect Functional Area for Cognitive Robots
Cheng, H., Cai, J., Liu, Q., Zhang, Z., Yang, K., Loy, C. C., & Lin, L. (2018) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2018.8460590
Learning detector ensembles for object detection
Zhou, C. (2018) · doi:10.32657/10220/46010
Deformable Feature Pyramid Network for Ship Recognition
Ding, Y., Zhang, Y., Qu, Y., et al. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-00764-5_6
Pedestrian Detection with a Directly-Cascaded Deconvolution-Convolution Structure
Chen, Z., Han, X., Lin, W., Cheng, M., Liu, G., & Xiong, H. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-00776-8_34
Deep learning tools for foreground-aware analysis of film colors
Flückiger, B., Evirgen, N., Paredes, E. G., et al. (2017) · Zurich Open Repository and Archive (University of Zurich) · doi:10.5167/uzh-153333
Comparing Interrelationships Between Features and Embedding Methods for Multiple-View Fusion
Piroddi, R., Goulermas, Y., Maskell, S. R., & Ralph, J. F. (2018) · International Conference on Information Fusion (FUSION) · doi:10.23919/icif.2018.8455547
Research on Simulation System of Small Unmanned Air-to-Ground Object Detection Platform
Liu, X., Chen, J., Yang, D., et al. (2018) · Journal of Physics Conference Series · doi:10.1088/1742-6596/1087/6/062053
U-Net Based Moving Target Detection for Unmanned Air Vehicles
Yu, Q., Yao, H., He, F., et al. (2018) · Chinese Control Conference (CCC) · doi:10.23919/chicc.2018.8483331
An Anti-Occlusion Tracking Algorithm
Min, Y., & Wei, Z. (2018) · International Conference on Computer Science and Application Engineering (CSAE) · doi:10.1145/3207677.3278074
Naidu, V., Bhamra, J. K., Ansari, A., et al. (2018) · International Conference on Electronics, Communication and Aerospace Technology (ICECA) · doi:10.1109/iceca.2018.8474885
Top-down Gamma Saliency - Learning to Search for Objects in Complex Scenes
Burt, R., & Príncipe, J. C. (2018) · doi:10.1109/ijcnn.2018.8489657
Toward Efficient Simultaneous Detection and Segmentation
Zhang, C., Li, Z., Liu, Q., et al. (2018) · IEEE International Conference on Multimedia Big Data · doi:10.1109/bigmm.2018.8499154
Computational UAV Cinematography for Intelligent A/V Shooting Based on Semantic Visual Analysis
Patrona, F., Mademlis, I., Tefas, A., et al. (2018) · doi:10.1145/3265845.3265857
Comparison of Multi-Object Recognition Models
Parubochyi, V., & Шувар, Р. (2018) · doi:10.30970/elit2018.a28
Exploring Multi-scale Deep Feature Fusion for Object Detection
Zhang, Q., Lai, J., Xie, X., et al. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-03341-5_4
Affective Computing and Bandits: Capturing Context in Cold Start Situations
Oehme, S., & Dietz, L. W. (2018) · Conference on Recommender Systems
PI V.I.S.I.O.N: Portable Infinitesimal Video Input Signal Processed Intelligent Object Naming
Diganth, P., Ankolekar, M. K., Neha, B. S., & Mishra, G. (2018) · International Conference on Computing, Communication and Networking Technologies (ICCCNT) · doi:10.1109/icccnt.2018.8494027
Compression of Deep Neural Networks with Structured Sparse Ternary Coding
Boo, Y., & Sung, W. (2018) · Journal of Signal Processing Systems · doi:10.1007/s11265-018-1418-z
Accuracy of a Driver-Assistance System in a Collision Scenario
Khan, W. A., & Klette, R. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-03801-4_23
LoANs: Weakly Supervised Object Detection with Localizer Assessor Networks
Bartz, C., Yang, H., Bethge, J., & Meinel, C. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-21074-8_29
Adaptive Confidence Threshold Algorithm for Vehicle Detection by Employing Temporal Information
Qi, S., Li, J., & Sun, Z. (2018) · International Conference on Intelligent Human-Machine Systems and Cybernetics · doi:10.1109/ihmsc.2018.00087
Dual-satellite integrated intelligent reconnaissance autonomous decision-making model
Jiang, H., Liu, X., & Zhao, H. (2018) · MATEC Web of Conferences · doi:10.1051/matecconf/201823204052
Celik, T., Hughes, B., & Burghardt, T. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-13469-3_113
Real-Time Texture-less Object Recognition on Mobile Devices
Chan, J., Lee, J. A., & Kemao, Q. (2018) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2018.8545158
Cross Modal Multiscale Fusion Net for Real-time RGB-D Detection
Yin, K., Liu, S., Liu, R., Chen, Y., & Shen, K. (2018) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2018.8545330
Visual lnertial Hybridization Technique based on Beacons identified by Deep Learning
Demange, V., Nicolaou, J., Delhaye, F., et al. (2018) · DGON Inertial Sensors and Systems (ISS) · doi:10.1109/inertialsensors.2018.8577143
Tracklet and Signature Representation for Multi-Shot Person Re-Identification
Baabou, S., Khan, F. M., Brémond, F., et al. (2018) · International Multi-Conference on Systems, Signals & Devices (SSD) · doi:10.1109/ssd.2018.8570441
A Comparative Study on Detection and Estimation of a 3-D Object Model in a Complex Scene
Le, V.-H., Vu, H., & Thủy, N. T. T. (2018) · International Conference on Knowledge and Systems Engineering/Proceedings · doi:10.1109/kse.2018.8573394
Enabling More Accurate Bounding Boxes for Deep Learning-Based Real-Time Human Detection
Jeong, H., Gwak, J., Park, C., et al. (2018) · Lecture notes in electrical engineering · doi:10.1007/978-981-13-2685-1_33
Ko, T., Shin, J., Kwon, S., et al. (2018) · Creative Construction Conference 2018 - Proceedings · doi:10.3311/ccc2018-035
Monitoring Visitor Numbers with Computer Vision
Staab, J., Taubenböck, H., & Job, H. (2018) · elib (German Aerospace Center)
Object Localization and Activities Identification Using Attribute Details in SMART Meeting Rooms
Andriana, D., Prihatmanto, A. S., Hidayat, E., et al. (2018) · doi:10.5121/csit.2018.81606
Text and Symbol Extraction in Traffic Panel from Natural Scene Images
Li, Z.-M., & Huang, L.-L. (2017) · Asian Conference on Pattern Recognition · doi:10.1109/acpr.2017.71
Assistive Technology Evolving as Intelligent System
Basu, A., Petropoulakis, L., Caterina, G. D., & Soraghan, J. J. (2020) · Springer eBooks · doi:10.1007/978-3-030-41862-5_27
On Tracking Realistic Targets in a Megacity with Contested Domain Access
Lee, J., Abdelzaher, T., Qiu, H., et al. (2018) · IEEE Military Communications Conference (MILCOM) · doi:10.1109/milcom.2018.8599773
Online Semantic Segmentation and Manipulation of Objects in Task Intelligence for Service Robots
Llopart, A., Ravn, O., Andersen, N. A., & Kim, J.-H. (2018) · International Conference on Control, Automation, Robotics and Vision (ICARCV) · doi:10.1109/icarcv.2018.8581135 · Cited by 1
YAPAY SİNİR AĞLARI İLE HELİKOPTER PİSTİ TESPİTİ
BAŞESKİ, E. (2018) · VII. UZAKTAN ALGILAMA VE CBS SEMPOZYUMU UZAL-CBS2018 · doi:10.15659/uzalcbs2018.6650
6DoF Pose Estimation for Similar Objects Using Spatial Relationship of Part-Affordance
Akizuki, S., & Aoki, Y. (2019) · Journal of the Japan Society for Precision Engineering · doi:10.2493/jjspe.85.107
Wang, Y., Peng, H., Li, Y., et al. (2018) · IEEE Advanced Information Technology, Electronic and Automation Control Conference (IAEAC) · doi:10.1109/iaeac.2018.8577218
Desenvolvendo Modelos de Deep Learning para Aplicações Multimídia no Tensorflow
Busson, A. J. G., Figueiredo, L., dos Santos, G. P., Damasceno, A. L. D. B., Colcher, S., & Milidiú, R. L. (2018) · doi:10.5753/sbc.455.7.03 · Cited by 2
Real-Time Vehicle Re-Identification System Using Symmelets and Deep PatchMatch Nets
Hsieh, J.-W., & Chen, H. C. (2018) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc.2018.00398
Nishikawa, Y., Sato, H., & Ozawa, J. (2018) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc.2018.00540
3D Primitive Approximation Method for Model-less Determining of Grasping Parameters
Torii, T., & Hashimoto, M. (2019) · Transactions of the Society of Instrument and Control Engineers · doi:10.9746/sicetr.55.35
Hata, N., Nakayama, T., Tanaka, A., Wakamatsu, T., Yoshida, A., Tateiwa, N., Nishikawa, Y., Ozawa, J., & Fujisawa, K. (2018) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata.2018.8622146
Work Flows for Cellular Epidemiology, From Conception to TranslationPreprint
Nathanson, A. D., Ngo, L., Garbowski, T., Srikantha, A., Wojek, C., Zeidler, D., & Tate, M. L. K. (2019) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/548412
Dataset Culling: Towards Efficient Training Of Distillation-Based Domain Specific ModelsPreprint
Yoshioka, K., Lee, E., Wong, S. S., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1902.00173
RStudio AI Blog: Concepts in object detection
Keydana, S. (2018)
Visual Tracking Based on Convolutional Neural Network
Li, X., Jiang, K. Y., Jia, S., Zhang, X., & Sun, Y. (2018) · Chinese Automation Congress · doi:10.1109/cac.2018.8623581 · Cited by 1
FSSPD: Fast Single Stage Pedestrian Detector for Autonomous Driving
Luo, J., Shi, Y., & Xie, C. (2019) · DEStech Transactions on Environment Energy and Earth Science · doi:10.12783/dteees/iceee2018/27819
Object detection deep learning networks for Optical Character Recognition
Bourez, C., & Coquard, A. (2018)
On the Applicability of Deep Learning for Road Signal Recognition
Soares, V. R., da Luz, M. R., Ribeiro, A. H., Rbeiro, R. S., Martins, S. R. M., Santos, M. A. O., & de Mira, J. (2018) · IEEE International Conference on Industry Applications · doi:10.1109/induscon.2018.8627071 · Cited by 1
Efficient Recurrent Detection for Visual Tracking
Hsu, H.-W., & Ding, J. (2018) · International Symposium on Computer, Consumer and Control · doi:10.1109/is3c.2018.00026
Design of Convolutional Neural Network for Classifying Depth Prediction Images from Overhead
Sumimoto, S., Miyata, Y., Yoshimura, R., et al. (2018) · International SoC Design Conference · doi:10.1109/isocc.2018.8649975
Vision Based Picking System for Automatic Express Package DispatchingPreprint
Wang, S., Jiang, X., Zhao, J., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1902.08951
SVSoC: Speculative Vision Systems-on-a-Chip
Gan, Y., Qiu, Y., Leng, J., et al. (2019) · IEEE Computer Architecture Letters · doi:10.1109/lca.2019.2903241
Object Detection on Base of Modified Convolutional Network
Alexeev, A., Matveev, Y. N., & Kukharev, G. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-13469-3_62
IN-VEHICLE CAMERA IMAGES PREDICTION BY GENERATIVE ADVERSARIAL NETWORK
Watanabe, J., & Gonsalves, T. (2019) · doi:10.5121/csit.2019.90205
Exploiting weak mask representation with convolutional neural networks for accurate object tracking
Huang, J., Zhou, W., Tian, Q. C., & Li, H. (2019) · Multimedia Tools and Applications · doi:10.1007/s11042-019-7219-y · Cited by 1
On Class Imbalance and Background Filtering in Visual Relationship DetectionPreprint
Sarullo, A., & Mu, T. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1903.08456
Deep Learning-based Regional Image Caption Generation with Refined Descriptions
Kinghorn, P. (2017) · Northumbria Research Link (Northumbria University)
Miyamoto, R., Migita, Y., Izumo, S., et al. (2019) · doi:10.1145/3307363.3307398
A Classify-Before-Detect Method For Weakly Supervised Object Localization
Dong, X., Wang, P., Fu, R., Gao, Y., & Wang, J. (2019) · Journal of Physics Conference Series · doi:10.1088/1742-6596/1176/3/032003
A Multi-Objective Recognition Algorithm with Time and Space Fusion
Wang, H., Chi, J., Wu, C., et al. (2019) · SAE technical papers on CD-ROM/SAE technical paper series · doi:10.4271/2019-01-1047
DNS: A multi-scale deconvolution semantic segmentation network for joint detection and segmentation
Feng, N., Dong, L., Zhang, Q., Zhang, N., Wu, X., & Chen, J. (2019) · MATEC Web of Conferences · doi:10.1051/matecconf/201927702005
VideoRecognition - Uma proposta de serviço para reconhecimento de elementos de vídeo em larga escala
Busson, A. J. G., Guedes, Á. L. V., dos Santos, G. N. P., Neto, C. D. S. S., Milidiú, R. L., & Colcher, S. (2018) · Brazilian Symposium on Multimedia and the Web · doi:10.5753/webmedia.2018.4598
Harvesting Visual Objects from Internet Images via Deep Learning Based Objectness AssessmentPreprint
Wu, K., Li, G., Li, H., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1904.00641
The convolutional neural networks: Applications in precision agriculture
Medojević, I., Marković, D. A., Simonović, V., Joksimović, A., & Rosić, J. Š. (2019) · Poljoprivredna tehnika · doi:10.5937/poljteh1901001m
Transfer Learning with Sparse Associative Memories
Jodelet, Q., Gripon, V., & Hagiwara, M. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-30487-4_39
Work Study System Using Indoor Positioning Technology
Tsuji, T., Kotsuka, Y., & Arima, S. (2018) · International Congress on Advanced Applied Informatics (IIAI-AAI) · doi:10.1109/iiai-aai.2018.00016
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.