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 2,301–2,400 of 3,144
Khalzaa, K., Karungaru, S., Terada, K., & Ayush, A. (2024) · International Symposium on Computer Science and Educational Technology (ISCSET) · doi:10.1109/iscset58624.2024.10807863 · Cited by 1
Camouflage Object Detection Algorithm Based on Improved YOLOv8n
Wang, Z., Wang, H., Zhang, W., & Zhao, P. (2024) · Communications in computer and information science · doi:10.1007/978-981-96-0313-8_27
Yi, D., Kong, X., Xia, Y., et al. (2024) · Journal of Physics Conference Series · doi:10.1088/1742-6596/2891/15/152020
Multi-path spatial attention for human pose estimation in complex scenes
Ruan, H., & Chen, X. (2024) · International Conference on Computer Information Science and Artificial Intelligence (CISAI) · doi:10.1145/3703187.3703283
“In recent years, attention mechanisms have been significantly developed and have performed well in tasks such as object detection [ 6 ] and image classification [ 7 ] .”
MOPE-YOLO: Improved Laboratory Safety Detection Algorithm Based on YOLOv8
Song, B. (2024) · International Conference on Computer Information Science and Artificial Intelligence (CISAI) · doi:10.1145/3703187.3703267
“With the development of artificial intelligence, detection tasks [5] are a hot research direction, which mainly combines two key technologies: target localization [6] and recognition [7].”
Automated Object Detection and Recognition in Satellite Imagery Using CNNs
Shanthi, H. J., Shobana, G., Kamalanaban, E., et al. (2024) · doi:10.1109/icicec62498.2024.10808576
RetractedTraining a Segmentation-Based Visual Anonymization Service for Street Scenes
Korb, M., & Werner Bailer, A. (2024) · Lecture notes in computer science · doi:10.1007/978-981-96-2074-6_26
Dung, T. A., Tanh, T. T., & Nguyen, K.-D. (2024) · International Conference on Control, Automation and Information Sciences (ICCAIS) · doi:10.1109/iccais63750.2024.10814389
“Object detection [1] [2] [3] is a common problem in the field of computer vision that aims to detect objects in images and videos.”
Mukhopadhyay, A., Pal, I., Pramanick, N., et al. (2025) · Journal of the Indian Society of Remote Sensing · doi:10.1007/s12524-024-02077-9
Xue, H., Ma, J., Yang, Y., et al. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5081464
Adaptive Shape Imitation and Selective Semantic Guidance for Industrial Surface Defect DetectionPreprint
Liang, X., Li, Y., Wang, X., et al. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5088043
Single- Frame Background Reconstruction Based on Image Semantic Propagation
Zhang, Y., Li, P. W., Xu, Y., Zhu, Q., He, Y., & Zhang, M. (2024) · International Conference on Control, Automation, Robotics and Vision (ICARCV) · doi:10.1109/icarcv63323.2024.10821580
Nearly Time-Optimal Online Pick and Place Trajectory Computation Using Quadratic ProgrammingPreprint
Marauli, T., Gratt, F., Gattringer, H., et al. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5089413
Song, M.-G., Kim, S., & Suh, J.-H. (2025) · Journal of the Korean Society for Precision Engineering · doi:10.7736/jkspe.024.097
To Detect, and Beyond: Integrating Text-Guided Object Detection and Super-Resolution
Yook, H. J., Chung, H. J., Choi, Y. C., Kim, S. Y., Kim, T. H., & Lee, Y. K. (2024) · International Conference on Information and Communication Technology Convergence (ICTC) · doi:10.1109/ictc62082.2024.10827061
Rapider-YOLOv7: Lightweight Infrared Object Detection Network
Xu, P., Yu, Y., Zou, R., et al. (2024) · International Conference on Pattern Recognition and Artificial Intelligence (PRAI) · doi:10.1109/prai62207.2024.10827808
“Object detection is one of the primary tasks in computer vision[1-2].”
Deep Learning-based Monitoring and Tracking System for Category 1 Livestock Infectious Diseases
Park, T., Shin, H., & Jung, J. (2024) · The Journal of Korean Institute of Information Technology · doi:10.14801/jkiit.2024.22.12.47
ML-Based Analysis on a Live Video Feed
Sharma, R., Bansal, K., Sharma, Y. K., & Shrivastava, S. (2024) · International Conference on Contemporary Computing and Informatics (IC3I) · doi:10.1109/ic3i61595.2024.10828746
“[5] provided a thorough study of things discovery strategies covering over 2 years, from the 1990s to 2022.”
YOLOv10 Computer Vision Performance Measurement for Agricultural Vacuum Seed Meters
Blaser, M., Porter, W., Fuhrer, L., et al. (2024) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata62323.2024.10825689
“Nowadays, object detection with computer vision is crucial for the evolvement of self-driving cars, robot vision, and video surveillance [17].”
Integrating Multiple Deep Learning Models for Disaster Description in Low-Altitude Videos
Wang, H. (2022) · University of North Texas Digital Library (University of North Texas) · doi:10.12794/metadc2048642
Automated Detection of Multi-type Small Lesions in CT Images Based on Deep Learning
Li, S. Z., Samonte, M. J. C., & Yan, F. (2024) · International Conference on Image, Vision and Computing (ICIVC) · doi:10.1109/icivc61627.2024.10837307
“At present, CNN algorithms for image recognition and detection are mainly divided into a one-stage detection model and a two-stage detection model [3].”
Discrete Anomalous Regions (DAR) - Going Beyond Heatmaps and Predicting Actionable Discrete Regions
Taylor, A. D. J., Morrison, J. J., Tregidgo, P., & Campbell, N. D. F. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-77389-1_25
Yan, R., Yin, Z., Dai, C., et al. (2025) · Digital Signal Processing · doi:10.1016/j.dsp.2025.105014
A Novel Physical World Adversarial Patch Attack for Infrared Pedestrian Detector
Liu, Z., Dai, J., & Geng, J. (2024) · IEEE International Conference on Unmanned Systems (ICUS) · doi:10.1109/icus61736.2024.10840169
“With the continuous innovation of deep learning research, deep neural networks have been widely applied in tasks such as image classification [1], object detection [2], object tracking [3], and image segmentation [4].”
An enhanced YOLOv8 and its application for risk prevention in underground excavation operations
Liu, T., Li, K., Pu, Y., Zhu, H., & Yi, J. (2024) · International Conference on Signal Processing · doi:10.1109/icsp62129.2024.10846727
“Although object detection has made great progress [19], there are still great problems and challenges.”
Two-Stage Residual Projection Network for Image Bit-Depth Enhancement
Liu, Z., Wang, Y., Sang, Y., et al. (2025) · IEEE Access · doi:10.1109/access.2025.3536302
“With the great success of deep learning in computer vision (CV), which applies to a variety of CV tasks such as super-resolution [24], [25], deblurring [26], [27], denoising [28], [29], other tasks [30], [31], [32].”
Ereken, Ö. F., & Tarhan, Ç. (2025) · Academic Platform Journal of Engineering and Smart Systems · doi:10.21541/apjess.1542885
Study on defect detection in lightweight insulators based on improved YOLOv8
Wang, P., Liu, Z., Cheng, X., et al. (2024) · Journal of Computational Methods in Sciences and Engineering · doi:10.1177/14727978241304269
Mdlis: An Integrated Model- and Data-Driven Method for Low-Light Instance SegmentationPreprint
Zhang, Y., Guo, J., Yue, H., Zheng, S., & An, G. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5123319
Deep-Optimal Leucorrhea Detection Through Fluorescent Benchmark Data Analysis
Li, S., Omer, A. M., Duan, Y., Fang, Q., Hamad, K. O., Fernandez, M., Lin, R., Wen, J., Wang, Y., Cai, J., et al. (2025) · Journal of Imaging Informatics in Medicine · doi:10.1007/s10278-025-01428-3
“In the contemporary landscape of medical image object detection, deep learning models are commonly categorized into three main groups: one-stage, two-stage, and transformer models [22, 23].”
A Method for Extracting Small Water Areas Based on an Improved FPN Network
Yu, Y., Wang, M., Zhao, Q., et al. (2025) · International Conference on Ubiquitous Information Management and Communication (IMCOM) · doi:10.1109/imcom64595.2025.10857523
“Meanwhile, with the continuous advancement of artificial intelligence algorithms, deep learning has made significant progress and breakthroughs in the field of computer vision, especially in areas such as object classification, image segmentation, and object detection[8], [9], [10], [11].”
YOLOv8-GR: Gesture Recognition by Improving of YOLOv8 Algorithm
Ding, Y., Guo, N., & Meng, H. (2024) · International Conference on Advanced Cloud and Big Data · doi:10.1109/cbd65573.2024.00070
“Compared to the two-stage algorithm, such as Faster R-CNN [3], one-stage gesture recognition algorithms (e.g. YOLO-You Only Look Once, SSD-Single Shot MultiBox Detector) have the advantage of high speed, and are more suitable for deployment on edge devices [4].”
An Image Based Automatic Water Level Monitoring System
Wang, Y., Li, M., Chen, F., Xu, J., & Lu, G. (2024) · International Conference on Artificial Intelligence and Computer Engineering (ICAICE) · doi:10.1109/icaice63571.2024.10864180
“Deep learning-based detection methods are capable of extracting deep features of the object, which results in better robustness against variations in the object [5].”
Uriti, A., & Pothabathula, N. J. (2024) · doi:10.1109/ic-sit63503.2024.10862633
Candela, F., Capua, C. D., Morabito, A. F., Morabito, F. C., & Restuccia, F. (2024) · IEEE International Workshop on Technologies for Defense and Security (TechDefense) · doi:10.1109/techdefense63521.2024.10863301
“Over the past 20 years, despite significant advancements in object recognition technology [6], the dual requirement of ground and aerial recognition remains a substantial challenge, as each context presents unique characteristics and difficulties.”
Fan, J., Shen, J., Zhao, Z., et al. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5123338
Advancements and Applications in Object Detection and Pattern Recognition
Govinda Rajulu., G., Savija, J., Shereen Priscila, S., Anish, T. P., Nalini, M., & Siva Subramanian, R. (2024) · International Conference on Sustainable Communication Networks and Application (ICSCNA) · doi:10.1109/icscna63714.2024.10864220
“In security & surveillance, these technologies improve real-time monitoring & threat detection, facial recognition, as well the implementation of anomaly detection systems that improve the safety of the public [4].”
Tajane, K., Khutale, P., Kore, A., et al. (2024) · International Conference on Advancements and Key Challenges in Green Energy and Computing (AKGEC) · doi:10.1109/akgec62572.2024.10868812
Tiny Target Detection with Adaptive Weighted Feature Fusion in UAV Images
Kang, X., Zheng, L., Deng, Z., Han, Y., Tang, L., & Deng, C. (2024) · IEEE International Conference on Signal, Information and Data Processing (ICSIDP) · doi:10.1109/icsidp62679.2024.10868873
Enhancing Robot Perception using Vision-Aware Cognition Model
Qu, J., Hanai, R., Ramírez-Alpizar, I. G., Domae, Y., & Miwa, S. (2025) · IEEE/SICE International Symposium on System Integration (SII) · doi:10.1109/sii59315.2025.10871077 · Cited by 1
“These models form the foundation for various high-level visual tasks such as image classification [11], object detection [12] and image segmentation [13].”
Open-Set Remote Sensing Object Detection Using Edge Information Extraction
Li, X., Dang, S., Sun, Y., et al. (2024) · IEEE International Conference on Signal, Information and Data Processing (ICSIDP) · doi:10.1109/icsidp62679.2024.10869041
State-of-the-art deep learning techniques for object identification in practical applications
Kanthirekha, M., & Padmaja, R. B. (2024) · i-manager’s Journal on Pattern Recognition · doi:10.26634/jpr.11.2.21475
Prefabricated Pizza Defect Detection Algorithm Based on CNN and Transformer
Sun, F., & Qu, Q. (2024) · China Automation Congress (CAC) · doi:10.1109/cac63892.2024.10864511
Uncertainty-Aware Cross-Modality Fusion for Visible-Infrared Object Detection
Zhao, J., Wang, Y., Zhang, Y., et al. (2024) · International Conference on Digital Image Computing: Techniques and Applications (DICTA) · doi:10.1109/dicta63115.2024.00029
Self-citationVisual Blind Spot Detection System for Bus Drivers Based on Lightweight Model
Jiang, B., Qian, J., Sun, J., et al. (2024) · doi:10.1145/3696474.3708460
“Zou et al. [3] summarized the object detection algorithms from the past 20 years, which can be categorized into two major types.”
A Review of Small-Sample Target Detection Research
Zhou, L., Wang, C., Shuai, Y., & Huang, P. (2025) · Lecture notes in electrical engineering · doi:10.1007/978-981-96-2625-0_13 · Cited by 1
yaguang, Z., Dong, L., Liu, M., et al. (2025) · Sixth Symposium on Novel Optoelectronic Detection Technology and Applications · doi:10.1117/12.3057037
Visual Detection and Identification of UAV s by YOLO Networks
Vaščák, J., Nepokrytyi, Y., Papcun, P., & Mičko, K. (2025) · IEEE World Symposium on Applied Machine Intelligence and Informatics (SAMI) · doi:10.1109/sami63904.2025.10883263
Pargi, M. K., Abraham, A., & Nagavarapu, S. C. (2025) · Lecture notes in intelligent transportation and infrastructure · doi:10.1007/978-3-031-72959-1_12 · Cited by 1
Traffic lights detection based on enhanced YOLOv5
Qian, Y., Liu, Y., Zhang, Z., et al. (2024) · International Conference on Electronic Information Technology and Computer Engineering (EITCE) · doi:10.1145/3711129.3711192
RF-Vision: Object Characterization using Radio Frequency Propagation in Wireless Digital TwinPreprint
Amatare, S., Gao, W., Kharel, A., et al. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5136513
Vision Module for Automatic Tracking on Bedside Intelligent Scope‐Holding Surgical Robot System
Wang, T., Yin, M., Shi, S., et al. (2025) · International Journal of Medical Robotics and Computer Assisted Surgery · doi:10.1002/rcs.70046
“Some researchers posit that the advent of deep learning represents a significant demarcation point in the evolution of target detection [11].”
Materials Classification via Piezoelectric Sensors for Robotic Grippers
Sabir, H. M. S., Mehmood, A., Tahir, M. H., Tahir, M. S., Elahi, H., & Tayyab, M. A. (2024) · International Conference on Robotics and Automation in Industry (ICRAI) · doi:10.1109/icrai62391.2024.10894683 · Cited by 1
“To achieve this goal various technologies for material classification have been adopted over the past years [1].”
FMA-YOLO: An Algorithm for Detecting Vehicles and Pedestrians in Infrared Road Scenarios
Cong, X., Li, Z., & Zi, L. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-81806-6_5
Jegadeesan, S., N., J., & Pradeep King, R. (2025) · doi:10.1109/icmsci62561.2025.10894208
“Zou et al. [5] did a 20-year survey on object detection, where trends such as shifting from feature engineering to end-to-end learning and increasing importance of benchmark datasets are noticed.”
Li, B., Chen, Q., Lv, B., Wang, K., & Li, X. (2025) · Journal of Electronic Imaging · doi:10.1117/1.jei.34.1.013056 · Cited by 1
Domain Adaptation for Object Detection via Adversarial Attack Augmentation
Nikitin, A., Горбачев, В. А., & Syrovatkin, S. (2025) · Studies in computational intelligence · doi:10.1007/978-3-031-80463-2_12
CIFAR-10 Object Detection Using ResNet-50 Model
Kumar, V., & Rajput, A. (2025) · Lecture notes in networks and systems · doi:10.1007/978-981-97-8836-1_26 · Cited by 4
Learning to Mine Context Information for Remote Sensing Small Object Detection
Li, L., Tang, J., Chi, Z., Niu, Y., Ren, J., Li, L., Yao, X., Cheng, G., & Han, J. (2025) · Lecture notes in electrical engineering · doi:10.1007/978-981-96-2236-8_30
Real-Time Automatic Checkout via Prompt-Based Product Extraction and Cross-Domain Learning
Pettersson, T., Riveiro, M., & Löfström, T. (2024) · International Conference on Machine Learning and Applications · doi:10.1109/icmla61862.2024.00217
“In the last decade, object detection has been mainly driven by deep learning methods [25], which are generally divided into one-stage and two-stage detectors.”
ASPoT8: An Efficient 8-bit Quantization Balancing Hardware and Accuracy for Object Detection
Hui, L. I., Xiaofeng, Y. A. N. G., Zheng, Z., Li, J., & Lu, S. (2025) · IEICE Transactions on Information and Systems · doi:10.1587/transinf.2024edl8089
LRDN: Lightweight Risk Detection Network for Power System Operations
Liu, L., Chen, Y., Feng, Y., Peng, T., Hu, X., & Jiang, M. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-2681-6_6 · Cited by 1
Liu, L., Chen, L., Yu, F. Q., et al. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-2681-6_5
Narayana, D., Jayakumar, C., Raghuram, S., et al. (2024) · IEEE Region 10 Conference (TENCON) · doi:10.1109/tencon61640.2024.10902871
“Starting with AlexNet in 2012 with about 10 layers, to VGG19 in 2014 and to ResNet101 in 2015 to DenseNet201 in 2017 the number of layers has increased from 10 to 201 [10].”
The Requirements and Constraints of Self-built Data Set on Detection Transformer in Complex Scenario
Shi, J., Wang, M., Liu, X., Zhang, Y., & Li, Y. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-2911-4_25
Learning discontinuity in orientation with cosine metric in real-oriented object detection
Lu, X., Kuang, G., Wu, Z., Wang, X., Yang, J., Chen, Q., & Liu, X. (2025) · International Conference on Video and Image Processing (ICVIP) · doi:10.1117/12.3059227
Laser Spots Array Detection for Structured-Light Endoscope
Jiang, Y., Zhao, Z., Cai, M., & Shuai, J. (2024) · International Conference on Machine Vision, Image Processing and Imaging Technology (MVIPIT) · doi:10.1109/mvipit65697.2024.00020
“…of the 16 pixels of the position x [1,16], with the middle pixel value is compared to obtain the state value of the value of the S, when if there are n consecutive points than the center of the intensity of the pixel p are greater, or are small then such a center point is a corner point [17][18] .”
Logomask: Robust Web Logo Detection by Hypergraph-Induced Text MaskingPreprint
Hu, C., Yang, Y., Li, S., et al. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5180564
Object detection driven composite block motion estimation algorithm for surveillance video coding
Pal, A. K., Biswas, B., Jichkar, M. D., Jena, A. N., & Kumar, M. (2025) · Multimedia Tools and Applications · doi:10.1007/s11042-025-20722-4
“Object detection [6] is a computer vision task that involves identifying and localizing objects within an image or a video stream.”
SequenceOut: Boosting CNNs by Freezing Layers
Prasad, S., Paul, R., & Kamat, M. (2025) · IEEE Signal Processing Letters · doi:10.1109/lsp.2025.3553430
“T HE integration of deep neural networks (DNNs) has rev-olutionized various computer vision (CV) tasks, excelling in areas such as image classification [1], [2], object detection [3], segmentation [4], and super-resolution [5].”
Elhanashi, A., & Saponara, S. (2025) · Elsevier eBooks · doi:10.1016/b978-0-443-30078-3.00001-9
SUS-ODRP: Object Detection and Relative Positioning Algorithm for Smartphone Unmanned Systems
Deng, H. Y., Zhang, M., & Wang, X. (2025) · Lecture notes in electrical engineering · doi:10.1007/978-981-96-3572-6_49
Defect detection of reactor pressure vessel sealing surface based on deep learning
Qin, M., & Qin, D. (2024) · International Symposium on Artificial Intelligence and Intelligent Manufacturing (AIIM) · doi:10.1109/aiim64537.2024.10934672
A Fire and Environmental Object Detection Method Baesd on Jointly Optimized YOLOv7
Zhang, Z. (2024) · International Conference on Computer, Big Data and Artificial Intelligence (ICCBD+AI) · doi:10.1109/iccbd-ai65562.2024.00017
“[37].”
Monocular 3D Object Detection using YOL011 and MiDAS for Autonomous Driving
Abdou, H. M., & Mashaly, M. E. (2024) · International Conference on Computer and Applications (ICCA) · doi:10.1109/icca62237.2024.10928166 · Cited by 1
“Figures 1, 2 and 3 present the detected objects alongside their respective 3D bounding boxes projected onto the scene.”
InfluentialTarabay, A., & Daher, N. A. (2025) · International Conference on Control, Automation, and Instrumentation (IC2AI) · doi:10.1109/ic2ai62984.2025.10932182
“Localizing and classifying objects are needed in many applications including, but not limited to, autonomous vehicles, surveillance and security, and robotics [3].”
Application of Computer Vision Methods to Old Tatar Text Recognition
Valishin, I. A. (2024) · Automatic Documentation and Mathematical Linguistics · doi:10.3103/s0005105525700256
Car Number Plate Recognition Scheme Using Morphology and Backpropagation Neural Network
Hussein, I. S., & Jasim, N. A. (2025) · Malaysian Journal of Science and Advanced Technology · doi:10.56532/mjsat.v5i1.434
“A review [5] states various methods for detecting objects in videos and images. like extraction and identification.”
Muley, R. R., BalaChowdeswari, M., Reshma, S., et al. (2025) · Smart innovation, systems and technologies · doi:10.1007/978-981-96-0143-1_26
Background-Enhanced Visual Prompting Transformer for Generalized Few-Shot Semantic Segmentation
Li, M., & Ma, X. (2025) · Electronics · doi:10.3390/electronics14071389
RAPTOR-AI: An open-source AI powered radiation protection toolkit for radioisotopes
Watabe, H., Yu, K. N., Krstic, D. Z., Nikezic, D. R., Kim, K. M., Yamaya, T., Kawachi, N., Tanaka, H., Jovanović, Z. D., Haque, A. K. F., et al. (2025) · Applied Radiation and Isotopes · doi:10.1016/j.apradiso.2025.111797
Yolov10-Based Student Activity Identification as Personalization of Appropriate Learning Methods
Nabil, F., Ayuningtyas, T. S., & Putra, J. A. (2024) · Beyond Technology Summit on Informatics International Conference (BTS-I2C) · doi:10.1109/bts-i2c63534.2024.10942238
“Although the challenge in object detection in classrooms is to recognize an image and provide each object with positional information about the box, YOLO can be used to monitor student activity in the classrooms [17].”
EUPHRÁSIO, F. P. A., de Andrade, R. M., Shiguemori, E. H., Silva, L. L., Freitas, M., Xavier, N. A. Z., & Sobrinho, A. S. D. S. (2025) · Anais da Academia Brasileira de Ciências · doi:10.1590/0001-3765202520240623
A Target Detection Algorithm for Marks Layout in Detail Drawings of Steel Structure
Man, Y., Zhang, Q., Cai, Y., & Chang, Z. (2025) · International Journal of Steel Structures · doi:10.1007/s13296-025-00952-w · Cited by 1
Kim, G.-N., Lee, H. W., Lee, H.-J., Jung, H.-J., & Choi, S.-H. (2025) · IEEE Access · doi:10.1109/access.2025.3558526
“Deep learning has rapidly emerged as a core technology in various fields, such as image classification [1], object detection [2], [3], and natural language processing [4], driving breakthroughs in automation and decision-making processes.”
A Generic Vehicle-to-Sensor Calibration Framework
Hu, S., Yoo, Y., Kim, J., Lim, C., Cho, D., & Kang, B. (2025) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61041.2025.00583
“The pursuit of fully autonomous vehicles has been a central focus of research for decades, leading to substantial advancements in critical areas such as object detection, lane detection, and depth estimation [17, 40, 43].”
Bit-Flip Induced Latency Attacks in Object Detection
Sistla, M., Yu, W., Shah, A. B., Huang, C., Wang, L., Wu, X., Chen, J., Pan, M., & Fu, X. (2025) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61041.2025.00653 · Cited by 1
“…of deep learning and computer vision have garnered significant attention for their pivotal roles in advancing intelligent systems, particularly in domains like autonomous driving and real-time surveillance, where OD stands as an indispensable component tasked with crucial responsibilities [41].”
DyRoNet: Dynamic Routing and Low-Rank Adapters for Autonomous Driving Streaming Perception
Huang, X. L., Cheng, Z.-Q., He, J.-Y., Li, C., Xiang, W., & Sun, B. (2025) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61041.2025.00581 · Cited by 4
“Traditional object detection algorithms [40], while effective in various contexts, often confront the challenge of latency due to inherent computational delays.”
Shapley Consensus Deep Learning for Ensemble Pruning
Djenouri, Y., Belbachir, A. N., Belhadi, A., Belmecheri, N., & Michalak, T. (2025) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61041.2025.00648
“Deep learning has garnered significant attention in computer vision applications, including classification [22], segmentation [23], and object detection [37].”
Ucurum, E., Birch, P. M., Han, X., Tian, Y., Young, R., & Chatwin, C. R. (2025) · Drones and autonomous vehicles/Drones and Autonomous Vehicles · doi:10.70322/dav.2025.10007 · Cited by 1
A Corrosion Object Detection Model Based on Yolov8n and Image Preprocess Methods
Zhao, Z., Bakar, E. B. A., Razak, N. B. A., et al. (2024) · International Conference on Control, Robotics and Cybernetics (CRC) · doi:10.1109/crc63701.2024.10949857
“Object detection, one of the most basic and difficult issues in computer vision, has drawn a lot of attention recently[9], which is the process of identifying the categories to which each item belongs and its location inside a given picture (object classification and object localization)[10].”
Small Defect Detection of Power Electronic Devices Based on YOLO-DHGC
Chen, L., Su, L., Li, T., & Yin, F. (2025) · Lecture notes in electrical engineering · doi:10.1007/978-981-96-4063-8_4
Real-Time Traffic Sign Detection and Recognition System using Computer Vision and Machine Learning
Sahu, M. B., Pudale, A., Kurudkar, T., et al. (2025) · International Journal of Advanced Research in Science Communication and Technology · doi:10.48175/ijarsct-25171
Small Target Detection Algorithm Based on SDBNet and Multiple Detection Heads
Wu, S., Zhao, C., & Qu, L. (2024) · International Conference on Image Processing, Computer Vision and Machine Learning (ICICML) · doi:10.1109/icicml63543.2024.10957927
UCA-YOLOv8n: a real-time and efficient fruit chunks detection algorithm for meal-assistance robot
Liu, F., & Hu, M. (2025) · PeerJ Computer Science · doi:10.7717/peerj-cs.2832
Trajectory Similarity-Based Traffic Flow Analysis Using YOLO+ByteTrack
Jang, J.-G., & Kwon, Y. (2025) · Journal of Multimedia Information System · doi:10.33851/jmis.2025.12.1.27 · Cited by 3
Towards Elephants Intelligent Monitoring in Zakouma National Park, Chad
Djibrine, O. H., Ahmat, D., Youssouf, A., & Ngueilbaye, A. (2025) · Communications in computer and information science · doi:10.1007/978-3-031-85933-5_7
Zhou, S., Yan, X., Liu, H., & Gong, C. (2025) · Sensors · doi:10.3390/s25082606 · Cited by 1
“The research can be classified into three categories: traditional filtering-based methods, sparse and low-rank representation-based methods, and data-driven methods [8].”
YOLO Meets FedAVG: A Privacy-Preserving Approach to Autonomous Vehicles Object Detection
Alahdal, N. M., Abukhodair, F., Meftah, L. H., & Cherif, A. (2025) · International Conference on Advanced Innovations in Smart Cities (ICAISC) · doi:10.1109/icaisc64594.2025.10959368 · Cited by 1
“The reliance on centralized data may limit the diversity of training sets, potentially impacting model performance in real-world scenarios [18].”
Towards Reflected Object Detection: A Benchmark
Wu, Y., Wang, Z., Wu, Y., Huang, L., Zhou, H., & Li, S. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-5809-1_9 · Cited by 2
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.