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 401–500 of 3,144
Zhang, H., Yang, Q., Liu, Q., Zhou, W., Jin, Y., Wang, H. E., & Pang, X. (2023) · Automation in Construction · doi:10.1016/j.autcon.2023.105151 · Cited by 18
Deep Learning Based Fire Risk Detection on Construction Sites
Ann, H. J., & Koo, K. Y. (2023) · Sensors · doi:10.3390/s23229095 · Cited by 21
“The field of object detection has witnessed significant development over the past 20 years, typically divided into two distinct periods: the traditional object detection period (prior to 2014) and the deep learning-based detection period (since 2014) [2].”
BackgroundCheng, J., Chen, Q., & Huang, X. (2023) · Fractal and Fractional · doi:10.3390/fractalfract7110820 · Cited by 17
Efficient Detection of Apparent Defects in Subway Tunnel Linings Based on Deep Learning Methods
Zheng, A., Qi, S., Cheng, Y., Wu, D., & Zhu, J. (2024) · Applied Sciences · doi:10.3390/app14177824 · Cited by 19
YOLO for Medical Object Detection (2018–2024)
Soni, A., & Rai, A. (2024) · IEEE International Conference on Electrical Power and Energy Systems (ICEPES) · doi:10.1109/icepes60647.2024.10653506 · Cited by 26
“Real-time object detection and localization have demonstrated remarkable performance by DL-based object detection algorithms [13]–[15].”
MethodZhou, R., Almustafa, M. K., Nehdi, M. L., & Su, H. (2024) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2024.09.039 · Cited by 18
Progressive Representation Learning for Real-Time UAV Tracking
Fu, C., Lei, X., Zuo, H., Yao, L., Zheng, G., & Pan, J. (2024) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros58592.2024.10803050 · Cited by 32
“Deep neural networks (DNNs) are commonly employed to extract object representations in visual tasks [8], [26].”
Li, Q., Zhang, Y., Fang, L., Kang, Y., Li, S., & Zhu, X. X. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2025.3543270 · Cited by 32
“Object detection technology is a fundamental area of research in unmanned aerial vehicle image processing tasks, with its development can be traced back to early image processing techniques, which evolved from traditional methods to advanced deep learning algorithms [25].”
QBox: Partial Transfer Learning With Active Querying for Object Detection
Tang, Y.-P., Wei, X.-S., Zhao, B., & Huang, S.-J. (2023) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2021.3111621 · Cited by 17
“OBJECT detection is one of the fundamental problems in computer vision [1].”
BackgroundMulti-Task Learning-Enabled Automatic Vessel Draft Reading for Intelligent Maritime Surveillance
Qu, J., Liu, R. W., Zhao, C., et al. (2023) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2023.3327824 · Cited by 16
“To address this issue, we employed YOLOv8 [9] as the baseline for the draft mark detection network and trained it on the proposed dataset.”
MethodSelf-citationTSegLab: Multi-stage 3D dental scan segmentation and labeling
Rekik, A., Hamadou, A. B., Smaoui, O., Bouzguenda, F., Pujades, S., & Boyer, E. (2024) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2024.109535 · Cited by 16
VSTDet: A lightweight small object detection network inspired by the ventral visual pathway
Niu, Y., Lin, C., Jiang, X., & Qu, Z. (2025) · Applied Soft Computing · doi:10.1016/j.asoc.2025.112775 · Cited by 20
RescueADI: Adaptive Disaster Interpretation in Remote Sensing Images With Autonomous Agents
Liu, Z., Zhao, D., Yuan, B., & Jiang, Z. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2025.3532594 · Cited by 42
“Unlike object classification datasets of natural images [31], [32], [33], [34] that focus on the foreground object in the image, scene classification in RSIs takes into account the background information.”
Saeedizadeh, N., Jalali, S. M. J., Khan, B., & Mohamed, S. M. K. (2025) · Expert Systems · doi:10.1111/exsy.70020 · Cited by 21
Review: Multiobject tracking in livestock − from farm animal management to state-of-the-art methods
Nidhi, M. H., Liu, K., & Flay, K. J. (2025) · animal · doi:10.1016/j.animal.2025.101503 · Cited by 22
Syed, S., Anderssen, K. E., Stormo, S. K., & Kranz, M. (2023) · Scientific Reports · doi:10.1038/s41598-023-29665-y · Cited by 20
Vision-Based Formation Control for an Outdoor UAV Swarm With Hierarchical Architecture
Ma, L., Meng, D., Huang, X., & Zhao, S. (2023) · IEEE Access · doi:10.1109/access.2023.3296603 · Cited by 20
“Zou et al. [14] classified the object detectors in the last two decades as traditional detectors and Deep Learning (DL) based detectors.”
BackgroundA Comprehensive Analysis of Real-Time Car Safety Belt Detection Using the YOLOv7 Algorithm
Nkuzo, L., Sibiya, M., & Markus, E. D. (2023) · Algorithms · doi:10.3390/a16090400 · Cited by 26
An Innovative Faster R-CNN-Based Framework for Breast Cancer Detection in MRI
Raimundo, J. N. C., Fontes, J. P. P., Magalhães, L., & Guevara, M. A. (2023) · Journal of Imaging · doi:10.3390/jimaging9090169 · Cited by 17
“Detection is an important process of CV, and a preliminary process for other processes such as segmentation and classification [24].”
MethodChen, S., Zhang, C., & Mu, H. (2024) · Neural Processing Letters · doi:10.1007/s11063-024-11571-7 · Cited by 24
A systematic literature review of computer vision applications in robotized wire harness assembly
Wang, H., Salunkhe, O., Quadrini, W., Lämkull, D., Ore, F., Despeisse, M., Fumagalli, L., Stahre, J., & Johansson, B. (2024) · Advanced Engineering Informatics · doi:10.1016/j.aei.2024.102596 · Cited by 32
Fei, M., Shen, Z., Song, Z., Wang, X., Cao, M., Yao, L., Zhao, X., Wang, Q., & Zhang, L. (2024) · Neural Networks · doi:10.1016/j.neunet.2024.106405 · Cited by 20
Deep Learning-Based Target-to-User Association in Integrated Sensing and Communication Systems
Cazzella, L., Mizmizi, M., Tagliaferri, D., Badini, D., Matteucci, M., & Spagnolini, U. (2024) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2024.3438128 · Cited by 17
“We refer the interested reader to [21] for an exhaustive survey on TD models.”
MethodA multi-scale rotated ship targets detection network for remote sensing images in complex scenarios
Li, S., Yan, F., Liu, Y., et al. (2025) · Scientific Reports · doi:10.1038/s41598-025-86601-y · Cited by 16
Image-based deep learning for smart digital twins: a review
Islam, M. R., Subramaniam, M., & Huang, P.-C. (2025) · Artificial Intelligence Review · doi:10.1007/s10462-024-11002-y · Cited by 29
“The artifacts of this development are grouped by commonality, and thus, one-stage and two-stage detectors [24], [25] become canonical categories for meta-architectures.”
Coronamask: A Face Mask Detector for Real-Time Data
Gupta, C. (2020) · International Journal of Advanced Trends in Computer Science and Engineering · doi:10.30534/ijatcse/2020/212942020 · Cited by 22
Jing, N., Wang, Y., Di, K., Xie, B., Zhao, C., Wang, B., Sun, S., Deng, X., Zhang, H., & Sheng, R. (2025) · Sensors · doi:10.3390/s25010243 · Cited by 20
Wang, C., Song, C., Xu, T., & Jiang, R. (2025) · Agriculture · doi:10.3390/agriculture15111213 · Cited by 22
“In order to scientifically and accurately evaluate different deep learning target-detection algorithms and determine their applicability and advantages in specific tasks, a reliable performance evaluation index system is particularly critical [56].”
Wang, Z., Yan, F., Wang, L., Yin, Y., & Lin, J. (2025) · Neural Networks · doi:10.1016/j.neunet.2025.107782 · Cited by 23
Palaniappan, D., Jain, R., Premavathi, T., Parmar, K. J., Ghribi, W., Ahmed, A. M., & Ahmad, N. (2025) · IEEE Access · doi:10.1109/access.2025.3599358 · Cited by 28
“In YOLO-based detection, key indicators include Intersection over Union (IoU), mean Average Precision (mAP), recall, and inference speed [69], [91], [92], [93], [94], [95], [96], [97], [98], [99], [100].”
A survey of transformer architectures for autonomous driving
Chu, F., Li, H., Xie, L., & Zhao, J. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.130338 · Cited by 28
Development and evolution of YOLO in object detection: A survey
Tian, Y., Xu, W., Yang, B., Yang, X., Guo, H., Wang, G., & Yu, H. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.132436 · Cited by 42
SO-DETR: Leveraging Dual-Domain Features and Knowledge Distillation for Small Object Detection
Zhang, H., Zhang, H., Mei, A., Gan, Z., & Zhu, G.-N. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11229240 · Cited by 44
“Object detection is a core task in computer vision that focuses on identifying and localizing objects in images [1].”
Guo, S., Wang, D., Feng, Z., & Guo, W. (2021) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2021.3116040 · Cited by 17
“Its applications are broad, including remote sensing [9], transportation control [10], fixation prediction [11], [12], and face recognition [13].”
BackgroundOptimized Small Waterbird Detection Method Using Surveillance Videos Based on YOLOv7
Lei, J., Shuhui, G., Rasool, M. A., Fan, R., Jia, Y., & Lei, G. (2023) · Animals · doi:10.3390/ani13121929 · Cited by 15
“Among recently published and recognized works [14], object detection based on DL remains a fundamental task in the field of artificial intelligence.”
BackgroundStrecker, J., Akhunov, K., Carbone, F., García, K., Bektaş, K., Gomez, A., Mayer, S., & Yıldırım, K. S. (2023) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3610879 · Cited by 18
“In recent years, thanks to the processing power of machines and the availability of training data, Convolutional Neural Networks (CNNs) started gaining a lot of attention [89].”
BackgroundHigh-Quality Object Detection Method for UAV Images Based on Improved DINO and Masked Image Modeling
Lu, W., Niu, C., Lan, C., Liu, W., Wang, S., Yu, J., & Hu, T. (2023) · Remote Sensing · doi:10.3390/rs15194740 · Cited by 18
Jiang, Y., Tang, Y.-J., & Ying, C. (2023) · Electronics · doi:10.3390/electronics12234820 · Cited by 16
Ran, G., Yao, X., Wang, K., Ye, J., & Ou, S. (2024) · Measurement Science and Technology · doi:10.1088/1361-6501/ad1eb6 · Cited by 18
“One of the reasons for this choice is that, among current object detection frameworks such as YOLO, RCNN, and ViT (especially DETR) [48], the ViT-based object detection framework stands out for its highest accuracy.”
Self-citationBenchmarking Automated Machine Learning (AutoML) Frameworks for Object Detection
Oliveira, S. D., Topsakal, O., & Toker, O. (2024) · Information · doi:10.3390/info15010063 · Cited by 20
Real-time and accurate meal detection for meal-assisting robots
Fan, Y., Zhang, L., Zheng, C., et al. (2024) · Journal of Food Engineering · doi:10.1016/j.jfoodeng.2024.111996 · Cited by 15
Ma, H., Li, Y., Gao, Y., Zhang, Z., Abuadbba, A., Fu, A., Al-Sarawi, S. F., Nepal, ., & Abbott, D. (2023) · IEEE Symposium on Reliable Distributed Systems (SRDS) · doi:10.1109/srds60354.2023.00018 · Cited by 35
“Thus, it has been applied to several real-world scenarios, e.g., robot vision, autonomous driving, human-computer interaction, content-based image retrieval, intelligent video surveillance, augmented reality, and pedestrian detection [1], [2].”
BackgroundTransfer learning with generative models for object detection on limited datasets
Paiano, M., Martina, S., Giannelli, C., & Caruso, F. (2024) · Machine Learning Science and Technology · doi:10.1088/2632-2153/ad65b5 · Cited by 22
“One of the traditional ML approaches is supervised learning that requires the input data to be labelled with the desired output of the model to be trained.”
Advanced RFID-Robot With Rotating Antennas for Smart Inventory in High-Density Shelving Systems
Motroni, A., D’Avella, S., Buffi, A., Tripicchio, P., Unetti, M., Cecchi, G., & Nepa, P. (2024) · IEEE Journal of Radio Frequency Identification · doi:10.1109/jrfid.2024.3369470 · Cited by 20
“Machine vision is the most commonly utilized technology for autonomous system navigation and object detection [7], [8], [9].”
BackgroundTongue feature dataset construction and real-time detection
Chang, W.-H., Chen, C.-C., Wu, H.-K., Hsu, P.-C., Lo, L.-C., Chu, H., & Chang, H. (2024) · PLoS ONE · doi:10.1371/journal.pone.0296070 · Cited by 19
“YOLO is famous for its speed, and there are still many other object detection models, each with its own strengths and weaknesses [48, 49].”
BackgroundImproved YOLOX-DeepSORT for Multitarget Detection and Tracking of Automated Port RTG
YU, Z., Zheng, X., Yang, J., & Su, J. (2024) · IEEE Open Journal of the Industrial Electronics Society · doi:10.1109/ojies.2024.3388632 · Cited by 15
“State-of-the-art (SOTA) target detection algorithms predominantly leverage deep learning networks, which can be broadly categorized into two-stage algorithms and one-stage algorithms based on their detection processes [2].”
BackgroundXiuzai, 张. Z., Tao, 沈. S., & Dai, 许. X. (2024) · Laser & Optoelectronics Progress · doi:10.3788/lop231803 · Cited by 17
Object Detection Using Convolutional Neural Networks: A Comprehensive Review
Issaoui, H., ElAdel, A., & Zaied, M. (2024) · IEEE International Symposium on Real-Time Distributed Computing (ISORC) · doi:10.1109/isorc61049.2024.10551342 · Cited by 21
“Apply a single neural network to the entire image [15].”
BackgroundHuman–AI Collaboration for Remote Sighted Assistance: Perspectives from the LLM Era
Yu, R., Lee, S., Xie, J., Billah, S. M., & Carroll, J. M. (2024) · Future Internet · doi:10.3390/fi16070254 · Cited by 23
“Object detection [102] aims to detect instances of objects of predefined categories (e.g., humans, cars) in images or videos.”
Huangfu, Z., Li, S., & Yan, L. (2024) · Computers, materials & continua/Computers, materials & continua (Print) · doi:10.32604/cmc.2024.054188 · Cited by 33
“With the wide application of deep neural network architectures [3] in fields such as image processing [4] and target detection [5] deep learning techniques have been rapidly developed.”
BackgroundNoh, K. M., Hong, S. K., Makonin, S., & Lee, Y. (2024) · IEEE Access · doi:10.1109/access.2024.3459629 · Cited by 21
“These applications involve predicting and identifying specific objects in photos or videos [1], [2], [3], [4], [5], [6], [7], [8].”
BackgroundProjecting Points to Axes: Oriented Object Detection via Point-Axis Representation
Zhao, Z., Xue, Q., He, Y., Bai, Y., Wei, X., & Gong, Y. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-73390-1_10 · Cited by 44
A lightweight deep-learning model for parasite egg detection in microscopy images
Xu, W., Zhai, Q., Liu, J., Xu, X., & Hua, J. (2024) · Parasites & Vectors · doi:10.1186/s13071-024-06503-2 · Cited by 25
“Object detection algorithms can be divided into two-stage detectors and one-stage detectors according to the detection process [20].”
BackgroundHuang, Y., Liu, R. W., Lin, Y., Kang, J., Zhu, F., & Wang, F. (2024) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2024.3488497 · Cited by 17
“Despite achieving a significant improvement in detection speed, the localization accuracy of YOLO witnessed a decline compared to two-stage detection methods, particularly for small objects [17].”
Lightweight UAV Small Target Detection and Perception Based on Improved YOLOv8-E
Zhao, Y., Wang, L., Lei, G., Guo, C., & Ma, Q. (2024) · Drones · doi:10.3390/drones8110681 · Cited by 21
Faseeh, M., Bibi, M., Khan, M. A., & Kim, D. (2024) · Results in Engineering · doi:10.1016/j.rineng.2024.103482 · Cited by 24
Synthetic generated data for intelligent corrosion classification in oil and gas pipelines
Ramos, L., Casas, E., & Rivas, F. (2024) · Intelligent Systems with Applications · doi:10.1016/j.iswa.2024.200463 · Cited by 16
A Survey of Deep Learning Approaches for Pedestrian Detection in Autonomous Systems
Sukkar, M., Jadeja, R. B., Shukla, M., & Mahadeva, R. (2024) · IEEE Access · doi:10.1109/access.2024.3524501 · Cited by 20
Zhang, H., Wu, S., Luo, X., Huang, Y., & Li, H. (2025) · Automation in Construction · doi:10.1016/j.autcon.2025.105962 · Cited by 20
Safety Helmet Detection in Industrial Environment using Deep Learning
Kamboj, A., & Powar, N. (2020) · doi:10.5121/csit.2020.100518 · Cited by 15
Er, M. J., Jie, C., Zhang, Y., & Gao, W. (2023) · doi:10.36227/techrxiv.19350389 · Cited by 17
Er, M. J., Chen, J., Zhang, Y., & Gao, W. (2023) · doi:10.36227/techrxiv.19350389.v4 · Cited by 19
Shia, W.-C., & Ku, T.-H. (2024) · Diagnostics · doi:10.3390/diagnostics14242875 · Cited by 16
“Recent advancements in object detection algorithms [11], particularly deep learning models [12], have revolutionized medical imaging analysis by enabling accurate detection of complex features such as microcalcifications.”
Rizk, M., & Bayad, I. (2025) · IEEE Access · doi:10.1109/access.2025.3529484 · Cited by 14
“DPM has introduced concepts like mixture models, hard negative mining (HNM), bounding box regression, and context priming [25].”
InfluentialLarge vision-language models enabled novel objects 6D pose estimation for human-robot collaboration
Xia, W., Zheng, H., Xu, W., & Xu, X. W. (2025) · Robotics and Computer-Integrated Manufacturing · doi:10.1016/j.rcim.2025.103030 · Cited by 22
Dong, L., Zhu, H., Ren, H., Lin, T., & Lin, K.-P. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.128247 · Cited by 15
Fade3D: Fast and Deployable 3D Object Detection for Autonomous Driving
Ye, W., Xia, Q., Wu, H. Y., Dong, Z., Zhong, R., Wang, C., & Wen, C. (2025) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2025.3568418 · Cited by 28
“Despite the rapid development, there are still challenges in inference efficiency [15], [16].”
NIRNet: Noise Incentive Robust Network in Remote Sensing Object Detection Under Cloud Corruption
Zhang, P., Cheng, G., Lang, C., Xie, X., & Han, J. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2025.3581342 · Cited by 32
“Extensive pioneering works in object detection attempt to develop a faster and stronger detector [10], [11], [12], [13], [14], [15].”
A review of artificial intelligence for sports: Technologies and applications
Li, W., Liu, M., Liu, J., Zhang, B., Yu, T., Guo, Y., & Dai, Q. (2025) · Intelligent Sports and Health · doi:10.1016/j.ish.2025.05.001 · Cited by 27
Self-citationLightweight underwater object detection method based on multi-scale edge information selection
Cai, S., Zhou, X., Cai, W., Wei, L., & Mo, Y. (2025) · Scientific Reports · doi:10.1038/s41598-025-13566-3 · Cited by 28
Lightweight Swin Transformer for high-precision industrial defect detection in smart manufacturing
Shin, J., Hamza, M., Kim, H., Jo, J., Park, B., & Kim, Y. H. (2025) · Alexandria Engineering Journal · doi:10.1016/j.aej.2025.08.055 · Cited by 21
Strengthening Small Object Detection in Adapted RT-DETR Through Robust Enhancements
Madan, M., & Reich, C. (2025) · Electronics · doi:10.3390/electronics14193830 · Cited by 20
Habash, N. M., Alqumsan, A. A., & Zhou, T. (2025) · Sensors · doi:10.3390/s25247563 · Cited by 35
Zhang, X., Cao, X., Zhang, H., Shen, Y., Yuan, X., Cui, Z., & Lu, Z. (2023) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2023.3324145 · Cited by 15
“After that, the YOLOv2 ∼ v5 algorithm are proposed with increased performance, and diverse versions can meet different requirements [22].”
BackgroundEnergy and Time-Aware Inference Offloading for DNN-based Applications in LEO Satellites
Chen, Y., Zhang, Q., Zhang, Y., Ma, X., & Zhou, A. (2023) · IEEE International Conference on Network Protocols (ICNP) · doi:10.1109/icnp59255.2023.10355644 · Cited by 17
“This involves capturing ground images and using a Deep Neural Network (DNN) model to infer occurrences such as forest fires, terrain, and geomorphic changes [2], [3].”
MethodChen, B., Xue, F., & Song, H. (2024) · Remote Sensing · doi:10.3390/rs16020237 · Cited by 20
Hou, L. X., Ma, C., Tang, W., Zhou, Y., Ye, S., Chen, X., Zhang, X., Yu, C., Chen, A., Zheng, D., et al. (2024) · Geoenergy Science and Engineering · doi:10.1016/j.geoen.2024.212662 · Cited by 17
Li, Z., Wang, Y., Zhang, Y., Gao, Y., Zhao, Z., Feng, H., & Zhao, T. (2024) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2024.3356507 · Cited by 27
“O BJECT detection, which needs to accurately distinguish the locations and categories of instances in complex remote sensing images, is an essential and vital task in remote sensing imagery interpretation and has made surprising progress with the rise of deep learning [1].”
BackgroundDeepSeaNet: A Bio-Detection Network Enabling Species Identification in the Deep Sea Imagery
Liu, A., Liu, Y., Xu, K., Zhao, F., Zhou, Y., & Li, X. (2024) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2024.3359350 · Cited by 14
“Object detection algorithm based on deep learning offers high accuracy and speed for localizing and classifying objects, making it a popular choice in various fields such as autonomous driving, surveillance security, robot vision, traffic monitoring, and augmented reality [9], [10].”
BackgroundMonoAux: Fully Exploiting Auxiliary Information and Uncertainty for Monocular 3D Object Detection
Li, Z., Zheng, W., Yang, L., Ma, L., Zhou, Y., & Peng, Y. (2024) · Cyborg and Bionic Systems · doi:10.34133/cbsystems.0097 · Cited by 25
Ghelmani, A., & Hammad, A. (2024) · Computer-Aided Civil and Infrastructure Engineering · doi:10.1111/mice.13157 · Cited by 19
SAFE: Saliency-Aware Counterfactual Explanations for DNN-based Automated Driving Systems
Samadi, A., Shirian, A., Koufos, K., Debattista, K., & Dianati, M. (2023) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc57777.2023.10422102 · Cited by 20
“Deep Neural Networks (DNNs) have achieved remarkable success in solving complex tasks, ranging from image recognition [1] to natural language processing [2] and many others.”
BackgroundChotikunnan, P., Puttasakul, T., Chotikunnan, R., Panomruttanarug, B., Sangworasil, M., & Srisiriwat, A. (2023) · Journal of Robotics and Control (JRC) · doi:10.18196/jrc.v4i3.17932 · Cited by 21
Human figure detection in Han portrait stone images via enhanced YOLO-v5
Zhang, J., Zhang, Y., Liu, J., Lan, Y., & Zhang, T. (2024) · Heritage Science · doi:10.1186/s40494-024-01232-2 · Cited by 19
General Deformable RoI Pooling and Semi-Decoupled Head for Object Detection
Han, B., He, L., Yu, Y., Lu, W. B., & Gao, X. (2024) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2024.3391899 · Cited by 15
“I MAGE is one of the most important carries of information, and the foundation of understanding image information is to know what objects are and their positions in an image, i.e., what objects are where [1].”
BackgroundYe, F., & Zhou, B. (2024) · Sensors · doi:10.3390/s24134108 · Cited by 14
“In recent years, with the technological advancement of optical sensors, remote sensing has become increasingly prevalent in grassland resource surveys [15], precision agriculture [16], and target detection [17].”
BackgroundPMHO: Point-Supervised Oriented Object Detection Based on Segmentation-Driven Proposal Generation
Zhang, S., Long, J., Xu, Y., & Mei, S. (2024) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2024.3450732 · Cited by 23
“Detailed annotations in these datasets, including precise object category, location, scale, and quantity information, are annotated, which greatly facilitate the advancement of the oriented object detection community [13], [14].”
BackgroundMethodLi, H., & Ma, H. (2024) · Applied Soft Computing · doi:10.1016/j.asoc.2024.112181 · Cited by 18
Desai, M. M., Mewada, H. K., Pires, I. M., & Roy, S. (2024) · Procedia Computer Science · doi:10.1016/j.procs.2024.11.096 · Cited by 14
UAV-based person re-identification: A survey of UAV datasets, approaches, and challenges
Albaluchi, Y., Fu, B., Damer, N., Ramachandra, R., & Raja, K. B. (2024) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2024.104261 · Cited by 17
Chen, X., & Lin, C. (2024) · Digital Signal Processing · doi:10.1016/j.dsp.2024.104957 · Cited by 17
A Survey of Zero-Shot Object Detection
Cao, W., Yao, X., Xu, Z., Ye, L., Pan, Y., & Ming, Z. (2025) · Big Data Mining and Analytics · doi:10.26599/bdma.2024.9020098 · Cited by 18
Liu, F., Yao, L. X., Zhang, C., Wu, T., Zhang, X., Jiang, X., & Zhou, J. W. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2025.3564261 · Cited by 44
“Following the same evaluation metrics of previous work [63], [64], [65], we employed the average precision (AP) [66] as the evaluation metrics on accuracy.”
Multiscale Traffic Sign Detection Method in Complex Environment Based on YOLOv4
Wang, Y., Bai, M., Wang, M., Zhao, F., & Guo, J. (2022) · Computational Intelligence and Neuroscience · doi:10.1155/2022/5297605 · Cited by 14
“Zou et al. [13] reviewed more than 400 papers on the development of object detection technology, including historical milestone detectors, detection frameworks, evaluation indicators, data sets, acceleration techniques, and detection applications systematically and comprehensively presenting the…”
BackgroundGUARDIAN: A Hardware-Assisted Distributed Framework to Enhance Deep Learning Security
Cai, Z., Ren, B., Ma, R., Guan, H., Tian, M., & Wang, Y. (2023) · IEEE Transactions on Computational Social Systems · doi:10.1109/tcss.2023.3262289 · Cited by 15
“It is widely used in image classification [1], image synthesis [2], object detection [3], and tracking [4] in the field of computer vision.”
MethodUnderstanding How Blind Users Handle Object Recognition Errors: Strategies and Challenges
Hong, J., & Kacorri, H. (2024) · The 26th International ACM SIGACCESS Conference on Computers and Accessibility · doi:10.1145/3663548.3675635 · Cited by 14
ODverse33: Is the New YOLO Version Always Better? A Multi Domain benchmark from YOLO v5 to v11Preprint
Jiang, T., & Zhong, Y. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5538699 · Cited by 28
Pool-mamba: Pooling state space model for low-light image enhancement
Zhang, Q., Shao, M., & Chen, X. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.130005 · Cited by 15
SatCooper: Enhancing Cooperative Inference Analytics for Satellite Service via Multi-Exit DNNs
Zhang, Q., Wang, S., Guan, J., Donta, P. K., Ma, X., Prasad, R. R. V., Dustdar, S., & Liu, X. (2025) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2025.3556457 · Cited by 24
“The applications periodically collect EO data and provide ubiquitous coverage during disaster management [3], [4].”
Building Surface Defect Detection Based on Improved YOLOv8
Lin, X., Meng, Y., Sun, L. J., Yang, X., Leng, C., Li, Y., Niu, Z., Gong, W., & Xiao, X. (2025) · Buildings · doi:10.3390/buildings15111865 · Cited by 21
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.