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 2,501–2,600 of 3,144
Guo, R., Yu, K., Yu, E., et al. (2025) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-031-94445-1_15
Song, S., Jo, M., Lee, B.-K., et al. (2025) · Agriculture · doi:10.3390/agriculture15181918
Guo, J., Guo, C., Liang, S., Li, Z., Wang, D., Lin, R., & Dang, Y. (2025) · IEEE/CIC International Conference on Communications in China (ICCC) · doi:10.1109/iccc65529.2025.11148883
“Object detection [1] techniques play a vital role in network O&M scenarios including device status monitoring, network topology analysis, and anomaly behavior identification.”
Improved Pipeline Disease Grading Detection Method for Visual Inspection of Sewer Pipeline Robots
Li, C., Li, S., Duan, X., et al. (2025) · IEEE International Conference on Multimedia and Expo workshops · doi:10.1109/icmew68306.2025.11152128
“R ELATED W ORKS The task of object detection is not only to identify objects in images, but also to determine the category and location of objects [17].”
Development of Multi-Robot Collaborative System for Complex Equipment Safety Monitoring Tasks
Gao, J., Xie, M., & Jiang, L. (2025) · IEEE Conference on Industrial Electronics and Applications (ICIEA) · doi:10.1109/iciea65512.2025.11148742
Lightweighting of Deep Learning Models with Application in Object Detection
Guo, J., Zhao, Z., Liu, Y., et al. (2025) · IEEE Conference on Industrial Electronics and Applications (ICIEA) · doi:10.1109/iciea65512.2025.11148973
“Two-stage algorithms, exemplified by R-CNN [2] , employ region proposal-based classification through sequential region generation and refinement stages.”
Performance Analysis of Yolo Versions on Road Environment
Ikmel, G., Saleh, S., Heller, A., et al. (2025) · Revista de Gestão Social e Ambiental · doi:10.24857/rgsa.v19n9-002
Urban Intersection Collision Warning System Utilizing Traffic Surveillance Cameras
Guan, Y., Miraftabzadeh, S. M., Yaïci, W., & Zaninelli, D. (2025) · International Conference on Applying New Technology in Green Buildings (ATiGB) · doi:10.1109/atigb66719.2025.11142082
“Since around 2014, deep learning has significantly boosted object detection accuracy [16, 17], with algorithms classified into two-stage (e.g., RCNN, FPN) and one-stage detectors (e.g., YOLO, SSD) [18].”
MultKMAWE: A Multi Key-Points Based Word Extraction Algorithm for Manchu Archives
He, J., Ma, X., Tian, T., Zhou, Y., Liu, W., & Zheng, R. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-04630-7_6
Real-Time Sugarcane Quality Classification Using YOLOv10: A Case Study in a High-Capacity Sugar Mill
Rabbani, M. A., Utama, N. I., & Fa’rifah, R. Y. (2025) · International Conference on Data Science and Its Applications (ICoDSA) · doi:10.1109/icodsa67155.2025.11157210
Dong, L., Ouyang, Z., Wu, Y., & Yuan, X. (2025) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2025.3611071
“Introducingcomputationoffloadingoffersanenor-mousofadvantages,suchasenhancingthespeedoftaskslike simultaneouslocalizationandmapping(SLAM)[5],obstacle recognition[6],andobjectdetection[7]inrobots.”
Deep Robust Object Detection Under High Illumination Conditions Using Modulo Images
Toscano-Palomino, L., Contreras, K., Monroy, B., et al. (2025) · doi:10.1109/stsiva66383.2025.11156687
“By leveraging neural networks trained on large-scale datasets, these methods allow the automatic recognition of complex visual patterns [9], greatly advancing the field of computer vision, particularly object detection using RGB images [10], [11].”
Bearing-Based Multi-Agent Formation Control: A Survey and TaxonomyPreprint
Su, H., Yang, Z., Zhu, S., et al. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5424095
A Wind Turbine Instance Segmentation Approach Based on Boundary Optimization
Xu, H., Huang, Z., Xiao, S., & Wang, Z. (2024) · International Conference on Mechanical, Control and Computer Engineering (ICMCCE) · doi:10.1109/icmcce63640.2024.11163433
“Then {C2, C3, C4, C5} are fed into feature pyramid network (FPN) [33] to generate four types feature maps {P2, P3, P4, P5}.”
Tang, J., Zu, Y., Zhu, Q., Wan, P., Zhang, D., & Shao, W. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-05169-1_10
El-Hussuna, A., Elhadi, M., Møgelmose, A., et al. (2025) · Turkish Journal of Colorectal Disease · doi:10.4274/tjcd.galenos.2025.2025-6-6
“13,14 Even so, improved results should be obtainable using more modern transformer-based methods, including action recognition methods, 15 such as ASFormer surgical phase detection; object detection methods, 16 such as DEtection TRansformer 17 for tool detection; and CoTracker 18 for surgical tool…”
Xu, Z. S., Jia, W., Yan, C., et al. (2025) · doi:10.1145/3762329.3762340
“In recent years, deep learning has driven significant advancements in debris detection, leveraging its powerful feature learning capabilities [11-14].”
A Web-Based Platform for Korean Calligraphy Learners Using Deep Learning
Yang, C., Osman, M. A., & Sarvghadi, M. A. (2025) · IEEE Access · doi:10.1109/access.2025.3612578 · Cited by 2
“Modern detectors like RetinaNet and Faster R-CNN now significantly surpass R-CNN in both speed and accuracy, reducing it to a historical footnote in object detection evolution [35].”
Image-Based Weapon System Dynamic Firing Boundary Measurement
Zhang, J. (2025) · IEEE Advanced Information Technology, Electronic and Automation Control Conference (IAEAC) · doi:10.1109/iaeac65194.2025.11166381
“In contrast, image processing technology offers a more efficient and non-contact measurement solution, which has been widely utilized in industrial size measurement and object detection [5].”
樊, 棠. (2025) · Artificial Intelligence and Robotics Research · doi:10.12677/airr.2025.145112
Mansur, S., Kulkarni, I., Mathreja, V., Madalageri, S. A., Muttal, C., & Varur, S. (2025) · Lecture notes in networks and systems · doi:10.1007/978-981-96-5723-0_26
MambaOVD: a Mamba-based open-vocabulary object detection method
Liu, K., Ma, L., & Lu, T. (2025) · Scientific Reports · doi:10.1038/s41598-025-18769-2
Real-Time Object Detection and Motion Estimation on UAVs With Onboard Edge Computing
Wang, L., Yang, M., Lian, S., & Zhang, F. (2025) · IEEE/ASME International Conference on Advanced Intelligent Mechatronics · doi:10.1109/aim64088.2025.11175707
“These methods generally achieve high localization accuracy, but at the expense of slow inference speed [14].”
Li, Z., Chen, Z., Xu, J., et al. (2025) · Evolving Systems · doi:10.1007/s12530-025-09740-7
YOLO-GNN: An Improved GNN Based YOLOv4 Algorithm for Street Pedestrian Detection
Peng, F., & Chen, Y. (2025) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-032-00218-1_25
Usha, R., & Baskar, R. (2025) · Smart innovation, systems and technologies · doi:10.1007/978-981-96-4410-0_36
541Machine learning algorithms for enhanced medical image analysis and diagnostics
Prasant, P., Rose, J. D., Pradeepkumar, G., Shanmugaraja, T., & Saikumar, P. J. (2025) · De Gruyter eBooks · doi:10.1515/9783111503202-012
Zhang, B., Zhang, F., Hui, J., Peng, X., Zhang, J., & Zhang, Y. (2025) · Marine Environmental Research · doi:10.1016/j.marenvres.2025.107563
Pipeline Inspection a Case Study for Human Cognition Inspired Condition Management System
Dhungana, H. (2025) · Communications in computer and information science · doi:10.1007/978-3-032-00986-9_25
Tri-FRNet: a three-path feature fusion network for high-precision small object detection
Fan, R., Nan, W., Jiang, A., Meng, H., Wang, M., Wang, X., Dang, J., & Luo, X. (2025) · Engineering Research Express · doi:10.1088/2631-8695/ae0f3b · Cited by 3
Open-Set Active Learning for Nucleus Detection From the Histopathological Images
Tang, J., Yue, Y., Chu, W., Wang, M., Wang, Y., Wan, P., Krylov, A. S., Shao, W., & Zhang, D. (2025) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2025.3617073 · Cited by 1
“…Score: Since the object-detection problem can be considered as the combination of the object-classification and object-localization tasks [48], we consider both of these two sides to calculate the uncertainty score of the j -th sample in the unlabeled pool as: where CI j and LI j refer…”
Object detection algorithm for UAV perspectives based on YOLOv8s
Li, X., Lv, J., & Xie, W. (2025) · doi:10.1145/3757110.3757179
Li, C. (2025) · Signal Image and Video Processing · doi:10.1007/s11760-025-04844-8
A Study on Airport Runway Detection Based on an Improved YOLOv11 Algorithm
Bai, Y., Xu, S., Liu, X., & Su, X. (2025) · International Conference on Artificial Intelligence, Big Data and Algorithms (CAIBDA) · doi:10.1109/caibda65784.2025.11183337
Detecting unknown objects in open world via open world objectness score and distance-sensitive NMS
Su, S., Xu, Y., Zhu, Y., & Wang, C. (2025) · Multimedia Systems · doi:10.1007/s00530-025-02006-x
“Object detection [1 ] is a significant research direction in com - puter vision, aiming to locate objects of interest in images and accurately classify each object.”
A Lightweight Real-Time Traffic Sign Detection Model Based on Improved YOLOv8n
Tian, P., & Xiong, J. (2025) · Chinese Control Conference (CCC) · doi:10.23919/ccc64809.2025.11178591
“In contrast, YOLOv8 [8], as a one-stage detection model [9, 10], adopts a lightweight design with fewer parameters and lower FLOPs.”
Research on Prefabricated Pizza Defect Detection Method Based on TCSR-CNN Model
Wang, Y., Qu, Q., Sun, F., et al. (2025) · Chinese Control Conference (CCC) · doi:10.23919/ccc64809.2025.11179611
A Wearable Stereo Vision-Based Obstacle Detection System for Visually Impaired Individuals
Ruo, A., Napolitano, D., & Villani, V. (2025) · Communications in computer and information science · doi:10.1007/978-3-032-08049-3_3
Membership Privacy Evaluation in Deep Spiking Neural Networks
Li, J., Abad, G., Picek, S., & Conti, M. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-07884-1_11 · Cited by 3
Zhan, D., Xu, K., Pan, Z., et al. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5598031
AquaNetCT: Detecting and Representing Urban Drainage Networks from Video Analysis
Ma, T.-T., Benferhat, S., Tran-Nguyen, M.-T., & Do, T. (2025) · Communications in computer and information science · doi:10.1007/978-981-95-3358-9_3 · Cited by 1
Lu, Y., & Zhang, Z. (2025) · International Conference on Computer Vision, Application, and Algorithm (CVAA) · doi:10.1109/cvaa66438.2025.11193401
“Pedestrian and vehicle object detection is crucial for intelligent transportation and autonomous driving, directly impacting system safety and efficiency [1]-[4].”
An incremental adversarial training method enables timeliness and rapid new knowledge acquisition
Ge, Y., Dong, Y., Sun, H., Liu, Y., & Wang, C. (2025) · Scientific Reports · doi:10.1038/s41598-025-19840-8
Enhanced Chart Detection in Document Images with Segmentation Backbone
Tran, D. H. L., Nguyen, H.-N., Huynh, V. T., Tran, T.-A., Mai, X. T., & Tran, H. T. (2025) · Communications in computer and information science · doi:10.1007/978-981-95-3355-8_30
Unsupervised lightweight 3D convolutional network for enhanced infrared imaging in wearable devices
Zhu, B., Zhang, J., Zhao, S., Zhang, Z., & Chen, E. (2025) · Frontiers of Computer Science · doi:10.1007/s11704-025-40948-7
Ge, T., Cai, P., Jia, Y., et al. (2025) · Symposium on Piezoelectricity, Acoustic Waves and Device Applications · doi:10.1109/spawda68082.2025.11203553
Siering, T., Steidel, M., & Steger, C. (2025) · Journal of Marine Science and Engineering · doi:10.3390/jmse13102015
“Due to the functioning of the YOLO architecture, instances of imprecise localization of such objects are more frequent [34,35].”
Li, N., Yang, K., & Chen, C. (2025) · International Conference on Intelligent Robotics and Control Engineering (IRCE) · doi:10.1109/irce66030.2025.11203069
Integrating Knowledge for High-Fidelity Remote Sensing Detection of Cross-River Bridges
Chen, L., Qi, Y., Sun, R., Zhou, H., & Zhang, X. (2025) · International Conference on Image, Vision and Computing (ICIVC) · doi:10.1109/icivc66358.2025.11200418 · Cited by 1
“The continuous evolution of network architectures and loss functions has pushed the boundaries of what can be achieved in object detection tasks [10].”
Lychee13-3634: A new lychee image dataset and classification methodological evaluation
Luo, S., Zheng, H., Lin, Z., Zeng, T., Huang, M., Xiao, Y. F., Grau, A., & Huang, J. (2025) · PLoS ONE · doi:10.1371/journal.pone.0334900
“…EfficientNetv2-m, EfficientNetv2-l [25], SENet [26], Vision Transformer [27], Res-Att-Net [28], MobileViT [29], SqueezeNet [30], ShuffleNetv2 [31], MobileNetV2 [32], and MobileNetV4 [33], as well as 5 YOLO (-v5 [34], - v7 [35], -v8 [36], -v9 [37], and -v10 [38]) algorithms for experiments.”
DRMix: Decomposition-Recomposition Data Augmentation with Diffusion Model
Wang, S., Wang, Z., Chen, Y., Zhou, M., & Luo, J. (2025) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3746027.3754902 · Cited by 2
“Image segmentation [4, 23, 31, 50] identifies key target regions and enables semantic understanding at different levels.”
Device-Cloud Collaborative Learning Framework for Efficient Unknown Object Detection
Zhao, K., Hu, X., & Li, Q. (2025) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3746027.3755681
Proposal for an Object Detection Method Using Multiple 4D Radars in Snowy Environment
Nakashima, T., Nishiwaki, S., & Emaru, T. (2025) · IEEE Radar Conference (RadarConf) · doi:10.1109/radarconf2559087.2025.11205128
A YOLOv5-Based Printed Circuit Board Defect Detection System
Lin, J., & Chong, L. W. (2025) · IEEE International Conference on Consumer Electronics - Taiwan (ICCE-Taiwan) · doi:10.1109/icce-taiwan66881.2025.11207944 · Cited by 1
“These methods used a sliding window approach but had limitations in terms of accuracy and computational efficiency [1]-[3].”
DOAM-MECA: A Robust Framework for Vehicle Detection Under Adverse Driving Conditions
Tran, N. H., Dao, K. A., & Nguyen, V. D. (2025) · Signal Image and Video Processing · doi:10.1007/s11760-025-04922-x
“The overall integration of the proposed DOAM and MECA modules into the YOLO detection pipeline is illustrated in Fig.”
InfluentialResearch on Small Object Detection Technology in Remote Sensing Images Based on Deep Learning
余, 江. (2025) · Computer Science and Application · doi:10.12677/csa.2025.157191
Panda, M. K., Sahoo, P. K., Rout, D. K., et al. (2025) · Knowledge-Based Systems · doi:10.1016/j.knosys.2025.114780
RGB-IR Object Detection in Aerial Imagery via Spectral-Aware Augmentation Techniques
Gautam, V., Sinha, S., & Prasad, S. (2025) · International Conference on Emerging Technology in Autonomous Aerial Vehicles (ETAAV) · doi:10.1109/etaav66793.2025.11213242
“Object detection (OD) is a fundamental task in computer vision (CV), with widespread applications ranging from autonomous navigation to surveillance and remote sensing [1].”
Diffattack-X: An effective transferable adversarial attack based on diffusion models
Li, L., Zhang, X., Wang, J., Liu, L., Wang, Y., Pu, Y., Ren, P., & Chu, J. (2025) · Applied Intelligence · doi:10.1007/s10489-025-06957-6 · Cited by 1
“Deep neural networks (DNNs) have achieved remarkable progress in fields like image classification [ 1, 2], object detection [ 3 ], face recognition [ 4], autonomous driving [ 5 ], solar irradiance prediction [ 6], and remote sensing [ 7].”
Zhu, L., Ren, S., Lu, B., & Chen, Z. (2025) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2025.3627247 · Cited by 1
“Traditional methods rely on manual features and template matching, and their performance is limited under complex scenes and diverse targets [4].”
FoodWeight1.4M: A Large-scale Multi-modal Dataset for Weight Estimation
Lü, Y., Xu, Z., Ma, D., Yang, J., Xiang, L., Wu, H., & He, Z. (2025) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme59968.2025.11209123
“In recent years, large vision language models (VLMs) have excelled in visual analysis tasks like detection [1].”
VoxelDet: Towards Accurate 3D Object Detection with Voxel Pruning and Fine Geometric Shape
Wen, J., Li, J., & Zhang, T. (2025) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme59968.2025.11208964
“However, point cloud scenes are large, sparse, and irregular, which brings great challenges to feature extraction and representation [1].”
Rethinking DeNoising Training for DETR-based Object Detection
Jiang, B., Fan, Y., Yang, C., Lei, C., Hu, R., & Zhou, Z. (2025) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme59968.2025.11209114
“Object detection aims to recognize and locate objects of interest in images [1].”
Object-Centric Feature Enrichment for Single-Domain Generalized Object Detection
Yuan, S., Zhang, Z., & Han, Y. (2025) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme59968.2025.11209999
Comparative Performance Analysis Method of Yolov9 and Yolov10 Models with Various Objects
DEMİR, M. (2025) · Bilişim Teknolojileri Dergisi · doi:10.17671/gazibtd.1624632
Lightweight Object Tracking and Localization for Assembly Guidance on AR Helmet
Ma, Z., Liu, Y., & Wan, R. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-3729-7_45
Sharma, A. K., Suryavanshi, H., Verma, K., & Shukla, M. (2025) · International Conference on Engineering Innovations and Technologies (ICoEIT) · doi:10.1109/icoeit63558.2025.11211827
“Deep neural networks are particularly advantageous for object detection, a critical task in computer vision when they are supplemented by well-annotated and robust datasets [2].”
High-level feature extraction: Fixed shape analysis
Nixon, M. S., & Aguado, A. S. (2025) · Elsevier eBooks · doi:10.1016/b978-0-443-36686-4.00009-2
Lecca, M., & Bianco, S. (2025) · Journal of the Optical Society of America A · doi:10.1364/josaa.569685 · Cited by 1
Visual navigation method for intelligent flight of highway inspection unmanned aerial vehicle
Song, L., Xu, Z., Tao, Y., Han, J., & Fang, J. (2025) · Machine Learning Engineering · doi:10.1088/3049-4761/ae1bab
Real-time Recognition of Hand-Drawn Objects using YOLO Detector
Hric, L., Bačík, J., Perduková, D., et al. (2025) · International Conference on Electrical Drives and Power Electronics (EDPE) · doi:10.1109/edpe66853.2025.11224231
“One of the most prominent families of one-stage object detectors is the YOLO (You Only Look Once) series [8, 9], developed by Ultralytics.”
Improving Automatic Check-Out Accuracy with Fine-tuned YOLOv10 and YOLOv12 Models
Skinderowicz, R. (2025) · Procedia Computer Science · doi:10.1016/j.procs.2025.09.577
RefineFuse: Light-Adaptive Cross-Spectrum Feature Integration for Night Vision Enhancement
Gao, W., Wei, Y., Zhang, Y., et al. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-4378-6_17
Nearly Time-Optimal Online Pick and Place Trajectory Computation using Quadratic Programming
Marauli, T., Gratt, F., Gattringer, H., et al. (2025) · IFAC-PapersOnLine · doi:10.1016/j.ifacol.2025.10.233
Detection, Segmentation, and Classification on Brain Tumor MRI Dataset
Bansal, S., Jadon, R. S., & Gupta, S. K. (2025) · Lecture notes in networks and systems · doi:10.1007/978-981-96-8694-0_39
Ko, J., Lee, D., Kim, Y., & Kim, H. (2025) · Journal of Real-Time Image Processing · doi:10.1007/s11554-025-01796-7
How Vision-Language Tasks Benefit From Large Pre-Trained Models: A Survey
Qi, Y., Hong-xi, L., Song, Y., Wu, X., & Luo, J. (2025) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2025.3632653 · Cited by 12
“Furthermore, the capabilities required by these tasks have shifted from basic perception [21], [22] to more advanced reasoning [23], [24], [25], [26], [27].”
MCRO-YOLO: An evolved Version of YOLO for Small Object Detection
Li, J., Shi, Q., Yang, F. O., Fu, S., & Hou, F. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11227312 · Cited by 2
“Faster R-CNN introduced the Region Proposal Network (RPN), enabling near real-time detection [11].”
Enhanced YOLOv7 for UAV Platforms: Achieving High Precision with Low Resource Utilization
Sui, C., Zhang, J., Jin, L., Lu, Q., & Chen, J. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11228323
“The main task of object detection [1] is to identify the location and category of objects in an image through bounding boxes.”
RPC-DETR: A Lightweight and Accurate Model for Foreign Object Detection on Transmission Lines
Liu, D., & Huang, J. (2025) · doi:10.1109/ijcnn64981.2025.11229210
“In recent years, advancements in computer vision technology [4] have provided valuable technical support for foreign object detection [5].”
DMP-DETR: Dilation Multi-Scale and Partial Channel Gated Fusion Attention For Steel Defect Detection
Zhao, S., Wu, C., & Yu, F. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11229140
“Current defect detection methods, including ultrasonic, magnetic particle, and manual inspections, face limitations such as long detection times, heavy reliance on subjective judgment, and a higher likelihood of misdiagnosis with large volumes of material [2].”
Enhancing Construction Site Safety and Efficiency with YOLO v8-Based Computer Vision Model
Sabek, M., González, V. A., Mei, Q., & Lee, G. (2025) · Lecture notes in civil engineering · doi:10.1007/978-3-031-97697-1_21
Digital Twins for Radar Object Detection: Improving Deep Learning with Synthetic Data
Reitz, P., Künzle, C., Franchi, N., et al. (2025) · European Radar Conference (EuRAD) · doi:10.23919/eurad65285.2025.11233887
“Modern one-stage detectors in computer vision use augmentation techniques to improve model robustness for rotation and scale changes [1].”
Yang, L., Editorial Office, Hang, G., et al. (2025) · Journal of Advanced Computational Intelligence and Intelligent Informatics · doi:10.20965/jaciii.2025.p1377
A multi-task progressive multi-feature fusion network for high-resolution cropland segmentationPreprint
Sun, Y., & Bai, Y. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5786809
Tsai, M., Hsu, P.-Y., Chung, W.-C., & Chen, M. (2025) · Applied Soft Computing · doi:10.1016/j.asoc.2025.114324
Semantic-Interactive Clustering Optimization With SAM for Weakly Supervised Person Search
Yang, X., Zhou, H., Cheng, D., et al. (2025) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2025.3636572
“scenes, combining the critical tasks of person detection [1], [2], [3] and person re-identification [4], [5], [6], [7].”
EverydAI: Redefining Everyday Decision-Making Through AI-Powered Assistance
R., O. I. I., B., C. E. P., A., M. D. L., Viloria-Núñez, C., & M., C. G. Q. (2025) · IEEE Technology and Engineering Management Conference - Latin America (TEMSCON LATAM) · doi:10.1109/temsconlatam65810.2025.11238565
Improved the Notched Character Defect Detection Algorithm of YOLOv8
Jiang, H., & Liu, L. (2025) · International Journal of Computer Science and Information Technology · doi:10.62051/ijcsit.v7n3.01
“These algorithms are primarily divided into two categories: traditional object detection algorithms and deep learning object detection algorithms [1].”
Motion-Adaptive HOG Descriptors for Real-Time Object Detection in Resource-Constrained EnvironmentsPreprint
Río-Álvarez, Á., Fernández-Lanvin, D., Suárez, J. D. A., et al. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5813509
Forest Fire Recognition Neural Networks Based on Edge ComputingPreprint
He, L., Tang, Q., Jiwa, A., Li, J., Zeng, C., & Du, Z. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5813592
RoNErF-CD: A Robust Nerf-Based Change Detection Method for UAV Video Observing
Zhang, J., Wu, Q., Zheng, Z., et al. (2025) · IEEE International Geoscience and Remote Sensing Symposium (IGARSS) · doi:10.1109/igarss55030.2025.11242844
“Recent advancements in object detection techniques have led to models that demonstrate robust performance across diverse datasets and scenarios, with minimal degradation in accuracy [3].”
DiMASH: Towards an AI-based digitization tool for technical building system diagrams
Gölzhäuser, S., Hain, A., Trötschler, T., et al. (2025) · Journal of Physics Conference Series · doi:10.1088/1742-6596/3140/4/042014
Detecting Obstacles on Railroads Using Computer Vision on UAVs
Anand, A., Krishna, N., & Vitzilaios, N. (2025) · IEEE/RJS International Conference on Intelligent RObots and Systems · doi:10.1109/iros60139.2025.11246411
“Obstacle detection has been a focus of research for several decades resulting in the development of numerous systems tailored to specific use cases [14].”
Object detection as an aid for locating the prostate in surface-based abdominal ultrasound images
Bennett, R., Barrett, T., Gnanapragasam, V. J., & Tse, Z. T. H. (2025) · Communications Engineering · doi:10.1038/s44172-025-00550-y
Motion-Adaptive HOG Descriptors for Real-Time Object Detection in Resource-Constrained EnvironmentsPreprint
Río-Álvarez, Á., Fernández-Lanvin, D., Suárez, J. D. A., et al. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5830454
VS-MSS: Visual saliency-based efficient and secure multi-secret sharing scheme over cloud storage
Rawat, A., Deshmukh, M., Singh, M., et al. (2025) · Journal of Supercomputing · doi:10.1007/s11227-025-08094-w
Li, J., Duan, J., Shao, C., & Yu, H. (2025) · Symmetry · doi:10.3390/sym17122040 · Cited by 1
“These advancements have been largely attributed to the availability of meticulously annotated [1–3] and well-balanced benchmarks like ImageNet [4], COCO [5], and Places [6].”
Carrington, C. A., Lawrence, P. J., Kuncheva, L. I., Williams, F. J., Hennessey, S. L., & Waggitt, J. J. (2025) · Bird Study · doi:10.1080/00063657.2025.2581897
SFC-Detector: Spatial-Frequency-Channel Joint Framework for Lightweight Bird Detection
Wang, G., Su, B., Liu, M., et al. (2025) · International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI) · doi:10.1109/cisp-bmei68103.2025.11259207
“In recent years, object detection technology has been widely applied in ecological monitoring, remote sensing, and security surveillance [5] .”
Metadata
- Authors
- Zou, Z., Chen, K., Shi, Z., Guo, Y., & Ye, J.
- Affiliations
- Shanghai Artificial Intelligence Laboratory (CN)
- Carleton University (CA)
- Alibaba Group (China) (CN)
- Venue
- Proceedings of the IEEE
- Published
- 2023-03
- Volume
- 111
- Issue
- 3
- Pages
- 257-276
- ISSN
- 0018-9219 (ISSN-L)
- 1558-2256
- OpenAlex
- W4320002812
- Cited by
- 3,689
- References
- 272
- Citations by year
- 2026: 610 · 2025: 1013 · 2024: 940 · 2023: 541
- FWCI
- 280.65
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- Proceedings of the IEEE (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- National Natural Science Foundation of China (62125102)
- National Key Research and Development Program of China
- Fundamental Research Funds for the Central Universities
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image and Video Retrieval Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Visual Attention and Saliency Detection
- Keywords
- object detection, evaluation metrics, deep learning
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-07, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-07 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.