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 2,701–2,800 of 3,144
Fight light with light: A review of physical adversarial attack within light transmission pipeline
Li, G., Xu, S., Cao, Y., Cao, M., & Zhang, Y. (2026) · Neurocomputing · doi:10.1016/j.neucom.2026.133034 · Cited by 3
Enhance Panoramic Object Detection Using Planar Image Datasets
Yu, L., Zhao, Q., Wang, B., Liu, X., Zhao, W., Wang, T., He, H., Dai, F., & Yan, C. C. (2026) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2026.3664985
“This disparity has constituted a critical obstacle, leading to a lower performance level in panoramic object detection as compared to planar object detection [13], and thereby impeding further research efforts.”
SFD-YOLO for small-object fragment impact detection in warhead target-plate testing
Liu, H., Ding, Y., You, W., & Li, Y. (2026) · Scientific Reports · doi:10.1038/s41598-026-40457-y
Enhanced mango fruit detection based on edge artificial intelligence
Lu, S., Li, L., Ren, Z., Wang, X., Yu, X., & Liang, Y. (2026) · Engineering Research Express · doi:10.1088/2631-8695/ae4675
Zhang, W., Liang, Y. L., Tao, J., Yang, Q., Liu, Z., & Li, C. Q. (2026) · CHAIN · doi:10.23919/chain.2026.000003
Gautron, R., Seurin, M., Rahn, E., Faye, É., & Bunn, C. (2026) · Smart Agricultural Technology · doi:10.1016/j.atech.2026.101901
Implementation of a Fallen Person Detector
Kim, J., & Kim, G.-W. (2025) · International Conference on Information and Communication Technology Convergence (ICTC) · doi:10.1109/ictc66702.2025.11388322
MS-DETR: Progressive Multi-Stage Feature Refinement for Small Object DetectionPreprint
Zhao, X., Wang, Z., Li, L., Shao, X., Yu, N., & Hu, M. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6278336 · Cited by 1
Marker-based Lightweight Monocular Visual Localization for Low-Cost Mobile Robot
Gao, H., Lu, Z., Zhao, Y., Li, X., & Wu, H. (2025) · IEEE Smart World Congress (SWC) · doi:10.1109/swc65939.2025.00091
“There are recent researches that focus on applying visual localization for robots [7].”
AMFF-YOLO: Low-Light Object Detection Method Based on Adaptive Multi-Scale Feature Fusion
Zhu, Z., Zheng, H., Yang, D., et al. (2025) · doi:10.1109/icairc68035.2025.11385236
“Object detection, a core task in computer vision, plays a vital role in autonomous driving, industrial inspection, and security monitoring [1].”
A Lightweight Small Target Detection Algorithm for UAV Aerial Photography Scenarios
Xiao, P., Yang, H., Jin, R., & Tang, D. (2025) · International Conference on Robotics, Intelligent Control and Artificial Intelligence (RICAI) · doi:10.1109/ricai68060.2025.11385014
“While one-stage algorithms ensure high inference speed, they suffer from insufficient feature extraction and poor multi-scale adaptability in small target tasks [6].”
Edge-Assisted Multi-Vehicle Cooperative Perception: An Approach Based on Relative Pose Estimations
Zhao, Y., He, S., Xiao, M., Wu, J., Shao, J., & Cai, J. (2026) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2026.3664614
“Two types of detectors are commonly used for 2D object detection: two-stage and single-stage detectors [21].”
A Real-Time Object Detection Model for Indoor Mobile Robots Based on YOLOv8-LCFD
Fan, Q., & Liu, J. (2025) · International Conference on Robotics, Intelligent Control and Artificial Intelligence (RICAI) · doi:10.1109/ricai68060.2025.11385029
“Object detection [1] , as one of the core tasks in computer vision, aims to accurately identify and localize various objects in a scene.”
Loy, W. Y. K., Ng, A. K., Goh, S. Y. H., et al. (2025) · IEEE International Conference on Service Operations and Logistics, and Informatics (SOLI) · doi:10.1109/soli66289.2025.11396271
“Two-stage detectors, such as R-CNN, Fast R-CNN, and Faster R-CNN [2], are detectors that first propose regions and then classify them.”
UAV Small Object Detection via Multi-Scale Feature Fusion and Adaptive Attention Mechanism
Shui, Y., & Zhi, X. (2025) · International Conference on Artificial Intelligence, Robotics, and Communication (ICAIRC) · doi:10.1109/icairc68035.2025.11384848 · Cited by 1
“Object detection has become a fundamental topic in computer vision, supporting various practical applications such as autonomous driving, intelligent monitoring, remote sensing interpretation, and UAV-based visual perception[1][3].”
An Efficient YOLOv8-Based Framework for Traffic Sign Detection Under Adverse Weather Conditions
Ou, Y., He, X., Chuai, Q., et al. (2025) · International Conference on Robotics, Intelligent Control and Artificial Intelligence (RICAI) · doi:10.1109/ricai68060.2025.11385287
“Among these technologies, autonomous driving has become one of the most prominent research directions and a key component in the development of Intelligent Transportation Systems (ITS) [1].”
Selective Multi-Scale Feature Fusion Network for Object Detection in Autonomous Driving
Dong, C., Li, Y., Du, H., et al. (2025) · doi:10.1109/iccvit67848.2025.11391336
“Researchers have extensively investigated object detection, and existing work can be broadly classified into traditional approaches [1] and deep-learning-based approaches [2].”
Guo, X., Zhang, A., Wang, J., et al. (2026) · International Conference on Consumer Electronics and Computer Engineering (ICCECE) · doi:10.1109/iccece69169.2026.11399801
“This paper uses mAP@0.5 and mAP@0.5:0.95 as evaluation metrics [10].”
InfluentialLED: A Benchmark for Evaluating Layout Error Detection in Document Analysis
Heo, I., Hwang, T., Jung, J., & Jung, S. (2026) · IEEE International Conference on Big Data and Smart Computing (BigComp) · doi:10.1109/bigcomp68355.2026.00055 · Cited by 1
“Despite rapid progress in object detection models [9]– [11] and vision-language models (VLMs) [12], DLA outputs still suffer from various types of errors.”
A lightweight multi-scale detection framework for X-ray images with supervised contrastive learning
Diao, Q., Chan, W. H., Zain, A. M., Moorthy, K., Chen, Y., Tong, H., & Huo, Y. (2026) · Scientific Reports · doi:10.1038/s41598-026-38000-0 · Cited by 2
“It is essential to design lightweight and computationally efficient architectures that support real-time inference on edge devices 9–11 .”
Yang, J., Ma, M., Wang, P., Li, Y., Pei, Z., Yao, C., & Guo, L. (2026) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2026.114325
Comparing Attention-Based Architectures for Advanced Vehicle Detection
Andhika, C. M., Nasution, S. M., Septiawan, R. R., et al. (2025) · 2025 International Conference on Applied Artificial Intelligence, Data Engineering and Sciences (ICAIDES) · doi:10.1109/icaides67265.2025.11404075
“Before transformers, object detection was dominated by two-stage detectors such as the R-CNN family [2].”
Elghaieb, I., Mzoughi, H., Naily, R., Zouinkhi, A., & Zaied, M. (2026) · Network Modeling Analysis in Health Informatics and Bioinformatics · doi:10.1007/s13721-026-00761-z
Ding, J., Zhuang, S., Ma, A., et al. (2026) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2026.3669745
“Recent studies have explored object detection methods based on handcrafted features [4].”
A Novel Detection Approach for Quasi-Convex Quadrilateral Aircraft Covers
Yue, W., Liu, Z., Wang, K., Hu, Z., & Wang, H. (2026) · IEEE Access · doi:10.1109/access.2026.3669209
“Image analysis and processing techniques are extensively utilized in object detection, tracking, and product quality evaluation [4], [5], [6], [7].”
Real-Time Monitoring Method for Drilling Site Cuttings Based on YOLOv12-seg
Yue, A., Chen, P., & Yang, Y. (2025) · doi:10.1109/mlcipr68329.2025.11407401
“In recent years, rapid advancements in computer vision and deep learning have significantly enhanced the performance of real-time object detection [3], laying a technical foundation for real-time cuttings detection.”
A reflection-based dataset for object and human detection
Kumar, S., & Selvakumar, K. (2026) · International Conference on Computational Intelligence in Data Science (ICCIDS) · doi:10.1109/iccids69108.2026.11407695
“Zou, Zhengxia, et al. surveyed Object detection frpm past twenty years[7] where all machine learning and deep learning were concluded as trending growth in AI.”
COMET: Communication and Memory Co-Design for Fine-Grained AI Inference in MCM Accelerators
Sheng, T., Sun, G., & Dong, D. (2026) · Proceedings - International Symposium on High-Performance Computer Architecture/Proceedings · doi:10.1109/hpca68181.2026.11408536
Yu, D., Miyazaki, T., & Omachi, S. (2026) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2026.3670542
AESOD: Towards accurate and efficient general-purpose small object detection
Peng, J., Lv, K., Lin, D., & Yuan, L. (2026) · Digital Signal Processing · doi:10.1016/j.dsp.2026.106037 · Cited by 1
A Weld Seam Recognition Method Based on Improved YOLO Model and Its Feature Point Extraction Method
Li, X., Dong, C., Wu, S., et al. (2026) · Applied Sciences · doi:10.3390/app16052499
A Deep Learning-Integrated Framework for Operational Rip Current Warning
Chuang, L. Z.-H., Chen, M., & Lien, J.-J. J. (2026) · Journal of Marine Science and Engineering · doi:10.3390/jmse14050496 · Cited by 1
“While these models often achieve superior detection accuracy, their sequential processing leads to slower inference speeds, making them less suitable for real-time scenarios [46,47].”
Light-VQA+: A Video Quality Assessment Model for Exposure Correction with Vision-Language Guidance
Zhou, X., Liu, X., Dong, Y., Kou, T., Gao, Y., Zhang, Z., Li, C., Wu, H., & Zhai, G. (2026) · International Journal of Computer Vision · doi:10.1007/s11263-025-02706-x · Cited by 12
A Small-Object Detection Framework with Context Gating and Multi-Level Dynamic PerceptionPreprint
Xie, R., & Gao, G. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6360462
Multimodal artificial intelligence for human–computer interaction enhanced breast lesion diagnosis
Zhai, Y., Tan, D., Sun, D., & Zheng, T. (2026) · Array · doi:10.1016/j.array.2026.100730
Xiong, H., Chen, Y., Fan, H., & Li, X. (2025) · International Conference on Virtual Reality and Visualization · doi:10.1109/icvrv67992.2025.00102 · Cited by 1
Li, P., & Zheng, Z. (2025) · doi:10.1109/icusac68314.2025.11414310
“Machine learning approaches for automatic navigation aid condition assessment from UAV imagery represent another promising extension that could transform inspection workflows from manual to automated anomaly detection [33].”
SegmentAndClassify: A Two-Stage Model for Large Scale Named Entity Recognition
Li, B. (2025) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata66926.2025.11400897
“The NER task bears intriguing similarities to the object detection (OD) task [7] in computer vision.”
A novel black-box adversarial attack for visible and infrared image fusion models
Gao, P. (2026) · Journal of King Saud University - Computer and Information Sciences · doi:10.1007/s44443-026-00608-7
DeepIL13Pred: A Fast and Efficient Approach for IL-13-Inducing Peptide Prediction
Fang, J., Wang, C., & Zhang, L. (2025) · International Conference on Advanced Computer Theory and Engineering · doi:10.1109/icacte66284.2025.11412046
“With the rapid advancement of computer technology, machine learning (ML) and deep learning (DL) approaches have demonstrated remarkable success across diverse fields, including image recognition [15], medical diagnostic assistance, and bioinformatics [16].”
LiteFuseNet:A Lightweight Edge-Aware Multi-Scale Detection for Mobile Robots
Li, W., Qi, J., Cui, Z., et al. (2025) · International Conference on Virtual Reality and Visualization · doi:10.1109/icvrv67992.2025.00030
“Object detection [1] is a fundamental research area in computer vision, aiming to localize and classify objects of various categories within images or videos.”
Efficient Cow Detection With CTri ‐ YOLOv11 : From Model Enhancement to Edge Deployment
Zheng, Z., Tang, J., Su, H., & Weng, Z. (2026) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.70570 · Cited by 1
FBAO: backdoor attack against object detection via frequency noise injection
Wang, Q., Shen, H., Wang, L., Yuan, L., Ren, Y., Jia, X., Sun, S., & Meng, W. (2026) · Applied Intelligence · doi:10.1007/s10489-026-07156-7 · Cited by 1
A Reference Model for the Analysis and Indexing of Metaverse Recordings for Information Retrieval
Steinert, P., Wagenpfeil, S., Frommholz, I., & Hemmje, M. (2026) · Big Data and Cognitive Computing · doi:10.3390/bdcc10030085
RFFRDet: A Refined Feature Fusion Rotation Detector for Prohibited Item Recognition in X-Ray Images
Li, M., Wang, M., Zhang, W., Guo, W., & Li, J. (2026) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2026.3672007
“Traditional object detection methods using horizontal bounding boxes (HBBs) have demonstrated success in various applications [1], [2].”
An evolutionary hyperparameter optimization framework for YOLO-based military aircraft detection
Wu, T.-H., Lai, C.-M., Yeh, W., & Liu, Y.-X. (2026) · Applied Soft Computing · doi:10.1016/j.asoc.2026.115011
Tennekoon, S., Wedasingha, N., Welhenge, A. M., Abhayasinghe, N., & Murray, I. D. (2026) · Knowledge-Based Systems · doi:10.1016/j.knosys.2026.115763
MFOG-net: Optimized video object detection network based on multi-scale spatiotemporal features
Xiao, G., Wan, S., Lv, C., & Ke, R. (2026) · Neurocomputing · doi:10.1016/j.neucom.2026.133354
Li, S., Meng, Q., Liu, X., Wang, Z., Kong, S., & Li, B. (2026) · PLoS ONE · doi:10.1371/journal.pone.0344151 · Cited by 2
“Although existing detectors [3], such as Faster R-CNN, have made notable strides, their performance in detecting densely packed small targets from UAV perspectives remains unsatisfactory—especially when the per-frame target density exceeds 50, where severe occlusion and marked scale variations…”
Nicodème, C., Niemann, T., & You, B. (2025) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc60802.2025.11423660
“They discard traditional convolution operators in favor of attention-alone calculation in order to overcome the limitations of CNNs and obtain a global-scale receptive field [39].”
Wang, Z., Liu, Z., Wu, S., et al. (2025) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc60802.2025.11423641
“As mentioned in the introduction, CNN-based deep learning approaches have been widely studied in intelligent transportation systems (ITS) [1].”
InfluentialA Complete Framework for Automatic Condition Evaluation of Trains' External Surface
Nicodème, C., You, B., & Sovanleng, L. Y. (2025) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc60802.2025.11423729
“Deep learning-based object detectors can be categorized into two main groups: two-stage and one-stage detectors [8,9].”
PMG-Net: progressive modular-guided network for small object detection
Lin, S., Li, X., Xue, L., Huang, Y., Chen, H., Chen, R., Wei, L., & Yang, C. (2026) · The Journal of Supercomputing · doi:10.1007/s11227-026-08410-y
Motion-Adaptive HOG Descriptors for Real-Time Object Detection in Resource-Constrained EnvironmentsPreprint
Río-Álvarez, Á., Fernández-Lanvin, D., Andres, J. D., et al. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6431451
Chen, K., Zhang, X., Shao, Y., Xiao, H., Zheng, D., Jiang, Z., & Lou, S. (2026) · Processes · doi:10.3390/pr14060952
Self-citationMotion-Adaptive HOG Descriptors for Real-Time Object Detection in Resource-Constrained EnvironmentsPreprint
Río-Álvarez, Á., Fernández-Lanvin, D., Andres, J. D., et al. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6431454
Light-Neck: Memory-Aware Feature Fusion for Real-Time Object Detection on Edge Devices
Liu, C. (2026) · doi:10.1109/emc68537.2026.11441943
“Real-time object detection is a key capability behind many modern systems, such as autonomous drone navigation, smart city surveillance, and industrial defect inspection [2].”
Dema, K. D., Coffin, J., Vaz, S. M. A., Wang, G., & Olsson, C. A. (2026) · Journal of Medical Internet Research · doi:10.2196/preprints.95887
Pavur, G., Galaitsi, S., Ellinport, B., et al. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6462628
Qin, J., Ding, H., & Wu, T. (2026) · Geomorphology · doi:10.1016/j.geomorph.2026.110299
Yue, X., Zhang, T., Deng, H., et al. (2026) · doi:10.1109/aisns67921.2026.11440451
“Currently, single-stage object detectors represented by the YOLO series [2] have become the mainstream choice in the industry due to their anchor-free design and efficient inference speed.”
Toward Deep Representation Learning for Event-Enhanced Visual Autonomous Perception: The eAP Dataset
Li, J., Li, S., Lian, Q., Li, P., Chen, X., & Zhou, Y. B. (2026) · IEEE Transactions on Robotics · doi:10.1109/tro.2026.3677912 · Cited by 2
“This selection of tasks has three reasons: 1) Importance of tasks: These two tasks span from object detection [6] to motion estimation [7], which are both fundamental problems in robotic perception.”
Strong IPR, Better Inclusion? Impact of WTO Accession on Female AI Inventors in ChinaPreprint
Agrawal, S., Rathi, S., Chatterjee, C., & Higgins, M. J. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6481863
Meng, S., Wu, L., Li, M., Yeh, A. G. O., & Xue, F. (2026) · Energy and Buildings · doi:10.1016/j.enbuild.2026.117384 · Cited by 4
“Window detection refers to the task of identifying interested attributes–such as the position, shape, and condition of windows–within a building, as an extension of object detection [33].”
A Fine-Grained Lightweight Urban Signalized-Intersection Dataset of Dense Conflict Trajectories
Chen, Y., Wu, Z., Zheng, G., Wu, X., Xu, L., Tang, H., He, Z., & Zeng, H. (2026) · Scientific Data · doi:10.1038/s41597-026-07110-9 · Cited by 2
IM-DETR: DETR with Mix-Encoder for Industrial Scenarios
Liu, S., Feng, Y., Wang, D., Zhou, Z., Wang, H., Wu, J., Wang, X., Wei, X., Yan, J., Xian, W., et al. (2026) · Applied Sciences · doi:10.3390/app16073345
Multi-scale Graph Convolutional Attention for Leather Fabric Surface Defect Detection
Li, P., Zhao, Y., & Ou, X. (2025) · International Conference on Computer Science and Management Technology (ICCSMT) · doi:10.1145/3795154.3795287
Crane Load Fall Zone Monitoring with SAM-2 and YOLO-V11
Deshmukh, P., & Kanade, V. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-14186-6_27
DFVNet: Density Feature Guided Small Object Detection in Video
Lv, J., Chen, L., Fu, Y., et al. (2025) · International Conference on Vision, Image and Signal Processing (ICVISP) · doi:10.1109/icvisp68610.2025.11451735
“However, Small object detection faces challenges like low resolution, motion blur, and occlusion[3].”
YOLO-MB: A Novel Framework for Object Detection with MSDE and BiFPNPreprint
Kang, C., & Wang, X. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6508317
Fast fuzzy clustering via sparse anchor graph with manifold and balance regularizations
Wang, J., Ma, Y., Zhang, C., et al. (2026) · Information Fusion · doi:10.1016/j.inffus.2026.104354
Real-Time LED Defect Detection Using YOLOv7-12 for Smart Manufacturing
Kongkaew, W., Sirasakamol, O., Yachiangkam, S., et al. (2026) · Joint International Conference on Digital Arts, Media and Technology with ECTI Northern Section Conference on Electrical, Electronics, Computer and Telecommunication Engineering (ECTI DAMT & NCON) · doi:10.1109/ectidamtncon67592.2026.11460030
“Such bootstrap-based validation has been widely applied in deep learning evaluation for robust performance comparison [23].”
Lasguignes, T. (2023) · theses.fr (ABES) · doi:10.70675/4c8ccd36z1853z4edfzbc13zf79277b7522e
Online context learning for socially-compliant robot navigation
Okunevich, I. (2024) · theses.fr (ABES) · doi:10.70675/39ee8d37z3ddez4ca2za227z281e93145ae1
EADA: Efficient adaptive data augmentation
Liu, S., Wang, Z., Zhang, Y., et al. (2026) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2026.104755
Real-time Indoor Localization with Embedded Computer Vision and Deep Learning
Daou, A. (2024) · theses.fr (ABES) · doi:10.70675/5b59245azb56bz414ez83b3z0125f8f15855
Prompt-Based Task-Conditioning Transformer for Low-Quality Detection
Liu, C., Zhang, Y., Lin, X., Dun, Y., & Qian, X. (2026) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2026.3682155
“Since the advent of computer vision, object detection [33] has been a major focus of research.”
Federation of heterogeneous models with machine learning-assisted model views
Miranda, J. P. (2025) · theses.fr (ABES) · doi:10.70675/de89abcdzc714z461cz8300z607cc2293274
Deep learning methods for object pose estimation and reconstruction in industrial environments
Durchon, H. (2025) · theses.fr (ABES) · doi:10.70675/5abc516az0f44z4796zbec9zd2388e9e2773
Tan, M., Yang, K., & Liao, H. (2026) · Neural Computing and Applications · doi:10.1007/s00521-026-12016-z
Research on Safety Detection and Management Optimization Based on Machine Vision Inspection
刘, 沅. (2026) · Mechanical Engineering and Technology · doi:10.12677/met.2026.152019
A pedestrian detection model based on YOLO for dense scenes
Xing, S., Wang, F. S., & Wang, H. (2026) · Optoelectronics Letters · doi:10.1007/s11801-026-4274-2 · Cited by 1
Confidence-driven HVAC component recognition integrating LLMs and computer vision
Zheng, Z., Lü, J., He, F., Wang, B., Yu, Z., Ji, L., & Zhao, Y. X. H. Z. L. M. (2026) · Building Simulation · doi:10.1007/s12273-026-1425-0
“This method often reduces recall when applied to complex engineering drawings, especially for small, ambiguous components or visually similar component symbols (Zou et al. 2023).”
Guo, K., Dong, J., Zhang, J., Song, Z., & Wang, H. (2026) · Microfluidics and Nanofluidics · doi:10.1007/s10404-026-02893-0
“The emergence of convolutional neural networks (CNNs) has revolutionized object detection, enabling significant advances in accuracy and efficiency across diverse applica - tion domains (Zhao et al. 2019; Zou et al. 2023).”
JIANG, X., Zhang, Z., & Wu, J. (2026) · IEEE Transactions on Consumer Electronics · doi:10.1109/tce.2026.3683776
“1) Sliding Window Algorithm: Sliding time windows are employed to smooth the virtual currency sentiment analysis results, aiming to reduce short-term fluctuations in the data and reveal longer-term trends more clearly [42].”
A dual-branch remote sensing object detection model with parameter-free attention
Li, Z., Jing, X., Wang, R., et al. (2026) · Frontiers in Earth Science · doi:10.3389/feart.2026.1770450
Self-citationYOLO-BDM: An improved ship detection algorithm based on YOLOv11n
Xiong, F., Han, D., Shen, X., & Zhu, M. (2026) · Computer Science and Information Systems · doi:10.2298/csis251018019x
An embedded vision-based system for cyclist detection and counting
Santos, L. A. D., Betini, R. C., & Nassu, B. T. (2026) · Journal of the Brazilian Computer Society · doi:10.5753/jbcs.2026.4937
“Deep learning approaches enable extracting features with greater representational power, which is important for the detection task, and have become the main mechanism currently used [Zou et al ., 2023].”
Demonet: Degradation-Aware Modality Interaction for Multi-Modal Object Detection in Car Cabin
Li, Y., Liu, T., & Yap, K. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11461976
STRPNet: Video Salient Object Detection via Spatio-Temporal Scene Relation Propagation
Qiu, S., Yang, J., Yu, J., et al. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11464131
NEGEV: Negative Sample-Aware Fine-Tuning for Open-Vocabulary Object Detection
Zhu, R., Liu, B., Lu, Z., Xu, K., & Liu, D. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11463649
FREDNET: A Frequency and Decomposed-Spatial Network for Industrial Defect Signal Detection
Zhou, H., Lai, T., Hao, C., Yue, W., Yue, S., & Zhang, H. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11462834
FGFF-NET: Frequency-Guided Feature Fusion Network for Visible-Infrared Object Detection
Zheng, Z., Liu, G., Dang, M., et al. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11460783
Li, Y., Chen, T., Wang, H., Zhao, J., & Du, B. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11464443
Robust Open-World Object Detection through Evidential Learning
Zhao, G., Xia, H., Li, X., et al. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11464119
Semantic-Aware Temporal Modeling for Intelligent Classroom Behavior Detection
Liu, X., & Zhang, B. (2026) · International Journal on Semantic Web and Information Systems · doi:10.4018/ijswis.408114 · Cited by 1
Woo, J., Park, J., & Lee, S. (2026) · Nonlinear Dynamics · doi:10.1007/s11071-026-12471-2
“These limitations compound the inherent uncertainties in object tracking algorithms [35, 36], making accurate state estimation challenging.”
InfluentialArtificial Intelligence for Creation of a Restoration Model: Turin’s Liberty Atlas
Ostorero, C. L., Gioberti, L., Gramaglia, S., Ornato, T., & Ostorero, T. (2026) · Lecture notes in civil engineering · doi:10.1007/978-3-032-15387-6_46
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.