Object Detection in 20 Years: A Survey
Open accessThe DOI matches its Crossref record; 309 of the 309 references it cites were found in a registry or an index; 84 of the 192 sources its claims cite were checked for support.
Abstract
Object detection, as of one the most fundamental and challenging problems in computer vision, has received great attention in recent years. Over the past two decades, we have seen a rapid technological evolution of object detection and its profound impact on the entire computer vision field. If we consider today’s object detection technique as a revolution driven by deep learning, then, back in the 1990s, we would see the ingenious thinking and long-term perspective design of early computer vision. This article extensively reviews this fast-moving research field in the light of technical evolution, spanning over a quarter-century’s time (from the 1990s to 2022). A number of topics have been covered in this article, including the milestone detectors in history, detection datasets, metrics, fundamental building blocks of the detection system, speedup techniques, and recent state-of-the-art detection methods.
Overview
CoChat Summary
TL;DR
This survey reviews two decades of object detection research (1990s–2022), tracing the transition from handcrafted-feature detectors to deep-learning-based two-stage, one-stage, and transformer detectors. It organizes the field around milestone detectors, datasets and metrics, key building blocks (multi-scale detection, context, hard negative mining, loss functions, NMS), speed-up techniques, and recent advances.
Key findings
- The field splits into a "traditional object detection period (before 2014)" and a "deep learning based detection period (after 2014)"; RCNN raised VOC07 mAP from 33.7% (DPM-v5) to 58.5%, SPPNet reached VOC07 mAP=59.2% at >20× faster than R-CNN, Fast RCNN reached 70.0% mAP at >200× faster than R-CNN, and Faster RCNN reached COCO mAP@.5=42.7%, VOC07 mAP=73.2% at 17fps.
- One-stage detectors traded some accuracy for speed: YOLO ran at 155fps with VOC07 mAP=52.7% (enhanced version 45fps, 63.4%), SSD reached COCO mAP@.5=46.5% at 59fps, and RetinaNet's focal loss brought one-stage accuracy to COCO mAP@.5=59.1%.
- Keypoint- and transformer-based detectors pushed accuracy further: CornerNet COCO mAP@.5=57.8%, CenterNet 61.1%, and Deformable DETR 71.9% on MS-COCO; the paper notes the top-10 COCO detection methods are all transformer-based.
- Datasets scaled dramatically: VOC07 has 5k train images/12k objects, VOC12 11k/27k, MS-COCO-17 164k images and 897k annotated objects over 80 categories, and Open Images 1,910k images with 15,440k boxes over 600 categories. Evaluation moved from miss-rate vs. FPPW to FPPI, then to AP/mAP, with MS-COCO averaging over IoU thresholds 0.5–0.95.
Methods
- Design: a narrative literature survey spanning roughly a quarter-century (1990s to 2022), structured around technical evolution rather than a systematic/quantitative review protocol.
- Coverage: milestone detectors (VJ, HOG, DPM, RCNN, SPPNet, Fast/Faster RCNN, FPN, YOLO, SSD, RetinaNet, CornerNet, CenterNet, DETR), datasets and metrics, technical building blocks, speed-up techniques, and recent advances (rotation/scale robustness, backbones, localization, segmentation loss, adversarial training, weakly supervised detection, domain adaptation).
- Analysis: qualitative synthesis of reported detector accuracies and speeds, with figures/tables summarizing dataset statistics and accuracy trends; no new experiments are conducted.
Limitations
- The paper states no explicit limitations section; it frames its scope as presenting the evolution of technologies "while neglecting their technical specifics," and notes that the evolution order shown in figures is primarily to assist reader understanding and "may have temporal overlap."
- Evident from the text: as a survey it reports no original experiments or controlled benchmarks, so the cited mAP/speed figures come from the original papers and are not independently verified; the coverage is also selective (milestone detectors and selected recent advances) rather than exhaustive.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
55 Valid · 18 Not valid · 32 Not checked · 50 Own results and interpretations
Some cited sources support this claim and some don’t — read each source’s verdict below.
In the paper
“In the deep learning era, due to the increase of computing power, bootstrap was shortly discarded in object detection during 2014-2016 [16-20].”
What the sources say
- Not checked — no full text of the sourcecites [16] matched to “Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation” (2014) source
- Disputedcites [17] matched to “Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition” (2014) sourceExperimental — accuracy not yet measured
Section 4.1 (page unavailable) says the authors used standard hard negative mining, iterated once, to train their object-detection SVMs. That is contrary to citing this 2014 detector as evidence that bootstrapping had been discarded. The paper does not establish a 2014–2016 trend or attribute one to increased computing power. (LLM, conf=0.78)
Checked by a reasoning model — may be wrong.
- Not checked — no full text of the sourcecites [18] matched to “Fast R-CNN” (2015) source
- Partly supportedcites [19] matched to “Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks” (2017) sourceExperimental — accuracy not yet measured
Section 4.2 (p. 10) says Fast R-CNN abandoned the SVM step that, in SPPnet, used hard-negative mining. This supports a narrower change in one detection system, but not the claim that bootstrapping was discarded across object detection during 2014–2016 or that increased computing power caused the change. (LLM, conf=0.83)
- Could not verifycites [20] matched to “You Only Look Once: Unified, Real-Time Object Detection” (2016) sourceExperimental — accuracy not yet measured
The Introduction (p. 1) contrasts YOLO with earlier detection methods, and Training (p. 3) describes how YOLO is trained. Neither passage addresses whether bootstrapping was discarded in object detection during 2014–2016 or attributes such a change to increased computing power; searches for bootstrapping and hard-negative mining found no passage that does. (LLM, conf=0.72)
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.
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Faster RCNN is the first near-realtime deep learning detector (COCO mAP@.5=42.7%, VOC07 mAP=73.2%, 17fps with ZF-Net [48]).”
What the sources say
- Partly supportedcites [19] matched to “Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks” (2017) sourceExperimental — accuracy not yet measured
Section 4.2 reports 42.7% COCO mAP@0.5; Section 4.1 reports 73.2% VOC 2007 mAP and 17 fps with ZF-Net. These are results from different model configurations: the 73.2% VOC result uses VGG-16, not ZF-Net. The paper describes Faster R-CNN as a fast detector but does not establish that it was the first near-real-time deep-learning detector. (LLM, conf=0.88)
- Partly supportedcites [47] matched to “Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks” (2017) sourceExperimental — accuracy not yet measured
Section 4.2 reports 42.7% COCO mAP@0.5, and Section 4.1 reports 73.2% VOC 2007 mAP and 17 fps with ZF-Net. The accuracy figures are from VGG-16 experiments, not the 17-fps ZF-Net configuration. The paper describes Faster R-CNN as a fast detector but does not establish that it was the first near-real-time deep-learning detector. (LLM, conf=0.88)
- Partly supportedcites [48] matched to “Visualizing and understanding convolutional networks” (2014) sourceExperimental — accuracy not yet measured
Section 3 (p. 4) describes the authors’ convolutional-network architecture, supporting the citation as an identification of the ZF-Net backbone. The paper does not report Faster R-CNN’s near-real-time status, COCO or VOC07 mAP, or 17-fps speed, so it does not support those performance claims. (LLM, conf=0.88)
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.
- Partly supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“In the case of sliding window based detectors, the imbalance between backgrounds and objects could be as extreme as 10 7 :1 [71].”
What the sources say
- Partly supportedcites [71] matched to “What Makes for Effective Detection Proposals?” (2016) sourceExperimental — accuracy not yet measured
The Introduction (p. 1) says sliding-window detection can search 10^6–10^7 windows per image. It does not say that 10^7 of those windows are backgrounds for each object, so it does not establish the claimed 10^7:1 imbalance. (LLM, conf=0.88)
hedged- 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
“It achieves state-of-the-art performance on MSCOCO dataset (COCO mAP@.5=71.9%).”
What the sources say
- Supportedcites [43] Zhu, 2020, Deformable DETR: Deformable transformers for end-to-end object detection, arXiv:2010.04159 source
Section 5.3 (pp. 8–9) compares Deformable DETR with state-of-the-art methods on COCO. Its table reports an AP50 of 71.9 for the ResNeXt-101 + DCN configuration with test-time augmentation; the accompanying text reports 52.3 overall AP for that configuration. (LLM, conf=0.91)
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
Every source the paper cites for this claim was checked and supports it.
In the paper
“Using FPN in a basic Faster R-CNN system, it achieves state-of-the-art single model detection results on the COCO dataset without bells and whistles (COCO mAP@.5=59.1%).”
What the sources say
- Supportedcites [24] matched to “Feature Pyramid Networks for Object Detection” (2017) source
The Introduction describes a state-of-the-art single-model COCO result using FPN with a basic Faster R-CNN detector, without bells and whistles. Section 5.2.3 reports AP@0.5 of 59.1 on COCO test-dev and says the single-model entry surpassed competition winners. Page numbers are not provided in the copy. (LLM, conf=0.94)
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.
- Supported
50 more claims · 21 with their cited sources checked
Create a free account to see all 155 claims and to verify the 3 references still open.
- It may state two separate claims as one. 40
- Probably not a substantial claim. 83
- The quote only partly states this claim. 1
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
“From navigating through occlusions to efficiently managing scale variations and fine-grained object detection scenarios [9], YOLO faces a myriad of obstacles.”
From YOLOv1 to v8: Unveiling Each Variant–A Comprehensive Review of YOLO (2024) · cites this paper as [9]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“The speed-up techniques in object detection can be divided into three levels of groups: speed up of 'detection pipeline', 'detector backbone', and 'numerical computation'. , as shown in Fig. 9. Refer to [123] for a more detailed version.”
From Object Detection in 20 Years: A Survey (2023) · cites this paper as [123]
The cited source says what the claim attributes to it.
In the citing paper
“The few surveys that mention both object detection and model compression [11] focus on the acceleration of”
From A survey of model compression strategies for object detection (2023) · cites this paper as [11]
The check wasn’t confident either way, so it gives no verdict — never disputed.
In the citing paper
“In addition to that, most of the reviews in related fields review the object detection model and model compression technology separately, and there is a lack of comprehensive reviews for both.”
From A survey of model compression strategies for object detection (2023) · cites this paper as [11]
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ II. OBJECT DETECTION IN 20 YEARS
“Fig. 2: A road map of object detection. Milestone detectors in this figure: VJ Det. [10, 11], HOG Det. [12], DPM [1315], RCNN [16], SPPNet [17], Fast RCNN [18], Faster RCNN [19], YOLO [20-22], SSD [23], FPN [24], Retina-Net [25], CornerNet [26], CenterNet [27], DETR [28].”
§ Object detection accuracy improvements
“CenterNet: X. Zhou et al proposed CenterNet [40] in 2019.”
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · cited 4×
“As the accuracy of a detector depends heavily on its feature extraction networks, in this paper, we refer to the backbone networks, e.g. the ResNet and VGG, as the “engine” of a detector.”
InfluentialImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155 · cited 5×
“In 2012, the world saw the rebirth of convolutional neural networks (CNNs) [35].”
InfluentialLeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
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 · cited 10×
“The main idea of multi-reference detection [19, 22, 23, 41, 47, 51] is to first define a set of references (a.”
InfluentialFaster 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
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333 · cited 1×
“It contains a detection challenge using ImageNet images [61].”
Gradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805 · cited 3×
“Some well-known detection models of the early time: (a) Eigenfaces [95], (b) Shared weight networks [96], (c) Space displacement networks (Lenet-5) [97], (d) Haar wavelets of VJ detector [10].”
BackgroundMethodDistinctive Image Features from Scale-Invariant Keypoints
Lowe, D. G. (2004) · International Journal of Computer Vision · doi:10.1023/b:visi.0000029664.99615.94 · Cited by 55,589 · cited 1×
“HOG can be considered as an important improvement of the scale-invariant feature transform [33, 34] and shape contexts [35] of its time.”
BackgroundYou Only Look Once: Unified, Real-Time Object Detection
Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.91 · Cited by 53,803 · cited 9×
“L2 loss is prevalent in early research [16], [20], [51], but it is highly affected by outliers and prone to gradient explosion.”
InfluentialDensely Connected Convolutional Networks
Huang, G., Liu, Z., Van Der Maaten, L., & Weinberger, K. Q. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.243 · Cited by 48,566
Research works printed but not linked: 9
- 10.5555/3045118.3045336 · doi:10.5555/3045118.3045336
- Girshick, 2023, Discriminatively Trained Deformable Part Models, Release 5
- 10.1109/TPAMI.2016.2577031 · DOI · Paper page
- Krasin, 2017, OpenImages: A Public Dataset for Large-Scale Multi-Label and Multi-Class Image Classification
- Alexe, What is an object, 73
- Müller, When does label smoothing help, 32, 1
- 10.1109/CVPR.2016.308 · DOI · Paper page
- 10.5555/2969033.2969125 · doi:10.5555/2969033.2969125
- 10.1109/ICCV.2017.244 · DOI · Paper page
Cited by
Items 601–700 of 3,144
THDet: A Lightweight and Efficient Traffic Helmet Object Detector based on YOLOv8
Li, Y., Xu, H., Zhu, X., Huang, X., & Li, H. (2024) · Digital Signal Processing · doi:10.1016/j.dsp.2024.104765 · Cited by 15
Semi-supervised recognition for artificial intelligence assisted pathology image diagnosis
Pan, Y., Gou, F., Xiao, C., Liu, J., & Zhou, J. (2024) · Scientific Reports · doi:10.1038/s41598-024-70750-7 · Cited by 13
“In pathology image analysis, fully supervised learning models require accurate pixel-level annotation, which can be time-consuming and require expert knowledge 23,24 .”
Wei, C., Wu, G., & Barth, M. (2024) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw63382.2024.00007 · Cited by 15
“As a vital component of computer vision, object detection is used in a wide range of applications such as autonomous driving, surveillance, and augmented reality [35].”
BackgroundJung, S., Jeoung, J., Kong, M., & Hong, T. (2024) · Building and Environment · doi:10.1016/j.buildenv.2024.112178 · Cited by 12
YOLOv8-CDD: an improved concrete defect detection method combined CNN with transformer
Wang, C., Chen, B., Li, Y., Wang, H., Tan, L., Zhang, Y., & Zhang, H. (2024) · Measurement Science and Technology · doi:10.1088/1361-6501/ad85f5 · Cited by 18
“In recent years, a large number of excellent algorithms based on CNNs and benchmark datasets have accelerated the development of the field of object detection [13, 14].”
Rashid, H., Habbouche, H., Amirat, Y., Mamoune, A., Titah-Benbouzid, H., & Benbouzid, M. (2024) · Journal of Marine Science and Engineering · doi:10.3390/jmse12101828 · Cited by 14
de Oliveira, D. B., & Mafra, S. B. (2024) · Sensors · doi:10.3390/s24216932 · Cited by 12
One to All: Toward a Unified Model for Counting Cereal Crop Heads Based on Few-Shot Learning
Wang, Q., Fan, X., Zhuang, Z., Tjahjadi, T., Jin, S., Huan, H., & Ye, Q. (2024) · Plant Phenomics · doi:10.34133/plantphenomics.0271 · Cited by 12
Analyzing usage patterns from video data through deep learning: The case of an urban park
Gravitz-Sela, S., Levy, A., Zehavi, S., Bryt, O., Shach‐Pinsly, D., & Plaut, P. (2024) · Computers Environment and Urban Systems · doi:10.1016/j.compenvurbsys.2024.102229 · Cited by 12
Enhancement of Sentinel-2A Images for Ship Detection via Real-ESRGAN Model
Aldoğan, C. F., Aksu, K., & Demirel, H. (2024) · Applied Sciences · doi:10.3390/app142411988 · Cited by 14
Green Apple Detector Based on Optimized Deformable Detection Transformer
Liu, Q., Meng, H., Zhao, R., Ma, X., Zhang, T., & Jia, W. (2024) · Agriculture · doi:10.3390/agriculture15010075 · Cited by 14
Guo, B., Li, X., & Li, D. (2025) · Structural Health Monitoring · doi:10.1177/14759217241308132 · Cited by 10
“18 Increasingly, researchers are using deep learning to overcome the limitations of conventional methods.”
Liao, K.-C., Lau, J., & Hidayat, M. (2025) · Aerospace · doi:10.3390/aerospace12010031 · Cited by 8
“(4) Mean Average Precision ( mAP ): The mAP is calculated as the average of the average precision ( AP ) values across all classes: where Rn and Pn are the recall and precision at the nth threshold.”
InfluentialJiang, Z., Han, Y., Cheng, Y., Wang, Z., & Meng, H. (2025) · Journal of Construction Engineering and Management · doi:10.1061/jcemd4.coeng-15670 · Cited by 12
Zedda, L., Loddo, A., & Ruberto, C. D. (2025) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2025.109704 · Cited by 20
Han, Z., Jia, D., & Zhang, L. (2025) · Measurement Science and Technology · doi:10.1088/1361-6501/adb326 · Cited by 14
“Despite the success of existing object detection algorithms in general settings [7], UAV perspectives pose unique challenges: small object sizes, frequent occlusions, blurred boundaries, and complex scenes—all of which increase detection difficulty in UAV datasets [8].”
Remote Sensing Small Object Detection Based on Multicontextual Information Aggregation
Wang, J., Ma, M., Huang, P., Mei, S., Zhang, L., & Wang, H. (2025) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2025.3543189 · Cited by 21
“image [5], [6], [7], [8], remote sensing images are typically captured by aircraft [9], [10], providing a high altitude perspective [11], and thus, exhibiting large fields of view [8] and complex interference factors [12], [13].”
SSW-YOLO: Enhanced Blood Cell Detection with Improved Feature Extraction and Multi-scale Attention
Sun, H. X., Wan, X., Tang, S., & Li, Y. (2025) · Journal of Imaging Informatics in Medicine · doi:10.1007/s10278-025-01460-3 · Cited by 14
Hu, C., Li, X., & Pang, J. (2025) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2025.3542447 · Cited by 11
“Fortunately, the detection techniques [83] of face and body are advanced enough to guarantee the reliable results in the closed-space.”
Interpreting Object-level Foundation Models via Visual Precision Search
Chen, R., Liang, S., Li, J., Liu, S., Li, M., Huang, Z., Zhang, H., & Cao, X. (2025) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52734.2025.02796 · Cited by 34
Efficient Detection in Aerial Images for Resource-Limited Satellites
Li, L., Cao, G., Liu, J., & Tong, Y. (2021) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2020.3046739 · Cited by 13
Multilayer Feature Extraction of AGCN on Surface Defect Detection of Steel Plates
Zhang, C., Cui, J., & Liu, W. (2022) · Computational Intelligence and Neuroscience · doi:10.1155/2022/2549683 · Cited by 18
“Consider RPN network can map the generated region to the feature map generated by the convolution network through “anchors,” realizing the connection between the two and further improving the detection speed and accuracy [36].”
BackgroundVehicle-Based Machine Vision Approaches in Intelligent Connected System
Ma, C., Song, J., Xu, Y., Fan, H., Wu, X., & Sun, T. (2023) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2023.3276325 · Cited by 15
Federated Learning-Based Insulator Fault Detection for Data Privacy Preserving
Luan, Z., Lai, Y., Xu, Z., Gao, Y. Q., & Wang, Q. (2023) · Sensors · doi:10.3390/s23125624 · Cited by 15
“Therefore, the use of object detection methods based on vision sensors for insulator fault detection has significant value and broad application potential [8].”
BackgroundUnderwater Target Detection Algorithm Based on Feature Fusion Enhancement
Chen, L., Yin, T., Zhou, S., et al. (2023) · Electronics · doi:10.3390/electronics12132756 · Cited by 11
Self-citationImproving Multi-Person Pose Tracking With a Confidence Network
Fu, Z., Zuo, W., Hu, Z., Liu, Q., & Wang, Y. (2023) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2023.3330532 · Cited by 17
“We briefly review the following two related topics, including multi-person pose estimation and multi-person pose tracking.”
BackgroundExperimental Study on Chess Board Setup Using Delta Parallel Robot Based on Deep Learning
Yarmohammadi, P., Khomami, N. A., Masouleh, M. T., & Zakerzadeh, M. R. (2023) · RSI International Conference on Robotics and Mechatronics (ICRoM) · doi:10.1109/icrom60803.2023.10412348 · Cited by 12
An effective graph embedded YOLOv5 model for forest fire detection
Yuan, H., Lu, Z., Zhang, R., Li, J., Wang, S., & Fan, J. (2024) · Computational Intelligence · doi:10.1111/coin.12640 · Cited by 12
Combating the hate speech in Thai textual memes
Mookdarsanit, L., & Mookdarsanit, P. (2021) · Indonesian Journal of Electrical Engineering and Computer Science · doi:10.11591/ijeecs.v21.i3.pp1493-1502 · Cited by 12
“From the reported results [70], SSD was the best speed in object detection; one-stage detection was quicklier than two-stage detection as shown in Figure 5.”
BackgroundMethodZhao, W., Lin, Z., Liang, J., Zhang, B., Wang, G., Lin, W., Xu, Y., & Wang, Z. (2025) · Materials Today · doi:10.1016/j.mattod.2025.10.007 · Cited by 13
Zhang, M., Feng, J., Yang, H., Guo, J., Li, Y., & Gao, X. (2025) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2025.3594958 · Cited by 17
“When dealing with target detection tasks [11] in visible images, challenges arise under conditions of weak illumination and occlusion.”
Chen, Y., Yu, F., Zhang, Q., & Pratama, M. (2025) · Knowledge-Based Systems · doi:10.1016/j.knosys.2025.114514 · Cited by 12
RSRefSeg 2: Decoupling Referring Remote Sensing Image Segmentation With Foundation Models
Chen, K., Liu, C., Chen, B., Zhang, J., Zou, Z., & Shi, Z. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2025.3647535 · Cited by 49
“Although groundbreaking progress in multimodal understanding has facilitated preliminary advances in this field, evidenced by the proposal of RRSIS benchmark tasks and the creation of the RefSegRS dataset [1, 12, 13], persistent limitations remain in existing methodologies [14, 15].”
Self-citationAdvances in machine learning–enhanced microfluidic cell sorting
Li, H., Bai, J., Ma, X., Li, L., Liu, Y., Liu, X., Shen, S., & Lim, C. T. (2025) · Science Advances · doi:10.1126/sciadv.aea6007 · Cited by 19
“YOLO frameworks represent a series of CNN-based object detection systems optimized for real-time multiobject identification in visual data streams ( 166 ).”
YOLO-PICO: Lightweight object recognition in remote sensing images using expansion attention modules
Aghili, M. E., Ghassemian, H., & Imani, M. (2026) · Pattern Recognition · doi:10.1016/j.patcog.2026.113114 · Cited by 16
A survey of online video advertising
Zhang, H., Mu, X., Yan, H., Ren, L., & Ma, J. (2023) · Wiley Interdisciplinary Reviews Data Mining and Knowledge Discovery · doi:10.1002/widm.1489 · Cited by 13
A survey of generative adversarial networks and their application in text-to-image synthesis
Zeng, W., Zhu, H.-L., Lin, C., & Xiao, Z.-Y. (2023) · Electronic Research Archive · doi:10.3934/era.2023362 · Cited by 11
“Directly promoting the continuous progress of the field of computer vision [1,2], deep learning has been widely applied in various fields of computer vision, such as image classification [3–5], object detection [6–8] and text-to-image (T2I) synthesis [9–11].”
BackgroundZero-DCE++ Inspired Object Detection in Less Illuminated Environment Using Improved YOLOv5
Balasundaram, A., Mohanty, A., Shaik, A., Krishnadoss, P., Poornachary, V. K., & Kavitha, M. S. (2023) · Computers, materials & continua/Computers, materials & continua (Print) · doi:10.32604/cmc.2023.044374 · Cited by 14
One-Stage Small Object Detection Using Super-Resolved Feature Map for Edge Devices
Huynh, X. N., Jung, G. B., & Suhr, J. K. (2024) · Electronics · doi:10.3390/electronics13020409 · Cited by 11
Xuan, H., Wu, Z., Yang, J. J., Jiang, B., Luo, L., Alameda-Pineda, X., & Yan, Y. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3363508 · Cited by 13
“Despite the fact that visual Object Detection [23], [24], [25] has been extensively researched, prevailing Object Detection frameworks cannot be directly utilized to localize the sound source at semantic object level.”
BackgroundPhaDe: Practical Phantom Spoofing Attack Detection for Autonomous Vehicles
Lin, F., Yan, H., Jin, L., Liu, Z., Lü, L., Ba, Z., & Ren, K. (2024) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2024.3376192 · Cited by 18
“Digital Object Identifier 10.1109/TIFS.2024.3376192 as object detection [1], traffic lane identification [2], and traffic light recognition [3].”
BackgroundInfluentialHu, M. Y., Zhang, M., & Yu, K. (2024) · PeerJ Computer Science · doi:10.7717/peerj-cs.2030 · Cited by 10
Simeth, A., Kumar, A. A., & Plapper, P. (2024) · Journal of Intelligent Manufacturing · doi:10.1007/s10845-024-02411-5 · Cited by 20
Liu, B., Chang, J., Hou, D., Pan, Y., Li, D., & Ruan, J. (2024) · Plant Phenomics · doi:10.34133/plantphenomics.0199 · Cited by 13
CF-YOLO: a capable forest fire identification algorithm founded on YOLOv7 improvement
Liu, W., Shen, Z., & Xu, S. (2024) · Signal Image and Video Processing · doi:10.1007/s11760-024-03288-w · Cited by 17
A Robust Robot Perception Framework for Complex Environments Using Multiple mmWave Radars
Chen, H., Liu, Y., & Cheng, Y. (2024) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2024.3420234 · Cited by 11
A UAV Aerial Image Target Detection Algorithm Based on YOLOv7 Improved Model
Qin, J., Yu, W., Feng, X., Meng, Z., & Tan, C.-H. (2024) · Electronics · doi:10.3390/electronics13163277 · Cited by 12
Liu, M., Hou, B., Ren, B., et al. (2024) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2024.3452680 · Cited by 9
“A more detailed overview of the literature can be found in [26], [27], and [28].”
BackgroundSelf-Supervised Marine Organism Detection From Underwater Images
Li, J., Yang, W., Qiao, S., Gu, Z., Zheng, B., & Zheng, H. (2024) · IEEE Journal of Oceanic Engineering · doi:10.1109/joe.2024.3455565 · Cited by 13
FG ‐ UNet : fine‐grained feature‐guided UNet for segmentation of weeds and crops in UAV images
Lin, J., Zhang, X., Qin, Y., Yang, S., Wen, X., Cernava, T., & Chen, X. (2024) · Pest Management Science · doi:10.1002/ps.8489 · Cited by 11
Non-exemplar Domain Incremental Learning via Cross-Domain Concept Integration
Wang, Q., He, Y., Dong, S., Gao, X., Wang, S., & Gong, Y. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72967-6_9 · Cited by 40
A review of computer vision applications for asset inspection in the oil and gas industry
Casas, E., Ramos, L., Romero, C., et al. (2024) · Journal of Pipeline Science and Engineering · doi:10.1016/j.jpse.2024.100246 · Cited by 10
Wu, J., Zhao, F., & Jin, Z. (2024) · Journal of Real-Time Image Processing · doi:10.1007/s11554-024-01601-x · Cited by 15
“Object detection using deep learning technology can be categorized into two-stage and single-stage algorithms, depending on whether separate candidate boxes need to be generated [4].”
Xie, S., Wu, H., Mao, W., Chu, X., Meng, Y., & Yang, X. (2025) · Ecological Informatics · doi:10.1016/j.ecoinf.2025.103020 · Cited by 16
Lightweight outdoor drowning detection based on improved YOLOv8
Liu, X., Shuai, T., & Liu, D. (2025) · Journal of Real-Time Image Processing · doi:10.1007/s11554-025-01638-6 · Cited by 15
“This approach can extract information about the target to be detected in the image, identify the target position, and has made significant breakthroughs in detection speed and accuracy [4, 5].”
Wang, R., Lin, C., & Li, Y. (2025) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2025.3545522 · Cited by 23
“W ITH the rapid development of deep neural networks, such as convolutional neural networks (CNNs) and Transformers, object detection models have achieved significant progress [1].”
ES-YOLOv8: a real-time defect detection algorithm in transmission line insulators
Song, X., Sun, Q., Liu, J., & Liu, R. (2025) · Journal of Real-Time Image Processing · doi:10.1007/s11554-025-01651-9 · Cited by 12
“Currently, main-stream deep learning-based object detection algorithms can be divided into two categories: those based on candidate region generation and regression approaches [11].”
Object detection on space-based optical images leveraging machine learning techniques
Rizzuto, S. S., Cipollone, R., Vittori, A. D., et al. (2025) · Neural Computing and Applications · doi:10.1007/s00521-025-11069-w · Cited by 10
“Neural network-based object detection, on the other hand, uses deep learning methods to recognize objects in images and categorize them into groups, like cars, animals, or people [6].”
ShadowFPN-YOLO: A Real-Time NMS-Free Detector for Remote Sensing Ship Detection
Yang, X. Q., Mohamed, A. S. A., & Wang, C. (2025) · IEEE Access · doi:10.1109/access.2025.3554018 · Cited by 15
“Building on rapid advancements in deep learning, numerous deep learning-based detectors have emerged as frontrunners in object detection, achieving significant improvements in accuracy [7].”
USD-YOLO: An Enhanced YOLO Algorithm for Small Object Detection in Unmanned Systems Perception
Deng, H. Y., Zhang, S., Wang, X., Han, T., & Ye, Y. (2025) · Applied Sciences · doi:10.3390/app15073795 · Cited by 18
DSOD-YOLO: A lightweight dual feature extraction method for small target detection
Nie, Y., Lai, H., & Gao, G. (2025) · Digital Signal Processing · doi:10.1016/j.dsp.2025.105268 · Cited by 12
Ding, Y., Yang, Y., Hao, H., Li, Z., Pan, C., Wang, P., Wang, C., Tan, H., Jin, R., Zhang, J., et al. (2025) · ACS Nano · doi:10.1021/acsnano.5c05791 · Cited by 12
Improved Space Object Detection Based on YOLO11
Zhou, Y., Zhang, T., Li, Z., & Qiu, J. (2025) · Aerospace · doi:10.3390/aerospace12070568 · Cited by 16
Wang, Q., Liu, R., Qin, S., et al. (2025) · International Journal of Electrical Power & Energy Systems · doi:10.1016/j.ijepes.2025.111088 · Cited by 10
DFAS-YOLO: Dual Feature-Aware Sampling for Small-Object Detection in Remote Sensing Images
Liu, X., Zhou, S., Ma, J., Sun, Y., Zhang, J., & Zuo, H. (2025) · Remote Sensing · doi:10.3390/rs17203476 · Cited by 15
Li, M., Zhou, C., Shao, L., et al. (2022) · International Journal of Aerospace Engineering · doi:10.1155/2022/4625001 · Cited by 10
“On the other hand, in recent years, deep learning technology has shown strong advantages in temporal law prediction [25] and target recognition [26], which had been widely used in vessel trajectory prediction [27, 28] and vehicle trajectory prediction [29].”
BackgroundCheng, Y., Li, Z., Królczyk, G. M., Yang, C., & Yan, R. (2023) · IEEE Sensors Journal · doi:10.1109/jsen.2023.3272643 · Cited by 10
“rized into one-stage detection and two-stage detection [31].”
BackgroundVarroa Mite Detection Using Deep Learning Techniques
Divasón, J., Martínez-de-Pisón, F. J., Romero, A., Santolaria, P., & Yániz, J. L. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-40725-3_28 · Cited by 12
Improving the Performance of Object Detection by Preserving Balanced Class Distribution
Lee, H., & Ahn, S. (2023) · Mathematics · doi:10.3390/math11214460 · Cited by 16
Martínez-Seras, A., Ser, J. D., & Bringas, P. G. (2023) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc57777.2023.10422139 · Cited by 11
“Such proposals have elevated object detection to unprecedented levels of performance, as evinced by comprehensive surveys on this topic [4].”
BackgroundPrecast concrete project image dataset for deep learning object detection
Jang, J. Y., Jeong, E., Park, S. H., Koo, C., & Kim, T. W. (2024) · Developments in the Built Environment · doi:10.1016/j.dibe.2024.100383 · Cited by 15
Small Target Detection Algorithm Based on Improved YOLOv5
Chen, R., Liu, Z., Ou, W., & Zhang, K. (2024) · Electronics · doi:10.3390/electronics13214158 · Cited by 11
YOLODrone+: Improved YOLO Architecture for Object Detection in UAV Images
Şahin, Ö., & Özer, S. (2022) · Signal Processing and Communications Applications Conference (SIU) · doi:10.1109/siu55565.2022.9864746 · Cited by 10
Pushing the Accuracy of Thai Food Image Classification with Transfer Learning
Ittisoponpisan, S., Kaipan, C., Ruang-on, S., Thaiphan, R., & Songsri-in, K. (2022) · Engineering Journal · doi:10.4186/ej.2022.26.10.57 · Cited by 12
“Additionally, DCNNs have also been adopted to solve many other machine learning problems such as Image Detection [9, 10, 11, 12], Voice Recognition [13, 14, 15, 16], and Natural Language Processing [17, 18, 19].”
MethodSwarm Foraging Under Communication and Vision Uncertainties
Obute, S. O., Kilby, P., Doğar, M. R., & Boyle, J. H. (2022) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2022.3164044 · Cited by 11
“However, the field of computer vision has significantly progressed due in part to advances in deep neural networks [16].”
BackgroundShen, G., Zhao, D., & Zeng, Y. (2022) · SSRN Electronic Journal · doi:10.2139/ssrn.4018613 · Cited by 10
Machine Vision based Sample-Tube Localization for Mars Sample Return
Daftry, S., Ridge, B., Seto, W., Pham, T.-H., Ilhardt, P., Maggiolino, G., van der Merwe, M., Brinkman, A., Mayo, J., Kulczyski, E., et al. (2021) · 2021 IEEE Aerospace Conference (50100) · doi:10.1109/aero50100.2021.9438364 · Cited by 10
“Object detection and localization, as of one the most fundamental and challenging problems in machine vision, has received great attention in recent years - see [22] for a review.”
BackgroundCeci n’est pas une chaise: Emerging practices in designer-AI collaboration
van der Burg, V., Akdag Salah, A., Chandrasegaran, S., & Lloyd, P. (2022) · Proceedings of DRS · doi:10.21606/drs.2022.653 · Cited by 10
“Object detection generally applies two core methods: those pertaining to neural networks or those that are based on non-neural approaches (Zou et al., 2019).”
BackgroundAdvancing Autonomous Aerial Refueling with Deep-Neural-Network-Based Image Segmentation
Mwaffo, V., Miller, D., & Costello, D. H. (2025) · Journal of Aerospace Information Systems · doi:10.2514/1.i011508 · Cited by 11
Alasmari, H., Amoudi, G., & Alghamdi, H. S. (2025) · Diagnostics · doi:10.3390/diagnostics15182301 · Cited by 13
“However, the model is still computationally expensive and time-consuming compared to one-stage detector models, so it is not used in some fields [22].”
InfluentialEmulating human-like adaptive vision for efficient and flexible machine visual perception
Wang, Y., Yang, Y., Yue, Y., Wang, H., Jiang, H., Han, Y., Ni, Z., Pu, Y., Shi, M., Lu, R., et al. (2025) · Nature Machine Intelligence · doi:10.1038/s42256-025-01130-7 · Cited by 38
“…models have exhibited substantial progress, approaching or surpassing expert-level performance across diverse fields, including large-scale image recognition 25–29 , object detection 30 , open-world visual perception 31 , medical image analysis 19–21 , 32– 34 and multimodal understanding 10– 13 .”
MuTrans: Multiple Transformers for Fusing Feature Pyramid on 2D and 3D Object Detection
Xie, B., Yang, L., Wei, A., Weng, X., & Li, B. (2023) · IEEE Transactions on Image Processing · doi:10.1109/tip.2023.3299190 · Cited by 9
“1) Spatial-Awareness: The convolutional neural network was limited in learning spatial transformations existed in images [7].”
BackgroundAnalyzing cultural relationships visual cues through deep learning models in a cross-dataset setting
Stacchio, L., Angeli, A., Lisanti, G., & Marfia, G. (2023) · Neural Computing and Applications · doi:10.1007/s00521-023-08966-3 · Cited by 8
“These results motivated us to perform an additional visual analysis to qualitatively explore the possible time-shift phenomenon in a cross-dataset setting.”
HAM-Transformer: A Hybrid Adaptive Multi-Scaled Transformer Net for Remote Sensing in Complex Scenes
Ren, K., Chen, X., Wang, Z., Liang, X., Chen, Z., & Miao, X. (2023) · Remote Sensing · doi:10.3390/rs15194817 · Cited by 9
Kim, S. W., Cheon, J., Choi, Y. H., Hwang, J., Shin, S.-M., Cho, Y. J., Lee, S., & Lee, S. B. (2023) · ULTRASONOGRAPHY · doi:10.14366/usg.23153 · Cited by 12
“Among the available object detection architectures, YOLO is the most appropriate for this purpose, as it offers the fastest predictions with sufficient accuracy [27].”
BackgroundAdvancements in Deep-Learning-Based Object Detection in Challenging Environments
Mukhopadhyay, A., & Biswas, P. (2024) · Wireless World Research and Trends Magazine · doi:10.13052/2794-7254.001 · Cited by 9
“Zou et al. [4] provide a comprehensive overview of the history, challenges, and recent advances in object detection.”
BackgroundMethodInfluentialAdversarial Attack on Yolov5 for Traffic and Road Sign Detection
Jain, S. (2024) · International Conference on Applied Artificial Intelligence (ICAPAI) · doi:10.1109/icapai61893.2024.10541282 · Cited by 13
Sun, Y., & Yin, B. (2024) · PLoS ONE · doi:10.1371/journal.pone.0300976 · Cited by 11
“For example, in Pascal VOC [24] and COCO public data sets, YOLOv5 training samples contain 16551 images”
Su, Q., & Mu, J. (2024) · Automation · doi:10.3390/automation5020011 · Cited by 11
Tang, J., Feng, Z., Liao, P., Chen, L., & Xiao, X. (2024) · Measurement Science and Technology · doi:10.1088/1361-6501/ad5de5 · Cited by 10
“The development of deep learning allows more and more researchers to use technologies such as object detection [22], semantic segmentation [23], and instance segmentation [24] to obtain semantic information of the environment.”
On-Edge High-Throughput Collaborative Inference for Real-Time Video Analytics
Wang, X., Shen, M., & Yang, K. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3424235 · Cited by 13
“Based on the prevalence of the computer vision technology, especially deep neural networks (DNNs), machines have reached or even exceeded the human level in video analytics tasks, such as object recognition [5] and detection [6].”
BackgroundNasraoui, A., Selmi, T., & Hajaiej, Z. (2024) · IEEE International Conference on Advanced Systems and Emergent Technologies (IC_ASET) · doi:10.1109/ic_aset61847.2024.10596153 · Cited by 11
“The key contribution of Faster R-CNN is the introduction of a Region Proposal Network (RPN) [14], which allows regions to be proposed almost free of charge [5] [15].”
MethodA Deep-Learning Approach to Detect and Classify Heavy-Duty Trucks in Satellite Images
Liu, X., Li, Y., Sizemore, L., Xie, X. S., & Wu, J. Y. (2024) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2024.3431452 · Cited by 12
“With the recent advancement of neural network architectures, deep learning methods are widely used in object detection tasks given their higher effectiveness compared to the traditional image processing methods [28].”
MethodJia, B., Ge, W., Cheng, J., et al. (2024) · IEEE photonics journal · doi:10.1109/jphot.2024.3453116 · Cited by 9
“Inspired by the success of deep learning in advanced computer vision tasks such as classification, detection, and segmentation [24], [25], [26], [27], [28], we introduce deep neural networks (DNNs) to obtain accurate light source position from captured images with various light spot sizes and shapes.”
MethodPerformance Evaluation of YOLOv5 on Edge Devices for Personal Protective Equipment Detection
Miglionico, G. C., Ducange, P., Marcelloni, F., Vallati, C., & Rienzo, F. D. (2024) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn60899.2024.10651429 · Cited by 11
“Deep learning is widely and successfully used in numerous computer vision applications, such as object recognition [4] [5] and image analysis [6] [7].”
Dang, Y., Chen, J., Chen, P., et al. (2024) · The Visual Computer · doi:10.1007/s00371-024-03634-6 · Cited by 9
“The deep learning-based object detection technology has been widely applied in the field of automation [16–18].”
Enhanced Disease Detection for Apple Leaves with Rotating Feature Extraction
Qiu, Z., Xu, Y., Chen, C., et al. (2024) · Agronomy · doi:10.3390/agronomy14112602 · Cited by 9
ARSOD-YOLO: Enhancing Small Target Detection for Remote Sensing Images
Qiu, Y., Zheng, X., Hao, X., Zhang, G., Leí, T., & Jiang, P. (2024) · Sensors · doi:10.3390/s24237472 · Cited by 11
Luo, F., Bian, W., Jie, B., Dong, H., & Fu, X. (2024) · Signal Image and Video Processing · doi:10.1007/s11760-024-03661-9 · Cited by 13
“This capability is crucial for improving the performance and reliability of drones in various combat scenarios [2, 3].”
Metadata
- Authors
- Zou, Z., Chen, K., Shi, Z., Guo, Y., & Ye, J.
- Affiliations
- Shanghai Artificial Intelligence Laboratory (CN)
- Carleton University (CA)
- Alibaba Group (China) (CN)
- Venue
- Proceedings of the IEEE
- Published
- 2023-03
- Volume
- 111
- Issue
- 3
- Pages
- 257-276
- ISSN
- 0018-9219 (ISSN-L)
- 1558-2256
- OpenAlex
- W4320002812
- Cited by
- 3,689
- References
- 272
- Citations by year
- 2026: 610 · 2025: 1013 · 2024: 940 · 2023: 541
- FWCI
- 280.65
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- Proceedings of the IEEE (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- National Natural Science Foundation of China (62125102)
- National Key Research and Development Program of China
- Fundamental Research Funds for the Central Universities
- 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, evaluation metrics, deep learning
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 2026-10-07, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-07 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
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.