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 2,001–2,100 of 3,144
Relation-based self-distillation method for 2D object detection
Wang, B., He, B., Li, C., Shen, X.-W., & Zhang, X.-Y. (2025) · Scientific Reports · doi:10.1038/s41598-025-93072-8 · Cited by 4
Simenthy, J. R., & Singh, P. (2025) · International Conference on Intelligent Systems and Computational Networks (ICISCN) · doi:10.1109/iciscn64258.2025.10934699 · Cited by 1
“Despite significant progress in this domain, achieving robust object detection in dynamic, real-world environments remains a formidable challenge, particularly when dealing with varying environmental conditions, complex backgrounds, and diverse object characteristics [2].”
Berghouse, M., & Parashar, R. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.110761 · Cited by 1
Zheng, C., Lu, J., Hu, K., Xiang, Q., & Miao, L. (2025) · Scientific Reports · doi:10.1038/s41598-025-97857-9 · Cited by 1
“It is different from general object detection (GOD) 15 and salient object detection (SOD) 16 since camouflaged objects are usually characterized by small scales, high similarity to the background, and occlusion, hence the COD task is more challenging.”
Gollapalli, G. S., Gadde, M. S. B., Gadde, M. M., et al. (2024) · OITS International Conference on Information Technology (OCIT) · doi:10.1109/ocit65031.2024.00062 · Cited by 1
“In the Indo Pacific region Crown of Thorns starfish (COTS) occur naturally [4].”
SMILE: Segmentation-Based Centroid Matching for Image Rectification via Aligning Epipolar Lines
Choi, J., & Lee, D. (2025) · Applied Sciences · doi:10.3390/app15094962 · Cited by 1
Integrating the Simplex Architecture to Enhance Safety in Deep Learning Autonomous Systems
Salamini, N., Nesti, F., Marinoni, M., Cicero, G., Serra, G., Biondi, A., & Buttazzo, G. (2025) · ACM/IEEE International Conference on Cyber-Physical Systems (ICCPS) · doi:10.1145/3716550.3725155 · Cited by 3
“The rapid advancement of artificial intelligence (AI) has led to the development of deep neural networks (DNNs) that surpass human performance in various specialized tasks, including image classification [5], object detection [10], and control [8].”
Abdulfattah, M. H., Sheikh, U. U., Masud, M. I., Othman, M. A., Khamis, N., Aman, M., & Arfeen, Z. A. (2025) · IEEE Access · doi:10.1109/access.2025.3570833 · Cited by 2
“2) MAP@0.5 mAP@0.5 is the Average Precision at an IoU threshold of 0.5, meaning that, a detection is considered correct if the predicted bounding box overlaps with the ground truth box by at least 50% [45], [46].”
InfluentialOSSA: Unsupervised One-Shot Style Adaptation
Gerster, R., Caesar, H., Rapp, M., Wolpert, A., & Teutsch, M. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-91672-4_9 · Cited by 3
Ren, J., Li, Y., Zhu, C., & Pang, J. (2025) · Engineering Research Express · doi:10.1088/2631-8695/addc36 · Cited by 1
SpatialIE: Towards adaptive floating waste detection in unpredictable weather
Yin, Y., Liu, X., Xu, C., Liu, Y., Zhu, T., & Huo, H. (2025) · Knowledge-Based Systems · doi:10.1016/j.knosys.2025.113621 · Cited by 2
A Survey on Deep Learning-Based Chinese Font Style Transfer
Ren, Z., Pan, Y., Chen, J., Zhao, L., Liao, M., Qian, X., & Gong, W. (2025) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2025.3574300 · Cited by 7
“…many challenging tasks in fields such as computer vision [20], [21], [22] and natural language processing [23], [24], [25], and have achieved state-of-the-art (SOTA) results in tasks such as image classification [26], [27], object detection [28], [29], [30], and semantic segmentation [31], [32].”
Liu, H., Zhang, S., Ren, K., Hu, Z. H., Li, X., & Nie, Z. (2025) · The Visual Computer · doi:10.1007/s00371-025-03992-9 · Cited by 2
Block-recurrent visual transformer for enhanced human detection in thermal imaging
Vu, P. C. L. T., Bao, P. T., & Trinh, T. D. (2025) · Machine Vision and Applications · doi:10.1007/s00138-025-01711-x · Cited by 3
“In this study, we evaluate the performance of the human detection method in thermal images using the Mean Aver - age Precision (mAP) metric [59 ], calculated according to the COCO dataset evaluation method.”
Event-RGB Fusion for Insulator Defect Detection Based on Improved YOLOv8
Sun, L., Li, Y., Zhao, X., Wang, K., & Guo, H. (2024) · Asian Conference on Artificial Intelligence Technology (ACAIT) · doi:10.1109/acait63902.2024.11022310 · Cited by 1
“Conversely, the method of one stage can achieve a complete single training of shared features, and the speed is greatly improved under the premise of ensuring a certain accuracy[7].”
Vourkos, E. G., Christoforou, E. G., Toulkeridou, E., Ramdani, N., & Panayides, A. S. (2025) · SN Computer Science · doi:10.1007/s42979-025-04042-w · Cited by 2
“Nowadays, several object detection algorithms exist, with different performance capabilities and different complexity [15].”
Gautam, A., Singh, S., Arora, K., et al. (2025) · International Conference on Signal Processing, Computing and Control (ISPCC) · doi:10.1109/ispcc66872.2025.11039317 · Cited by 1
Leroy, P., Abisset‐Chavanne, E., Pommier, R., & Montemurro, M. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.111516 · Cited by 4
Exploiting a Deformable and Dilated Feature Fusion Module for Object Detection
Qi, X., Johar, M. G. M., Khatibi, A., & Tham, J. (2025) · Electronics · doi:10.3390/electronics14132716 · Cited by 1
AI-Based Vehicle State Estimation Using Multi-Sensor Perception and Real-World Data
Ruggaber, J., Pölzleitner, D., & Brembeck, J. (2025) · Sensors · doi:10.3390/s25144253 · Cited by 1
Fan, X.-R., Li, X., Guo, Z., Tolba, A. K. R., & Alfarraj, O. (2025) · Journal of Computing and Information Science in Engineering · doi:10.1115/1.4069118 · Cited by 2
Liu, Y., Wu, Y., & Yuan, Y. (2025) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2025.3586353 · Cited by 4
“However, these methods often exhibit reduced performance in detecting small targets because they have a limited capacity to preserve fine-grained boundary details and to accurately delineate ambiguous edge features [12].”
Facial Beauty Prediction Combining Dual-Branch Feature Fusion With a Stacked Broad Learning System
Gan, J., Chen, H., Xu, W., Li, H., Zhuang, Z., & Chen, Z. (2025) · IEEE Access · doi:10.1109/access.2025.3588197 · Cited by 1
“In recent years, deep neural networks have been widely used in visual tasks such as classification [4], detection [5], segmentation [6], and image generation [7].”
Marine Organism Detection Algorithm Based on MSPSO-YOLOv8
Wang, G., Yang, J., & Sun, L. (2025) · International Conference on Computer Vision, Image and Deep Learning (CVIDL) · doi:10.1109/cvidl65390.2025.11085432 · Cited by 1
“In contrast, the deep learning framework represented by convolutional neural networks [1], with its hierarchical feature extraction mechanism and end-to-end optimization capabilities, provides an innovative methodological breakthrough for solving the long-standing technical problems in the field of…”
Complex Traffic Scenes Detection Based on Multiscale and Multilevel Feature Fusion Method
Liu, S., Hu, N., & Li, A. (2025) · Chinese Control and Decision Conference (CCDC) · doi:10.1109/ccdc65474.2025.11090513 · Cited by 1
PestOOD: An AI-Enabled Solution for Advancing Grain Security via Out-of-Distribution Pest Detection
Tian, J., Ma, C., Li, J., & Zhou, H. (2025) · Electronics · doi:10.3390/electronics14142868 · Cited by 2
Song, J., & Lee, S. J. (2025) · Sensors · doi:10.3390/s25175366 · Cited by 1
“In the field of computer vision, significant progress has been made not only in well-established areas such as object detection [1] and semantic segmentation [2], but also in depth estimation [3].”
Enhanced car detection and ranging in adverse conditions using improved YOLO-LiRT and FSGBMN
Luo, T., Guan, Z., Pang, D., & Dou, R. (2025) · The Journal of Supercomputing · doi:10.1007/s11227-025-07822-6 · Cited by 2
Zhang, L., Ye, J., & Liu, Y. (2025) · doi:10.1109/icicr65456.2025.00033 · Cited by 1
“Early methods relied on handcrafted features (such as SIFT and HOG) and classifiers (such as SVM and Boosting), which showed limited robustness and real-time performance in complex scenarios [4].”
Self-citationPark, J., Koh, J. W., Kim, J., Yoon, T., & Jeong, J. (2025) · Results in Engineering · doi:10.1016/j.rineng.2025.107413 · Cited by 1
Intersection-based Ensemble for Small Multi-Object Tracking in Challenging Environments
Whang, G.-Z., & Chu, W.-T. (2025) · doi:10.23919/mva65244.2025.11175071 · Cited by 1
“The former typically aims to achieve higher detection accuracy, while the latter prioritizes real - time inference [27].”
Poker Watcher: Playing Card Detection Based on EfficientDet and Sandglass Block
Chen, Q., Rigall, E., Wang, X., Fan, H., & Dong, J. (2020) · International Conference on Awareness Science and Technology (iCAST) · doi:10.1109/icast51195.2020.9319468 · Cited by 1
Research on Face Detection Algorithm Based on Improved YOLOv5
Mao, Z., Chen, X., Yan, X., & Zhao, Y. (2022) · Proceedings of International Conference on Artificial Life and Robotics · doi:10.5954/icarob.2022.os11-7 · Cited by 1
Yolov5-DP: A New Method for Detecting Pedestrian Aggregation
Yang, K., Chen, X., Yan, X., et al. (2022) · Proceedings of International Conference on Artificial Life and Robotics · doi:10.5954/icarob.2022.os11-5 · Cited by 1
Шинкарук, О. М., Babii, Y., Kyrylenko, V., Kupriyenko, D., ФАРІОН, О., & Babaryka, A. (2019) · doi:10.36059/978-966-397-184-1 · Cited by 1
Garg, A., Dagar, A., Khurana, C., Singh, R., & Anshu, M. K. (2022) · International Journal for Research in Applied Science and Engineering Technology · doi:10.22214/ijraset.2022.42947 · Cited by 1
Deep Semantic Segmentation Models in Computer Vision
Andreini, P., & Dimitri, G. M. (2022) · European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN) · doi:10.14428/esann/2022.es2022-5 · Cited by 1
“For instance successful applications of DL in computer vision can be found in the tasks of object detection [10, 11], image reconstruction [12] and image generation [13].”
BackgroundAprendizado Profundo aplicado à Visão Robótica utilizando dispositivo embarcado Raspberry Pi
Bordado, M. A., Cardoso, Á. A., & Franco, R. A. P. (2022) · doi:10.5753/erigo.2022.227735 · Cited by 1
Target Detection in Video Images Using HOG-Based Cascade Classifier
Namah, A. A., Mirza, N. M., & Al-Zuky, A. A. D. (2022) · Revue d intelligence artificielle · doi:10.18280/ria.360507 · Cited by 1
“Hence, a computational models and techniques developed with the help of computer vision to enable computer understanding digital images and react suitably [6].”
MethodXie, B., Yang, L., Yang, Z., Wei, A., Weng, X., & Li, B. (2022) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros47612.2022.9981047 · Cited by 2
“Spatial-awareness: CNN was limited in learning spatial transformations existed in images [7].”
BackgroundRealtime Recognition of Handwritten Lontara Makassar Characters Using Yolov5 Algorithm
Bakhri, I. A., & Sidik, H. P. (2022) · International Conference on Information Technology, Information Systems and Electrical Engineering (ICITISEE) · doi:10.1109/icitisee57756.2022.10057924 · Cited by 1
“Most object detection systems use object classification in images by applying models to pictures at several locations and scales and assigning credits to images as material for detection [24].”
Robust Vision SLAM Based on YOLOX for Dynamic Environments
Yan, H., Zhou, X., Liu, J., Yin, Z., & Yang, Z. C. (2022) · IEEE International Conference on Communication Technology (ICCT) · doi:10.1109/icct56141.2022.10073383 · Cited by 1
“Object detection[5] has two meanings: • Determining which target objects are on the image, and solving the problem of the existence of target objects.”
BackgroundDeteksi Objek dan Pengukuran Panjang serta Berat Ikan Menggunakan YOLOv3-ResNet18
Liawatimena, S., Abdurahman, E., Trisetyarso, A., & Wibowo, A. (2023) · Penerbit BRIN eBooks · doi:10.55981/brin.668.c554 · Cited by 1
Based On Improved Yolov5 Mine Infrared Target Detection Algorithm
Li, Q. (2022) · International Conference on Algorithms, High Performance Computing and Artificial Intelligence (AHPCAI) · doi:10.1109/ahpcai57455.2022.10087877 · Cited by 1
PoliTo at SemEval-2023 Task 1: CLIP-based Visual-Word Sense Disambiguation Based on Back-Translation
Vaiani, L., Cagliero, L., & Garza, P. (2023) · doi:10.18653/v1/2023.semeval-1.199 · Cited by 1
“…task is relevant to address well-known real-world challenges such as multimodal machine translation (Barrault et al., 2018; Gella et al., 2019), image caption generation (Wang et al., 2020a; Pra-manick et al., 2022), visual search and object recognition (Yao et al., 2019; Zou et al., 2023).”
BackgroundGood practice in training set preparation for marine navigation systems
Khatry, R., & Thompson, A. (2022) · doi:10.47120/npl.ms33 · Cited by 1
Perception models for selective harvesting robots in fruit and vegetable production
Blok, P. M. (2022) · doi:10.18174/579739 · Cited by 1
Pereira, A. L., Kohler, M., Castro, J. D. B., & Pacheco, M. A. C. (2023) · Research Square · doi:10.21203/rs.3.rs-2899695/v1 · Cited by 1
Hua, Z., Jiao, Y., Wang, Z., et al. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4566703 · Cited by 1
Pal, A. K., Biswas, B., Jichkar, M. D., Jena, A. N., & Kumar, M. (2023) · Research Square · doi:10.21203/rs.3.rs-3638041/v1 · Cited by 1
Mobile Robots Underwater Object Detection Using Deep LearningPreprint
Raisi, Z., & Nazarzehi, V. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4663189 · Cited by 1
Zeng, C., Hartmann, T., & Ma, L. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4677638 · Cited by 1
Enhanced tooth segmentation algorithm for panoramic radiographs
Carneiro, J. A. (2023) · Digital Library of Theses and Dissertations (Universidade de São Paulo) · doi:10.11606/d.59.2023.tde-20022024-073306 · Cited by 4
A study on urban street garbage detection based onYOLOXPreprint
Li, L., Zhang, H., Lu, F., Wang, Z., & Huan, L. (2024) · Research Square · doi:10.21203/rs.3.rs-4002747/v1 · Cited by 2
Fd-Detr: Striking the Balance between Accuracy and Speed in Fall Detection ModelsPreprint
Zhu, Y., Zeng, B., Zheng, Y., & Hu, H. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4768681 · Cited by 1
Detection of Title Blocks in Construction Documents Using Faster R-CnnPreprint
Sajadfar, N., Singh, A. K., Ray, N., et al. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4845684 · Cited by 1
duan, Z., Wang, Y., & Zhao, S. (2024) · Research Square · doi:10.21203/rs.3.rs-3798770/v1 · Cited by 1
Zhou, X., Zia, M. B., Gururajan, R., et al. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5367031 · Cited by 1
A nanopathology pipeline for clinical research across scales using human tissuePreprint
Burrell, A., Lawson, M., Ronchi, P., Xiong, X., Albers, J., Mclean, A. G., Willicombe, M. K., Moran, L. B., Hounsome, J., Jones, M. L., et al. (2025) · medRxiv · doi:10.1101/2025.08.29.25334660 · Cited by 1
“Supervised deep learning-based object detectors (Zou et al., 2023) are also likely worth investigating considering their success in automating analysis in a wide range of EM-related applications, from transmission EM (Su et al., 2023) to cryo-electron tomography (Genthe et al., 2023) and…”
Kim, Y., Kim, C.-H., Yun, C.-S., et al. (2025) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2025.09.17.676694 · Cited by 1
A Comprehensive Hyperspectral Image Dataset for Forest Fire Detection and Classification
Mani, A., Chen, X., Gorbachev, S., Yan, J., Dixit, A., Sun, Y., Yan, Z., Wu, J., Deng, J., Jiang, X., et al. (2025) · Scientific Data · doi:10.1038/s41597-025-06404-8 · Cited by 3
Real-Time UAV-Based Detection and Tracking for Maritime Search and Rescue (SAR) OperationsPreprint
Raza, D. R., Rehman, Z.-U., Frnda, J., Aadil, F., & Sharif, M. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6384651 · Cited by 1
An advanced implementation idea for detecting real-time object occupancy
James, C., & James, V. (2020) · Journal of Student Research · doi:10.47611/jsr.vi.917
OBJECT DETECTION WITH THE HIGH-FREQUENCY CHANGE OF OBJECTS CLASSES
Lou, L., Zhang, S., & Zhang, S. (2020) · The international archives of the photogrammetry, remote sensing and spatial information sciences/International archives of the photogrammetry, remote sensing and spatial information sciences · doi:10.5194/isprs-archives-xliii-b3-2020-125-2020
Aiello, G. (2020) · Digital Commons - URI (University of Rhode Island) · doi:10.23860/thesis-aiello-gabriella-2020
Deep neural networks based visual object detection in videos
Jin, R. (2020) · DR-NTU (Nanyang Technological University) · doi:10.32657/10356/144136
Singh, A., Kumar, N., & Kumar, T. (2021) · International Journal of Current Research and Review · doi:10.31782/ijcrr.2021.sp203
“10 Human being perceives information from sense organs and its perception varies from person to person in terms of features such as shape, colour and size.”
BackgroundInspection of Electric Power Distribution Systems with SCRDet
Restani, G. D. M., Coelho, L. D. S., & Filho, J. F. B. (2021) · Congresso Brasileiro de Inteligência Computacional (CBIC) · doi:10.21528/cbic2021-90
Rowghanian, V. (2022) · Research Square · doi:10.21203/rs.3.rs-1286015/v1
“5x5, [1, 4, 6, 4, 1]/16 lter plus cutting off values above π/2.”
BackgroundAutomatic Mask Detection at Public Places
Al-Gamal, A. A. M. (2021) · RESEARCH REVIEW International Journal of Multidisciplinary · doi:10.31305/rrijm.2021.v06.i12.008
Dynamic Label Assignment for End-to-End Object Detection
(2022) · Journal of Research in Science and Engineering · doi:10.53469/jrse.2022.04(01).16
Performance monitoring of deep learning vision systems during deployment
Rahman, Q. M. (2022) · Queensland University of Technology · doi:10.5204/thesis.eprints.229733
High-altitude Multi-object Detection and Tracking based on Drone Videos
Zhao, Q., & Peng, L. (2022) · Journal of Networking and Network Applications · doi:10.33969/j-nana.2022.020103 · Cited by 1
“The convolutional neural networks (CNN)-based multi-object detection algorithms [1] are divided into one-stage and two-stage ones.”
BackgroundMethodA Approach of Evaluation the Lettuce Height Based on Convolutional Neural NetworkPreprint
Guo, X., Zhong, Y., Feng, Y., Zhao, M. L., Zhang, M., & Wang, M. (2022) · SSRN Electronic Journal · doi:10.2139/ssrn.4089874
Extracting the height of lettuce by using neural networks of image recognition in deep learningPreprint
Wang, M., Guo, X., Zhong, Y., et al. (2022) · doi:10.1002/essoar.10510405.1
Training dataset generation for automatic registration of a duplicate bridge gamePreprint
Wzorek, P., & Kryjak, T. (2021) · doi:10.36227/techrxiv.16676734
Training dataset generation for automatic registration of a duplicate bridge gamePreprint
Wzorek, P., & Kryjak, T. (2021) · doi:10.36227/techrxiv.16676734.v1
“Nowadays, object detection methods with the highest accuracy are based on deep convolutional neural networks [1].”
BackgroundAbbas, A. K. A. (2021) · Queensland University of Technology · doi:10.5204/thesis.eprints.207935
Crowd Detection Algorithm for Complex Scene Based on Improved Yolov3Preprint
Li, Z., Wang, X., Wen, Y., Zhao, L., & Gao, X. (2022) · SSRN Electronic Journal · doi:10.2139/ssrn.4142433
Automatic Street Lighting System with Vehicle Detection using Deep Learning Based Remote SensingPreprint
Akram, M. S., Chen, L., Saleem, A., & Ullah, H. (2022) · SSRN Electronic Journal · doi:10.2139/ssrn.4107251 · Cited by 1
Computer Vision-based Monitoring of Harvest Quality
Rasmussen, C. B. (2021) · VBN Forskningsportal (Aalborg Universitet) · doi:10.54337/aau468596652
Automatic testing of organic strain gauge tactile sensors.
Goulet, B. (2022) · ThinkIR: The University of Louisville's Institutional Repository (University of Louisville) · doi:10.18297/etd/3897
Um Estudo de Caso para Deteccao de Ovocitos de Peixe Utilizando Redes Neurais Convolucionais
Cruz, Y. L. K. F., Santana, E. É. C., Silva, A. F. M., et al. (2022) · doi:10.5753/ercemapi.2022.224774
Research on YOLOv5s Target Detection Method Based on Local Self-attention
(2022) · Journal of Research in Science and Engineering · doi:10.53469/jrse.2022.04(10).06
Implementing Autonomous Driving System in a Virtual Environment
Pokhrel, C., & Khatiwada, A. (2022) · Advances in Engineering and Technology An International Journal · doi:10.3126/aet.v2i01.50448
Object Detection Based On Multi-Process
Shan, Z., Yang, H., Yang, X., et al. (2022) · IEEE International Conference on Networking, Sensing and Control (ICNSC) · doi:10.1109/icnsc55942.2022.10004179
“Segmentation describes images at the pixel level and is used for scenarios that require more understanding[9].”
MethodRweshobora, K., Kazumali, E., & Khelef, A. (2023) · International Journal of Computer Applications Technology and Research · doi:10.7753/ijcatr1202.1007
Object detection with deep neural networks under constrained scenarios
Zhang, G. (2022) · DR-NTU (Nanyang Technological University) · doi:10.32657/10356/164687
Lin, H., Han, P., Qiu, J., et al. (2022) · International Conference on Computer Science and Blockchain (CCSB) · doi:10.1109/ccsb58128.2022.00022
Mask Recognition through Deep Learning
Falak, A., Mishra, A., Mittal, V., & Singh, S. K. (2022) · International Conference on Advances in Computing, Communication Control and Networking (ICAC3N) · doi:10.1109/icac3n56670.2022.10074457
VSLink: A Fast and Pervasive Approach to Physical Cyber Space Interaction via Visual SLAM
Zhou, H., Huang, J., Fan, H., Ren, G., Gao, Y. C., & Dong, W. (2022) · International Conference on Mobility, Sensing and Networking (MSN) · doi:10.1109/msn57253.2022.00054
“For example, image classification [10], object detection [11], image retrieval [12], [13] and image localization [14] can achieve different degrees of object recognition.”
BackgroundPrototype Deep Learning System for Terrain Relative Navigation Missions
Saravana Kumar, B., & Gajjar, N. (2023) · International Journal of Electrical and Electronics Engineering · doi:10.14445/23488379/ijeee-v10i3p105
Towards Interpretable Feature Representation for Domain Adaptation Problem
Fang, Y., Chen, Z., Zhou, Q., & Li, X. (2022) · IEEE International Conference on Tools with Artificial Intelligence (ICTAI) · doi:10.1109/ictai56018.2022.00018
“Deep learning has achieved remarkable success on various vision tasks, such as image recognition [1] [2] [3] [4] and object detection [5] [6] [7].”
BackgroundAn Exploration of Controlling the Content Learned by Deep Neural Networks
Yang, L. (2021) · FIU - Digital Commons (Florida International University) · doi:10.25148/etd.fidc010269
Object Detection with a Knowledge Graph-Guided Semantic Distance NetworkPreprint
Gilliard, E., Liu, J., Aliyu, A. A., & Pan, J. Z. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4455699
Counting Objects in Images using DeepLearning: Methods and Current ChallengesPreprint
D’Alessandro, A., Amiri, A. M., & Hamarneh, G. (2023) · Research Square · doi:10.21203/rs.3.rs-2986682/v1 · Cited by 4
Golroudbari, A. A., & Sabour, M. H. (2023) · Authorea · doi:10.22541/au.168727976.63672670/v1 · Cited by 1
A serial dual-channel library occupancy detection system based on Faster RCNNPreprint
Yang, G., Chang, X., Wang, Z., et al. (2023) · Preprints.org · doi:10.20944/preprints202306.2050.v1
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.