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 47,901–48,000 of 51,398
Grzeskowiak, F. (2021) · theses.fr (ABES) · doi:10.70675/02068852ze36cz4e87z9f96z321c58d7d91c
Deep learning for computational phenotyping in cell-based assays
Boyd, J. (2020) · theses.fr (ABES) · doi:10.70675/140b4351zf0f1z4c9az9d06z54438ee98410 · Cited by 2
Weakly supervised learning for image classification and potentially moving obstacles analysis
Chiaroni, F. (2020) · theses.fr (ABES) · doi:10.70675/7280ff3cz9ff6z48b5z96a9zc27c3374f45e
Estimation de poses 3D multi-personnes à partir d'images RGB
Benzine, A. (2020) · theses.fr (ABES) · doi:10.70675/2b8b4e1bzb956z4f5cz8655zc7dbff1fdbf9
Robust detection of astronomical sources using convolutional neural networks
Paillassa, M. (2020) · theses.fr (ABES) · doi:10.70675/eadcd5fdz3c39z4c82z9901z314800455d3d · Cited by 1
Cendre, R. (2021) · theses.fr (ABES) · doi:10.70675/92fd40b8z03c6z4261z88dez1d4b85e069a4 · Cited by 1
Handling the speed-accuracy trade-off in deep-learning based pedestrian detection systems
Ujjwal, U. (2019) · theses.fr (ABES) · doi:10.70675/04f27b78ze0c6z442azb7b1zcac3bbaeb4db · Cited by 1
Convolutional Neural Networks for embedded vision
Brillet, L. F. (2020) · theses.fr (ABES) · doi:10.70675/2d60ad43z0e59z4417za440z5c7d5dd5493d
Multi-agent reinforcement learning and object detection asstructured prediction
Carion, N. (2020) · theses.fr (ABES) · doi:10.70675/dd567c2az5c46z45f1z906fzc680ab8febb9 · Cited by 3
Indoor Scene Understanding using Non-Conventional Cameras
Labrador, C. F. (2020) · theses.fr (ABES) · doi:10.70675/7af47b94z536cz49cdza539zc99752cca57b · Cited by 2
Real-Time Object Counting on Industrial Conveyor Belts Using YOLOv11 and Zone-Based Algorithm
Tam, T. N., & Ky, T. V. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-21625-0_24
Estimation de la pose 3D d’objets dans un environment industriel
Pitteri, G. (2020) · theses.fr (ABES) · doi:10.70675/158365c2z46e2z4d5fza900z71cfb7bef6d0 · Cited by 1
Deep similarity metric learning for multiple object tracking
Cuan, B. (2019) · theses.fr (ABES) · doi:10.70675/74da1028z94e4z4881za75czd22893bac75e
Hoang, K. (2021) · theses.fr (ABES) · doi:10.70675/e36ffbb4zbf05z4358za463zc57f0652a48e · Cited by 1
Representation Transfer via Invariant Input-driven Continuous Attractors for Fast Domain Adaptation
Xu, T. J., Wu, S., Luo, J., Lin, F., Jiang, J., Chen, G., Yang, Y., Ye, J., & Yang, D. (2026) · Communications Biology · doi:10.1038/s42003-026-09938-8
“For RGB video preprocessing, we fi rst employ YOLOv8 71 to detect the subject and extract a 500 × 500 region centered on the detected bounding box from the original 1920 × 1080 video.”
Positionnement visuel dans un monde d'objets
Gaudillière, V. (2020) · theses.fr (ABES) · doi:10.70675/ade672b6z76f9z4a73za0f2za41d2e63fdb3
Instantiation of a textual description schema of video surveillance scenes
Youssef, W. F. (2019) · theses.fr (ABES) · doi:10.70675/701db432zbd9bz44c9zaa1fz8d9a9e50cea1
Apprentissage profond et traitement d'images pour la détection de fumée
Kaabi, R. (2020) · theses.fr (ABES) · doi:10.70675/cf3ca16bzda10z4877zafd9z9359dec9a9c4
Action-aware anchor-based frame selection strategy for action recognition
Xu, Z., Feng, Y., Zhou, F., Lin, G., & Su, Z. (2026) · Image and Vision Computing · doi:10.1016/j.imavis.2026.105976
YOLOv8-Based Real-Time Fiducial Mark Defect Detection in High-Speed SMT Under Data Imbalance
Kim, D., Ueno, G., Lee, H., et al. (2026) · Journal of Digital Contents Society · doi:10.9728/dcs.2026.27.3.803
Niu, R., Wei, Z., Jin, P., Zhang, Q., & Li, Z. (2026) · Sensors · doi:10.3390/s26072220
Comparative Analysis on Machine Learning for DoS Detection in Network-on-Chip
Wang, H., Ren, J., Hu, S., et al. (2025) · Springer eBooks · doi:10.1007/978-3-032-08514-6_6
YOLO-RBSD: an efficient and accurate rice blast spore detector based on improved YOLOv8
Li, C., Huang, D., & Zhou, H. (2026) · Plant Methods · doi:10.1186/s13007-026-01526-5
“…fall into two categories [9]: two-stage algorithms like Faster R-CNN [10] and Cas-cade R-CNN [11], which extract candidate regions before classification and regression, and one-stage algorithms like SSD [12], RetinaNet [13], and YOLO [14], which directly output class and location information.”
Shelf Analysis Using YOLO for Optimized Product Placement and Inventory Management
Gupta, P., Suman, A., Bisen, D., & Saurabh, P. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-19300-1_1
Nguyen, M. T. P., Ngoc, T. B. B., Tran, M., et al. (2026) · Lecture notes on data engineering and communications technologies · doi:10.1007/978-3-032-13102-7_3
Suh, Y.-J., & Jang, H. (2026) · Journal of Digital Contents Society · doi:10.9728/dcs.2026.27.3.813
Traffic Sign Detection for Autonomous Driving at 1:10 Scale a YOLO Approach
Carlos, L. A. M., Femat, E. P. S., Garcia, H. L., et al. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-19019-2_11
Muzata, R., Nkundineza, C., & Kimotho, J. K. (2026) · Engineering Technology & Applied Science Research · doi:10.48084/etasr.17251 · Cited by 1
“By treating object detection as a single regression problem, the initial YOLO model transformed the field and paved the way for major advancements in subsequent iterations [1, 8].”
Towards Trustworthy Defense AI: Real-Time Military Asset Detection with On-Demand Explainable YOLOv8
Al-Omari, O. M., Alyousef, A., Fati, S. M., Othman, E. M. A., & Naeem, M. R. (2026) · Engineering Technology & Applied Science Research · doi:10.48084/etasr.17259
“In particular, the YOLO series has proven high accuracy in object detection with the additional benefit of real-time processing, which is critical in defense surveillance and UAV-based reconnaissance operations [4].”
High-Precision Tomato Segmentation Using Lightweight Convolutional Architectures
Ngoc, T. T. T., Do, T. T., Bui, D. K., & Nguyen, V. T. (2026) · Lecture notes on data engineering and communications technologies · doi:10.1007/978-3-032-13102-7_8
Proactive Motorcycle Safety: Development of an Edge-Based Blind Spot Warning System
Fernandes, T., da Silva, J. A. C., Pinto, B., Silva, T., Pendão, C., & Filipe, V. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-05748-8_25
Research on Rice Pest Detection and Classification Based on YOLOv5 and Transformer Combination
Yang, Q., Chen, Y., Hai, Q., Razzaq, S., Cui, Y., Wang, X., & Zhou, B. (2026) · AgriEngineering · doi:10.3390/agriengineering8040138
SmarTTrack: A Mobile Crowdsensing System for Vehicle Multi-tracking in Smart Cities
Neto, C. M. F. D. N., Nunes, T. G. M., Coutinho, L. R., et al. (2026) · Information systems engineering and management · doi:10.1007/978-3-032-19196-0_1
Approximate computing for embedded machine learning
Yang, X. (2021) · theses.fr (ABES) · doi:10.70675/4dba639az3f2ez40c6z8b3cz87ec988baa75
Reconnaissance d'espèces de poissons dans des images vidéo sous marines
Tamou, A. B. (2021) · theses.fr (ABES) · doi:10.70675/fd0f9332zf0bcz48e9z8919zc894aa835586
Road Traffic Models for Validation of Autonomous Vehicle Functionalities
Zhao, L. (2021) · theses.fr (ABES) · doi:10.70675/5eadb44az85bfz4e55zb9e1z952f93bb39fc
Real-Time LED Defect Detection Using YOLOv7-12 for Smart Manufacturing
Kongkaew, W., Sirasakamol, O., Yachiangkam, S., et al. (2026) · Joint International Conference on Digital Arts, Media and Technology with ECTI Northern Section Conference on Electrical, Electronics, Computer and Telecommunication Engineering (ECTI DAMT & NCON) · doi:10.1109/ectidamtncon67592.2026.11460030
“The YOLO family have been widely adopted for real-time defect detection due to their high accuracy and computational efficiency [4], [7].”
Gonthier, N. (2021) · theses.fr (ABES) · doi:10.70675/9abc66b4zca61z423bz85dcz07b849b15209 · Cited by 1
Chan, Y., Ciou, Z.-Y., Chen, Y., et al. (2026) · Journal of Food Engineering · doi:10.1016/j.jfoodeng.2026.113112
GeoMarX: empowering geospatial marking and annotation for complex targets in urban environments
Cao, R., Pan, J., Liao, C., Zhang, W., & Zhuang, Y. (2026) · Urban Informatics · doi:10.1007/s44212-026-00102-5
Deep Multimodal Learning for Joint Textual and Visual Reasoning
Bordes, P. (2020) · theses.fr (ABES) · doi:10.70675/8bd1beefz5760z4f96z8d8cz87e025608c32
Object viewpoint estimation in the wild
Xiao, Y. (2021) · theses.fr (ABES) · doi:10.70675/a1b6f6ffz2eb3z4d6ezb629z5647792bde63
Embedded Machine Vision: Machine Learning and Performance Metrics
Holosha, A. O., Kovbasa, S., & Lyshevski, S. E. (2026) · IEEE International Conference on Advanced Trends in Radioelectronics, Telecommunications and Computer Engineering (TCSET) · doi:10.1109/tcset65181.2026.11461102
“Deep learning models are trained to optimize objective functions [7-12].”
Mimouna, A. (2021) · theses.fr (ABES) · doi:10.70675/b4a6b801zab88z421cz82a3z481c405a8d90 · Cited by 5
Chantawong, S., Sirasakamol, O., Wongjan, A., et al. (2026) · Joint International Conference on Digital Arts, Media and Technology with ECTI Northern Section Conference on Electrical, Electronics, Computer and Telecommunication Engineering (ECTI DAMT & NCON) · doi:10.1109/ectidamtncon67592.2026.11459985
“Development of YOLOv8 for Real-Time Object Detection The YOLO family has transformed real-time object detection through its single-pass architecture, offering a strong balance between accuracy and speed [11].”
Guo, Z., Wang, Y., Sun, W., Ruan, J., Han, Y., & Chen, S. (2026) · IEEE Transactions on Very Large Scale Integration (VLSI) Systems · doi:10.1109/tvlsi.2026.3678459
“Unlike image-level annotation tasks such as image classification [6] and object detection [7], stereo matching is a pixel-level annotation task in which neural networks process input images to produce output images [5], requiring metic-ulous handling of each pixel for accuracy.”
Inversion of geophysical data by deep learning
Chapellín, J. C. (2022) · theses.fr (ABES) · doi:10.70675/d4571399zd878z4f64za595z5d8a5902dbed · Cited by 4
A Cooperative Hand Gesture Recognition System for Human Machine Interface to Control Robotic Arms
DeHaven, A. L., & Park, J. (2026) · SAE technical papers on CD-ROM/SAE technical paper series · doi:10.4271/2026-01-0252
Learning off-road maneuver plans for autonomous vehicles
Osanlou, K. (2021) · theses.fr (ABES) · doi:10.70675/41637fdaz54c1z41fcz90c1z447f575444b9
JONUZI, V. M., & Mishkovski, I. (2026) · Informatics · doi:10.3390/informatics13040057 · Cited by 1
Teaching Predicate-based Autotelic Agents
Akakzia, A. (2022) · theses.fr (ABES) · doi:10.70675/9b85df43z32c4z4101z8095z2f0bec7cdd3e
Reduced CNN Model for Rotation-Invariant Classification
Salas, R. R. (2021) · theses.fr (ABES) · doi:10.70675/3a3858bdz5dc9z4523z9a89zd9c4d7238260 · Cited by 1
Lie symmetries in cortical inspired CNNs
Bertoni, F. (2022) · theses.fr (ABES) · doi:10.70675/e556cd86z2e04z4433zb355zdecd17e31675
The challenge of robust trait estimates with Deep Learning on high resolution RGB images
David, É. (2021) · theses.fr (ABES) · doi:10.70675/b630e4a6ze3bfz4a08z8a34z149a4825e7b8 · Cited by 4
Suivi multi-objets basé sur des tracklets dans un réseau de caméras
Dorai, Y. (2021) · theses.fr (ABES) · doi:10.70675/dc13ed92z675az4e45zbb53zd02b4117bef8
Apprentissage par transfert pour réseaux adversaires génératifs
Gouray, J.-B. (2021) · theses.fr (ABES) · doi:10.70675/09ec8c85z3cd1z4001za618ze4e53f0d0846
Assessment of Edge Machine-Learning Systems under Radiation-Induced Effects
Trindade, M. G. (2021) · theses.fr (ABES) · doi:10.70675/f5059808z4029z40afz983ez963fb3b627bd
Dey, A. (2022) · theses.fr (ABES) · doi:10.70675/bbc1d3b6z9f35z4e71za7b8za73d0939f820 · Cited by 4
Deep Neural Network Compression for Visual Recognition
Dupont, R. (2023) · theses.fr (ABES) · doi:10.70675/42b047f5ze4c0z4685zb43az56bb33196d6b
Apprentissage profond auto-supervisé par simulation pour la saisie robotique adaptative
Depierre, A. (2021) · theses.fr (ABES) · doi:10.70675/879b6cb1z4eaaz480bzafd2zad300dec31ef
On the role of Actions and Machine Learning in Artificial Agent Perception.
Caselles-Dupré, H. (2021) · theses.fr (ABES) · doi:10.70675/6cfe7f36z5adcz4a30za086z8f2bdc924098 · Cited by 1
Analysis of space and atmospheric radiation-induced effects on memory devices
Luza, L. M. (2021) · theses.fr (ABES) · doi:10.70675/42193828zb755z44c0z9202z65867b3cef7d · Cited by 1
Delorme, G. (2021) · theses.fr (ABES) · doi:10.70675/a34a9807z8263z4e5az9f6azf1d31953b95d
Deep Learning End-to-end Person Search and Multiple Pedestrian Tracking
Hu, R. (2021) · theses.fr (ABES) · doi:10.70675/f4487889z00f8z4f51zb57dzd5030ad0c984 · Cited by 1
Smart River : Towards Efficient Cooperative Autonomous Inland Navigation
Hammedi, W. (2022) · theses.fr (ABES) · doi:10.70675/5570927dz7575z4e59z8a9fz823b53b1cdf2 · Cited by 1
Détection automatique de pathologies du rachis lombaire en IRM par réseaux de neurones convolutifs
Guinebert, S. (2022) · theses.fr (ABES) · doi:10.70675/bc89d7c3z731ez43d5zb11bz518cb0d7e85e
Ma, S., Xu, M., Dao, M., & Li, H. (2026) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2026.111353 · Cited by 2
Realization of a diagnostic aid in orthodontics by deep learning
Doan, T. T. (2021) · theses.fr (ABES) · doi:10.70675/0dd414c4z04afz4f12zbe07z0e5c7fdebb94
How polarimetry may contribute to deep road scene analysis in adverse weather conditions
Blin, R. (2021) · theses.fr (ABES) · doi:10.70675/ee0bf17bzcef4z49d7za988z687cd723b2c3 · Cited by 1
2D and 3D Geometric Attributes Estimation in Images via deep learning
Qiu, X. (2021) · theses.fr (ABES) · doi:10.70675/8a226ac9zb095z400fzbc92zf6461be079a6
Deep Learning for Chairlift Scene Analysis : Boosting Generalization in Multi-Domain Context
Alqasir, H. (2020) · theses.fr (ABES) · doi:10.70675/0715d2b1zfeb5z4fc2z975dz05d447a31ed9
Object detection and traffic prediction using Deep Learning on compressed road images and videos
Deguerre, B. (2021) · theses.fr (ABES) · doi:10.70675/6677b6b5z754ez4988zaba1zcf509878c8db
End-to-End Ego-Vehicle Localization using Multi-sensor and a Low Cost Map
Kasmi, A. (2021) · theses.fr (ABES) · doi:10.70675/4a6d129cz6098z4041zba71z53d3ccb12eeb
YOLOv10s-STD:一种无人机视角下的高精度目标检测算法
Qi, 张. Z., Yongxian, 宋. S., Yan, 阎. Y., Miao, 杨. Y., & Quan, 陈. C. (2026) · Laser & Optoelectronics Progress · doi:10.3788/lop251904
Takyi, S., Özgüven, E. E., Horner, M. W., et al. (2026) · International Journal of Disaster Risk Science · doi:10.1007/s13753-026-00711-3
YOLOv8-Nano Driven Foot Stampede Prediction with Homography Mapping
Umamageswaran, J., Satya, C. G. S., & Reddy, C. K. (2026) · IEEE International Conference on Interdisciplinary Approaches in Technology and Management for Social Innovation (IATMSI) · doi:10.1109/iatmsi68868.2026.11465201
“Detection and tracking of individuals have been addressed using models such as Faster R-CNN, SSD, and YOLO [5].”
SAGE-YOLO: a strip-aware and global-state-space enhanced detector for tea bud detection
gao, X., Fu, X., Fu, Z., Hui, M., Wang, H., Liu, J., & Ning, K. (2026) · Measurement Science and Technology · doi:10.1088/1361-6501/ae5c2b
“Representative architectures, including YOLO [15], Faster Region-based Convolutional Neural Network (R-CNN) [16], and single shot multibox detector [17], have achieved notable success across a broad spectrum of agricultural vision tasks, such as fruit and vegetable detection, pest monitoring, and…”
Liu, L., Li, Z., Yang, Z., & Ma, J. (2026) · International Conference on Neural Networks, Information and Communication Engineering (NNICE) · doi:10.1109/nnice68970.2026.11465720
“Although advanced object detection models [1]– [5] have demonstrated excellent performance on high-quality standard datasets such as COCO, their training and evaluation processes heavily rely on labeled data collected in ideal laboratory environments.”
GenTouchVR: Generating a Touchable Virtual Reality Environment from a Single Image
Park, J., Nam, S., Kim, J., Ju, U., & Choi, S. (2026) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2026.3680620
“YOLO [36], DETR [7]) often failed to detect objects in real-world images that might have lay outside their training datasets.”
Segmentation of road scene omnidirectional images
Sekkat, A. R. (2022) · theses.fr (ABES) · doi:10.70675/6c5add14zaebez4287z800dzab48102c8f8b
Deep learning for automatic facial expression assessment with application to the expression of pain
Vu, M. T. (2022) · theses.fr (ABES) · doi:10.70675/b3a4930cz2ae5z4f53z9602ze781cb8f524a
Détection 3D pour la réalité mixte en maintenance industrielle
Roman, P. P. D. S. (2022) · theses.fr (ABES) · doi:10.70675/ca43c4cbz926fz42b0z94e8z2ac3cb283625
Computer vision for the analysis of intra-cellular RNA localization patterns
Imbert, A. (2022) · theses.fr (ABES) · doi:10.70675/bb85932czd594z4c4fzb785z51e20a62ad87
Transformer-Based Small Object Detection in Complex UAV Aerial Scenes
Wang, Y., Yuan, C., & Yang, Q. (2026) · International Conference on Neural Networks, Information and Communication Engineering (NNICE) · doi:10.1109/nnice68970.2026.11465721
“Conventional CNN-based detectors, including Faster R-CNN [1] and the YOLO series [7], [8], [10], [11], typically rely on multi-scale feature pyramid structures such as FPN [17], PANet [14], NAS-FPN [15], and BiFPN [16] to strengthen cross-scale representations and improve small-object detection…”
Sensor fusion with deep neural networks for 3D object detection for autonomous vehicles
Minh, N. A. (2023) · theses.fr (ABES) · doi:10.70675/7e54c100zeaddz4f34zbffczf99c15dae587
Multi-Sensor based Perception and State Estimation for Autonomous Vehicles
Chen, S. (2022) · theses.fr (ABES) · doi:10.70675/38ba0254z6431z409bzb02az81722d6eece3
Blons, M. (2023) · theses.fr (ABES) · doi:10.70675/1411766ezb88fz4369zb400ze4c095094765 · Cited by 1
Understanding and enforcing robustness in neural networks, modern perspectives and challenges
Piat, W. (2023) · theses.fr (ABES) · doi:10.70675/eeb5d27dz2706z4218z90daz7dc73d67a9af
Explainable link prediction in large complex graphs - application to drug repurposing
Islam, K. (2022) · theses.fr (ABES) · doi:10.70675/d26d8afbz8030z4275z9ac3z9024fbc1f4e0
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.