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 34,901–35,000 of 51,399
Feasibility of a Wearable 360° Camera for Personalized Proximity Warning on Construction Sites
Yoo, J., 황성주Hwang, S., Seo, J., & Choi, B. (2026) · Journal of Construction Engineering and Management · doi:10.1061/jcemd4.coeng-17958 · Cited by 1
Zhai, Z., Li, Y., Xu, C., & Su, S. (2026) · Digital Signal Processing · doi:10.1016/j.dsp.2026.106180 · Cited by 1
Chai, B., Wang, J., Zheng, Z., Chen, L., Gong, X., & Liu, W. (2026) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2026.3684509 · Cited by 2
Palmieri, J., Lippi, M., & Marino, A. (2026) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2026.105480 · Cited by 4
SheepTrack: Occlusion-Robust Detection and Tracking for Dense Sheep Monitoring
Feng, X., Li, J., Yi, J., & Wang, Z. (2026) · Electronics · doi:10.3390/electronics15081679 · Cited by 1
Mulford, K. L., Khela, M. S., Wang, E., Dean, M. C., Trousdale, R. T., Pagnano, M. W., Taunton, M. J., & Wyles, C. C. (2026) · The Journal of Arthroplasty · doi:10.1016/j.arth.2026.04.036 · Cited by 2
Chou, J., Phakdee, B., Lin, Z.-T., Yu, C.-P., Wu, P.-H., & Shih, C. (2026) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2026.111679 · Cited by 4
E 2 -Former: An Edge-Enhanced Transformer for UAV-Based Small Object Detection
Zhang, J., Zhang, Y., Easa, S. M., 谢伯祥, Lin, L., Zhou, X., Zeng, N., Zhang, W., & Song, M. (2026) · IEEE Internet of Things Journal · doi:10.1109/jiot.2026.3684962 · Cited by 7
“To improve detection e ffi ciency, single-stage detectors like YOLO [31] perform target classification and localization directly on feature maps, significantly increasing detection speed.”
A deformable convolution and shuffle attention enhanced network for surface defect detection
Tang, Y., Lv, X., & Sun, T. (2026) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2026.114864 · Cited by 1
Detecting Rocks on Rail Tracks: an On-board Computer Vision Based Approach
Carletti, V., Foggia, P., Ranieri, S., Saggese, A., Spingola, C., & Vento, M. (2026) · SN Computer Science · doi:10.1007/s42979-026-04974-x · Cited by 1
Zare, O., Beigzadeh, M., Bzuayene, A. A., Arslan, E., Haghvirdizadeh, H., Rad, S. Y. B., Abbasi, A., Joloudari, J. H., & Gaftandzhieva, S. N. (2026) · Scientific Reports · doi:10.1038/s41598-026-35390-z · Cited by 6
“The introduction of the You Only Look Once (YOLO) series of object detection algorithms has significantly reduced these constraints by combining high detection accuracy with the capability for real-time processing 4,5 .”
IoT and ML for identification and behavioural analysis in shrimp aquaculture
Paul, L., Yadav, V. K., Bhowmik, T., et al. (2026) · Discover Sustainability · doi:10.1007/s43621-026-03086-z · Cited by 1
“The training process involves 50 epochs, with performance measures tracked via box loss, objectness loss, classification loss, and mean average precision (mAP) [49, 30].”
InfluentialEun, S., Jee, S. H., & Kim, Y. (2026) · Journal of Medical and Biological Engineering · doi:10.1007/s40846-026-01029-7 · Cited by 2
“YOLO (You Only Look Once) is a detector that divides an input image into a grid and directly predicts bounding box coordinates and class probabilities in a single pass, enabling real-time inference performance [23].”
Winter Classification of Mandibular Impacted Third Molars Based On Convolutional Neural Networks
Güller, M. T., Kumbasar, N., Miloğlu, Ö., et al. (2026) · Current Research in Dental Sciences · doi:10.17567/currresdentsci.1488041 · Cited by 1
Tang, Z., Wang, H., & Chamchong, R. (2026) · Scientific Reports · doi:10.1038/s41598-026-49498-9 · Cited by 1
“One-stage detectors, represented by You Only Look Once (YOLO) 7 , Single Shot MultiBox Detector (SSD) 8 , RetinaNet 9 , Real-Time Detection Transformer (RT-DETR) 10 and Fully Convolutional One-Stage Object Detection (FCOS) 11 , execute localization and classification simultaneously, delivering…”
Kechen, 南. N., Gang, 李. L., Yueting, 赵. Z., & Shanmeng, 赵. Z. (2026) · Laser & Optoelectronics Progress · doi:10.3788/lop252186 · Cited by 1
Tang, D., Tang, S., & Zheng, D. (2026) · PLoS ONE · doi:10.1371/journal.pone.0340499 · Cited by 1
“Notable examples include SSD [9], RetinaNet [10], and the YOLO series [11–13].”
Wang, Y., Zhuang, X., Wang, Y.-X., et al. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11465107 · Cited by 1
Yao, Z., Nian, Y., Lian, J., Ding, F., & Niu, L. (2026) · Scientific Reports · doi:10.1038/s41598-026-48903-7 · Cited by 1
Hamzaoui, M., Aoueileyine, M. O.-E., Filali, I., & Bouallegue, R. (2026) · IET Image Processing · doi:10.1049/ipr2.70373 · Cited by 1
DSSM: Dynamic Streaming Pipeline With Spatiotemporal Model Toward Remote Sensing Object Detection
Jing, S., Zhao, Y., Li, Z., Li, X., Xu, X., Wang, H., Lv, H., Sun, M., Zhang, Y., & Feng, Y. (2026) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2026.3686603 · Cited by 1
Bordet, T., Redondin, M., Bornhofen, S., Denaës, S., & Histace, A. (2026) · Applied Sciences · doi:10.3390/app16094091 · Cited by 1
Shi, P., Wu, H., Gu, Y., & Xin, Y. (2026) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2026.3686416 · Cited by 1
Stereo-Based 3-D Anomaly Object Detection for Autonomous Driving: A New Dataset and Baseline
Mu, S., Gu, Z., Lyu, H., Gao, Y., & Xu, S. (2026) · IEEE Internet of Things Journal · doi:10.1109/jiot.2026.3686669 · Cited by 4
“…an upsampling head H dis ( · ) is used to predict the binocular disparity In detectors based on anchors, such as Retina-Net [63] and YOLO series [64], anchors are sampled into positive and negative samples based on the intersection over union (IoU) relationship between the anchor-level output…”
Real-Time Human Detection in Thermal Images: Challenges and Solutions with ThermoSense
Sharma, N., Verma, B., Saxena, M., Kumar, A., & Dhyani, R. (2026) · International Conference on Advancing Sustainable Solutions through Technologies (ICASST) · doi:10.1109/icasst68917.2026.11484462 · Cited by 1
Chen, X., Chen, W., Yang, X., & Yin, Z. (2026) · Engineering Research Express · doi:10.1088/2631-8695/ae64ae · Cited by 1
“CNN (convolutional neural network) -based object detection approaches [15] such as one-stage detectors [16–19] and two-stage detectors [20, 21] have been adopted for construction safety tasks.”
Shen, Z., Lv, Y., Yuan, R. B., et al. (2026) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2026.3687972 · Cited by 1
Shutkina, E. V., Тынченко, В. С., & Kurashkin, S. O. (2026) · International Russian Smart Industry Conference (SmartIndustryCon) · doi:10.1109/smartindustrycon68821.2026.11493050 · Cited by 1
“In 2015, Joseph Redmon and others introduced the YOLOv1 framework [14].”
Mengyu, D., Xiaorong, W., Qiu, L., Menghao, L., Chen, J., & Liang, H. (2026) · Precision Agriculture · doi:10.1007/s11119-026-10357-2 · Cited by 1
“In contrast, representative one-stage algorithms YOLO (Redmon et al., 2016) and SSD (Liu et al., 2016), directly obtain object categories and locations from input images.”
Hou, C., & Liu, P. (2026) · Fire · doi:10.3390/fire9050182 · Cited by 2
Multi-Type Ship Detection in Complex Marine Backgrounds Using an Enhanced YOLO-Based Network
Du, A., Xu, H., & Yao, W.-Q. (2026) · Italian National Conference on Sensors · doi:10.3390/s26092718 · Cited by 1
“Mainstream algorithms are generally categorized into two-stage detectors, exemplified by the R-CNN series [3], and single-stage detectors, including the SSD, RetinaNet, and YOLO series [4].”
Torres‐Galván, J. C., & Ramírez‐Elías, M. G. (2026) · Journal of Phytopathology · doi:10.1111/jph.70304 · Cited by 2
Ploysungvan, P., & Evans, W. K. (2025) · Artificial Intelligence and Cloud Computing Conference (AICCC) · doi:10.1145/3789982.3790010 · Cited by 1
“Each grid cell is responsible for predicting [16] the bounding box and the class of the object located within that grid.”
An Ai-Based Real-Time Multi-Linguistic Sign Language Interpreter for Deaf and Speech-Impaired
G, S. S., Deekshitha, M. M., Prajwal, H., et al. (2026) · doi:10.1109/comp-sif69752.2026.11481883 · Cited by 1
“YOLO, one of the convolutional frameworks, is proposed by Redmon et al. [6], which performs object detection as a single regression problem and can reach real-time performance of more than 45fps with the help of the standard GPUs.”
Real-Time Crowd Monitoring System Using Sensors and Image Processing
Arul Sangeetha, S., Logeshwaran, P. P., Sudarshan, R., Vardhan, H., & Karthik Raja, C. (2026) · Journal of Ubiquitous Computing and Communication Technologies · doi:10.36548/jucct.2026.2.005 · Cited by 1
Few-Shot Pattern Detection via Template Matching and Regression
Jo, E., Kang, D., Kim, S., Choi, Y., & Cho, M. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.02004 · Cited by 5
“Both aim to reduce the annotation cost of object detection [12, 33, 57, 64] by learning to detect all instances of given support exemplars.”
SPD: Shallow Backdoor Protecting Deep Backdoor Against Backdoor Detection
Yuan, S., Li, X., Cao, X., Zhang, H. L., Zhu, M., & DENG, R. H. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.00384 · Cited by 1
“Although deep neural networks (DNNs) have been widely applied in various fields, such as computer vision [18, 21, 36], language processing [8, 40] and autonomous driving [1, 31, 56], they still suffer from serious security threats, such as * Corresponding author backdoor attacks [15].”
Yang, W., Liu, G., & Ming, D. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.00423 · Cited by 3
“…learning, particularly the remarkable achievements of convolutional neural networks (CNNs) in image classification [20, 22, 41], object detection [38, 39], and other tasks [32, 47], the security and robustness of deep neural networks (DNNs) have become an increasingly prominent focus of research.”
MotionCtrl: A Real-Time Controllable Vision-Language-Motion Model
Cao, B., Zheng, S., Wang, Y., Xia, L., Wei, Q., Jin, Q., Liu, J., & Lu, Z. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01139 · Cited by 7
“Instead, we adopt HuMo263 as our motion feature in this paper (see Appendix 1), which preserves the original rotation information and directly parameterizes the human pose.”
Automated Model Evaluation for Object Detection Via Prediction Consistency and Reliability
Yoo, S., Kwon, H., Hwang, J., & Lee, K. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01838 · Cited by 4
“Object detectors are typically categorized into 1) two-stage methods, such as R-CNN variants [12, 13, 39], which generate and refine region proposals, and 2) one-stage methods, such as YOLO [37] and RetinaNet [31], which perform detection in a single pass.”
Wang, Y., Cao, T., Zhang, H., He, Z., Liang, K., & Ma, Z. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01583 · Cited by 5
“To further guarantee the image quality, we apply detectors[33, 38, 46] to filter out undesirable images while maintaining as much valuable information as possible.”
Q-Norm: Robust Representation Learning via Quality-Adaptive Normalization
Zhang, L., Zhou, Y., Gao, F., Li, Z., Qiao, M., Xu, J., & Wang, N. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01290 · Cited by 1
“Deep learning has achieved remarkable success in image classification [19, 40], object detection [12, 28, 37, 52, 55, 69], and segmentation [27, 29, 35].”
Jurczak, M., Charzewski, Ł., Goźlińska, B., Albrycht, P., Kobus, K., Ludwin, A., Jabiry‐Zieniewicz, Z., Kominek, S., Basinski, G., Korzeb, B., et al. (2026) · Cancers · doi:10.3390/cancers18091485 · Cited by 1
Are All Marine Species Created Equal? Performance Disparities in Underwater Object Detection
Wille, M., Fischer, T., & Raine, S. (2026) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61042.2026.00443 · Cited by 5
“Popular approaches build upon Fast-and Faster-RCNN [11, 27] and YOLO [26].”
ART: Actor-Related Tubelet for Detecting Complex-shaped Action Tubes
Zhao, J.-J. (2026) · IEEE Workshop/Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61042.2026.00038
A Method for Road Damage Detection Using Heterogeneous Data Based on Hybrid Kernel Attention
Cheng, J., Cai, B., Lu, C., Wang, M., & Wang, R. (2026) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2026.3689971 · Cited by 1
Eyiokur, F. İ., Yaman, D., Ekenel, H. K., & Waibel, A. H. (2026) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61042.2026.00384 · Cited by 4
“75 , Grounding DINO with a more complex backbone achieves the best performance.”
Roadside Monocular 3D Detection Prompted by 2D Detection
Ma, Y., Hua, W., Li, Y., & Kong, S. (2026) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61042.2026.00189 · Cited by 3
LIRS-YOLO: A Lightweight YOLO-Based Method for Infrared Features and Small Object Detection
Guan, J., Yao, X., Zhao, Q., Wang, X., & Zheng, Y. (2026) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2026.3690625 · Cited by 2
ORCA: Object Recognition and Comprehension for Archiving Marine Species
Wong, Y. K., Liang, H., Ma, Z., Chen, Y. H., Zheng, Z., Gotama, R., Sebastian, P., Sparks, L., & Yeung, S.-K. (2026) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61042.2026.00161 · Cited by 1
“Conventional one-stage [15, 42, 54] and two-stage [17, 55, 56] detectors rely on fixed predefined category sets, which limit their applicability in marine domains, where species diversity varies greatly across regions.”
CSIS Ecosystem: Impacts of Pragmatic Detection on a Campus Surveillance Case Study
Mane, B., Neto, F. H. D. A. M., Figueiredo, R. D. C., et al. (2026) · doi:10.5753/sbsi.2026.248739 · Cited by 1
“Originally introduced by [Redmon et al. 2016], YOLO formulates object detection as a single regression problem, enabling fast and accurate inference in a single forward pass.”
Deng, Z., Case, A., & Sentis, L. (2026) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61042.2026.00326 · Cited by 2
“We employ YOLO [18] to initialize the target with a bounding box in the first frame and subsequently track it across frames.”
Tong, L., Jia, L., Han, H., Qin, Y., Li, Z., Zhang, H., & Wang, Z. (2026) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2026.3687092 · Cited by 1
“…detectors like CenterNet [39], CornerNet [40], and FCOS [41] rely on dense grid points to predict bounding boxes while the anchor-based single-stage detectors including YOLO family [42], [43], [44], [45], [46], SSD [47], RetinaNet [34] generate predictions with anchors defined on feature grids.”
AI Powered Traffic Violations Detection
Kumar, P. U., Srinivasulu, B., Teja, P. B., Dudhada, Y. S., Darren, N. J., & Kondaveeti, S. (2026) · International Conference on Machine Learning and Autonomous Systems (ICMLAS) · doi:10.1109/icmlas67792.2026.11483802 · Cited by 1
Liu, T., Cao, X., Zhou, X., Wang, J., Wan, J., & Dai, X. (2026) · International Journal of Computational Intelligence Systems · doi:10.1007/s44196-026-01350-8 · Cited by 1
“YOLO (You Only Look Once) [11 , 12] and SSD (Single Shot MultiBox Detector) [13] both use a single-stage detec - tor with FPN feature fusion structure.”
Hasan, T., Ilham, M. F., & Nasim, M. F. T. (2025) · International Conference on Computer and Information Technology (ICCIT) · doi:10.1109/iccit68739.2025.11490422 · Cited by 1
Hu, X., Hou, C., & Zhai, R. (2026) · Signal Processing Image Communication · doi:10.1016/j.image.2026.117578 · Cited by 2
Patch of Invisibility: Naturalistic Black-Box Adversarial Attacks on Object Detectors
Lapid, R., Mizrahi, E., & Sipper, M. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-25314-9_9 · Cited by 2
RFE-YOLO: A Lightweight Receptive Field-Enhanced Network for UAV Imagery Object Detection
Peng, Y., & Ge, X. (2026) · Sensors · doi:10.3390/s26092903 · Cited by 1
“In the realm of conventional remote sensing, mainstream methodologies are predominantly driven by convolutional neural networks (CNNs), which are categorized into two-stage detectors [11–13] and one-stage detectors [18,19].”
AI-Based Flood Early Warning and Risk Communication System
Albano, R., Asif, M., Ermini, R. G. A., et al. (2026) · doi:10.3390/engproc2026135010 · Cited by 1
“…installed in the Matera case study for monitoring rainfall, and the video feed is integrated with object detection algorithms (you look only once (YOLO by Redmon et al. [4])) for computation of flood depths and risk level for car drivers to warn them of increasing water depths during flood events.”
WGH-YOLO: an efficient solar cell defect detector based on YOLOv11n
Kan, L., Zhou, Y., Ma, Y., et al. (2026) · Measurement Science and Technology · doi:10.1088/1361-6501/ae69fd · Cited by 1
“The pivotal methodology in the field of object detection, Redmon et al [32] proposed the YOLO detection model.”
DASFA-Net for Accurate Ship Detection in Optical Remote Sensing Images
Li, H., Zhang, T., Jiang, S., Zhi, X., Wang, D., Gao, L., Yang, D., & Li, J. (2026) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2026.3691594 · Cited by 3
Chowdhury, F., Galib, S. M., Adnan, M. N., Siddique, M. M., Karim, M. R., & Anjum, K. M. T. (2026) · Annals of Emerging Technologies in Computing · doi:10.33166/aetic.2026.02.001 · Cited by 1
“Widely used DL techniques include Convolutional Neural Networks (CNN), Faster R-CNN, Inception Networks, YOLO, and ResNet [23].”
董大纲, & Fuzhen, 黄. H. (2026) · Acta Optica Sinica (Online) · doi:10.3788/aosol260468 · Cited by 1
Real Time Suspicious Activity Detection Using CNN and LSTM
Priya, K., A.Mutharasi, D.Anitha, & Krishnammal, N. (2026) · IEEE International Conference for Convergence in Computing Technology (I3CTCON) · doi:10.1109/i3ctcon68242.2026.11507417 · Cited by 1
Li, H., Zhang, R., Zhang, R., et al. (2026) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2026.3690314 · Cited by 1
Li, Z., Wang, D., Li, Q., Cao, Y., Jiang, X., & Li, P. (2026) · Measurement Science and Technology · doi:10.1088/1361-6501/ae6c42 · Cited by 1
“Since the release of the first version of YOLO, several improved versions have been introduced [11].”
AI - Powered Threat Detection and Emergency Alert Transmission for Smart CCTV Cameras
Narasimha, V. S., Harinath, V., Suresh, B., et al. (2026) · International Conference on Inventive Computation Technologies (ICICT) · doi:10.1109/icict68280.2026.11510994 · Cited by 1
“Real-time detection of a human face has been achieved using both CNN’s and Region -based detectors e.g. YOLO and SSD[2],[3],[4],[5].”
Autonomous seeking and mapping coral reef biodiversity hotspots with a multimodal AUV
McCammon, S., Cai, L., Yang, D., et al. (2026) · Science Robotics · doi:10.1126/scirobotics.adx9939 · Cited by 1
Han, J., Sun, F., Xu, Z., Song, L., & Fang, J. (2026) · Remote Sensing · doi:10.3390/rs18101547 · Cited by 2
Pietzsch, S., Dybeck, J. L., Roth, M., et al. (2026) · Journal on Image and Video Processing · doi:10.1186/s13640-026-00695-6 · Cited by 1
“The following methods were applied for image segmentation: the classical algorithms MOSES-Impacts [6] for surface damage and pyRES [8] for RCFs, as well as the learning-based models YOLO [11] and Detectron2 [16, 17].”
MD-YOLO: A Multi-Scale Adaptive and Dual-Attention Enhanced YOLOv11 for Small Object Detection
Zhou, W., & Gong, G. (2026) · Electronics · doi:10.3390/electronics15102099 · Cited by 1
Qi, Y., Zhang, Z., Hu, Y., Liu, P., Gao, M., & Zhai, G. (2026) · Applied Sciences · doi:10.3390/app16104820 · Cited by 2
Scale-bridging characterization and modeling of statistically inhomogeneous Moso bamboo
Speichinger, L., Förster, R., & Böhlke, T. (2026) · Construction and Building Materials · doi:10.1016/j.conbuildmat.2026.146522 · Cited by 1
DSC-YOLOv11: An efficient method for detecting industrial surface defects
Ma, C., Chen, J., & Pan, Y. (2026) · Measurement · doi:10.1016/j.measurement.2026.121910 · Cited by 1
Alsaidalani, B. A., & Yafooz, W. M. S. (2026) · International Conference on Smart Electronic Devices and Intelligent Systems (ICSEDIS) · doi:10.1109/icsedis68157.2026.11517991 · Cited by 1
Yang, Y., Ye, R., Yin, X., Tian, H., Feng, Z., Zhang, Y. S., Yang, J., Zhang, X., Dong, X., & Tajima, R. (2026) · Remote Sensing · doi:10.3390/rs18101620 · Cited by 1
Integrated Laser Imaging for Fusiform Fish Measurement in Aquaculture
Wang, S., Zhang, S., Shi, Y., et al. (2026) · Fishes · doi:10.3390/fishes11050298 · Cited by 1
“For instance, R. Cheng et al. [14] estimated the length of underwater fish using a binocular imaging system, while H. Liu et al. [15] combined a binocular imaging system with the YOLO [16] V5 network to estimate length and width.”
Xue, S., Li, N., Li, Z., Wang, D., Zhu, T., Jing, X., Guo, H., & Ni, C. (2026) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2026.111875 · Cited by 1
Sun, Y., Miao, X., Zhang, Y., et al. (2026) · Agriculture · doi:10.3390/agriculture16101110 · Cited by 1
“…single-stage detectors of the YOLO family formulate object localization and classification as an end-to-end regression task, achieving real-time inference while maintaining competitive accuracy, and have consequently emerged as the mainstream technical paradigm for fruit defect detection [11,12].”
Artificial intelligence applied to the automated detection and identification of Devonian miospores
Lokteva, V., Serobyan, V., Tetard, M., et al. (2026) · Journal of Micropalaeontology · doi:10.5194/jm-45-405-2026 · Cited by 1
Gjesteby, L., Carruthers, A., Werblin, J. S., et al. (2026) · Bioengineering · doi:10.3390/bioengineering13050556 · Cited by 1
Karwandyar, S., Pingel, T. J., & Nikulin, A. (2026) · Geomatics · doi:10.3390/geomatics6030054 · Cited by 1
“…similar approaches have been used in computer vision tasks, such as R-CNN, which requires a two-stage approach, the YOLO methodology is advantageous in its ability to use a unified single-pass approach to predict class probabilities and bounding boxes, reducing the computational cost and time [35].”
Dentalx: Context-Aware Dental Disease Detection With Radiographs
Tan, Z. Q., Zhu, X., Addison, O., & Li, Y. (2026) · IEEE International Symposium on Biomedical Imaging (ISBI) · doi:10.1109/isbi61048.2026.11515626 · Cited by 2
“The YOLO [6] model was employed to detect caries in bitewing radiographs [7] while Chen et al .”
Drone Support in Precision Agriculture to Fight Against Parasites
Digumarthi, S., Pooja, I., Lemont, G. A., et al. (2026) · doi:10.1109/missf68264.2026.11522061 · Cited by 1
Automated traffic signs condition monitoring using machine vision
Dwairi, M., Manasreh, D., Melhem, M., & Nazzal, M. D. (2026) · Innovative Infrastructure Solutions · doi:10.1007/s41062-026-02676-0 · Cited by 1
“…detection architec - tures introduced in the literature, the You Only Look Once (YOLO) family has consistently demonstrated strong performance across standard evaluation metrics including pre - cision, recall, and mean Average Precision (mAP) while maintaining real-time inference capability [ 8].”
Li, D., He, C., Tu, P., Yang, S., Lv, X., & Liu, J. F. (2026) · Sensors · doi:10.3390/s26103234 · Cited by 3
“Low contrast caused by light scattering, the dense distribution of small objects, and substantial scale variation make it difficult for conventional backbones to learn sufficiently discriminative features, often resulting in degraded detection performance [17,18].”
Al-Khazraji, A. M. H., Golmohammadi, S., & Ghavifekr, A. A. (2026) · Textiles · doi:10.3390/textiles6020063 · Cited by 1
“There are several state-of-the-art and cutting-edge object detection models developed in this field, the most popular of which are YOLO (You Only Look Once) [20], SSD (Single Shot MultiBox Detector) [21], and Efficient-Det [22].”
Rahim, U. F., Rahman, M. M., & Mineno, H. (2026) · Agriculture · doi:10.3390/agriculture16101130 · Cited by 1
Morphology-Adaptive YOLO for Underwater Crack Detection in Hydraulic Structures
Chen, Z., Zhou, C., Guo, J., & Yin, G. (2026) · Water · doi:10.3390/w18101241 · Cited by 2
Liu, Y., Wei, B., Zhang, Q., et al. (2026) · Measurement · doi:10.1016/j.measurement.2026.121940 · Cited by 1
Optimized Dual-template Matching Method for Mobile Device-based Vibration Measurement in Sea Trials
Eom, S.-M., Lee, B., Cho, J., et al. (2026) · Measurement · doi:10.1016/j.measurement.2026.122021 · Cited by 1
Hoffmann, S., Hoseini, M., Wingartz, M., et al. (2026) · International Journal of Forest Engineering · doi:10.1080/14942119.2026.2665577 · Cited by 1
Shi, M., Qiu, X., Li, A., et al. (2026) · Journal of Marine Science and Engineering · doi:10.3390/jmse14100945 · Cited by 1
“Detection-based methods, such as Faster R-CNN [12], SSD [13], and YOLO [14], are effective in target localization.”
Chen, F., Zhu, M., Zhou, Q., et al. (2026) · Lecture notes in electrical engineering · doi:10.1007/978-981-95-7936-5_28 · Cited by 1
3-D SLAM and Deep Learning for Real-Time Fire Localization in Ship Engine Rooms
KIM, S. (2026) · IEEE Access · doi:10.1109/access.2026.3696438 · Cited by 1
Gao, B., Yang, Y., Chen, X., Cai, X., & Nan, X. (2026) · Journal of Imaging · doi:10.3390/jimaging12060221 · Cited by 1
“Deep learning detection models can be divided into one-stage and two-stage models: One-stage models such as YOLO (You Only Look Once) [12–20] and SSD (Single Shot MultiBox Detector) [21] offer high inference speed and are suitable for real-time detection scenarios; two-stage models such as the…”
Ahmad, S., Liu, J., & Tian, L. (2026) · Crop Protection · doi:10.1016/j.cropro.2026.107707 · Cited by 2
Enhanced YOLO26 for Thermographic Fault Detection in Underground Duct Cables
Chen, Z., Hu, K., Liu, J., et al. (2026) · Applied Sciences · doi:10.3390/app16115348 · Cited by 1
Sun, Y.-H., Shen, G., Fernandes, J., Chen, J., Shada, A. L., Heise, C. P., Jiang, H., & Hu, Y. H. (2026) · Updates in Surgery · doi:10.1007/s13304-026-02687-7 · Cited by 3
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.