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 201–300 of 3,144
Oriented SAR Ship Detection Based on Edge Deformable Convolution and Point Set Representation
Guan, T., Chang, S., Deng, Y., et al. (2025) · Remote Sensing · doi:10.3390/rs17091612 · Cited by 33
“Although researchers have conducted extensive studies on ship detection in SAR images and proposed numerous detection models [10–12], the technology for detecting ships in SAR imagery still encounters several challenges [13–15].”
A Benchmark Review of YOLO Algorithm Developments for Object Detection
Hua, Z., Aranganadin, K., Yeh, C.-C., Hai, X., Huang, C.-Y., Leung, T. C., Hsu, H., Lan, Y., & Lin, M. (2025) · IEEE Access · doi:10.1109/access.2025.3586673 · Cited by 57
“Algorithms like support vector machines (SVMs) [11], random decision forests [12], and convolutional neural networks (CNNs) [13] enabled significant breakthroughs in tasks such as image classification [14], object detection [15], and semantic segmentation [16].”
Review on One-Stage Object Detection Based on Deep Learning
Zhang, H., & Cloutier, R. S. (2022) · ICST Transactions on e-Education and e-Learning · doi:10.4108/eai.9-6-2022.174181 · Cited by 45
“At present, it is closely related to the development of the Internet of Things (IoT), which has been highly recognized by the society in the fields of video surveillance and intelligent transportation [1-3].”
BackgroundRethinking Attentive Object Detection via Neural Attention Learning
Ge, C., Song, Y., Ma, C., Qi, Y., & Luo, P. (2023) · IEEE Transactions on Image Processing · doi:10.1109/tip.2023.3251693 · Cited by 33
“Object detection has been sufficiently surveyed in [8] and [9].”
BackgroundAlberto, J., Ruiz-Sarmiento, J.-R., & González-Jiménez, J. (2023) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2023.107365 · Cited by 40
Near-Edge Computing Aware Object Detection: A Review
Setyanto, A., Sasongko, T. B., Fikri, M. A., & Kim, I. K. (2023) · IEEE Access · doi:10.1109/access.2023.3347548 · Cited by 46
“Object detection development during the past two decades was provided by [13].”
BackgroundFEB-YOLOv8: A multi-scale lightweight detection model for underwater object detection
Zhao, Y., Sun, F., & Wu, X. (2024) · PLoS ONE · doi:10.1371/journal.pone.0311173 · Cited by 47
Real-time and high-accuracy defect monitoring for 3D concrete printing using transformer networks
Zhao, H., Sun, J., Wang, X., Wang, Y., Su, Y., Wang, J., & Wang, L. (2024) · Automation in Construction · doi:10.1016/j.autcon.2024.105925 · Cited by 34
A Deep Reinforcement Learning Based Real-Time Solution Policy for the Traveling Salesman Problem
Ling, Z., Zhang, Y., & Chen, X. (2023) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2023.3256563 · Cited by 35
“Mature structures have been widely applied in object detection [23], semantic segmentation [24], medical [25], et al. Some literature attempted to solve the multiagent path finding (MAPF) problem with DCNNs [26], [27].”
BackgroundYOLO-CSM-Based Component Defect and Foreign Object Detection in Overhead Transmission Lines
Liu, C., Ma, L., Sui, X., Guo, N., Yang, F., Yang, X., Huang, Y., & Wang, X. (2023) · Electronics · doi:10.3390/electronics13010123 · Cited by 40
A Lightweight Model of Underwater Object Detection Based on YOLOv8n for an Edge Computing Platform
Fan, Y., Zhang, L., & Li, P. (2024) · Journal of Marine Science and Engineering · doi:10.3390/jmse12050697 · Cited by 36
Efficient forest fire detection based on an improved YOLO model
Cao, L., Shen, Z., & Xu, S. (2024) · Visual Intelligence · doi:10.1007/s44267-024-00053-y · Cited by 42
“The first is the two-stage detection strategy based on regional targets [7], such as region-based convolutional neural network (R-CNN) [8] and Fast R-CNNs [9, 10], which has high accuracy but moves slowly.”
An efficient detector for detecting surface defects on cold-rolled steel strips
Chen, S., Jiang, S., Wang, X., Sun, P., Hua, C., & Sun, J. (2024) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2024.109325 · Cited by 43
Open World Object Detection: A Survey
Li, Y., Wang, Y., Wang, W., Lin, D., Li, B., & Yap, K. (2024) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2024.3480691 · Cited by 66
“Although many comprehensive review papers on conventional object detection exist, such as [27], [28], [29], [30], [31], they do not fully address OWOD problems.”
Wang, H., Pan, C., Guo, X. J., Ji, C., & Deng, K. (2021) · Wiley Interdisciplinary Reviews Computational Statistics · doi:10.1002/wics.1547 · Cited by 51
The challenge of comprehensive nailfold videocapillaroscopy practice: a further contribution
Gracia-Tello, B., Ibáñez, E. R., Mateo, P. F., Comet, L. S., Robles, E. M., Blanco, J. J. R., Marí-Alfonso, B., Garriga, G. E., Parra, J. T., Ortego‐Centeno, N., et al. (2021) · Clinical and Experimental Rheumatology · doi:10.55563/clinexprheumatol/6usce8 · Cited by 40
“Our first-phase and auxiliary models are object detection models (13), they detect and classify all capillaries of an image in a single pass.”
BackgroundTransfer Learning-Based Lightweight SSD Model for Detection of Pests in Citrus
Wang, L., Shi, W., Tang, Y., Liu, Z., He, X., Xiao, H., & Yang, Y. (2023) · Agronomy · doi:10.3390/agronomy13071710 · Cited by 31
Significant Feature Elimination and Sample Assessment for Remote Sensing Small Objects’ Detection
Ma, W., Wang, X., Zhu, H., Yang, X., Yi, X., & Jiao, L. (2024) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2024.3379436 · Cited by 47
“With the development of computer hardware, deep learning networks have been applied to object detection tasks [5], [6], [7].”
MethodMTP-YOLO: You Only Look Once Based Maritime Tiny Person Detector for Emergency Rescue
Shi, Y., Li, S., Liu, Z., Zhou, Z., & Zhou, X. (2024) · Journal of Marine Science and Engineering · doi:10.3390/jmse12040669 · Cited by 34
“Vision-based object detection algorithms mainly include the following categories: two-stage object detectors represented by the RCNN series, one-stage detectors represented by the YOLO series [1], and Transformer-based DETR series [2].”
MethodInfluentialEL-Net: An efficient and lightweight optimized network for object detection in remote sensing images
Dong, C. Y., Jiang, X., Hu, Y., Du, Y., & Pan, L. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.124661 · Cited by 37
A lightweight weed detection model with global contextual joint features
Guo, A., Jia, Z., Wang, J., Zhou, G., Ge, B., & Chen, W. (2024) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2024.108903 · Cited by 37
Zhang, Z., Yang, Y., Xu, X., Liu, L., Yue, J., Ding, R., Lu, Y., Liu, J., & Qiao, H. (2024) · Remote Sensing · doi:10.3390/rs16163046 · Cited by 45
Chen, L., Li, G., Xie, W., Tan, J., Li, Y., Pu, J., Chen, L., Gan, D., & Shi, W. (2024) · Energies · doi:10.3390/en17205177 · Cited by 47
Explainability-based knowledge distillation
Sun, T., Chen, H., Hu, G., & Zhao, C. (2024) · Pattern Recognition · doi:10.1016/j.patcog.2024.111095 · Cited by 42
YOLOv8-Lite: A Lightweight Object Detection Model for Real-time Autonomous Driving Systems
Yang, M., & Fan, X. (2024) · ICCK Transactions on Emerging Topics in Artificial Intelligence · doi:10.62762/tetai.2024.894227 · Cited by 47
“In summary, these algorithms have their own strengths and weaknesses in terms of detection performance, speed, and applicability, thus requiring comprehensive consideration based on specific application requirements and scene constraints when selecting the appropriate algorithm[22].”
Wu, F., Zhu, R., Meng, F., et al. (2024) · Agronomy · doi:10.3390/agronomy14123002 · Cited by 30
Yang, X. Q., & Mohamed, A. S. A. (2024) · Neurocomputing · doi:10.1016/j.neucom.2024.129248 · Cited by 36
Small Object Detection Method for UAV Remote Sensing Images Based on αS-YOLO
Hou, W., Wu, H., Wu, D., Shen, Y., Liu, Z., Zhang, L., & Li, J. (2025) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2025.3539873 · Cited by 50
“Deep neural networks, such as Faster R-CNN [14], YOLO [15], and their variants, are widely utilized for small object detection, leveraging their strong feature learning and representation capabilities to enhance detection accuracy and robustness [1].”
Deep learning-based rebar detection and instance segmentation in images
Sun, T., Fan, Q., & Shao, Y. (2025) · Advanced Engineering Informatics · doi:10.1016/j.aei.2025.103224 · Cited by 36
Deepness: Deep neural remote sensing plugin for QGIS
Aszkowski, P., Ptak, B., Kraft, M., Pieczyński, D., & Drapikowski, P. (2023) · SoftwareX · doi:10.1016/j.softx.2023.101495 · Cited by 41
Khan, M. A., & Park, H. (2024) · Electronics · doi:10.3390/electronics13020364 · Cited by 33
Adversarial attacks in computer vision: a survey
Li, C., Wang, H., Yao, W., & Jiang, T. (2024) · Journal of Membrane Computing · doi:10.1007/s41965-024-00142-3 · Cited by 42
“Deep neural networks (DNNs) have made great progress in various computer vision tasks [1, 2].”
Karbouj, B., Topalian-Rivas, G. A., & Krüger, J. (2024) · Procedia CIRP · doi:10.1016/j.procir.2024.01.077 · Cited by 38
Lung-YOLO: Multiscale feature fusion attention and cross-layer aggregation for lung nodule detection
Tang, C., Zhou, F., Sun, J., & Zhang, Y. (2024) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2024.106815 · Cited by 31
Efficient Optimized YOLOv8 Model with Extended Vision
Zhou, Q., Wang, Z., Zhong, Y., Zhong, F., & Wang, L. (2024) · Sensors · doi:10.3390/s24206506 · Cited by 41
MISF-Net: Modality-Invariant and -Specific Fusion Network for RGB-T Crowd Counting
Mu, B., Shao, F., Xie, Z., Chen, H., Zhu, Z., & Jiang, Q. (2025) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2025.3535330 · Cited by 37
“With the development of deep learning technology [42], [43], [44], using convolutional neural networks to extract image features [45], [46], [47], [48], [49] has become the mainstream in crowd counting.”
RFAG-YOLO: A Receptive Field Attention-Guided YOLO Network for Small-Object Detection in UAV Images
Wei, C., & Wang, W. (2025) · Sensors · doi:10.3390/s25072193 · Cited by 38
“The deep learning-based object detection methods are broadly categorized into two main paradigms: two-stage [6] and one-stage [7] approaches.”
Kim, J., Kim, G., Yoshitoshi, R., & Tokuda, K. (2025) · Sensors · doi:10.3390/s25154586 · Cited by 47
“Smaller nonmarketable objects and certain classes of impurities are typically underrepresented in datasets; however, their accurate detection remains crucial for proper sorting [4,5].”
A Comprehensive Systematic Review of YOLO for Medical Object Detection (2018 to 2023)Preprint
Qureshi, R., Ragab, M. G., Abdulkadir, S. J., Muneer, A., ALQUSHAIB, A., Sumiea, E. H., & Alhussian, H. (2023) · doi:10.36227/techrxiv.23681679 · Cited by 32
Wu, J., Zheng, R., Jiang, J., Tian, Z., Chen, W., Wang, Z., Yu, F. R., & Leung, V. C. M. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3373028 · Cited by 39
“…effect for our model, moreover, we use eight state of the arts lightweight object detection algorithms, YOLOXs [44], PPYOLOEs [45], YOLOv5s, YOLOv7-tiny-silu [30], YOLOv8s [31], Nanodet [46], ThunderNet [47], and MobileDets [48], to evaluate the detection performance of our lightweight YOLOv8.”
BackgroundMethodInfluentialYao, H., Fan, Y., Liu, Y., Cao, D., Chen, N., Luo, T., Yang, J., Hu, X., Ji, J., & You, Z. (2024) · Journal of Road Engineering · doi:10.1016/j.jreng.2024.01.006 · Cited by 38
Railway rutting defects detection based on improved RT-DETR
Yu, C., & Chen, X. (2024) · Journal of Real-Time Image Processing · doi:10.1007/s11554-024-01530-9 · Cited by 34
Research on the directional bounding box algorithm of YOLO11 in tailings pond identification
He, L.-H., Zhou, Y., Liu, L., Zhang, Y., & Ma, J. (2025) · Measurement · doi:10.1016/j.measurement.2025.117674 · Cited by 37
Guo, H., Wu, Q., & Wang, Y. (2025) · Remote Sensing · doi:10.3390/rs17111920 · Cited by 42
Meng, T., Huang, J. H., Chew, C., Yang, D., & Zhong, Z. (2023) · IEEE Sensors Journal · doi:10.1109/jsen.2023.3260193 · Cited by 35
“Software-level research is popular and focuses on various sensor algorithms [8], [9], [10], [11], [12], including the object detection, traffic signal recognition, sensor fusion, and so on.”
BackgroundLansari, M., Bellafqira, R., Kapusta, K., Thouvenot, V., Bettan, O., & Coatrieux, G. (2023) · Machine Learning and Knowledge Extraction · doi:10.3390/make5040070 · Cited by 44
Zhao, Z., & Li, S. (2024) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2024.3368630 · Cited by 41
“Readers can refer to [22] for an exhaustive literature review on object detection.”
BackgroundLightweight YOLOv8 for Wheat Head Detection
Fang, C., & Yang, X. (2024) · IEEE Access · doi:10.1109/access.2024.3397556 · Cited by 34
“Although two-stage object algorithms offer high detection accuracy, their detection speeds are slow, rendering them unsuitable for real-time detection [33].”
BackgroundPrompt-Driven Dynamic Object-Centric Learning for Single Domain Generalization
Li, D., Wu, A., Wang, Y., & Han, Y. (2024) · 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/cvpr52733.2024.01667 · Cited by 50
Artificial Intelligence in Dermatology: A Review of Methods, Clinical Applications, and Perspectives
Zbrzezny, A. M., & Krzywicki, T. (2025) · Applied Sciences · doi:10.3390/app15147856 · Cited by 49
AccDecoder: Accelerated Decoding for Neural-enhanced Video Analytics
Yuan, T., Mi, L., Wang, W., Dai, H., & Fu, X. (2023) · IEEE Conference on Computer Communications (INFOCOM) · doi:10.1109/infocom53939.2023.10228933 · Cited by 38
“Although existing DNN-aware video enhancement provides a promising way to improve the inference accuracy [16], there is still much room for improvement.”
BackgroundImpact of annotation quality on model performance of welding defect detection using deep learning
Cui, J., Zhang, B., Wang, X., Wu, J., Liu, J., Li, Y., Zhi, X., Zhang, W., & Yu, X. (2024) · Welding in the World · doi:10.1007/s40194-024-01710-y · Cited by 25
“Furthermore, these defects are relatively small, making their annotation challenging [15].”
Combining transformer global and local feature extraction for object detection
Li, T., Zhang, Z., Zhu, M., Cui, Z., & Wei, D. (2024) · Complex & Intelligent Systems · doi:10.1007/s40747-024-01409-z · Cited by 30
“Object detection [1] is a fundamental vision task in computer vision that focuses on categorizing objects for recognition and location localization.”
Dynamic Sensing and Correlation Loss Detector for Small Object Detection in Remote Sensing Images
Shen, C., Qian, J., Wang, C., Yan, D., & Zhong, C. (2024) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2024.3407858 · Cited by 33
IG-GAN: Interactive Guided Generative Adversarial Networks for Multimodal Image Fusion
Sui, C., Yang, G., Hong, D., et al. (2024) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2024.3433619 · Cited by 26
Zhou, W., Cai, C., Li, C., Xu, H., & Shi, H. (2024) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2024.3472805 · Cited by 28
“Object detection is a critical problem in computer vision, aiming to find the bounding boxes and object classes of objects in a given image [25].”
BackgroundBento, J., Paixão, T., & Alvarez, A. B. (2025) · Applied Sciences · doi:10.3390/app15063154 · Cited by 35
FD-YOLO11: A Feature-Enhanced Deep Learning Model for Steel Surface Defect Detection
Dang, Z., & Wang, X. (2025) · IEEE Access · doi:10.1109/access.2025.3559733 · Cited by 35
“One-stage algorithms, on the other hand, are faster and can retrieve all the target objects via a one-step inference process [16].”
Storytelling with Image Data: A Systematic Review and Comparative Analysis of Methods and Tools
Lotfi, F., Beheshti, A., Farhood, H., Pooshideh, M., Jamzad, M., & Beigy, H. (2023) · Algorithms · doi:10.3390/a16030135 · Cited by 24
“Generally, the object detection approaches could be divided into traditional ML-and DL-based categories [38].”
Razzaq, M. A., Hussain, J., Bang, J., Hua, C.-H., Satti, F. A., Rehman, U. U., Bilal, H. S. M., Kim, S. T., & Lee, S. (2023) · Sensors · doi:10.3390/s23094373 · Cited by 36
“So, ROI was utilized to speed up other generic object recognition characteristics using a histogram of oriented gradients (HoG) feature descriptor to deal with feature invariances [28].”
MethodRefined feature fusion for in-field high-density and multi-scale rice panicle counting in UAV images
Chen, Y., Xin, R., Jiang, H., Liu, Y., Zhang, X., & Yu, J. (2023) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2023.108032 · Cited by 28
YOLO Network with a Circular Bounding Box to Classify the Flowering Degree of Chrysanthemum
Park, H., & Park, J. (2023) · AgriEngineering · doi:10.3390/agriengineering5030094 · Cited by 27
YOLO-PAM: Parasite-Attention-Based Model for Efficient Malaria Detection
Zedda, L., Loddo, A., & Ruberto, C. D. (2023) · Journal of Imaging · doi:10.3390/jimaging9120266 · Cited by 31
“One-stage detectors are faster and more compact, making them more suitable for time-critical applications and computationally constrained edge devices [53,54].”
BackgroundUnderwater fish detection and counting using image segmentation
Zhang, L., Qiu, Y., Fan, J., Li, S., Hu, Q., Xing, B., & Xu, J. (2024) · Aquaculture International · doi:10.1007/s10499-024-01402-w · Cited by 30
Kassab, M., Zitar, R. A., Barbaresco, F., & Seghrouchni, A. E. F. (2024) · IEEE Transactions on Aerospace and Electronic Systems · doi:10.1109/taes.2024.3368991 · Cited by 29
“The handcrafted features used in traditional object detection models lack image representation techniques [8].”
BackgroundMethodHV-YOLOv8 by HDPconv: Better lightweight detectors for small object detection
Wang, W., Meng, Y., Li, S., & Zhang, C. (2024) · Image and Vision Computing · doi:10.1016/j.imavis.2024.105052 · Cited by 28
Real-Time Monitoring of Personal Protective Equipment Compliance in Surveillance Cameras
Al-Azani, S., Luqman, H., Alfarraj, M., Sidig, A. A. I., Khan, A. H., & Alhamed, D. H. (2024) · IEEE Access · doi:10.1109/access.2024.3451117 · Cited by 45
“The advances in technology, including machine learning, hyper-performance computing, and cloud data storage, make it possible to develop computer-vision-based systems for several tasks, including image classification [5], object detection [6], and action recognition [7], among others [8].”
BackgroundMethodA Novel YOLOv5_ES based on lightweight small object detection head for PCB surface defect detection
橘高, 義., Li, Z., Wang, Y., & Zhu, S. (2024) · Scientific Reports · doi:10.1038/s41598-024-74368-7 · Cited by 33
Ghazouali, S. E., Gucciardi, A., Venturini, F., Venturi, N., Rueegsegger, M., & Michelucci, U. (2024) · Remote Sensing · doi:10.3390/rs16244715 · Cited by 38
Wu, Y., Suo, Y., Meng, Q., Dai, W., Miao, T., Zhao, W., Yan, Z., Diao, W., Xie, G., Ke, Q., et al. (2024) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2024.3519891 · Cited by 66
YOLO-OB: An improved anchor-free real-time multiscale colon polyp detector in colonoscopy
Yang, X. R., Song, E., Ma, G., Zhu, Y., Yu, D., Ding, B., & Wang, X. (2024) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2024.107326 · Cited by 36
Object Detection Based on CNN and Vision‐Transformer: A Survey
Cao, J., Peng, B., Gao, M., Hao, H., Li, X., & Mou, H. (2025) · IET Computer Vision · doi:10.1049/cvi2.70028 · Cited by 44
Sem-Aug: Improving Camera-LiDAR Feature Fusion With Semantic Augmentation for 3D Vehicle Detection
Zhao, L., Wang, M., & Yue, Y. (2022) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2022.3191208 · Cited by 27
Yan, L., Chen, Y., Zheng, L., & Zhang, Y. (2024) · Heritage Science · doi:10.1186/s40494-024-01185-6 · Cited by 27
“In the past few decades, computer vision technology has been widely used in many fields, such as image recognition [9–11], object detection [12–17], image segmentation [18], and image retrieval [19–24].”
MethodPickYOLO: Fast deep learning particle detector for annotation of cryo electron tomograms
Genthe, E., Miletic, S., Tekkali, I., James, R. H., Marlovits, T. C., & Heuser, P. (2023) · Journal of Structural Biology · doi:10.1016/j.jsb.2023.107990 · Cited by 22
Khatua, A., Bhattacharya, A., Goswami, A. K., & Aithal, B. H. (2024) · Spatial Information Research · doi:10.1007/s41324-024-00574-0 · Cited by 26
“The inquiry on challenges and issues has been subdivided into several components, encompassing detection type, object localization diversity, intra-class discrepancies, viewing perspective, dense and obstructed objects, augmentation, etc., as indicated by Zhengxia et al. [8].”
AI in Current and Future Agriculture: An Introductory Overview
Kisliuk, B., Krause, J. C., Meemken, H., Saborío, J. C., Müller, H., & Hertzberg, J. (2023) · Künstliche Intell. · doi:10.1007/s13218-023-00826-5 · Cited by 35
“In recent years, many such models and algorithms were released and have continued to increase their levels of performance [205].”
Deep learning-assisted medical image compression challenges and opportunities: systematic review
Bourai, N. E. H., Merouani, H. F., & Djebbar, A. (2024) · Neural Computing and Applications · doi:10.1007/s00521-024-09660-8 · Cited by 35
“…across diverse areas of computer vision [51, 287, 308], including image classification, speech recognition [65, 158], object detection [319, 330, 337], image segmentation [192], semantic segmentation [91, 104], natural language processing [200, 211, 317], image capture, pose estimation [100],…”
Local and Global Feature-Aware Dual-Branch Networks for Plant Disease Recognition
Lin, J., Zhang, X., Qin, Y., Yang, S., Wen, X., Cernava, T., Migheli, Q., & Chen, X. (2024) · Plant Phenomics · doi:10.34133/plantphenomics.0208 · Cited by 35
RTM-UAVDet: A Real-Time Multimodal UAV Detector
Wang, G., Jiang, Q., Jin, X., Woźniak, M., Yao, P. W. S., & Yao, S. (2024) · IEEE Transactions on Aerospace and Electronic Systems · doi:10.1109/taes.2024.3446460 · Cited by 33
“Object detection based on images is a crucial task in computer vision [20].”
WGS-YOLO: A real-time object detector based on YOLO framework for autonomous driving
Yue, S., Zhang, Z., Shi, Y., & Cai, Y. (2024) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2024.104200 · Cited by 31
Advancements in perception system with multi-sensor fusion for embodied agents
Du, H., Ren, L., Wang, Y., Cao, X. S., & Sun, C. (2024) · Information Fusion · doi:10.1016/j.inffus.2024.102859 · Cited by 38
YOLO-HF: Early Detection of Home Fires Using YOLO
Peng, B., & Kim, T.-K. (2025) · IEEE Access · doi:10.1109/access.2025.3566907 · Cited by 34
“Deep learning-based object detection can be categorized as either two-or one-stage methods [13], [39].”
InfluentialGenerative AI-driven data augmentation for enhanced construction hazard detection
Lee, Y., Kang, G., Kim, J., Yoon, S., & Jeon, J. (2025) · Automation in Construction · doi:10.1016/j.autcon.2025.106317 · Cited by 32
Efficient Localization and Spatial Distribution Modeling of Canopy Palms Using UAV Imagery
Cui, K., Tang, W., Zhu, R., Wang, M., Larsen, G. D., Pauca, V. P., Alqahtani, S., Yang, F., Segurado, D., Fine, P. B., et al. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2025.3584093 · Cited by 54
“Traditional instance segmentation models, such as those based on YOLO and R-CNNs [35], integrate mask branches to predict pixel-level outputs.”
Video Crowd Localization With Multifocus Gaussian Neighborhood Attention and a Large-Scale Benchmark
Li, H., Liu, L., Yang, K., Liu, S., Gao, J., Zhao, B., Zhang, R., & Hou, J. Y. (2022) · IEEE Transactions on Image Processing · doi:10.1109/tip.2022.3205210 · Cited by 41
“human heads are often tiny and overlapped with each other [17].”
BackgroundAveiro, J., Freitas, F. F., Ferreira, M., Onofre, A., Providência, C., Gonçalves, G., & Font, J. A. (2022) · Physical review. D/Physical review. D. · doi:10.1103/physrevd.106.084059 · Cited by 29
Multimodal Data Augmentation for Visual-Infrared Person ReID with Corrupted Data
Josi, A., Alehdaghi, M., Cruz, R. M. O., & Granger, É. (2023) · IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW) · doi:10.1109/wacvw58289.2023.00008 · Cited by 37
“, individuals in airport, and vehicles in traffic) rely on challenging tasks, like object detection [55, 51], tracking [29], and re-identification (ReID) [24, 50].”
BackgroundReal-time 6DoF full-range markerless head pose estimation
Algabri, R., Shin, H., & Lee, S. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.122293 · Cited by 28
Role of Sensing and Computer Vision in 6G Wireless Communications
Kim, S., Moon, J., Kim, J.-H., Ahn, Y., Kim, D., Kim, S., Shim, K., & Shim, B. (2024) · IEEE Wireless Communications · doi:10.1109/mwc.016.2300526 · Cited by 32
“With an adoption of DL technique, performance of CV techniques has been improved dramatically, surpassing the cognitive ability of humans in face detection, medical image diagnosis, and visual surveillance [4].”
MethodAung, N. H. H., Sangwongngam, P., Jintamethasawat, R., Shah, S., & Wuttisittikulkij, L. (2024) · IEEE Transactions on Intelligent Vehicles · doi:10.1109/tiv.2024.3415771 · Cited by 45
“The authors of [9], [10] provide a survey of long-term coverage for 3D object detection methods.”
The use of CNNs in VR/AR/MR/XR: a systematic literature review
Cortes, D., Bermejo, B. G., & Juiz, C. (2024) · Virtual Reality · doi:10.1007/s10055-024-01044-6 · Cited by 49
Multi-Scale Feature Fusion Enhancement for Underwater Object Detection
Xiao, Z., Li, Z., Li, H., Li, M., Liu, X., & Kong, Y. (2024) · Sensors · doi:10.3390/s24227201 · Cited by 33
“Driven by deep learning techniques, a rapid evolution of image-based object detection techniques has sprung up over the past two decades [9].”
Advanced Object Detection in Low-Light Conditions: Enhancements to YOLOv7 Framework
Zhao, D., Shao, F., Zhang, S., Yang, L., Zhang, H., Liu, S., & Liu, Q. (2024) · Remote Sensing · doi:10.3390/rs16234493 · Cited by 27
LCDDN-YOLO: Lightweight Cotton Disease Detection in Natural Environment, Based on Improved YOLOv8
Feng, H., Chen, X., & Duan, Z. (2025) · Agriculture · doi:10.3390/agriculture15040421 · Cited by 31
CNN based 2D object detection techniques: a review
Lamichhane, B. R., Srijuntongsiri, G., & Horanont, T. (2025) · Frontiers in Computer Science · doi:10.3389/fcomp.2025.1437664 · Cited by 33
Deep Learning for Low-Light Vision: A Comprehensive Survey
Zhao, Q., Li, G., He, B., & Shen, R. (2025) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2025.3566647 · Cited by 39
“Meanwhile, previous surveys on object detection have focused either on solving the general problem of object detection [29], [30], [33], [39], [40] or on specific object detection [27], [28], [31], [32], [41], [42], [43], such as pedestrian detection [41], face detection [28], and text detection…”
A comprehensive analysis of YOLO architectures for tomato leaf disease identification
Ramos, L., & Sappa, A. D. (2025) · Scientific Reports · doi:10.1038/s41598-025-11064-0 · Cited by 52
“Two common variants are mAP@50 and mAP@50:95 49 .”
A Study of YOLO Algorithm for Target Detection
Wen, H., Dai, F., & Yuan, Y.-S. (2021) · Proceedings of International Conference on Artificial Life and Robotics · doi:10.5954/icarob.2021.os13-9 · Cited by 23
DEW-YOLO: An Efficient Algorithm for Steel Surface Defect Detection
Li, J., & Chen, M. (2024) · Applied Sciences · doi:10.3390/app14125171 · Cited by 29
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.