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 1,001–1,100 of 3,144
Bearing-based multi-agent formation control: A survey and taxonomy
Su, H., Yang, Z., Zhu, S., et al. (2026) · Annual Reviews in Control · doi:10.1016/j.arcontrol.2025.101043 · Cited by 5
Hussain, S., Mumtaz, I., Wang, C., & Lv, P. (2026) · Egyptian Informatics Journal · doi:10.1016/j.eij.2026.100888 · Cited by 6
Large Multimodal Model-Based Environment-Aware Beam Management
Kim, S., Saha, S., Jeong, S., Shim, B., & Win, M. Z. (2026) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2025.3611419 · Cited by 14
“7 Object detection is a computer vision (CV) technique that identifies the bounding box and the class of target object [51].”
Advancements in orchard thinning technologies: A comprehensive review
Xin, J., Zhang, Z., Dai, Y., Mhamed, M., Abid, F., Igathinathane, C., Thuy, N. T. D., Ampatzidis, Y. G., & Azizi, A. (2026) · Smart Agricultural Technology · doi:10.1016/j.atech.2026.101852 · Cited by 5
Deep learning-based object detection: A comprehensive review of YOLO, RCNN, and SSD series
Zeng, W., Mao, G., Li, M., & Yin, S. (2026) · Electronic Research Archive · doi:10.3934/era.2026124 · Cited by 11
Few-Shot Industrial Meter Detection Based on Sim-to-Real Domain Adaptation and Category Augmentation
Zeng, M., Zhong, S., & Ge, L. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3332939 · Cited by 5
Adversarial Attacks against Traffic Sign Detection for Autonomous Driving
Xu, F., Li, Y., Yang, C., et al. (2023) · CAA International Conference on Vehicular Control and Intelligence (CVCI) · doi:10.1109/cvci59596.2023.10397303 · Cited by 5
“Cameras can capture rich color and texture information, in recent years, vision-based 2D object detection has achieved a lot of success [1].”
BackgroundOBB detector: occluded object detection based on geometric modeling of video frames
Agrawal, S., & Natu, P. (2024) · The Visual Computer · doi:10.1007/s00371-024-03374-7 · Cited by 5
“…of Computer Engineering, Mukesh Patel School of Technology Management & Engineering, SVKM’s Narsee Monjee Institute of Management Studies (NMIMS) University, Mumbai, India object detection and classification using several frameworks to improve the accuracy of object detection algorithms [1, 2].”
Tian, Y., Tang, G., Zhang, H., Liang, L., Ma, J., Gao, Y., Zhou, C., & Li, S. (2024) · Physics in Medicine and Biology · doi:10.1088/1361-6560/ad3c0c · Cited by 6
Phase division and recognition of crystal HRTEM images based on machine learning and deep learning
Zhang, Q., Yang, L., Bai, R., et al. (2024) · Micron · doi:10.1016/j.micron.2024.103665 · Cited by 5
Syamal, S., Huang, C. Z., & Petrunin, I. V. (2024) · IEEE International Workshop on Metrology for Automotive (MetroAutomotive) · doi:10.1109/metroautomotive61329.2024.10615661 · Cited by 9
“Foundational insights provided by [6], [7] underscore the superiority of CNNs in learning hierarchical features, facilitating this transition.”
BackgroundAutomated Extraction of Data From MOSFET Datasheets for Power Converter Design Automation
Tian, F., Sui, Q., Cobaleda, D. B., et al. (2024) · IEEE Journal of Emerging and Selected Topics in Power Electronics · doi:10.1109/jestpe.2024.3456592 · Cited by 5
“On the other hand, one-stage methods, such as YOLO [18] and CornerNet [19], accomplish localization and classification in a single flow for object detection [8], [20].”
Object Detection for the Visually Impaired: A Systematic Literature Review
Nugraha, G. F., Aradea, A., Rianto, R., & Mardiati, R. (2024) · International Conference on Wireless and Telematics (ICWT) · doi:10.1109/icwt62080.2024.10674727 · Cited by 7
“Object Detection is a part of computer vision whose task is to detect visuals containing a particular class in a digital image [14].”
BackgroundAdaptive Multi-task Learning for Few-Shot Object Detection
Ren, Y., Li, Y., & Kong, A. W. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72667-5_17 · Cited by 13
“Rapid advancement of deep learning techniques has led to significant improvements in object detection [60].”
Road Object Detection Using Yolov8
Sunitha, G., Priya, V. S., Kumar, V. S., Priya, G. G. L., & Kumar, T. N. (2024) · International Conference on Electronics and Sustainable Communication Systems (ICESC) · doi:10.1109/icesc60852.2024.10689873 · Cited by 5
“Object recognition and tracking are challenging tasks in vision-based applications [2].”
BackgroundDing, H., Huang, N., Wu, Y., & Cui, X. (2024) · IEEE Transactions on Aerospace and Electronic Systems · doi:10.1109/taes.2024.3480890 · Cited by 5
“As a key research area and hot topic in computer vision, object detection technology has achieved remarkable results in various fields, such as intelligent navigation, autonomous driving, detection and surveillance systems, aerospace, and military defense [1], [2], [3].”
GLSD: a global large-scale ship database with baseline evaluations
Shao, Z., Wang, Y., Wang, J., Deng, L., Huang, X., Lü, T., Luo, F., & Zhang, R. (2024) · Geo-spatial Information Science · doi:10.1080/10095020.2024.2416896 · Cited by 7
“, the traditional methods and deep-learning methods [1].”
InfluentialAn FPGA Accelerator Design of Spiking Neural Network for Energy-Efficient Object Detection
Li, T., Huang, X., Li, Y., Qiu, N., Yin, H., Zhu, C., & Li, Y. (2024) · IEEE Transactions on Consumer Electronics · doi:10.1109/tce.2024.3502112 · Cited by 7
“Object detection is an essential task in the field of computer vision, which aims to locate and recognize multiple objects in images or videos precisely [40].”
Minimal Defect Detection on End Face of Lithium Battery Shells
Xing, Y., Liu, Q., Xing, Y., Liu, Z., & Wang, W. (2024) · Sustainability · doi:10.3390/su162310502 · Cited by 5
2D human pose tracking in the cardiac catheterisation laboratory with BYTE
Bütler, R. M., Vijfvinkel, T. S., Frassini, E., van Riel, S., Bachvarov, C., Constandse, J. C., van der Elst, M., van den Dobbelsteen, J. J., & Hendriks, B. H. W. (2024) · Medical Engineering & Physics · doi:10.1016/j.medengphy.2024.104270 · Cited by 5
“BYTE [18] is a state-of-the-art tracking algorithm that re-identifies bounding boxes produced by an object detector [21] between frames.”
Jointly RS Image Deblurring and Super-Resolution With Adjustable-Kernel and Multi-Domain Attention
Zhang, Y., Zheng, P., Zeng, C., et al. (2024) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2024.3515636 · Cited by 5
López-Muńoz, P., Frutos, L. G. S., Abarca, C., Alegre, F. J., Calle, J. L., & Monserrat, J. F. (2024) · Telecom · doi:10.3390/telecom5040064 · Cited by 7
Enhancing 3D object detection in autonomous vehicles based on synthetic virtual environment analysis
Li, V., Siniosoglou, I., Karamitsou, T., Lytos, A., Moscholios, I. D., Goudos, S. K., Banerjee, J. S., Sarigiannidis, P. G., & Argyriou, V. (2024) · Image and Vision Computing · doi:10.1016/j.imavis.2024.105385 · Cited by 15
Raw Camera Data Object Detectors: An Optimisation for Automotive Video Processing and Transmission
Chan, P. H., Wei, C., Huggett, A., & Donzella, V. (2025) · IEEE Access · doi:10.1109/access.2025.3529287 · Cited by 8
“The R-CNN and YOLO series are the most commonly used DNNs for object detection tasks, but there is a trade-off between detection accuracy and detection speed [7].”
Klir, S., Lerch, J., Benkner, S., & Khanh, T. Q. (2025) · Sensors · doi:10.3390/s25020419 · Cited by 7
Cheng, H., Gu, Y., Mengting, X., Qiuyuan, Z., & Wei, L. (2025) · IEEE Access · doi:10.1109/access.2025.3547831 · Cited by 7
“Among CNN-based methods, further classifications include single-stage object detection methods based on regression analysis and two-stage methods based on candidate regions [2].”
A Two-Stage YOLOv8 Approach for Waste Detection and Classification in Cognitive Cities
Nayfeh, A., Al-Azani, S., & Samma, H. (2025) · Transportation research procedia · doi:10.1016/j.trpro.2025.03.111 · Cited by 7
Ibrahim, M. R. (2025) · Neural Computing and Applications · doi:10.1007/s00521-025-11152-2 · Cited by 5
“However, the advent of deep learning has revolutionised the field, introducing more sophisticated and effective methods [14–16].. Convolutional Neural Networks (CNNs) now dominate object detection, facilitating powerful feature extraction and recognition capabilities.”
An improved YOLOv5 model for aeolian saltating particle recognition in high-speed videos
Xi, A., Mei, F., Li, H., Li, Z., Chen, H., Su, J., & Chen, J. (2025) · Measurement · doi:10.1016/j.measurement.2025.117321 · Cited by 6
Eom, T.-H., & Kim, H. (2025) · IEEE Sensors Journal · doi:10.1109/jsen.2025.3554806 · Cited by 5
“CNN-based object detection systems are especially susceptible to these issues, as they heavily depend on the characteristics of the training data provided during the learning process, making them less adaptable to external factors like variable illumination in input images [3].”
Liu, X., Liu, C., Zhou, X., & Fan, G. (2025) · Multimedia Systems · doi:10.1007/s00530-025-01820-7 · Cited by 8
“Evaluation metrics To provide an accurate evaluation of the performance of En-YOLO, we will use the mAP [1] and COCO evaluation metrics [2].”
Wang, Y., Zhang, S., Xu, J., Cheng, Z., & Du, G. (2025) · Symmetry · doi:10.3390/sym17071116 · Cited by 10
Deepak, G. D., & Bhat, S. K. (2025) · International Journal of Intelligent Transportation Systems Research · doi:10.1007/s13177-025-00519-3 · Cited by 10
Real-Time Progress Monitoring of Bricklaying
Magdy, R., Hamdy, K., & Essawy, Y. A. S. (2025) · Buildings · doi:10.3390/buildings15142456 · Cited by 9
徐, 梦. (2025) · Software Engineering and Applications · doi:10.12677/sea.2025.144079 · Cited by 5
Lindemann, L., Zhao, Y., Yu, X., Pappas, G. J., & Deshmukh, J. V. (2025) · IEEE Control Systems · doi:10.1109/mcs.2025.3611545 · Cited by 98
Deokar, S., & Khandekar, S. (2022) · International Conference on Augmented Intelligence and Sustainable Systems (ICAISS) · doi:10.1109/icaiss55157.2022.10011078 · Cited by 5
“Zhengxia Zou, et al, listed briefly a few methods that were used in the period of 20 years [4].”
MethodIndustrial Robotic Intelligence Simulation in Metaverse Scenes
Wang, Y., Wang, C., & Zhang, H. (2022) · China Automation Congress (CAC) · doi:10.1109/cac57257.2022.10054666 · Cited by 5
“Use the framework in this paper to build the basic industrial environment [21] of the Metaverse.”
MethodReddy, R. A., Kashif, S. B., Kumar, K. E., et al. (2023) · International Congress on Human-Computer Interaction, Optimization and Robotic Applications (ICHORA) · doi:10.1109/hora58378.2023.10155780 · Cited by 5
“Using deep learning algorithms in object detection leads to highly accurate results[7].”
BackgroundLearning with noisy labels via logit adjustment based on gradient prior method
Fu, B., Peng, Y., & Qin, X. (2023) · Applied Intelligence · doi:10.1007/s10489-023-04609-1 · Cited by 8
“Deep learning has achieved tremendous success in fields like text analysis, object recognition [1], and image classification.”
BackgroundYang, J., Yang, J., Luo, L., Wang, Y., Wang, S., & Liu, J. (2023) · Electronics · doi:10.3390/electronics12173711 · Cited by 8
“Recent advances in deep learning have led to remarkable success in computer vision tasks, including object recognition [1], object detection [2], and semantic segmentation [3].”
BackgroundRemote Monitoring of Amur Tigers in Forest Ecosystems Using Improved YOLOX Algorithm
Xie, Y., & Yu, W. (2023) · Forests · doi:10.3390/f14102000 · Cited by 5
Scene image recognition with knowledge transfer for drone navigation
Du, H., Wang, W., Wang, X., Jingqiu, Z., & Wang, Y. (2023) · Journal of Systems Engineering and Electronics · doi:10.23919/jsee.2023.000096 · Cited by 5
Oral Tissue Detection in Photographic Images Using Deep Learning Technology
Jaidee, E., Wongsapai, M., Suthachai, T., Theppitak, S., Ittichaicharoen, J., Warin, K., Suebnukarn, S., & Wuttisarnwattana, P. (2023) · International Computer Science and Engineering Conference · doi:10.1109/icsec59635.2023.10329780 · Cited by 6
“Additionally, the implementation of multi-reference and multi-resolution detection techniques in SSD significantly improves the detection accuracy of a one-stage detector, especially for smaller objects [10].”
BackgroundMethodInfluentialDATASET AND IMPROVED YOLOV7 FOR TEXT-BASED TRAFFIC SIGN DETECTION
Chi, X., Huang, H., Yang, J., Zhao, J. L., & Zhang, X. (2023) · The international archives of the photogrammetry, remote sensing and spatial information sciences/International archives of the photogrammetry, remote sensing and spatial information sciences · doi:10.5194/isprs-archives-xlviii-1-w2-2023-881-2023 · Cited by 5
Liang, B., Wang, X., Zhao, W., et al. (2023) · Sensors · doi:10.3390/s24010012 · Cited by 5
“According to the number of stages in the object recognition process, deep = learning-based methods for object recognition fall into two categories: two-stage series and one-stage series [16].”
BackgroundAutomated patient localization in challenging hospital environments
Jan, M. T., Garbin, C., Ruetschi, J., Marques, O., & Kalva, H. (2024) · Multimedia Tools and Applications · doi:10.1007/s11042-024-18118-x · Cited by 5
“In complex environments, the location of the patient may not be clear to the remote healthcare professional because of multiple pieces of equipment and personnel in the frame approaches [12].”
Wang, Z., Cao, T., Shi, B., Guo, W., & Ge, Q. (2023) · International Conference on Information Communication and Signal Processing (ICICSP) · doi:10.1109/icicsp59554.2023.10390757 · Cited by 5
“The main contribution of SSD is the introduction of multi-reference and multiresolution detection techniques, which significantly improve detection accuracy, especially for small objects [12].”
BackgroundAIGuard: Criminal Tracking in CCTV Footage Using MTCNN and ResNet
Singh, A., & Tiwari, R. K. (2024) · doi:10.1109/confluence60223.2024.10463292 · Cited by 5
“Object detection, a pivotal facet of computer vision that has undergone substantial evolution in the past two decades, encompassing both general and saliency target detection [3].”
BackgroundProgressive Learning Model for Big Data Analysis Using Subnetwork and Moore-Penrose Inverse
Zhang, W., Yang, Y., Li, Z., & Wu, Q. M. J. (2024) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2024.3375774 · Cited by 5
“First, it has been established in previous researches [52], [53] that pre-trained very deep networks struggle to be effective in remote sensing domains, such as radar signal processing, mainly due to the significant disparity be-tween remote-sensing images and everyday images.”
BackgroundSionkowski, P., Kruszewska, N., Kreitschitz, A., Gorb, S. N., & Domino, K. (2024) · Entropy · doi:10.3390/e26050380 · Cited by 5
“One line of future research will refer to the application of image segmentation meth-ods [85] and object detection (see recent methods proposed in [86,87]) with reference to the AI approach.”
MethodQuantifying Nematodes through Images: Datasets, Models, and Baselines of Deep Learning
Yuan, Z.-P., Musa, N., Dybal, K., Back, M. A., Leybourne, D. J., & Yang, P. (2023) · IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom) · doi:10.1109/trustcom60117.2023.00344 · Cited by 7
“Table II and Figure 1 show the details of these datasets.”
BackgroundRan, Q., Li, M., Zhao, B., He, Z., & Wu, Y. (2024) · Remote Sensing · doi:10.3390/rs16112026 · Cited by 5
“Two-stage target-detection algorithms first detect the candidate region where the target may exist and then classify the candidate region and target position [14].”
BackgroundA Comprehensive Investigation on Real—Time Object Detection in Deep Learning
Rajeshkumar, M., & Arun Raj., L. (2023) · International Conference on Advances in Electronics Computers and Communications · doi:10.1109/icaecc59324.2023.10560332 · Cited by 5
On Object Detection and Explainability with Sonar Imagery
El-Mihoub, T. A., Gadi, A., Nolle, L., & Stahl, F. T. (2024) · IEEE International Maghreb Meeting of the Conference on Sciences and Techniques of Automatic Control and Computer Engineering (MI-STA) · doi:10.1109/mi-sta61267.2024.10599670 · Cited by 7
“However, their performance trailed that of two-stages detectors, notably for small and dense objects [7].”
BackgroundMethodZhou, K., Wang, Y., Lv, T., Shen, Q., & Cao, X. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3449994 · Cited by 8
“Object detection has been a popular research topic that has received continuous attention over several decades [9].”
BackgroundImproved YOLOv8n for Foreign-Object Detection in Power Transmission Lines
Wang, H., Luo, S., & Wang, Q. (2024) · IEEE Access · doi:10.1109/access.2024.3452782 · Cited by 5
“Object detection is an important task in the field of computer vision [1], whose main purpose is to correctly recognize specific objects in an image or video.”
BackgroundSource-free Domain Adaptation for Video Object Detection Under Adverse Image Conditions
Zhang, X., & Chou, C.-H. (2024) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw63382.2024.00507 · Cited by 6
“Typically, labeling in the target domain is relatively scarce [28].”
Small Target Detection Algorithm for UAV Aerial Photography Based on Improved YOLO V8n
Li, X. L., & Bao, Y. (2024) · International Conference on Data-driven Optimization of Complex Systems (DOCS) · doi:10.1109/docs63458.2024.10704374 · Cited by 5
“…detection and two-stage detection, two-stage target detection algorithms are represented by R-CNN, Fast R-CNN, Faster R-CNN, R-FCN, etc.[1], which firstly generates the candidate region through the region proposing network, and then classifies and predicts the localisation of the…”
MethodAutomatic object detection for disassembly and recycling of electronic board components
Puttero, S., Nassehi, A., Verna, E., Genta, G., & Galetto, M. (2024) · Procedia CIRP · doi:10.1016/j.procir.2024.07.036 · Cited by 6
Zhang, R., Li, Y., & Guan, Z. (2024) · Scientific Reports · doi:10.1038/s41598-024-81430-x · Cited by 6
A Deep Learning-Based Mapping Model for Three-Dimensional Propeller RANS and LES Flow Fields
Jin, J., Ye, Y., Li, X., Li, L., Shan, M., & Sun, J. (2025) · Applied Sciences · doi:10.3390/app15010460 · Cited by 6
Cheng, X., Fang, Y., Feng, J., & Yin, H. (2025) · Signal Image and Video Processing · doi:10.1007/s11760-025-03877-3 · Cited by 5
“YOLOv8[22],releasedbyUltralyticsinearly2023,improves upon YOLOv5 [23], the improvement of YOLOv8 is to replace the C3 module in the YOLOv5 model with the C2f module.”
Deep-learning-based detection of underwater fluids in multiple multibeam echosounder data
Perret, T., Chenadec, G. L., Gaillot, A., Ladroit, Y., & Dupré, S. (2025) · Frontiers in Remote Sensing · doi:10.3389/frsen.2025.1532714 · Cited by 7
“Two families of object detection algorithms were proposed in recent years (Zou et al., 2023).”
NetraAadhaar: A Deep Learning-Driven Aadhaar Verification Platform for the Aid of Visually Impaired
Patil, A., Khan, T., & Mollah, A. F. (2025) · IEEE Access · doi:10.1109/access.2025.3563786 · Cited by 6
“Restrictions apply. in various images [13], [14].”
UTrack: Multi-object Tracking with Uncertain Detections
Solano‐Carrillo, E., Sattler, F., Alex, A., Klein, A., Costa, B. P., Rodríguez, Á. B., & Stoppe, J. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-91585-7_14 · Cited by 17
A comprehensive review on computer vision analysis of aerial data
Tetarwal, V., Kaur, M., & Kumar, S. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.111206 · Cited by 12
Zhao, Y., Ma, Q., Lei, G., Wang, L., & Guo, C. (2025) · Drones · doi:10.3390/drones9080551 · Cited by 5
Plata, I. T., Panganiban, E. B., Alado, D. B., et al. (2021) · International Journal of Advanced Computer Science and Applications · doi:10.14569/ijacsa.2021.0121234 · Cited by 5
AUPOD: End-to-End Automatic Poster Design by Self-Supervision
Huang, D., Li, J., Liu, C., & Liu, J. (2022) · IEEE Access · doi:10.1109/access.2022.3171033 · Cited by 7
“With the great success on various fundamental tasks in computer vision: image cropping [1], object detection [2], semantic segmentation [3] and others, some researchers turned to their application on automatic graphic design.”
BackgroundMengmeng, 吴. W., Zebin, 张. Z., Yaozhe, 宋. S., et al. (2023) · Laser & Optoelectronics Progress · doi:10.3788/lop213048 · Cited by 5
A Triple Deep Image Prior Model for Image Denoising Based on Mixed Priors and Noise Learning
Hu, Y., Xu, S., Cheng, X., Zhou, C., & Hu, Y. (2023) · Applied Sciences · doi:10.3390/app13095265 · Cited by 7
Team DETR: Guide Queries as a Professional Team in Detection Transformers
Qiu, T., Zhou, L., Xu, W., Cheng, L., Feng, Z., & Song, M. (2023) · Proceedings - International Conference on Image Processing · doi:10.1109/icip49359.2023.10222890 · Cited by 7
“Object detection is an essential task in computer vision, widely used in face recognition, autonomous driving, and security monitoring [1, 2, 3, 4].”
BackgroundHybrid Cross-Feature Interaction Attention Module for Object Detection in Intelligent Mobile Scenes
Tian, D., Han, Y., Liu, Y., Li, J., Zhang, P., & Liu, M. (2023) · Remote Sensing · doi:10.3390/rs15204991 · Cited by 5
Improving Cloud Detection in WFV Images Onboard Chinese GF-1/6 Satellite
Chang, H., Fan, X., Huo, L., et al. (2023) · Remote Sensing · doi:10.3390/rs15215229 · Cited by 5
Chang, L., Zhao, X., Yue, T., Yang, X., Li, C., Lin, S., & Zhou, J. (2023) · IEEE Transactions on Very Large Scale Integration (VLSI) Systems · doi:10.1109/tvlsi.2023.3330648 · Cited by 6
“To maximize the performance of the intelligent system, the specific AI processor is used to accelerate the AI tasks, including intelligent detection, automatic speech recognition, and automatic drive [1], [2], [3].”
MethodHausler, S., Garg, S., Chakravarty, P., Shrivastava, S., Vora, A., & Milford, M. J. (2023) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros55552.2023.10341550 · Cited by 4
“2D Object detection from monocular images is a wellstudied problem with recent advances heavily relying on deep learning [15]–[17], including popular earlier methods like Faster RCNN [18] and YOLO [19].”
MethodPoster: mmBox: mmWave Bounding Box for Vehicle and Pedestrian Detection Under Outdoor Environment
Gu, Z., Regmi, H., & Sur, S. (2023) · Proceedings/Proceedings - International Conference on Network Protocols · doi:10.1109/icnp59255.2023.10355609 · Cited by 5
“These boxes are essential for tasks like object tracking, instance segmentation, etc. [3].”
BackgroundLymphocyte Detection Method Based on Improved YOLOv5
Jiang, P., Li, Y., Liu, Y., et al. (2023) · IEEE Access · doi:10.1109/access.2023.3347451 · Cited by 5
“Significant advancements have been made in the development of object detection models over the years [5], leading to improved accuracy and efficiency.”
BackgroundJoshi, A., Amrita, A., Mathur, R. S., Kumar, N., & Tripathi, P. (2024) · Wiley eBooks · doi:10.1002/9781394200733.ch9 · Cited by 6
Lorenzo, G. D., Angelini, F., Pierallini, M., Tolomei, S., Benedittis, D. D., Denaro, A., Rivieccio, G., Caria, M. C., Bonini, F., Grassi, A., et al. (2025) · Scientific Data · doi:10.1038/s41597-025-05182-7 · Cited by 6
Chen, Q., Wen, J., Lin, T., & Ren, H. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2024.109994 · Cited by 5
RAW-Diffusion: RGB-Guided Diffusion Models for High-Fidelity RAW Image Generation
Reinders, C., Berdan, R., Beşbınar, B., Otsuka, J., & Iso, D. (2025) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61041.2025.00817 · Cited by 13
“Deep learning methods have demonstrated remarkable performance across various domains of computer vision [7, 22, 29, 30, 40, 62, 70, 71, 96], including significant improvements in object detection through data-driven approaches [8, 50, 67–69, 72, 100].”
HIFNet: wavelet transform-enhanced UAV object detection in complex conditions
Shang, L., Lei, H., Wu, Z., & Yang, W. (2025) · The Journal of Supercomputing · doi:10.1007/s11227-025-07338-z · Cited by 4
“With the rapid advancement of deep learning technology, especially the widespread adoption of Convolutional Neural Networks (CNNs), the significance of object detection in the field of computer vision becomes increasingly prominent [1, 2].”
DISO-DETR: A Detail-Enhanced Infrared Small Object Detection Transformer Based on UAV Imagery
Liu, Y., Jin, T., & Hui, B. (2025) · International Conference on Software Engineering and Computer Science (CSECS) · doi:10.1109/csecs64665.2025.11009603 · Cited by 4
“Object detection, a fundamental technology in the field of computer vision, has evolved over several decades [6], progressing from classical two-stage algorithms, such as the R-CNN series [7], to single-stage algorithms like SSD [8] and YOLO [9].”
Chimienti, M., Kato, A., Seydi, V., Schoombie, S., Hinke, J. T., Joy, R., Lidgard, D. C., Oosthuizen, W. C., Papastamatiou, Y. P., Ropert‐Coudert, Y., et al. (2025) · Methods in Ecology and Evolution · doi:10.1111/2041-210x.70063 · Cited by 7
Recognition of suspended particles based on Mueller matrix microscopic imaging and deep learning
Li, J., Jiang, C., Hu, Y., Yao, L., & Zhang, S. (2025) · Marine Pollution Bulletin · doi:10.1016/j.marpolbul.2025.118330 · Cited by 4
MRC-DETR: A High-Precision Detection Model for Electrical Equipment Protection in Power Operations
Li, S., Zhou, Y., Wang, M., Li, L., & Wu, T. (2025) · Sensors · doi:10.3390/s25134152 · Cited by 6
“Object detection is a core task in computer vision, aimed at locating all objects in an im‑ age and identifying their categories [37].”
FAMNet: A Lightweight Stereo Matching Network for Real-Time Depth Estimation in Autonomous Driving
Zhang, J., Tong, Q., Yan, N., & Liu, X. (2025) · Symmetry · doi:10.3390/sym17081214 · Cited by 5
Finding New Hot Subdwarf Stars in SDSS Images
Zhang, J., Bu, Y., Wu, H., Zhang, Y., Li, S., Lei, Z., Yi, Z., Kong, X., & Liu, M. (2025) · The Astronomical Journal · doi:10.3847/1538-3881/adccb5 · Cited by 4
PADetBench: Towards benchmarking texture- and patch-based physical attacks against object detection
Lian, J., Jianhong, P., Wang, L., Wang, Y., Mei, S., & Chau, L. (2025) · Knowledge-Based Systems · doi:10.1016/j.knosys.2025.114395 · Cited by 9
An improved cross-dimensional collaborative bridge defect detection model based on UAV images
Ni, J., Ji, Q., Zhao, Y., Cao, W., & Shi, P. (2025) · Measurement Science and Technology · doi:10.1088/1361-6501/ae09c0 · Cited by 4
“In another study, Zou et al [40] integrated YOLOv4 with separable convolution to detect various defects, including cracks, flaking, and exposed rebar.”
Rao, Y., An, T., Xuan, Y., Wang, R., Zhou, Q., Guan, H., & Li, M. (2025) · npj Heritage Science · doi:10.1038/s40494-025-02079-x · Cited by 6
Zhou, Y., & Zhao, B. (2025) · PeerJ Computer Science · doi:10.7717/peerj-cs.3322 · Cited by 9
Yang, C., Sheng, H., Kolbinson, K. T., Shaterian, H., Ashe, P. C., Gao, P., Zhang, W., Quilichini, T. D., & Xiang, D. (2025) · Plant Methods · doi:10.1186/s13007-025-01451-z · Cited by 4
Wang, X., Wang, Y., Bai, M., & Ma, Q. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2025.3635890 · Cited by 10
“O BJECT detection is a crucial field of computer vision [1], with applications in a range of domains, including autonomous driving, face recognition, and image analysis [2], [3], [4], [5], [6], [7].”
Qu, Y., Chow, C.-O., Chuah, J. H., & Soon, K. L. (2025) · Advances in Space Research · doi:10.1016/j.asr.2025.08.042 · Cited by 7
A YOLO-OC real-time small object detection in ocean scenes
Zhang, Y., Qin, T., & Zhou, Y. (2026) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2025.104625 · Cited by 4
Patel, M. K., Bull, G., Egan, L. M., Swain, N., Rolland, V., Stiller, W. N., & Conaty, W. C. (2026) · Biosystems Engineering · doi:10.1016/j.biosystemseng.2025.104379 · Cited by 5
Performance analysis of Convolutional Neural Networks on edge devices for Computer Vision tasks
Bricola, A., Noceti, N., & D’Agostino, D. (2026) · Array · doi:10.1016/j.array.2026.100692 · Cited by 5
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.