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 37,301–37,400 of 51,399
Lightweight Detection Algorithm for Dense Pedestrian in Airport Terminals
Gao, Q., Lu, J., & Zhang, Y. (2025) · International Conference on Intelligent Perception and Pattern Recognition (IPPR) · doi:10.1109/ippr66507.2025.11198481 · Cited by 1
“In 2016, the single-stage detection model YOLOv1 [5] innovatively framed the object detection task as a complete regression problem, eliminating the operation of generating candidate box regions in traditional two-stage methods and achieving end-to-end detection.”
Evaluating graphical perception capabilities of Vision Transformers
Poonam, P., Vázquez, P., & Ropinski, T. (2025) · Computers & Graphics · doi:10.1016/j.cag.2025.104458 · Cited by 3
“CNNs [48] were among the first computational models that were able to showcase remarkable capabilities in image recognition [32, 45, 77], object detection [31, 67, 68], and semantic segmentation [8, 69].”
Automatic detection of the number of aircraft over satellite data using deep learning
Singla, J. G., Jaiswal, G. K., Chaudhary, R., et al. (2025) · Journal of Earth System Science · doi:10.1007/s12040-025-02673-4 · Cited by 1
A hybrid pipeline for aircraft role classification in satellite imagery
Tandogan, T., & Saygılı, G. (2026) · Signal Image and Video Processing · doi:10.1007/s11760-026-05321-6 · Cited by 1
“This normalization ensures resolution invariance, allowing the model to generalize across images of different sizes while preserving the geometric integrity of the annotated shapes [9].”
Abouelmagd, L. M., Askr, H., Darwish, A., & Hassanien, A. E. (2025) · BioEnergy Research · doi:10.1007/s12155-025-10914-z · Cited by 1
“1 [31].”
Context-Aware LLM-Based Human-Robot Interaction
Canh, T. N., HoangVan, K., & HoangVan, X. (2025) · Lecture notes in networks and systems · doi:10.1007/978-981-95-1746-6_8 · Cited by 2
Chen, H., Zhu, C.-S., Bai, H.-W., et al. (2025) · Measurement science and technology · doi:10.1088/1361-6501/ae2d80
“Although this approach removed the limitations of anchor boxes on model performance, the reliance on NMS became the most significant factor affecting YOLO’s detection speed and accuracy [16–19].”
A dataset of dune morphology in China’s deserts at 30m resolution from 2000 to 2020
ZHANG, T., Shan, C. A. O., Zhaobin, W. A. N. G., et al. (2025) · China Scientific Data · doi:10.11922/11-6035.ncdc.2024.0024.zh · Cited by 1
Intersection-based Ensemble for Small Multi-Object Tracking in Challenging Environments
Whang, G.-Z., & Chu, W.-T. (2025) · doi:10.23919/mva65244.2025.11175071 · Cited by 1
“For detection, numerous detectors have been developed, such as Cascade R - CNN [14] , YOLO [15] , and Transformer - based architectures like DETR [16] .”
An Efficient CNN-Based Detector for Weld Defect Detection Based on Enhanced YOLOv8
Wang, Y., Huang, N., Li, G., et al. (2025) · Youth Academic Annual Conference of Chinese Association of Automation (YAC) · doi:10.1109/yac66630.2025.11150199 · Cited by 1
“For example, AlexNet [7], VGGNet [8], Faster R-CNN [9], and the YOLO series [10]–[12], with their respective unique innovations, have laid the foundation for the application of deep learning in the field of object detection.”
Brown, D., & Bradshaw, K. (2025) · International Conference on Artificial Intelligence, Big Data, Computing and Data Communication Systems (icABCD) · doi:10.1145/3759023.3759124 · Cited by 1
“The You Only Look Once (YOLO) family of detectors [16, 21] has also demonstrated exceptional performance, particularly in terms of speed and efficiency.”
Huo, Y., Yao, M., Tian, Q., Zhang, S., Zhao, J., Liu, X., & Wang, H. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11227997 · Cited by 8
DSCG-YOLO: a lightweight visual inspection model for exoskeleton in stair walking scenarios
Luo, T., Yao, W., Liang, S., Ma, X., Li, Y., & Tuo, Q. (2025) · Signal Image and Video Processing · doi:10.1007/s11760-025-04995-8 · Cited by 1
“The You Only Look Once (YOLO), a real-time object detection algorithm [26], is characterized by its lightweight architecture and superior detection speed.”
EdgeNavMamba: Mamba-Optimized Object Detection for Energy-Efficient Edge Devices
Aalishah, R., Navardi, M., & Mohsenin, T. (2025) · IEEE International Conference on Cyber Security and Cloud Computing / IEEE International Conference on Edge Computing and Scalable Cloud (CSCloud/EdgeCom) · doi:10.1109/edgecom66327.2025.00017 · Cited by 7
“Since You Only Look Once (YOLO) [15] revolutionized object detection by using regression on bounding boxes, several efforts have applied these methods to YOLO.”
InfluentialDuong, V. H., Truong, V. D., Dinh, D. K., Vu, H., Luong, T. V., & Nguyen, T. C. (2025) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw69036.2025.00555 · Cited by 1
Nguyen, H. H., Pham, H. D. T., Le, K. M., & Nguyen, C. T. (2025) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw69036.2025.00569 · Cited by 1
Efficient and Distortion-Aware Fisheye Object Detection for Edge Devices
Gia, B. T., Khanh, T. B. C., Thanh, T. L. T., Trong, H. H., Do, T., Ngo, T. D., Le, D.-D., & Satoh, S. (2025) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw69036.2025.00572 · Cited by 2
“Initially proposed by Redmon et al. [8], the YOLO framework rev-olutionized real-time object detection by unifying the traditionally separate processes of region proposal and classification into a single, end-to-end neural network.”
SAW YOLO lightweight network for fire hazard detection in ancient wooden structures
Hui, Z., & Fang, T. (2026) · Scientific Reports · doi:10.1038/s41598-025-30061-x · Cited by 1
“In accordance with the Cultural Relic Building Fire Risk Assessment Method [16], which defines fire prevention as a systematic approach to prevent and control fire spread while minimizing losses, this study focused on the potential fire hazards caused by incense burning.”
Text Search: Towards Fast Text Localization in Scene Images
Yang, L., Cheng, S. S. M., Verma, P. K., & Wang, S. (2016) · IEEE International Symposium on Multimedia (ISM) · doi:10.1109/ism.2016.0024 · Cited by 1
High-speed railway real-time localization auxiliary method based on deep neural network
Chen, D., Zhang, W., & Yang, Y. (2017) · AIP conference proceedings · doi:10.1063/1.5012495 · Cited by 1
Pixel-based airplanes segmentation in remote sensing image
Liu, M., Gao, Z., Li, S., et al. (2017) · Chinese Control and Decision Conference (CCDC) · doi:10.1109/ccdc.2017.7979346 · Cited by 1
Research on Scene Parsing Algorithm Cascading Object Detection Network
Guo, X. W., Wen, Y., Ma, D., Jin, Y., & Yu, H. (2017) · IEEE International Conference on Computational Science and Engineering (CSE) and IEEE International Conference on Embedded and Ubiquitous Computing (EUC) · doi:10.1109/cse-euc.2017.87 · Cited by 1
A Fast Vehicle Detection Approach with Multilayer Perceptron Convolution Layers
Chen, H., Cheng, Y., & Zhang, C. (2017) · doi:10.1145/3127404.3127467 · Cited by 1
Direct multi-scale dual-stream network for pedestrian detection
Jung, S., & Hong, K.-S. (2017) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2017.8296262 · Cited by 1
Real-time object detection by a multi-feature fully convolutional network
Guo, Y., Guo, X., Jiang, Z., Men, A., & Zhou, Y. (2017) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2017.8296365 · Cited by 1
Container Code Detection by Deep Convolutional Network
Wang, Z., & Ma, S. (2017) · doi:10.2991/gcmce-17.2017.16 · Cited by 1
A distributed object detector-tracker aided video encoder for smart camera networks
Jagarlapudi, S. B., Gorur, P., & Amrutur, B. S. (2017) · International Conference on Distributed Smart Cameras · doi:10.1145/3131885.3131920 · Cited by 1
Pedestrian detection based on DCT of multi-channel feature
Liu, C., Wu, Z., Zhang, Z.-F., & Hu, L. (2017) · IEEE International Conference on Communication Software and Networks · doi:10.1109/iccsn.2017.8230297 · Cited by 1
Occlusion resolving inside public crowded scenes based on social deep learning model
Elons, A. S., & Abol-Ela, M. (2017) · International Conference on Intelligent Computing and Information Systems (ICICIS) · doi:10.1109/intelcis.2017.8260050 · Cited by 1
Alimuin, R., Guiron, A., & Dadios, E. P. (2017) · IEEE International Conference on Humanoid, Nanotechnology, Information Technology, Communication and Control, Environment, and Management (HNICEM) · doi:10.1109/hnicem.2017.8269461 · Cited by 1
Research and Implementation of Indoor Positioning Algorithm for Personnel Based on Deep Learning
Yue, H., Xiao, Z., Wang, J., et al. (2018) · Lecture notes on data engineering and communications technologies · doi:10.1007/978-3-319-75928-9_70 · Cited by 1
Egocentric Video Multi-viewer for Analyzing Skilled Behaviors based on Gaze Object
Umezawa, Y., Hirayama, T., Enokibori, Y., et al. (2018) · ACM International Conference on Intelligent User Interfaces (IUI) · doi:10.1145/3180308.3180342 · Cited by 1
Single Shot Text Detector with Rotational Prior Boxes
Zhu, W. D., Lou, J. J., Xia, Q., & Ren, M. (2018) · Neural Processing Letters · doi:10.1007/s11063-018-9810-z · Cited by 1
There is only you: Actively diminishing people in a scene
Kim, C., Lee, J., Lee, K., & Park, J.-I. (2018) · International Conference on Electronics, Information, and Communication (ICEIC) · doi:10.23919/elinfocom.2018.8330604 · Cited by 1
Stacked Marginal Time Warping for Temporal Alignment
Zhang, X., Nie, L., Lan, L., et al. (2018) · Neural Processing Letters · doi:10.1007/s11063-018-9834-4 · Cited by 1
Rethinking Energy-Efficiency of Heterogeneous Computing for CNN-Based Mobile Applications
Wang, Z., Li, X., Wang, C., Cheng, Z., Song, J., & Zhou, X. (2017) · IEEE International Symposium on Parallel and Distributed Processing with Applications (ISPA) · doi:10.1109/ispa/iucc.2017.00074 · Cited by 2
Fast FFT-Based Inference in 3D Convolutional Neural Networks
Xie, B., Zhang, G., Shen, Y., Liu, S., & Ge, Y. (2018) · Advances in intelligent systems and computing · doi:10.1007/978-3-319-93554-6_40 · Cited by 1
Multitarget tracking using multifeature model with acceleration feature
Liu, H., Chang, F., Liu, C., & Liang, F. (2018) · Optical Engineering · doi:10.1117/1.oe.57.7.073105 · Cited by 1
Dynamic object counting application based on object detection and tracking
Shi, J., & Tao, W. (2018) · International Conference on Digital Image Processing · doi:10.1117/12.2503014 · Cited by 1
Zhou, S., & Wei-hua, L. (2017) · International Conference on Computer Systems, Electronics and Control (ICCSEC) · doi:10.1109/iccsec.2017.8446790 · Cited by 1
Toward semantic loop closure in simultaneous localization and mapping systems
Zhang, Y.-C., Huang, C., Yang, C.-Y., & Chen, Y.-H. (2018) · Current Developments in Lens Design and Optical Engineering · doi:10.1117/12.2320035 · Cited by 1
Three-Stream Action Tubelet Detector for Spatiotemporal Action Detection in Videos
Wu, Y., Wang, H., & Li, Q. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-00767-6_28 · Cited by 1
Region-Based Convolutional Neural Networks for Profiled Fiber Recognition
Chen, Z., Wang, X., Zheng, Y., & Wan, Y. (2018) · International Conference on Audio, Language and Image Processing · doi:10.1109/icalip.2018.8455689 · Cited by 1
A Summary of the 4th International Workshop on Recovering 6D Object Pose
Hodaň, T., Kouskouridas, R., Kim, T., Tombari, F., Bekris, K. E., Drost, B., Groueix, T., Walas, K., Lepetit, V., Leonardis, A., et al. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-11009-3_36 · Cited by 11
Soccer Video Super-Resolution via Sub-Pixel Convolutional Neural Network
Wang, H., & Lu, Y. (2018) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2018.8489036 · Cited by 1
SFCM: Learn a Pooling Kernel for Weakly Supervised Object Localization
Li, Z., Shi, Y., Tian, Y., Zeng, W., & Wang, Y. (2018) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme.2018.8486593 · Cited by 1
Missing Recover with Recurrent Neural Networks for Video Object Detection
Shen, R., Wang, W., Zhang, S., & Tang, J. (2018) · Communications in computer and information science · doi:10.1007/978-981-13-2922-7_19 · Cited by 1
Incorporating wheelchair users in people detection
Martín-Nieto, R., García‐Martín, Á., & Martínez, J. M. (2018) · Multimedia Tools and Applications · doi:10.1007/s11042-018-6822-7 · Cited by 1
Asymmetric Two-Stream Networks for RGB-Disparity Based Object Detection
Lu, R., Lai, J., & Xie, X. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-03341-5_1 · Cited by 1
Robust Face Detector with Fully Convolutional Networks
Su, Y., Wan, X., & Guo, Z. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-03338-5_18 · Cited by 1
A Proposed Heterogeneous Convolutional Neural Network for Embedded Automotive Vision Algorithms
Mansour, I., Hoffman, R. R., Rawashdeh, O. A., & Seifert, B. (2018) · IEEE International Conference on Electro Information Technology · doi:10.1109/eit.2018.8500249 · Cited by 1
A Modified PSRoI Pooling with Spatial Information
Zheng, Y., Hu, X., Bi, N., et al. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-03335-4_38 · Cited by 1
Convolutional LSTM Based Video Object Detection
Wang, X., Xie, X., & Lai, J. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-03335-4_9 · Cited by 1
Interestingness Prediction & its Application to Immersive Content
Marquant, G., Demarty, C.-H., Chamaret, C., et al. (2018) · International Conference on Content-Based Multimedia Indexing (CBMI) · doi:10.1109/cbmi.2018.8516524 · Cited by 1
Liu, Q., & Han, T. (2018) · Proceedings/Proceedings - International Conference on Network Protocols · doi:10.1109/icnp.2018.00041 · Cited by 1
Deep Directional Network for Object Tracking
Hu, Z., & Shi, X. (2018) · Algorithms · doi:10.3390/a11110178 · Cited by 1
Micro-UAV onboard vehicle detection: architecture and experiments
Zhou, Z., Zhou, Y., Tang, D., Zhao, K., & Hu, T. (2018) · IEEE International Conference on Intelligence and Safety for Robotics (ISR) · doi:10.1109/iisr.2018.8535835 · Cited by 1
Understanding Deep Neural Network by Filter Sensitive Area Generation Network
Yang, Q., Qiao, H., & Xu, J. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-04167-0_18 · Cited by 1
Carata, S.-V., Constantin, M. G., Ghenescu, V., Chindea, M., & Ghenescu, M. T. (2018) · IEEE International Geoscience and Remote Sensing Symposium (IGARSS) · doi:10.1109/igarss.2018.8518138 · Cited by 1
A Fast Orientation Invariant Detector Based on the One-stage Method
Yin, J., Pan, H., Su, H., et al. (2018) · MATEC Web of Conferences · doi:10.1051/matecconf/201823204036 · Cited by 1
Object Detection Based on CNNs: Current and Future Directions
Chen, L., Sadka, A. H., Dong, J., & Zhou, H. (2018) · Springer eBooks · doi:10.1007/978-3-319-89914-5_2 · Cited by 4
Detecting Sex From Handwritten Examples
Saha, S., Khaled, M. A. B., Islam, M. S., Puja, N. S., & Hasan, M. (2018) · International Conference on System, Computation, Automation and Networking (ICSCAN) · doi:10.1109/icscan.2018.8541214 · Cited by 1
Appearance Variation Insensitive State Regression for Visual Tracking
Ma, L., & Liu, Z. (2018) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2018.8545353 · Cited by 1
Automatic Prostate Segmentation on MR Images Using Enhanced Holistically-Nested Networks
Jit, D., Qian, J., Yu, J., Kurihara, T., & Zhan, S. (2018) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2018.8545341 · Cited by 1
Deep Neural Networks Optimization Based On Deconvolutional Networks
Liu, Z., Zhang, C., Li, C., Ding, S., Liu, S., & Dong, Y. X. (2018) · International Conference on Graphics and Signal Processing (ICGSP) · doi:10.1145/3282286.3282299 · Cited by 1
A Comprehensive Study on Upper-Body Detection with Deep Neural Networks
Zhu, Y., & Zhang, L. (2018) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2018.8545209 · Cited by 1
Large Scale Fashion Search System with Deep Learning and Quantization Indexing
Dinh, T. H., Văn, T. P., Thanh, T. M., et al. (2018) · doi:10.1145/3287921.3287964 · Cited by 1
SWATT: Synchronized Wide-area Sensing and Autonomous Target Tracking
Teng, E., Ramirez, C. G., & Iannucci, B. (2018) · IEEE Conference on Technologies for Homeland Security (HST) · doi:10.1109/ths.2018.8574189 · Cited by 1
Yang, Y., Mai, X., Wu, H., Nie, M., & Wu, H. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-05051-1_35 · Cited by 1
Learning Invariant Features in Modulatory Networks through Conflict and Ambiguity
Grant, W. S., & Itti, L. (2018) · Neural Computation · doi:10.1162/neco_a_01156 · Cited by 1
Human Activity Recognition without Vision Tracking
Flores-Vázquez, C., Aranda, J., Icaza, D., et al. (2019) · IntechOpen eBooks · doi:10.5772/intechopen.82660 · Cited by 1
Object detection based on Online hard examples mining with residual network
Chao, Z., & Ying, C. (2018) · IEEE Advanced Information Technology, Electronic and Automation Control Conference (IAEAC) · doi:10.1109/iaeac.2018.8577519 · Cited by 1
Unsupervised Video Prediction Network with Spatio-temporal Deep Features
Jin, B., Zhou, R. F., Zhang, Z., & Dai, M. Q. (2018) · International Conference on Mechatronics and Machine Vision in Practice (M2VIP) · doi:10.1109/m2vip.2018.8600864 · Cited by 1
Real-world pedestrian detection method enhanced by semantic segmentation
Peng, Q. (2019) · Journal of Electronic Imaging · doi:10.1117/1.jei.28.1.013008 · Cited by 1
Video Predictive Object Detector
Gasmallah, M., & Zulkernine, F. H. (2018) · IEEE Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON) · doi:10.1109/iemcon.2018.8615054 · Cited by 1
Accuracy improvement of functional attribute recognition by dense CRF considering object shape
Iizuka, M., Akizuki, S., & Hashimoto, M. (2019) · Electronics and Communications in Japan · doi:10.1002/ecj.12151 · Cited by 1
Companion Following Robotic Wheelchair with Bus Boarding Capabilities
Mamun, S. A., Ali, S., Fukuda, H., Lam, A., Kobayashi, Y., & Kuno, Y. (2018) · International Conference on Informatics, Electronics & Vision (ICIEV) · doi:10.1109/iciev.2018.8641059 · Cited by 1
Cleaning Behavior Estimation for Self-Supported Cognitive Rehabilitation System
Kojima, H., Kitano, M., Yokota, K., et al. (2018) · IEEE International Conference on Artificial Intelligence in Engineering and Technology (IICAIET) · doi:10.1109/iicaiet.2018.8638470 · Cited by 1
Ensemble of Convolutional Neural Networks for Heart Segmentation
Fok, W., Jamart, K., Zhao, J., et al. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-12029-0_31 · Cited by 1
Comparison of Support Vector Machines and Deep Learning for Vehicle Detection.
Kaplan, Ö., & Şaykol, E. (2018) · Cited by 2
Teleoperation Snake Robots with Panorama Vision
Chen, L. F., Yuwen, X., Bing, Z., et al. (2018) · doi:10.1109/hfr.2018.8633487 · Cited by 1
Nigar, N., & Uddin, M. N. (2018) · International Conference on Computer and Information Technology (ICCIT) · doi:10.1109/iccitechn.2018.8631913 · Cited by 1
Key Character Detection Based on Deep Neural Network for Document Images
Tu, J.-C., Lin, G.-S., Chang, C.-C., et al. (2018) · International Symposium on Computer, Consumer and Control · doi:10.1109/is3c.2018.00086 · Cited by 1
Memory Warps for Long-Term Online Video Representations and Anticipation
Vu, T. H., Choi, W., Schulter, S., & Chandraker, M. K. (2019) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv.2019.00128 · Cited by 3
Pedestrian Detection in Unmanned Aerial Vehicle Scene
Guo, Q., Li, Y., & Wang, D. (2019) · Studies in computational intelligence · doi:10.1007/978-3-030-04946-1_26 · Cited by 1
The Warning System for Speed Cameras on the Road by Deep Learning
Wu, C.-C., Lin, Y. C., Hu, D.-X., et al. (2019) · Advances in intelligent systems and computing · doi:10.1007/978-3-030-15035-8_74 · Cited by 1
A New Dataset for Vehicle Logo Detection
Yang, S., Bo, C., Zhang, J., Wang, M., & Chen, L. (2019) · Studies in computational intelligence · doi:10.1007/978-3-030-04946-1_17 · Cited by 3
Robust graticule intersection localization for rotated topographic maps
Dong, L., Qin, Y., & Zheng, F. (2019) · Machine Vision and Applications · doi:10.1007/s00138-019-01025-9 · Cited by 1
Massive Colonoscopy Images Oriented Polyp Detection
Chen, M., Du, P., & Zhang, D. (2018) · International Conference on Biomedical and Bioinformatics Engineering (ICBBE) · doi:10.1145/3301879.3301903 · Cited by 1
Hardware Oriented Vision System of Logistics Robotics
Liang, F., & Zhang, C. (2018) · IEEE International Conference on Anti-counterfeiting, Security, and Identification (ASID) · doi:10.1109/icasid.2018.8693116 · Cited by 1
Survey of Pedestrian Action Recognition in Unmanned-Driving
Chen, L., Ma, N., Wang, P., Pang, G., & Shi, X. (2019) · Communications in computer and information science · doi:10.1007/978-981-13-7983-3_44 · Cited by 1
Real-time Obstacle Detection on Embedded System
Hung, S.-H., Chen, K.-W., Chen, C., et al. (2018) · IEEE Visual Communications and Image Processing (VCIP) · doi:10.1109/vcip.2018.8698625 · Cited by 1
A Part-Based Gaussian Reweighted Approach for Occluded Vehicle Detection
Huang, Y., Zhou, Z., Wang, T., et al. (2019) · IEICE Transactions on Information and Systems · doi:10.1587/transinf.2018edl8257 · Cited by 1
Localized Object Information from Detected Objects Based on Deep Learning in Video Scene
Lee, A. W. C., & Yong, S.-P. (2018) · IEEE Conference on Systems, Process and Control · doi:10.1109/spc.2018.8704126 · Cited by 1
Study of 3D Target Replacement in AR Based On Target Tracking
Bai, J., Nie, G.-Y., Song, W., Liu, Y., & Wang, Y. (2019) · Asia Pacific Workshop on Mixed and Augmented Reality (APMAR) · doi:10.1109/apmar.2019.8709287 · Cited by 1
A few-shot learning framework for air vehicle detection by similarity embedding
Chen, J., Liu, Y., Liu, Y., Wang, S., & Chen, S. (2019) · International Conference on Graphics and Image Processing (ICGIP) · doi:10.1117/12.2524389 · Cited by 1
Learning an Object Detector Using Zoomed Object Regions
Cho, S.-J., Kim, S., Uhm, K.-H., et al. (2019) · International Conference on Electronics, Information, and Communication (ICEIC) · doi:10.23919/elinfocom.2019.8706381 · Cited by 1
Aurora Image Search With Saliency Deep Features
Yang, X., Wang, N., Song, B., & Gao, X. (2019) · IEEE Access · doi:10.1109/access.2019.2917723 · Cited by 1
Forget and Diversify: Regularized Refinement for Weakly Supervised Object Detection
Son, J., Kim, D., Lee, S., Kwak, S., Cho, M., & Han, B. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-20870-7_39 · Cited by 4
A Detection Aided Multi-Filter Target Tracking Algorithm
Min, Y., Wei, Z., & Tan, K. (2019) · IEEE Access · doi:10.1109/access.2019.2919785 · 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.