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 901–1,000 of 3,144
Pallet Detection and 3D Pose Estimation via Geometric Cues Learned from Synthetic Data
Beleznai, C., Reisinger, L., Pointner, W., & Murschitz, M. (2025) · Lecture notes in computer science · doi:10.1007/978-981-97-8705-0_19 · Cited by 9
PolarBEVU: Multi-Camera 3D Object Detection in Polar Bird’s-Eye View via Unprojection
Hou, M., Lyu, C., Wang, G., Ma, B., Xu, R., Hu, J., & Fan, X. (2025) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2025.3546767 · Cited by 12
“As an important research topic in autonomous driving, 3D object detection aims to predict the category, size, and location of targeted objects in the 3D world [19], [20], [21], [22].”
Branch-YOLO: An efficient object detector for thin structure objects like pantograph
Li, Y., Han, J., Li, H., & Zhang, W. (2025) · Digital Signal Processing · doi:10.1016/j.dsp.2025.105121 · Cited by 6
Lai, S., & Deal, B. M. (2025) · Discover Cities · doi:10.1007/s44327-025-00075-1 · Cited by 11
“The model’s accuracy was evaluated using precision, recall, and mean Average Precision (mAP) scores [37].”
PestDet: A unified detection framework for accurate and efficient stored-grain pest detection
Tian, J., Sun, M., Zhou, H., & Li, J. (2025) · Ecological Informatics · doi:10.1016/j.ecoinf.2025.103145 · Cited by 7
SOE-YOLO: A Small-Object Enhancement Detection Network
Zhang, C., Gu, C., Duan, Q., & Zhao, S. (2025) · IEEE Sensors Journal · doi:10.1109/jsen.2025.3568844 · Cited by 11
A deep learning-based algorithm for the detection of personal protective equipment
Tong, B., Li, G., Bu, X., Wang, Y., & Yu, X. (2025) · PLoS ONE · doi:10.1371/journal.pone.0322115 · Cited by 7
“Deep learning-based object detection algorithms are typically divided into two categories [30]: two-stage object detection algorithms and one-stage object detection algorithms.”
DDH-YOLO: A dual-head YOLOv8 model for small object detection in UAV aerial images
Liu, Y., & Yang, Z. (2025) · Signal Image and Video Processing · doi:10.1007/s11760-025-04429-5 · Cited by 9
“The YOLO series has become widely adopted in fields such as industry, healthcare, smart transportation, and the military[19].”
Real Time Deep Learning Based Pothole Detection on Low Cost Embedded Devices for ADAS
Martins, W. D., Osório, F. S., & Bruno, D. R. (2025) · Brazilian Conference on Robotics (CROS) · doi:10.1109/cros66186.2025.11066083 · Cited by 9
SD-YOLO: A Robust and Efficient Object Detector for Aerial Image Detection
Qi, S., Sun, Y., Song, X., Li, J., Shang, T., & Yu, L. (2025) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2025.3591493 · Cited by 8
“I N RECENT years, research in aerial image object detection has achieved significant development [1], [2], [3], driven by the progress in artificial intelligence technology and the urgent demands of fields such as power equipment, agriculture, search and rescue and surveillance of traffic scenes.”
Object Detection With Different Categories Using YOLOv8 for Optical Remote Sensing Images
Madajczak, A., & Ciecholewski, M. (2025) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2025.3594426 · Cited by 6
“Generally, quite a lot of research has been done to detect objectsofasinglecategory[42].”
IntSTR: An integrated spatio-temporal relation transformer for video object detection
Zheng, W., Zheng, H., Sun, Y., & Jing, Y. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.131704 · Cited by 9
Oriented Tiny Object Detection: A Dataset, Benchmark, and Dynamic Unbiased Learning
Xu, C., Zhang, R., Yang, W. T., Zhu, H., Xu, F., Ding, J., & Xia, G.-S. (2025) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2025.3634161 · Cited by 17
“Unfortunately, previous studies mainly focus on detecting generic objects [4] or arbitrarily oriented objects [5].”
Wang, C., Liang, H., Chen, H., Khan, R., Shen, D., Liu, H., Shen, D., Wang, W., Liu, J., Panthier, F., et al. (2025) · npj Digital Medicine · doi:10.1038/s41746-025-02109-9 · Cited by 12
Liu, R., Zhu, Z., Ge, H., et al. (2025) · Ocean Engineering · doi:10.1016/j.oceaneng.2025.123206 · Cited by 6
Lei, H., Xu, L., Liu, C., & Dong, Y. (2026) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2025.3650459 · Cited by 10
“R ECENTLY, significant advancements have been made in object detection technologies based on visible light or infrared imaging [1], [2], [3], [4].”
Water Surface Target Detection Based on Improved YOLOv3 in UAV Images
Zhang, B., Qian, X., Yang, R., et al. (2021) · International Conference on Communications and Broadband Networking (ICCBN) · doi:10.1145/3456415.3456424 · Cited by 6
“On the contrary, target detection technology has high precision and strong generalization ability in most fields [2], so we choose to use target detection technology to identify and locate surface targets.”
BackgroundMao, J., Cheng, L., Ji, C., Jing, M., Duan, Z., Li, N., Gesang, Z., & Li, M. (2022) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2022.3199249 · Cited by 8
“Object detectionindeeplearninginvolvesfindingalltheobjectsof interestinanimageanddeterminingtheirlocationsandsizes, whichisacoreprobleminthefieldofcomputervision[15].”
Comprehensive Study on Shape Representation Methods for Shape-Based Object Recognition
Jiang, Z., & Zhou, C. (2023) · Journal of Optics · doi:10.1007/s12596-023-01356-x · Cited by 12
“The authors in [19] presented a comprehensive survey of object detection techniques over a span of 20 years.”
A Systematic Literature Review of Computer Vision Applications in Robotized Wire Harness Assembly
Wang, H., Salunkhe, O., Quadrini, W., et al. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2309.13744 · Cited by 6
Puppis: Hardware Accelerator of Single-Shot Multibox Detectors for Edge-Based Applications
Vrbaski, V., Jošić, S., Vranjković, V. S., Teodorovic, P., & STRUHARIK, R. J. R. (2023) · Electronics · doi:10.3390/electronics12224557 · Cited by 8
Kaymakcı, Z. E., Akarsu, M., & Öztürk, C. N. (2023) · International Conference on Innovations in Intelligent Systems and Applications (INISTA) · doi:10.1109/inista59065.2023.10310562 · Cited by 8
“Traditional object detectors depending on algorithms like Viola-Jones, histogram of oriented gradients (HOG), or dis-criminatively trained part-based models (DPM) have been replaced by CNN-based object detectors today [1].”
MethodYu, H., Hua, Z., Miao, X., Wang, S., Pan, G., An, J., Svensson, T., Thompson, J., & Yanıkömeroğlu, H. (2023) · IEEE Wireless Communications · doi:10.1109/mwc.003.2300194 · Cited by 7
“In addition, various fast RCNN algorithms may be implemented on cheap chips [9 13].”
MethodAutomatic flaw detection of carbon fiber prepreg using a CFP-SSD model during preparation
Liu, X., Gan, X., & Ping, A. (2023) · Measurement Science and Technology · doi:10.1088/1361-6501/ad1815 · Cited by 6
“Deep learning-based object detection solves high-dimensional data with evident benefits and emulates human thought processes in its operation [18–20].”
G-Net: An Efficient Convolutional Network for Underwater Object Detection
Zhao, X., Wang, Z., Deng, Z., & Qin, H. (2024) · Journal of Marine Science and Engineering · doi:10.3390/jmse12010116 · Cited by 7
“Target detection, as one of the most fundamental and important tasks in computer vision, has received widespread attention in recent years [21].”
Proximity-Based Optical Camera Communication with Multiple Transmitters Using Deep Learning
Nasution, M. R. A., Herfandi, H., Sitanggang, O. S., Nguyen, H. Q., & Jang, Y. M. (2024) · Sensors · doi:10.3390/s24020702 · Cited by 6
Shi, W., Zhang, S., & Zhang, S. (2024) · Computer Modeling in Engineering & Sciences · doi:10.32604/cmes.2023.044863 · Cited by 19
In Situ Surface Defect Detection in Polymer Tube Extrusion: AI-Based Real-Time Monitoring Approach
Jo, C. M., Jang, W. K., Seo, Y. H., & Kim, B. H. (2024) · Sensors · doi:10.3390/s24061791 · Cited by 8
“Its advantages include excellent detection performance and speed, better than the R-CNN series of algorithms that evolved as two-stage detectors in the early object detection field [26,27].”
BackgroundMethodMinimalism is King! High-Frequency Energy-Based Screening for Data-Efficient Backdoor Attacks
Xun, Y., Jia, X., Gu, J., Liu, X., Guo, Q., & Cao, X. (2024) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2024.3380821 · Cited by 13
“D EEP neural networks (DNNs) have achieved state-of-the-art performances in various tasks, such as image classification [1], [2], [3], object detection [4], [5], [6], image segmentation [7], [8], [9].”
BackgroundEB-Net: an efficient balanced network for accuracy and speed of remote sensing detection
Zhang, D., Wang, D., Yu, C., Hao, X., & Liang, L. (2024) · International Journal of Remote Sensing · doi:10.1080/01431161.2024.2343137 · Cited by 7
GhostNet-YOLO Algorithm for Object Detection in UAV Image
Kumar, S., Kumar, A., & Kumar, K. (2023) · International Conference on Image Information Processing (ICIIP) · doi:10.1109/iciip61524.2023.10537737 · Cited by 11
Shao, Z., Yang, K., Sun, P., Hu, Y., & Boukerche, A. (2024) · Computer Communications · doi:10.1016/j.comcom.2024.06.015 · Cited by 9
Ji, K., An, Q., & Hui, X. (2024) · Physics of Fluids · doi:10.1063/5.0211212 · Cited by 7
Overlapping Shoeprint Detection by Edge Detection and Deep Learning
Li, C., Narayanan, A., & Ghobakhlou, A. (2024) · Journal of Imaging · doi:10.3390/jimaging10080186 · Cited by 5
“Recent approaches, predominantly relying on convolutional neural networks (CNN) for object detection, have shown a notable degree of success of single objects in various image analysis tasks [1–4].”
BackgroundApplication of Synthetic Data on Object Detection Tasks
Nguyen, H. L., Le, D. T., & Hoang, H. H. (2024) · Engineering Technology & Applied Science Research · doi:10.48084/etasr.7929 · Cited by 7
“Object detection is a crucial computer vision job that deals with detecting instances of certain classes of visual things (such as people, animals, or automobiles) in digital images [8].”
BackgroundHigh-resolution solar panel detection in Sfax, Tunisia: A UNet-Based approach
Bouaziz, M. C., Koundi, M. E., & Ennine, G. (2024) · Renewable Energy · doi:10.1016/j.renene.2024.121171 · Cited by 14
Wang, L., Ji, W., Wang, G., Feng, Y., & Du, M. (2024) · Alexandria Engineering Journal · doi:10.1016/j.aej.2024.07.105 · Cited by 7
SSN: Scale Selection Network for Multi-Scale Object Detection in Remote Sensing Images
Lin, Z., & Leng, B. (2024) · Remote Sensing · doi:10.3390/rs16193697 · Cited by 9
Zhang, Q., Min, B., Hang, Y., Chen, H., & Qiu, J. (2024) · Scientific Reports · doi:10.1038/s41598-024-74365-w · Cited by 8
“Overall network structure Yolov8, another major update from ultralytics, has a wide range of applications in image classification 23 , object detection 24 , image segmentation 25 , pose estimation and tracking 26 .”
BackgroundAn Efficient Method for Sea Cucumber Recognition and Sorting Based on Improved YOLOv9 and RepViT
Huang, M., & Honglei, W. E. I. (2024) · IEICE Transactions on Fundamentals of Electronics Communications and Computer Sciences · doi:10.1587/transfun.2024eap1101 · Cited by 7
Gamage, B., Holloway, L. M., McDowell, N., Do, T.-T., Price, N. S. C., Lowery, A. J., & Marriott, K. (2024) · International ACM SIGACCESS Conference on Computers and Accessibility (ASSETS) · doi:10.1145/3663548.3675637 · Cited by 11
“For example, while SOTA object detection algorithms can achieve an accuracy of 85% [215], they are typically evaluated on high-performance hardware with large models containing thousands of parameters.”
Li, C., Xiang, X., Li, Q., et al. (2024) · IEEE Wireless Communications Letters · doi:10.1109/lwc.2024.3490578 · Cited by 6
Less is more: A semi-supervised fine-grained object detection for satellite video
Zhou, Z., & Li, S. (2024) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2024.109609 · Cited by 11
Xu, Y., & Fu, Y. H. (2024) · Applied Sciences · doi:10.3390/app142210713 · Cited by 8
Dong, H., Wang, N., Fu, D., Wei, F., Liu, G., & Liu, B. (2024) · Drones · doi:10.3390/drones8110692 · Cited by 9
Zhang, H., Li, X., Ramelli, F., David, R. O., Pasquier, J. T., & Henneberger, J. (2024) · Atmospheric measurement techniques · doi:10.5194/amt-17-7109-2024 · Cited by 14
Liang, W., Sun, Y., Zhang, S., Bai, L., & Yang, J. (2024) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2024.3517537 · Cited by 8
“Currently, the main methods for detecting defects on magnetic chips are manual detection methods, traditional methods based on support vector machines (SVMs) [1] and histograms of oriented gradients (HOGs) [2], and methods based on deep learning [3], [4], [5].”
Explainable Attention-Based AAV Target Detection for Search and Rescue Scenarios
Liu, S., Yi, L., Xiong, X., Tolba, A. K. R., Ding, J., & Li, C. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3519158 · Cited by 9
“Unlike two-stage detection, one-stage methods trained end-to-end offer faster detection speeds, meeting the demands of real-time processing [11], [12], [13].”
Underwater Detection: A Brief Survey and a New Multitask Dataset
Yu, W., Wang, Y., Zhu, B., Lin, C., Wu, D., Xue, X., & Wang, R. (2024) · International Journal of Network Dynamics and Intelligence · doi:10.53941/ijndi.2024.100025 · Cited by 17
Scale-Consistent and Temporally Ensembled Unsupervised Domain Adaptation for Object Detection
Guo, L., Zhang, Y., Liu, J., Liu, H., & Li, Y. (2025) · Sensors · doi:10.3390/s25010230 · Cited by 7
“Recent advancements in deep learning have led to significant progress in object detection across various applications, including autonomous driving, security surveillance, and medical imaging [1].”
Fanfan, 刘. L., Chengmei, 朱. Z., Nana, 赵. Z., & Jinghua, 吴. W. (2024) · Laser & Optoelectronics Progress · doi:10.3788/lop241203 · Cited by 7
Cross-Scale Feature Interaction Network for Semantic Segmentation in Side-Scan Sonar Images
Wang, Z., You, Z., Xu, N., Wang, B., & Huang, D.-S. (2025) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2025.3534285 · Cited by 12
“With the wide application of deep learning in computer vision tasks [16], [17], [18], benefit from the robust feature extraction capability of convolutional neural networks (CNNs) [19], it has been applied to solve the problem of SSS image semantic segmentation.”
A Real-Time Fish Detection System for Partially Dewatered Fish to Support Selective Fish Passage
Gregory, J., Miehls, S., Eickholt, J., & Zielinski, D. P. (2025) · Sensors · doi:10.3390/s25041022 · Cited by 7
“Object detection combines object identification and localization by classifying objects within an image and drawing a bounding box around individual object instances [57].”
Jiao, L., Liu, H., Liang, Z., Chen, P., Wang, R., & Liu, K. (2025) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2024.3502719 · Cited by 8
“Initially, investigations predominantly centered on detecting objects in a horizontal orientation [27], reflecting the conventional notion that objects in natural settings tend to align upward owing to gravitational forces.”
Optimal fuzzy-PID controller design for object tracking
Melese, Y. L., Alitasb, G. K., & Belete, M. D. (2025) · Scientific Reports · doi:10.1038/s41598-025-92309-w · Cited by 6
RMF‐ED: Real‐Time Multimodal Fusion for Enhanced Target Detection in Low‐Light Environments
Wu, Y., Cui, J., Niu, K., Lu, Y., Cheng, L., Cai, S., & Xu, C. (2025) · IET Cyber-Systems and Robotics · doi:10.1049/csy2.70011 · Cited by 6
NSC-YOLOv8: A Small Target Detection Method for UAV-Acquired Images Based on Self-Adaptive Embedding
Chen, D., Chen, D., Zhong, C., & Zhan, F. (2025) · Electronics · doi:10.3390/electronics14081548 · Cited by 6
Denoising and Feature Enhancement Network for Target Detection Based on SAR Images
Yang, C. F., Li, C., & Zhu, Y. (2025) · Remote Sensing · doi:10.3390/rs17101739 · Cited by 7
Masked face with facial expression recognition based on deep learning
Abdullah, N. Y., & Alkababji, A. M. (2022) · Indonesian Journal of Electrical Engineering and Computer Science · doi:10.11591/ijeecs.v27.i1.pp149-155 · Cited by 8
“In the recent years, the deep learning-based detector proved an excellent performance in feature extraction [18], A convolutional neural network (CNN), which has a superior feature extraction capability, that make pattern recognition tasks relevant to computer vision more accurate [19].”
BackgroundMarine Fish Object Detection Based on YOLOv5 and Attention Mechanism
Chen, L., Zang, Z., Huang, T., & Zhao, L. (2022) · IEEE Smart World Congress (SWC) · doi:10.1109/smartworld-uic-atc-scalcom-digitaltwin-pricomp-metaverse56740.2022.00185 · Cited by 7
Solovchenko, A. E., Shurygin, B., Nesterov, D. A., & Sorokin, D. V. (2023) · Biophysical Reviews · doi:10.1007/s12551-023-01125-x · Cited by 6
“The turn of the century thus saw a paradigm shift in image data processing from merely applying spectral and radiometric corrections to performing complex semantic tasks such as object detection and classification (Zou et al. 2023).”
BackgroundA Review on Object Detection Algorithms based Deep Learning Methods
Wan, X., Mohd, M. R. S., Johari, J., & Ruslan, F. A. (2023) · Journal of Electrical & Electronic Systems Research · doi:10.24191/jeesr.v23i1.001 · Cited by 8
Guo, C. Q., Qiu, S., Ni, T., Wang, B., & Liu, Q. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3329160 · Cited by 6
“In the deep-learning era, object detection can be grouped into two genres: “two-stage detection” and “one-stage detection” [27].”
Comparison of Faster R-CNN ResNet-50 and ResNet-101 Methods for Recycling Waste Detection
(2023) · International Journal of Computer Applications Technology and Research · doi:10.7753/ijcatr1212.1006 · Cited by 9
Clement, D. M., Mottino, S., & Costello, D. H. (2023) · IEEE International Automated Vehicle Validation Conference (IAVVC) · doi:10.1109/iavvc57316.2023.10328136 · Cited by 6
“This provides an excellent use case for a computer vision object detection neural network which can Object detection neural networks are an instance of supervised learning, which uses labeled datasets to train algorithms to classify data and/or predict outcomes [15]–[17].”
BackgroundImproved YOLOv4 based on dilated coordinate attention for object detection
Yang, Z., Zheng, Y., Shao, J., et al. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-17817-1 · Cited by 6
“Object detection [1, 2] has always been a research hotspot in computer vision.”
Shape Anchor Guided Holistic Indoor Scene Understanding
Dong, M., Huan, L., Xiong, H., Shen, S., & Zheng, X. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.02003 · Cited by 7
Jing, X., Liu, X., & Liu, B. (2024) · Mathematics · doi:10.3390/math12050622 · Cited by 9
A Novel Feature Fusion Framework for Industrial Automation Single-Multiple Object Detection
Lyu, P., Liu, J., Zhang, Y., Ye, B., Lan, T., Bai, L., Cai, Z., & Jiang, Z. (2024) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2024.3353814 · Cited by 6
“Detection algorithms contain many branches of research [10], [11], [12].”
BackgroundMethodReal-Time Localization of Objects using Radio Frequency Propagation in Digital Twin
Amatare, S., Singh, G. K., Kharel, A., et al. (2024) · IEEE Military Communications Conference (MILCOM) · doi:10.1109/milcom61039.2024.10774060 · Cited by 6
“Also, the rapid advancement of object localization techniques have been largely credited to the development of deep convolutional neural networks and the enhanced computing power of GPUs [1].”
InfluentialFace Recognition Method of Mask Occlusion
Shuai, Z., & Feng, S. (2021) · IEEE International Conference on Smart Internet of Things (SmartIoT) · doi:10.1109/smartiot52359.2021.00022 · Cited by 6
Ling, Z., Liu, R., Zhang, Y., & Chen, X. (2021) · IEEE Transactions on Systems Man and Cybernetics Systems · doi:10.1109/tsmc.2021.3130109 · Cited by 6
Su-cheng, K. (2022) · Computational Intelligence and Neuroscience · doi:10.1155/2022/3843155 · Cited by 6
“Object detection is a basic computer vision task that combines the two tasks of target localization and recognition, the purpose of which is to nd several targets in the complex background of the image, give each target a precise target enveloping box, and determine the category to which the target in the enveloping…”
BackgroundIndustry 4.0 - Perspectives and Applications
Gordan, M., Ghaedi, K., & Saleh, V. (2022) · Artificial intelligence · doi:10.5772/intechopen.100660 · Cited by 16
Comparative Review of Object Detection Algorithms in Small Single-Board Computers
Rashid, T. M. N. B. T., & Fadzil, L. M. (2023) · International Journal on Recent and Innovation Trends in Computing and Communication · doi:10.17762/ijritcc.v11i7.7904 · Cited by 6
Applications of artificial intelligence in the circuit and modulation design of DC-DC converters
Li, X. (2023) · DR-NTU (Nanyang Technological University) · doi:10.32657/10356/165390 · Cited by 6
Chaudhry, H. N., Kulsoom, F., & Khan, Z. U. (2025) · IEEE Access · doi:10.1109/access.2025.3609656 · Cited by 6
“YOLO is a cutting-edge algorithm that excels in both speed and accuracy for object detection tasks [61].”
Deep Optimized Broad Learning System for Applications in Tabular Data Recognition
Zhang, W., Yang, Y., Wu, Q. M. J., & Liu, T. (2024) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2024.3473809 · Cited by 5
“Moreover, radar signal images differ significantly from everyday images, and using pretrained DL models, such as pretrained transformers and CNNs, proves less effective than anticipated [69].”
Apply prior feature integration to sparse object detectors
Yu, Q., Wang, Q., Wu, C., Wang, C., Cheng, L., Hu, Y., & Wang, H. (2024) · Pattern Recognition · doi:10.1016/j.patcog.2024.111103 · Cited by 5
Lane extraction from trajectories at road intersections based on Graph Transformer Network
Wan, C., Yue, P., Yang, C., et al. (2024) · International Journal of Geographical Information Systems · doi:10.1080/13658816.2024.2433086 · Cited by 5
Yoshimi, Y., Mine, Y., Yamamoto, K., Okazaki, S., Ito, S., Mizuho, S. A. N. O., Peng, T., Nakamoto, T., Nagasaki, T., Kakimoto, N., et al. (2024) · Dental Materials Journal · doi:10.4012/dmj.2024-186 · Cited by 9
Zhou, G., Wang, G., Huang, Y., Wang, W., Qu, Z., & Yin, C. (2025) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2025.3526161 · Cited by 8
“Traditional object detection frameworks often struggle with the unique challenges posed by remote sensing images, such as drastic scale variances and long-tail class distribution [5], [6].”
Optimized molecule detection in localization microscopy with selected false positive probability
Hekrdla, M., Roesel, D., Hansen, N., Frederick, S., Umar, K., & Petráková, V. (2025) · Nature Communications · doi:10.1038/s41467-025-55952-5 · Cited by 9
“Additionally, machine learning approaches, including traditional segmentation methods and emerging deep learning techniques, are becoming increasingly relevant in this fi eld 7,10,12 – 15 .”
Developing YOLOv5s model with enhancement mechanisms for precision parts with irregular shapes
Dong, L., Zhu, H., Ren, H., Lin, T., & Lin, K.-P. (2025) · Advanced Engineering Informatics · doi:10.1016/j.aei.2025.103257 · Cited by 6
Detail-enhanced lightweight network for small object detection in aerial images
Wang, X., Lin, C., & Pan, Y. (2025) · The Visual Computer · doi:10.1007/s00371-025-03878-w · Cited by 7
“All instances are categorized based on their absolute size into four classes: very small ([8]), small ([8, 16]), medium ([16, 32]), and large ([64]).”
AIFE-Net: Transformer-based adaptive multi-scale feature extraction encoder for object detection
Zhang, Z., Zhang, J., Wei, J., Han, L., & Li, T. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.130366 · Cited by 5
Digital Genealogy: AIGC-Driven Evolution of Digital Twin for Future Smart Manufacturing
Ren, L., Dong, J., Zeng, X., Yang, L., & Wang, Y. (2025) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2025.3579689 · Cited by 17
“4, begins with a physical image of an object in the real world [34], [35].”
Forgetting the Background: A Masking Approach for Enhanced Infrared Small-Target Detection
Liu, Y., Ma, Z., Zhu, W., Li, N., Li, C., Xiong, K., Wang, Z., Feng, W., Jiang, J., & Quan, Y. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2025.3589602 · Cited by 16
“Adhering to this tradition, in a general scene, ISTD is actually a segmentation task that aims to separate targets from the background with pixel-wise identification [5], [22], rather than a visual object detection with bounding boxes and categories [23], [24].”
GO-N3RDet: Geometry Optimized NeRF-enhanced 3D Object Detector
Li, Z., Yu, H., Ding, Y., Qiao, J., Azam, B., & Akhtar, N. (2025) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52734.2025.02534 · Cited by 10
“Employing low-cost cameras instead of costly LiDAR or depth sensors [16,24,25,50] makes this paradigm of 3D object detection practically appealing.”
Cross-DINO: Cross the Deep MLP and Transformer for Small Object Detection
Cao, G., Huang, W., Lan, X., Zhang, J., Jiang, D., & Wang, Y. (2025) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2025.3599074 · Cited by 17
An End-to-End Computationally Lightweight Vision-Based Grasping System for Grocery Items
Mansakul, T., Tang, G., Webb, P., Rice, J., Oakley, D., & Fowler, J. E. (2025) · Sensors · doi:10.3390/s25175309 · Cited by 10
“Conversely, one-stage methods (e.g., YOLO, DETR, and SSD) are more suitable for real-time applications due to their speed and relatively lightweight architecture [18].”
Hoang, Q.-V., & Le, T.-H. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.112263 · Cited by 6
PMDS-YOLO: A lightweight multi-scale detector for efficient aquatic product detection
Xu, X., Xie, Z., Wang, N., et al. (2025) · Aquaculture · doi:10.1016/j.aquaculture.2025.743210 · Cited by 5
YOLOv8-GR: real time gesture recognition by improving of YOLOv8 algorithm
Guo, N., Ding, Y., & Meng, H. (2025) · Complex & Intelligent Systems · doi:10.1007/s40747-025-02107-0 · Cited by 5
“…gesture recognition algorithms, including YOLO (You Only Look Once) and SSD (Single Shot MultiBox Detector), have gained popularity due to their superior speed and efficiency, making them more appropriate for real-time applications and deployment on devices with limited computational resources [9].”
Wang, Z., Yu, P., Zhang, X., & Sun, H. (2025) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2025.104565 · Cited by 8
Wang, Q., Wang, D., Lu, J., Xiao, G., Liang, D., Lu, G., & Shao, H. (2025) · Scientific Reports · doi:10.1038/s41598-025-24260-9 · Cited by 5
A lightweight detection network integrating multi-scale semantic refinement for steel strip defects
Bian, B., Chen, L., Han, Z., Wu, S., Li, W., & Chen, H. (2025) · Robotics and Computer-Integrated Manufacturing · doi:10.1016/j.rcim.2025.103188 · Cited by 9
Opportunities challenges and roadmap for humanoid robots in construction
Uthai, T., You, H., Wang, M., Smith, K. E., Spackman, E., Ryan, Z., Li, S., & Du, J. (2025) · Scientific Reports · doi:10.1038/s41598-025-30252-6 · Cited by 20
“AI algorithms for object detection and semantic scene parsing often leverage deep neural networks, which have shown remarkable progress on benchmarks 88,89 .”
Small target worker detection based on improved YOLOv12 for large construction scenes
Yin, Y., & Liu, X. (2025) · Automation in Construction · doi:10.1016/j.autcon.2025.106722 · Cited by 7
Liu, Q., Wan, X., Sheng, Y., Wang, S., & Wei, B. (2025) · Italian National Conference on Sensors · doi:10.3390/s26010103 · Cited by 3
Metadata
- Authors
- Zou, Z., Chen, K., Shi, Z., Guo, Y., & Ye, J.
- Affiliations
- Shanghai Artificial Intelligence Laboratory (CN)
- Carleton University (CA)
- Alibaba Group (China) (CN)
- Venue
- Proceedings of the IEEE
- Published
- 2023-03
- Volume
- 111
- Issue
- 3
- Pages
- 257-276
- ISSN
- 0018-9219 (ISSN-L)
- 1558-2256
- OpenAlex
- W4320002812
- Cited by
- 3,689
- References
- 272
- Citations by year
- 2026: 610 · 2025: 1013 · 2024: 940 · 2023: 541
- FWCI
- 280.65
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- Proceedings of the IEEE (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- National Natural Science Foundation of China (62125102)
- National Key Research and Development Program of China
- Fundamental Research Funds for the Central Universities
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image and Video Retrieval Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Visual Attention and Saliency Detection
- Keywords
- object detection, evaluation metrics, deep learning
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-07, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-07 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.