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 47,201–47,300 of 51,399
Case Study of Personal Protective Equipment in Chemical Industries
Thakare, O. S., & Niwas, R. (2026) · Springer transactions in civil and environmental engineering · doi:10.1007/978-981-96-8683-4_23
Nimbalkar, Y. H., Muskan, Nimbalkar, Y., et al. (2025) · IEEE Pune Section International Conference (PuneCon) · doi:10.1109/punecon67554.2025.11379268
“These advancements make it possible to use Convolutional Neural Networks (CNN) and real-time object detectors (like YOLO (You Only Look Once)) to quickly and accurately recognize individuals in complex and crowded environments [5].”
YOLOv11-Driven Framework for Football Strategy Enhancement Using OpenCV
Soundarya, M., Mu, S., & Vasuppradha, S. (2025) · International Conference on Artificial Intelligence and Knowledge Discovery in Concurrent Engineering (ICECONF) · doi:10.1109/iceconf65644.2025.11379385
Robust Pothole Detection Using YOLOv5 and Optimized Datasets for Intelligent Transportation Systems
Ahlawat, C., Khurana, R., Tufchi, S., et al. (2026) · International Journal of Intelligent Transportation Systems Research · doi:10.1007/s13177-026-00630-z
Ma-Yolo: Video Object Detection Via Motion-Assisted Yolo
Wang, X., Chen, H.-S., Zhou, Z., Yao, J.-E., & Kuo, C. J. (2025) · IEEE International Conference on Image Processing Workshops (ICIPW) · doi:10.1109/icipw68931.2025.11386241
“Modern deep detectors, such as YOLO [4], deliver strong detection accuracy and relatively high per-frame inference speed, widely adopted in real-time applications and edge deployments.”
Samaras, A.-D., Moustakidis, S., Apostolopoulos, I. D., Papageorgiou, E. I., Papathanasiou, N. D., Apostolopoulos, D. J., & Papandrianos, N. I. (2026) · Journal of Intelligent Systems · doi:10.1515/jisys-2025-0064 · Cited by 4
“More speci fi cally, the study achieves peak accuracy by adopting contemporary ML/DL models such as ResNet [24], MobileNet [25], and YOLOv8 [26], underscoring its commitment to cutting-edge methodologies.”
STAR: Spatial and Temporal Context-Aware Network for Resident Space Object Detection
Gan, B., Liang, W., & Niu, Z. (2026) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2026.3665808
EFD-YOLO: An Enhanced Face Detection Model with Deformable Convolution and 3D Feature Fusion
Zhang, X., He, X., Lu, X., & Cao, Y. (2025) · International Conference on Artificial Intelligence and Computer Engineering (ICAICE) · doi:10.1109/icaice68195.2025.11382421
“For instance, cascaded CNN architectures achieve high accuracy through coarse-to-fine detection refinement, while adaptations of general object detectors like YOLO [3] and Faster R-CNN [4] leverage well-established backbones to balance speed and precision.”
Cell Anaemia Detection using Vision Transformer
Mahalakshmi, S. B., S, K. K. G., Murali, V., & KamalrajSubramaniam (2025) · International Conference on Evolutionary Computing and Mobile Sustainable Networks (ICECMSN) · doi:10.1109/icecmsn68058.2025.11382991
“Public health research highlights the importance of scalable diagnostic tools [17][18], supported by open access datasets [19][20], and successful execution of pre-trained models [21][22].”
PV Plant Installed Capacity Verification Based on High-Resolution UAV Imagery and YOLO11OBB
Li, S., Yang, Y., Qu, X., Xiong, Z. Q., Lai, J., Liu, M., & Yi, L. (2025) · International Conference on Power System and Energy Internet (PoSEI) · doi:10.1109/posei67825.2025.11382430
“Horizontal target detection, a recent research hotspot, uses models like You Only Look Once(YOLO) [7], [8] and Faster R-CNN [9] to detect modules in UAV images [10]– [12], yet PV modules are mostly arranged along slopes or rooftop inclines, resulting in low matching between horizontal bounding…”
PLM-Net: Physics and Large-Model Guided Network for Single Image Dehazing
Yin, Z., Lu, T., Lu, T., et al. (2025) · International Conference on Robot Systems and Applications (ICRSA) · doi:10.1109/icrsa66467.2025.11383797
“This not only impairs human vision but also hinders computer vision tasks such as segmentation [1], [2], detection [3], [4], and person re-identification [5], [6], which rely on clean visual input.”
Lightweight Dangerous Goods Detection Algorithm in X-ray Image Based on Improved YOLOv11
Peng, J., Yu, Z. F., Wang, B., & Sun, Y. (2025) · International Conference on Artificial Intelligence and Computer Engineering (ICAICE) · doi:10.1109/icaice68195.2025.11382480
“One-stage detectors (e.g., SSD [2] , YOLO [3] ) combine localization and classification in a single pass, offering faster inference and better suitability for real-time deployment.”
WS-DETR: A Wavelet-mamba and shared query attention enhanced DETR for traffic object detection
Xu, L., Liu, S., Chen, Z., & Wang, S. (2026) · Signal Image and Video Processing · doi:10.1007/s11760-026-05184-x
AI-Based Visual Inspection System for Oxygen Indicator Detection in Food Packaging
Aharari, A., & Oghushi, K. (2025) · IEEE Region 10 Conference (TENCON) · doi:10.1109/tencon66050.2025.11375084
“…as a single regression problem, enabling real-time detection with a single forward pass of a CNN. Unlike traditional detectors that used region proposals followed by classification (e.g., R-CNN), YOLO [9] processed the entire image at once, providing a major improvement in inference speed.”
Automating Industrial Quality Assurance: A Zero-Shot MLLM Framework for Defect Detection and 3R
Liu, S., Koch, D., Kaiser, J.-P., & Stamer, F. (2026) · Procedia CIRP · doi:10.1016/j.procir.2025.09.037 · Cited by 2
Research on Multi-Granularity Guided Small Object Detection on Water Surfaces
Wei, R., Wang, G., & Liu, Q. (2025) · International Conference on Computer, Big Data and Artificial Intelligence (ICCBD+AI) · doi:10.1109/iccbdai66607.2025.11388388
“Mainstream detectors like Faster R-CNN [5], YOLO [6], and DETR [7] perform well on general datasets (e.g., COCO, VOC), but exhibit high miss-detection rates and poor localization on water-surface small objects.”
How Machines See and Generate Images
Picascia, S., & Ferrara, A. (2026) · Lecture notes in morphogenesis · doi:10.1007/978-3-032-08726-3_3
Dehazing Algorithm Selection System with Feature Extraction for Single Image
Toyoshima, Y., & Miyahara, K. (2025) · IEEE Region 10 Conference (TENCON) · doi:10.1109/tencon66050.2025.11375016
“The system output was entered into the object detection process, YOLO v5 [16], for the validation purpose.”
Computer Vision-Guided Humans and Animals Detection in Aquatic Disaster Zones
Maurya, R., Sajeena Muhamed, S., Behera, S. K., et al. (2025) · IEEE Region 10 Conference (TENCON) · doi:10.1109/tencon66050.2025.11374951
“By merging the outputs from these models, the system provides an accurate target in the form of a bounding box [6].”
Yang, S., Hu, Q., Lin, L., Ding, H., Zhang, Y., & Du, L. (2026) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2026.3656570
“Advanced algorithms, such as Faster R-CNN [21] and generic object detection methods [22], [23], [24], [25], [26], [27], [28], [29], [30], have demonstrated success in detecting visible surface defects (e.g., broken sheds) from aerial imagery.”
A Novel Benchmark for Domain Generalization in Zero-Target-Sample Capsule Detection
Chen, C., Li, Y., Zhang, Y., Ling, F., Li, C., Ye, J., & Fang, S. (2025) · International Conference on Computer, Big Data and Artificial Intelligence (ICCBD+AI) · doi:10.1109/iccbdai66607.2025.11389067
“They have shown superior performance in object detection, with models like YOLO providing real-time detection and enhanced accuracy for small objects, making them suitable for tracking reentry capsules[7][8][9][10].”
Wang, Q., Fu, D., Sai, Q., et al. (2026) · Machine Vision and Applications · doi:10.1007/s00138-026-01800-5
“Representative detection models include Faster R-CNN [ 26 ], SSD based on VGG16 [ 27 , 28 ], fully convolutional one-stage detectors like FCOS [ 29 , 30 ], and the YOLO series.”
Robotic arm visual-servoing for AI-driven chess gameplay using LLM-based plannner
Ilgun, A. E., Cadirci, O., Ozkan, B., Akgul, B., & Bayraktar, E. (2026) · Neural Computing and Applications · doi:10.1007/s00521-025-11700-w
“For both training and inference, we employ YOLOv8 [7], the state-of-the-art YOLO model as of April 2023 [8], renowned for its high-performance object detection.”
Lightweight multi-class abnormal behavior detection algorithm in complex scenarios
Li, J., & Wang, L. (2026) · PeerJ Computer Science · doi:10.7717/peerj-cs.3582
YOLO-TLD: transmission line abnormal target detection model
Ling, L., Huang, J., & Lu, Y. (2026) · Discover Applied Sciences · doi:10.1007/s42452-026-08250-8 · Cited by 1
Vision-Based Putting Distance Estimation Using an Object Detection Model
Yun, J., Han, S., Kim, J., & Choi, H. (2026) · Journal of Broadcast Engineering · doi:10.5909/jbe.2026.31.1.169
TSUKUDA, N., NAKATANI, Y., Tatsuya, K. A. I., et al. (2026) · Japanese Journal of JSCE · doi:10.2208/jscejj.25-16083
Chang, I., & Park, G.-M. (2026) · Journal of Broadcast Engineering · doi:10.5909/jbe.2026.31.1.77
Power Line Component Detection Using Quantized YOLO for Resource-Constrained Single-Board Computer
Zhang, H., & Surantha, N. (2025) · International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS) · doi:10.1109/ispacs68724.2025.11382607
Pham, D.-L., Cho, E., & Kim, K. B. (2025) · doi:10.1109/fllm67465.2025.11391076
“The COME-HVLM machine is fundamentally built upon a real-time YOLO (You Only Look Once) video object detection model [13] [6].”
Krisnawati, M., HyoTaek, L., Gook, L. B., et al. (2025) · International Conference on Information and Communication Technology Convergence (ICTC) · doi:10.1109/ictc66702.2025.11388070
“[2] Rather than the inception method from GoogleNet, we can alternate to decrease the feature space followed by 3x3 convolutional layers using the 1x1 convolutional layers.”
Depth-aware Style Transfer for Robust Data Augmentation in Object Detection
Ryu, I., & Lee, J.-S. (2025) · International Conference on Information and Communication Technology Convergence (ICTC) · doi:10.1109/ictc66702.2025.11388128
“Given its importance, significant research has been devoted to designing detectors such as Faster R-CNN [1] and YOLO [2], which have achieved remarkable progress in both accuracy and efficiency.”
YOSHIDA, N., & ONITSUKA, K. (2026) · Japanese Journal of JSCE · doi:10.2208/jscejj.25-16108
Robust Weed Detection with Evidential Neural Network-Based Uncertainty Quantification
Kan, J., Li, Z., Zhou, J. J., & Chen, F. (2026) · Communications in computer and information science · doi:10.1007/978-981-95-6888-8_11
Nguyen, M. D., & Ro, S. (2025) · Information and Communication Technology Convergence · doi:10.1109/ictc66702.2025.11387887
“In the first stage, groups of people with a high likelihood of violent behavior are detected and localized using YOLO [11], combined with the Deep SORT [12] object tracking algorithm.”
LLM-based Rarity-Aware Caption Expansion for Diffusion Dataset Condensation in Object Detection
Tran, L.-T., & Bae, S. (2026) · Journal of Broadcast Engineering · doi:10.5909/jbe.2026.31.1.162
Data Quality Analysis Framework for Defense Objective Detection Systems
Noh, S., Choi, E., & Lee, J. (2025) · International Conference on Information and Communication Technology Convergence (ICTC) · doi:10.1109/ictc66702.2025.11389027
“Redmon et al. [17] achieved breakthrough performance in real-time object detection through GPU-optimized YOLO architecture, showing how parallel processing enables practical deployment of complex systems.”
Kumar, M. R., Marimuthu, M., Kiruthika, E., Saranya, R., Sathiyapriya, V., & Revathi, P. (2025) · International Conference on Electronics and Computing, Communication Networking Automation Technologies (ICEC2NT) · doi:10.1109/icec2nt65402.2025.11379956
“Due to their extensive blind zones, long braking distances, and high momentum, HDVs pose unique safety challenges in both urban and highway environments [1].”
A Survey of Object-Detection Datasets Applied to Defense Environments
Jeong, Y., & Noh, S. (2025) · International Conference on Information and Communication Technology Convergence (ICTC) · doi:10.1109/ictc66702.2025.11388154
“To address computational limitations, Redmon et al. [15] presented YOLO, a novel framework that predicts object bounding boxes and categories directly from entire images in a single inference pass.”
OHARA, K., NAKAMURA, T., Hirokazu, S. U. M. I., et al. (2026) · Japanese Journal of JSCE · doi:10.2208/jscejj.25-16109
Real-Time Surface Defect Detection for Electrical Equipment Based on Lightweight Yolov5
He, X., & Chen, H. (2025) · doi:10.1109/aecse67874.2025.11383573
“From YOLOv1[3] pioneering the end-to-end detection framework, to YOLOv3 introducing multi-scale prediction, and further to YOLOv4[11] and YOLOv5 enhancing performance through the introduction of Mosaic data augmentation, adaptive anchor box calculation, and more efficient backbone and Path…”
Identification of Pests Using Neural Networks
Jayabalaji, K. A., S, A. S. K., Abinaya, A., & Ms. Aiswarya, S. (2025) · International Conference on Intelligent Innovations in Engineering and Technology (ICIIET) · doi:10.1109/iciiet65921.2025.11377609
Byeon, H.-U., Park, H.-M., Eom, T.-H., et al. (2026) · IEEE Internet of Things Journal · doi:10.1109/jiot.2026.3666212
“Notably, CNN-based object detection models, such as region-based CNN (R-CNN) [20], you only look once (YOLO) [21], and single-shot multibox detector (SSD) [22], have dramatically improved real-time performance.”
A Method for Estimated Respiratory Rates of Supine Patients Using a Pose Estimation Function
Imaizumi, N., Funasaki, H., Ohyama, F., et al. (2025) · International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS) · doi:10.1109/ispacs68724.2025.11382941
Uhlmann, T., Dadgar, A., Weigand, F., & Brunnett, G. (2026) · Advances in Science, Technology & Innovation/Advances in science, technology & innovation · doi:10.1007/978-3-032-03488-5_16
Real-time object detection and warning for road intersection safety: A YOLOv9-based approach
Narkhede, M. M., Chaudhari, R. S., & Chopade, N. B. (2026) · Sadhana · doi:10.1007/s12046-025-03057-6
“Faster R-CNN [24] 0.75 5 SSD [14] 0.79 19 YOLOv3 [16] 0.60 20 YOLOv9 (Ours) 0.89 52 The simulation study highlights the significant potential of the YOLOv9-based system in mitigating potential VRU-vehicle conflicts and near-miss incidents.”
InfluentialYu, Y., Wang, Y., & Liu, R. (2026) · Scientific Reports · doi:10.1038/s41598-026-40060-1
Student Engagement and Cheating Detection Using Transfer Learning
Azeem, N. A., Waghchaure, A. S., & Kumar, M. A. (2026) · Lecture notes in networks and systems · doi:10.1007/978-981-96-9494-5_10
Hong, J., Chen, C., Li, M., Qiu, J., Dong, B., & Lin, Y. (2026) · BioMedical Engineering OnLine · doi:10.1186/s12938-026-01518-5
“Representative detection frameworks such as YOLO [12], SSD [13], DETR [14], and Faster R-CNN [15] have demonstrated strong performance across various tasks.”
Time-Efficient Transfer Learning Approach for Waste Detection
Bhangale, C., Gabhane, P., & Kumar, M. A. (2026) · Lecture notes in networks and systems · doi:10.1007/978-981-96-9494-5_7
Indonesian Food Detection with YOLO and Calorie Estimation Using Lightweight LLMs
Nasari, M., Tarigan, G. A., Masaling, N. A. P., Joddy, S., & Minor, K. A. (2025) · International Seminar on Research of Information Technology and Intelligent Systems (ISRITI) · doi:10.1109/isriti68345.2025.11393164 · Cited by 1
“This allows YOLO to directly output bounding boxes and class probabilities in a single pass from raw image pixels [8], achieving real-time inference while maintaining competitive accuracy [9].”
Smart Driver Assistance System Using AI
Abirajah, P. A., Win, A. S. G., & Evangelin, A. P. (2025) · doi:10.1109/giest66547.2025.11387504
“Initial pipelines used Histogram of Oriented 979-8-3315-7436-9/25/$31.00 ©2025 IEEE Gradients and Local Binary Patterns with SVM, which deteriorated when the pose, illumination and occlusion changed [6].”
InfluentialImplementation of YOLOv11 and MobileNetV3 for Road Damage Detection on Image Data
Saputra, J., & Ramadhani, K. N. (2025) · International Seminar on Research of Information Technology and Intelligent Systems (ISRITI) · doi:10.1109/isriti68345.2025.11393359
“The You Only Look Once (YOLO) family is widely used because it combines high accuracy with real-time inference, with successive versions from YOLOv1 [6] to YOLOv11 [7] improving the speed–accuracy balance.”
Yahuza, K., Umar, A. M., Ebenezer, A. T., Salisu, B., Yusha’u, E. S., Kaware, M. S., & Samaila, A. A. (2025) · UMYU Scientifica · doi:10.56919/usci.2544.023 · Cited by 1
“YOLO is a real-time object detection algorithm that identifies and localizes objects within an image (Redmon et al ., 2016).”
InfluentialReal-Time FPGA-Based Object Detection with Bit-Width Adaptive Quantization
Asghari, B., & Leung, H. (2025) · IEEE Smart World Congress (SWC) · doi:10.1109/swc65939.2025.00083
“Tiny YOLO is a lightweight variant of the original YOLO object detector, introduced by Redmon [11], and is designed specifically for resource-constrained devices.”
Ansari, S., Gudlangari, A. S. A., & Nayak, P. K. (2025) · International Symposium on Ocean Technology (SYMPOL) · doi:10.1109/sympol68153.2025.11395922
“YOLO (You Only Look Once), first introduced by Joseph Redmon at CVPR 2016, is a single-stage object detection model that performs detection in a single forward pass, unlike two-stage methods such as R-CNN [33,34].”
Comparison of small object detection approaches in unmanned aerial vehicle (UAV) images
SadeghiBakhi, M., Arnab, A. A., Ma, K. F., Wang, X., & Leung, H. (2025) · IEEE Smart World Congress (SWC) · doi:10.1109/swc65939.2025.00084
“On the other hand, one-stage detectors, including models like YOLO [16] and SSD [17], perform detection in a single, unified step by directly predicting bounding boxes and class probabilities across a dense spatial grid.”
Detection of Road Damages and Defects Using YOLOv11
Tilmisani, R. A., & Kosala, G. (2025) · International Seminar on Research of Information Technology and Intelligent Systems (ISRITI) · doi:10.1109/isriti68345.2025.11393104
“Convolutional Neural Networks (CNNs) underpin modern object detection frameworks by extracting hierarchical image features [4].”
A high-throughput cost-effective platform for monitoring viscoelastic transitions in hydrocolloids
Fridman, A., Bakalis, S., Selvan, R., & Boom, R. M. (2026) · Journal of Food Engineering · doi:10.1016/j.jfoodeng.2026.113039
Liu, B., AlSalmi, H., & John, C. M. (2026) · Applied Computing and Geosciences · doi:10.1016/j.acags.2026.100329 · Cited by 1
A Systematic Analysis of Object Detection Approaches in Images: A Comprehensive Review
Bansal, N., Dash, S., Kaur, K., & Garg, D. (2025) · International Conference on Innovations and Emerging Technologies in AI & Communication Systems (IETACS) · doi:10.1109/ietacs68750.2025.11385542 · Cited by 1
“Yolo [22] [23] was the first model that detected real-time object detection.”
YOLOv7-AFDH: An anchor-free and decoupled-head based object detection model
Liu, H., Jiang, X., Ji, Z., et al. (2025) · IEEE Smart World Congress (SWC) · doi:10.1109/swc65939.2025.00190
“Joseph Redmon et al. [10] introduced YOLOv1, the first regression-based object detection algorithm.”
Deep Learning Based Image Retrieval for Strawberry Plant Disease Identification
Nasution, A. S., Al-Hakim, A. A. H., Haryandi, M. E., et al. (2025) · International Seminar on Research of Information Technology and Intelligent Systems (ISRITI) · doi:10.1109/isriti68345.2025.11393417
“This capability is invaluable for enabling targeted treatments and effectively curbing the spread of diseases within a field, underscoring the critical importance of integrating such efficient object detection models into our research methodology [20].”
Multi-scale Target Detection of Unmanned Ground Vehicles Based on YOLO-MAC
Wang, Y., Qin, Y., Liu, W., et al. (2025) · IEEE Smart World Congress (SWC) · doi:10.1109/swc65939.2025.00106
“In 2015, with the YOLO algorithm proposed by Joseph Redmon [9], opened the door to the one-stage detection algorithm.”
Improved Object Detection Framework with Thermal Imaging
Sofi, T. A., & Sumathi, P. (2025) · IEEE India Council International Conference (INDICON) · doi:10.1109/indicon68490.2025.11392866
“YOLO (You Only Look Once) is a set of algorithms with incremental improvement in each iteration of the model version [17].”
Lightweight Detection of Infrared Images of Power Equipment Based on Improved PP-YOLO
Wang, X., Wu, W., Liu, X., et al. (2025) · International Conference on Electrical Engineering and Control Technologies (CEECT) · doi:10.1109/ceect67814.2025.11393117
“Anchor frame-based single-stage detectors are YOLO series[7-9], SSD[10, 11], etc..”
Classification of Eye Diseases Based on Eye Fundus Images Using the YOLO11 Algorithm
Taqillah, M. D., Ilmi, N., & Suryoprayogo, H. (2025) · International Seminar on Research of Information Technology and Intelligent Systems (ISRITI) · doi:10.1109/isriti68345.2025.11393343
“This ”one-pass” architecture allows YOLO to perform object detec-tion—predicting objects and their locations—simultaneously within a single convolutional network, distinguishing it from multi-stage methods like R-CNN [18].”
Lake, T. A., Laginhas, B. B., Farrell, B. T., Meentemeyer, R. K., & Jones, C. M. (2026) · ISPRS Open Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.ophoto.2026.100122 · Cited by 1
Smart Vision Aid for the Blind: Enhancing Exploration
Brehar, R. D., Elena-Andreea, S., Hulea, A.-F., & Muresan, M. P. (2026) · Lecture notes in electrical engineering · doi:10.1007/978-3-032-17899-2_9
МЕТОД БЕЗДРОТОВОЇ ПЕРЕДАЧІ ЗОБРАЖЕНЬ З ВИКОРИСТАННЯМ НЕЙРОМЕРЕЖ
Слюсар, В. І., & Бігун, Н. (2023) · Озброєння та військова техніка · doi:10.34169/2414-0651.2023.4(40).105-114
Development of a Digital Tool for Quantifying and Classifying Traffic Entities
Roberto-Marian, O., & RUSCA, F. V. (2025) · Romanian Journal of Transport Infrastructure · doi:10.2478/rjti-2025-0010 · Cited by 1
“Models in the YOLO (You Only Look Once) [3] family are notable for their real-time performance.”
A low-complexity and lightweight detection network for surface defects on liquid crystal display
Ruan, G., Liao, Z., Shan, H., Ni, Y., Chen, L., Kong, X., & Yang, K. (2026) · The Journal of Supercomputing · doi:10.1007/s11227-026-08335-6
“Notably, You Only Look Once (YOLO) [24] achieves significantly accelerated detection rates.”
Multi-Modal Few-Shot Object Detection with Meta-Learning-Based Cross-Modal Prompting
Han, G., Chen, L., Ma, J., Huang, S., Chellappa, R., & Chang, S. (2026) · International Journal of Computer Vision · doi:10.1007/s11263-025-02592-3 · Cited by 27
Yu, C., Zeng, H., Liu, T., & Li, J. (2025) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio66223.2025.11378229
“Single-stage algorithms, such as the YOLO [10] model, perform object localization and classification in a single forward pass, resulting in a faster detection speed.”
Infrared ship target detection algorithm PEW_YOLOv8 in complex environments
Dong, T., Zhu, M., & Tang, G. (2026) · Scientific Reports · doi:10.1038/s41598-026-40574-8
“one-stage detection algorithms based on regression, such as YOLO (You Only Look Once) 8 and SSD (Single Shot MultiBox Detector) 9 .”
Real-Time Multi-Feature Fatigue Driving Detection System Based on Improved YOLOv11 Algorithm
Chen, X., Surinta, O., & Jareanpon, C. (2025) · International Conference on Information Science, Parallel and Distributed Systems (ISPDS) · doi:10.1109/ispds67367.2025.11390995
“The YOLO series, as a mainstream one-stage real-time object detection framework, has evolved continuously since YOLOv1 (2016) laid the foundation of "single forward pass for whole-image detection[4]".”
Wildlife Detection via 40kHz Ultrasonic Signals: Dataset Design and Deep Learning Evaluation
Kang, S., Kang, H., Ahn, S., Ahn, T.-H., Hiday, L., & Smith, A. (2025) · 2025 International Conference on Robotic Computing and Communication (RoboticCC) · doi:10.1109/roboticcc68732.2025.00021
“In recent years, various camera-based computer vision approaches, such as real-time detectors in the You Only Look Once(YOLO) [2] family and transformer-based species classifiers, have been proposed [3], [4].”
Goldshmidt, R. (2025) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw69036.2025.00189
“Users can integrate results from any detection system suited to their application domain, including category-specific models like YOLO [11] variants or open-vocabulary systems like GroundingDINO [6].”
A Lightweight Small Target Detection Algorithm for UAV Aerial Photography Scenarios
Xiao, P., Yang, H., Jin, R., & Tang, D. (2025) · International Conference on Robotics, Intelligent Control and Artificial Intelligence (RICAI) · doi:10.1109/ricai68060.2025.11385014
“Mainstream target detection algorithms are categorized into one-stage (e.g., RT-DETR [2], YOLO [3]) and two-stage (e.g.,SPP-Net [4], Fast R-CNN [5]) approaches.”
Steller Sea Lion Counting Across Multiple Aerial Cameras
Dawkins, M., Crall, J., Sweeney, K., Birkemeier, B., Siekierski, N., & Du, D. (2025) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw69036.2025.00227
“Object detection, alongside animal detection and clas-sification specifically, is also not new, with a number of prior works addressing problems within these domains [6, 13, 14, 18, 19] several of which we utilize [2, 13, 18] for baseline detection model generation.”
UAV Detection Based on Clarity-Adaptive Enhancement and Multi-Scale Rotation-Equivariant Features
Ren, Y., Zhou, T., Long, X., et al. (2025) · International Conference on Robotics, Intelligent Control and Artificial Intelligence (RICAI) · doi:10.1109/ricai68060.2025.11385020
“Redmon et al. [7] proposed dividing the input image into multiple regions and extracting features from the entire image via a network to obtain bounding box coordinates, confidence scores, and class information for each region, achieving end-to-end detection and greatly improving speed, though…”
A Bio-inspired Method and System for Accurate Detection of Spatial Objects via Visual-Tactile Fusion
Wang, Y., Chen, M., & Zhang, T. (2025) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio66223.2025.11376175
“Among numerous methods, vision-based detection approaches like YOLO [4] and FAST R-CNN [5] have found extensive applications in 2D object detection due to their advantages of lower hardware costs and relatively easy deployment.”
Vehicle Re-identification System using Residual Network with Instance-Batch Normalization
Goh, K.-O. M., Hossen, M. I., Low, W. J., et al. (2026) · Journal of Informatics and Web Engineering · doi:10.33093/jiwe.2026.5.1.17
PLOT-TAL: Prompt-Learning with Optimal Transport for Few-Shot Temporal Action Localization
Fish, E., & Gilbert, A. (2025) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw69036.2025.00616 · Cited by 4
Synthetic Image Generation for Underwater Diver Detection
Hożyń, S. (2026) · IEEE Access · doi:10.1109/access.2026.3667212
Weakly Supervised MaxN Estimation in Baited Remote Underwater Videos
Sorrenti, A., Russo, L. G., Samarasinghe, S., Palazzo, S., & Spampinato, C. (2025) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw69036.2025.00224 · Cited by 1
“Popular architectures such as YOLO [24], Faster R-CNN [25], and Mask R-CNN [10] have been widely adopted for fish detection in both images and video sequences.”
Seok, S., Park, H.-S., Kim, S., Lee, Y., & Kim, T. (2026) · Journal of Bio-Environment Control · doi:10.12791/ksbec.2026.35.1.026
Singh, S. P., Madhuri, C. B., & Satheesh, P. (2026) · i-manager’s Journal on Image Processing · doi:10.26634/jip.12.4.22715
Flow-Graph-Aware Tiling and Rescheduling for Memory-Efficient On-Device Inference
Jeong, Y., Park, T., & Park, Y. (2026) · IEEE/ACM International Symposium on Code Generation and Optimization (CGO) · doi:10.1109/cgo68049.2026.11395230
“Deep neural networks (DNNs) are widely used as a core technology in various real-world fields such as health care [1], [2], automotive [3]–[5], computer vision [6]–[8], and natural language processing [9]–[11].”
Neri, F., Zhang, Z., & Xue, Y. (2026) · Integrated Computer-Aided Engineering · doi:10.1177/10692509261421247
“YOLO 18 reformulates object detection as a single-stage regression problem, directly predicting bounding boxes and class probabilities on image grids, achieving a balance between accuracy and speed that enables wide adoption in real-time applications.”
Intelligent Analysis and Image–Text Matching of CAD Drawings for Robotic Services
Dai, J., Guo, W., Tang, Y., et al. (2025) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio66223.2025.11377371
“Recent research has explored deep learning–based meth-ods for primitive recognition and symbol detection, achieving notable progress using object detection frameworks such as SSD [3] and YOLO [4].”
Improved Yolo11n Model for Enhanced Apple Detection in Complex Environments
Yang, M., Hao, J., Zhan, Y., & Chen, J. (2025) · International Conference on Artificial Intelligence, Robotics, and Communication (ICAIRC) · doi:10.1109/icairc68035.2025.11385191
“In contrast, one-stage detectors such as SSD [4] and the YOLO series [1] [5] [2] perform localization and classification simultaneously in a single network pass, offering an excellent trade-off between speed and accuracy.”
Recognizing Robotic Components in Complex Environment
Ren, H., Li, Y., Wang, Y., Guran, N. B., Hu, C., Yang, Y., Hu, Y., Hu, J., Deng, J., & Xie, X. (2025) · International Conference on Robotic Computing and Communication (RoboticCC) · doi:10.1109/roboticcc68732.2025.00024
“Another significant advancement in object detection and segmentation is YOLOv11 [16], which builds upon the efficiency and real-time capabilities of the You Only Look Once (YOLO) [17] series.”
Relation-Anchored Local Cross-Spectral Alignment for Multispectral NTRM Detection
Chen, T., Cao, T., Yin, Z., et al. (2025) · International Conference on Robotics, Intelligent Control and Artificial Intelligence (RICAI) · doi:10.1109/ricai68060.2025.11385158
“Since YOLOv1, the series has evolved through multi-scale prediction in YOLOv3, lightweight optimization in YOLOv5, structural redesign and efficient inference in YOLOv8, and further refined detection designs in YOLOv10 and YOLO11, continuously improving feature extraction and detection accuracy [7].”
Enhanced YOLO11 for Road Surface Defect Detection
Chen, S., Zhang, L., Li, S., et al. (2025) · International Conference on Machine Learning and Natural Language Processing (MLNLP) · doi:10.1109/mlnlp66797.2025.11388711
“Single-stage methods, such as YOLO [1] and SSD [2] , perform localization and classification simultaneously, providing faster detection and lower computational cost.”
Park, K., & Baek, S. (2026) · Korean Society of Hazard Mitigation · doi:10.9798/kosham.2026.26.1.47
“해당 모델은 단일 이미지 입력으로 부터 객체의 위치 정보와 신뢰도 점수를 동시에 산출할 수 있어 다수의 차량이 존재하는 도로 환경에서도 신속한 객체 검출이 가능하다 (Redmon et al., 2016).”
A Method for Detecting Surface Defects in Steel Based on an Improved YOLOv10 Algorithm
Zhang, X. L., Zhou, D.-F., Wang, X., et al. (2025) · Cross Strait Radio Science and Wireless Technology Conference (CSRSWTC) · doi:10.1109/csrswtc67757.2025.11384328
AMS-YOLO: An Improved Object Detection Algorithm for UAV Aerial Images
Liu, Y. (2025) · doi:10.1109/icairc68035.2025.11384967
“The core characteristic of YOLO series algorithms [3-7] is their ability to simultaneously output object class labels and bounding box coordinates through a single forward pass of the network, without requiring additional intermediate processing steps.”
YOLOv11-Based Visual Servoing for a Low-Cost 3D-Printed Mobile Robotic Arm
Xiao, S., Zheng, K., Luo, J., et al. (2025) · International Conference on Robotics, Intelligent Control and Artificial Intelligence (RICAI) · doi:10.1109/ricai68060.2025.11384832
“Among existing methods, YOLO [6] has become one of the most widely used deep learning models for real-time object detection.”
Intrinsically-Interpretable Siamese Networks for Identity Recognition
Rocha, M., Cardoso, J. S., & Montenegro, H. (2025) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw69036.2025.00619
“To limit comparisons to only discriminative pairs, we guide the process using semantically-grounded facial region activations derived from a YOLOv8 segmentation model [11, 23], as illustrated in Figure 4.”
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.