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 2,901–3,000 of 3,144
A Lightweight and High-Precision PCB Surface Defect Detection Method Based on YOLOv8
Wang, Z., Gao, Y., Xiao, Y., & He, Q. (2026) · Journal of Imaging · doi:10.3390/jimaging12060266 · Cited by 1
“In this paper, the YOLOv8 detection model [20] is further improved.”
Robust and Accurate Line Following Navigation by Hybrid Infrared-Visual Modes for Mobile Robots
Sun, B., Xiao, L., Xiong, H., et al. (2026) · IEEE International Symposium on Circuits and Systems proceedings · doi:10.1109/iscas66217.2026.11562500
“Proposed by J. Redmon et al. in 2015 [11], YOLO (You Only Look Once) is the first one-stage detector in deep learning [12].”
AlignLite: A Lightweight Framework for Weakly Aligned Multimodal Object Detection
Yang, H., Zhang, X., Zhang, Y. A., et al. (2026) · IEEE International Symposium on Circuits and Systems proceedings · doi:10.1109/iscas66217.2026.11562850
“…a stark trade-off: robust, dual-stream models [15], [16] that manage offsets are computationally expensive, while efficient, lightweight shared-backbone models [17] typically assume perfect alignment and fail under real-world misalignment, rendering them unsuitable for edge deployment [18], [19].”
da Cunha, L. C. C., Santiago, J. S. B., Sena, L., Cavalcante-Neto, J. B., Nogueira, Y. L. B., & Machado, J. C. (2026) · Journal of the Brazilian Computer Society · doi:10.5753/jbcs.2026.5323
“Other applications include surveillance systems [Zou et al ., 2019], medical imaging for detecting tumors [Litjens et al ., 2017], retail for inventory management, customer behavior analysis [Liu et al ., 2020], and PCB damage detection [Alves et al ., 2022; Santiago et al ., 2024].”
Domain Adaptation for Cross-View Localization via Multi-Teacher Knowledge Distillation
Chen, C., Yuan, Q., Liang, S., et al. (2026) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3820050
Li, J., & Chen, J. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6963091
ES-DETR: Real-time detection transformer with encover and soft-dropout
He, Y., Zheng, Z., Wang, Z., Zhang, X., Li, T., & Cheng, L. (2026) · Neural Networks · doi:10.1016/j.neunet.2026.109281
Synthetic Data Set for Surgical Instrument Detection
Coelho, N. R., Leite, J. E. D., Silva, M. R. D., et al. (2026) · doi:10.1109/cros69211.2026.11565743
“To automatically analyze a kit of surgical instruments, it is proposed to capture an image of the kit and to analyze it relying on computer vision and, more specifically, on deep-learning object detection algorithms [11] [12].”
Enhancing small object detection: a transformer-based middleware approach
Gu, F., Wang, Z., Zhang, Z., Zhang, Z., & Wu, J. (2026) · The Visual Computer · doi:10.1007/s00371-026-04545-4
Automatically detect Solidago canadensis using an improved attention mechanism network
Du, H., Gao, H., & Sun, C. (2026) · Multimedia Systems · doi:10.1007/s00530-026-02393-9
“Early object detection systems primarily relied on hand-crafted features combined with shallow classifiers [ 12].”
FFAA-Net: a full-scale frequency-aware and anisotropic attention network for UAV object detection
Zhou, Z., Zhu, T., Xu, J., & Zhao, J. (2026) · Multimedia Systems · doi:10.1007/s00530-026-02438-z
“This aliasing effect during spatial reduction significantly weakens the representation ability of deep features for small targets [31].”
Ahmed, A., Osman, A., & Czimber, K. (2026) · Trees Forests and People · doi:10.1016/j.tfp.2026.101367 · Cited by 1
Machine Vision-Based Automated Flake Detection with Feedback-Driven Model Improvement
Karimi, B., & Whitaker, B. M. (2026) · Intermountain Engineering, Technology and Computing (IETC) · doi:10.1109/ietc69527.2026.11568601
“Object detection differs from image classification by simultaneously localizing objects via bounding boxes and assigning class labels [6], [7].”
Zhang, C., Chen, J., Tang, D., & Zhang, Z. (2026) · Proceedings of the Institution of Mechanical Engineers Part C Journal of Mechanical Engineering Science · doi:10.1177/09544062261461647
A Comprehensive Review of Modern Computer Vision: From Classical Methods to Deep Learning
Hasan, M. M., & Setu, S. S. (2026) · Scientia. Technology, science and society. · doi:10.59324/stss.2026.3(6).14
Joint Super-Resolution Reconstruction for Small Traffic Sign Detection via Multitask Learning
Lv, Z., Wang, S., Zheng, L., Tang, Y., & Yuan, Q. (2026) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2026.3704948
“In general, CNN-based object detection methods can be categorized into two main groups [29]: two stage detectors and one stage detectors.”
Yuanhan, Z., Cheng, Q., Rao, Y., Liu, F., Zhou, Y. Q., Chao, Y., Liu, Z., Pu, G., Zhu, J., Du, A., et al. (2026) · Journal of Water Process Engineering · doi:10.1016/j.jwpe.2026.110454
Filtering-aware Sparse Transformer for Event-based Object Detection
Ma, P., He, C., & Liu, W. T. (2026) · doi:10.1109/icaisisas68969.2026.11567697
“Object detection serves as a fundamental technology in dynamic scenarios such as autonomous driving and robotic perception [1].”
Haoyue, F., Xingyu, W., & Du, H. (2026) · International Symposium on Autonomous Systems (ISAS) · doi:10.1109/icaisisas68969.2026.11567900
“…detectors from the YOLO family have become the *de facto* standard for meeting the latency constraints of dynamic roadway environments [4], [5], [6], and their widespread deployment across heterogeneous urban sensing pipelines amplifies the security implications of any vulnerability they harbor.”
Di, X., Cai, W., Wang, X., Yin, Z., Li, S., & Jia, H. (2026) · Entropy · doi:10.3390/e28070718
“The increasing reliance on deep learning-based object detectors in safety-critical cyber-physical systems [1], such as autonomous vehicles and surveillance drones, has made their robustness a paramount security concern [2].”
Reliable collaborative inference for embodied AI empowered by application-aware IPv6 networking
Chen, J., Fu, Z., Shang, Q., & Ma, H. (2026) · Journal of Information and Intelligence · doi:10.1016/j.jiixd.2026.06.004
Deep learning-enabled microfluidic digital PCR platform for efficient seven-color quantification
Wang, Z., Yang, K., Zhang, J., et al. (2026) · The Analyst · doi:10.1039/d6an00369a
Chen, Z., Ma, L., Zhang, Y. L., et al. (2026) · Optics & Laser Technology · doi:10.1016/j.optlastec.2026.115781
Road attribute detection system using object detection model
Jaleel, U., & Lalmawipuii, R. (2026) · AIP conference proceedings · doi:10.1063/5.0331711
Scarano, S., & Seshadri, A. (2026) · ASCE International Conference on Transportation and Development (ICTD) · doi:10.1061/9780784487013.069
Li, M., Zhang, J., Zhang, Y., Yang, J. Y., Dras, M., van den Hengel, A., & Qi, Y. (2026) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2026.3707553
“Traditional object detection primarily relies on RGB images [14].”
Liu, Q., Yu, Z., Zhu, L., et al. (2026) · Neural Networks · doi:10.1016/j.neunet.2026.109290
Towards a Holistic and Practical Adversarial Defense: A Modular Framework from Data to Model
Xie, J., Liu, X., Niu, X., Li, B., Zhang, Z. Z., Hu, T., Huo, S., Zhang, Y., Yi, P., & Shang, K. (2026) · Lecture notes in electrical engineering · doi:10.1007/978-981-95-7668-5_48
Towards Robust Multimodal Detection via Progressive Cross‐Domain Feature Fusion
Wang, Y., Wang, Y., Shen, B., Dang, Z., & Hou, Z. (2026) · IET Computer Vision · doi:10.1049/cvi2.70074
RDC-Net: Handling Asymmetric and Multi-Scale Road Damages via Dynamic Relational Mixing
Zhao, S., Yan, M., & Shen, Z. (2026) · International Symposium on Computer Technology and Information Science (ISCTIS) · doi:10.1109/isctis70043.2026.11572609
“In recent years, deep learning has been widely used in fields such as road damage detection, vehicle identification [3], and remote sensing ship detection [4], with mainstream methods including the two-stage Faster R-CNN [7] and one-stage series [1].”
Learning Shape Anchors for Holistic Indoor Scene Understanding
Dong, M., Huan, L., Zheng, X., Shen, S., Gong, J., & Xue, N. (2026) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2026.3708125
“1) 3D Object Detection: Over the past years, deep detectors have gained great success in 2D object detection [32], [33].”
Self-evolving Agentic Image Restoration via Deliberate Planning and Intuitive Execution
Cui, S., Ji, F., Sun, G. X., Guo, Y., Tang, X., Li, J., & Xu, F. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37422-6_22 · Cited by 2
Self-citationSiStNet: A Single-Stage Convolutional Neural Network for Vehicle Detection
Azadvatan, Y., & Kurt, M. (2026) · Applied Sciences · doi:10.3390/app16136476 · Cited by 2
Açıcı, K., Kökver, Y., Çatalca, H. H., DEMİR, Ö., Ekinci, F., & Güzel, M. S. (2026) · El-Cezeri Fen ve Mühendislik Dergisi · doi:10.31202/ecjse.1970237
RMO-DETR: robust small-organoid detection in high-resolution microscopy images
Wu, T., Feng, Z., Sun, R., Jia, Z., Li, S., Chen, W., Zhang, L., Jia, Z., Ge, M., & Dong, W. (2026) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2026.110895
Du, Q., Zhao, M., Lu, S., et al. (2026) · Sensors · doi:10.3390/s26134145
Computer Vision for Monitoring Wild Bees and Wasps: A Structured Literature Review
Liu, C., Mäder, P., & Seeland, M. (2026) · Ecology and Evolution · doi:10.1002/ece3.73794 · Cited by 1
tibari, I., Lachgar, M., Achbarou, O., et al. (2026) · IEEE International Symposium on Signal, Image, Video and Communications (ISIVC) · doi:10.1109/isivc69944.2026.11574088
“The possibility of overfitting and the inability to extrapolate to real-world conditions can be enhanced due to working with a small dataset [12], [13].”
Detection of oriented lunar rockfalls and kinematic analysis in Tycho Crater
Miao, D., Yan, J., & Tu, Z. (2026) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2026.06.036
Camera measurement-free passive monocular visual localization
Bi, J., Wen, Z., Yu, B., Zhang, K. F., Huang, L., Zhao, X., Wang, X., Bi, L., & Yao, G. (2026) · Pattern Recognition · doi:10.1016/j.patcog.2026.114403
Chen, M., Zhou, H., & Sun, K. (2026) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2026.3709284
Efficient Pre-Deployment CNN Compression for Edge Inference
Farghaly, A. S., Elsedfy, M. O., & Elshafey, M. A. (2026) · doi:10.1109/iicc69623.2026.11582168
“The MNIST dataset contains 70,000 grayscale 28 × 28 handwritten digit images (0–9), split into 60,000 training and 10,000 test samples [7], and is used as a controlled benchmark [2].”
Wang, Q., He, Y., Chen, J., Jia, X., Wu, G., Wang, D., & Pan, G. (2026) · IEEE Internet of Things Journal · doi:10.1109/jiot.2026.3709847
“O BJECT detection [1], [2] is a fundamental computer vision task that identifies object categories and localizes them with bounding boxes.”
Farady, I., Kasemtaweechok, C., Chootong, C., et al. (2026) · Communications in computer and information science · doi:10.1007/978-981-95-9843-4_24
Служала, О. Т., & Ovsyak, O. (2026) · Науковий вісник НЛТУ України · doi:10.36930/40360314
Locating Mobile Devices Equipped With Cameras Using LASER Beacons
Massaneiro, L. J., Mathias, L. C., & Abrão, T. (2026) · International Wireless Communications and Mobile Computing Conference (IWCMC) · doi:10.1109/iwcmc69287.2026.11580018
“Object detection in images is a widely studied problem and forms the basis of several applications in computer vision, potentially involving high computational complexity [18].”
Disentangling Pictorial Cue Understanding from Language Bias in VLMs via Depth Ordering Task
Liu, Y., Kotseruba, I., & Tsotsos, J. K. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37020-4_35 · Cited by 1
SCR-YOLO: a small-object detection model for beach litter with spatial and contextual refinements
Fang, A., Zhang, Y., Xiao, X., et al. (2026) · Journal of Control and Decision · doi:10.1080/23307706.2026.2687795
Detection of Cow Face and Subregions Using a New Annotated Dataset
Almeida, M. E. G., Bittencourt, P. D. A. B., Maia, B. L. C., et al. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-30491-9_35
AMFNet: adaptive multi-scale fusion network for small object detection
Tian, B., Hu, M., Li, L., Zhao, X., Tang, M., & Wang, Z. (2026) · Complex & Intelligent Systems · doi:10.1007/s40747-026-02369-2
“In UAV aerial scenes, due to imaging height and top-down viewing angles, targets often exhibit small scales, dense distributions, and complex backgrounds [4].”
Güngör, Z. K., Vehbi, H., & Cansın, A. (2026) · BMC Musculoskeletal Disorders · doi:10.1186/s12891-026-10124-4
“…such as YOLO predict bounding boxes and class labels in a single forward pass, trading a modest reduction in peak accuracy for substantially faster inference and a simpler deployment footprint — properties that are attractive for pre-screening and worklist-pri-oritization scenarios [8, 9].”
Shi, H. Z., Wang, M., Lin, K., Chen, Y., Chen, Y., Zhou, G., & He, M. (2026) · International Conference on Computer Supported Cooperative Work in Design (CSCWD) · doi:10.1109/cscwd68734.2026.11582288
“RELATED WORK Deep learning-based object detectors for small objects in UAV imagery are typically divided into two categories: one-stage and two-stage detectors [10].”
Vehicle Detection in Synthetic Aperture Radar Images with Multi-Scale and Outlook Attention
Zhengqin, Y., Lian, H., Xie, Y., et al. (2026) · International Conference on Computer Supported Cooperative Work in Design (CSCWD) · doi:10.1109/cscwd68734.2026.11582191
Nogay, H. S. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7075309
Marine Debris Detection in Underwater Environments: Recent Developments and Future Directions
Rajasri, K., & Vivekanandan, D. K. (2026) · International Conference on System, Computation, Automation and Networking (ICSCAN) · doi:10.1109/icscan66520.2026.11588470
Grenèche, T., Sabathier, C., Onofri, C. A. D. T., et al. (2026) · Journal of Nuclear Materials · doi:10.1016/j.jnucmat.2026.156894
Cross-Modal Weak Supervision Training of UAV Detection Model for Degraded Environments
Stipičević, M., Ivanković, M., Stipetić, S., & Radišić, T. (2026) · International Convention on Information and Communication Technology, Electronics and Microelectronics · doi:10.1109/mipro70003.2026.11591746
ACF-DP-YOLO: Attention-Enhanced and Dual-Pyramid Fusion Network for Insulator Defect Detection
Yang, X., Xiong, H., Yang, C., Wei, C., Liu, J., & Fu, L. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-2487-6_24
DL-DETR: Exploring the Future Directions of Fusion Between Dictionary Learning and DETR
Liu, F. T., Ji, D., Si, H., & Guo, Y. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-22267-1_38
Self-citationAdROD: Adaptive Redundancy for Object Detection in Autonomous Driving
Nagao, S., & Machida, F. (2026) · doi:10.1109/dsn-w70714.2026.00043
“Object detection is an essential task for enabling various applications, such as autonomous driving, autonomous robotics, and medical image diagnosis [29] [16] [8].”
BM-YOLO: A novel framework for real-time defect detection in breathable membrane
Xu, X. X., Song, J., Zhou, H., & Yan, X. (2026) · Measurement · doi:10.1016/j.measurement.2026.122468
HVPNet: A bio-inspired network for general salient and camouflaged object detection
Xu, J., Zhou, Q., Li, Z., Shi, Y., Yi, Y., & Yu, J. (2026) · Neural Networks · doi:10.1016/j.neunet.2026.109340 · Cited by 7
“Both tasks play crucial roles in practical applications such as video surveillance [2], intelligent security systems [3], object tracking [4], and video summarization [5].”
Dual-view weakly-supervised learning for apple tree flower counting
Vitousek, M., Vrba, J., Cejnek, M., et al. (2026) · Frontiers in Plant Science · doi:10.3389/fpls.2026.1869941
“Furthermore, YOLO exhibits exceptional accuracy, consistently achieving state-of-the-art results on benchmark data sets for object detection and segmentation (Zou et al., 2023).”
Oriented multi-scale feature learning model for orientation measurement of refractory brick
Zhou, S., Ao, S., Fu, L., Yan, X., & Ju, Z. (2026) · Measurement · doi:10.1016/j.measurement.2026.122505
Heng, X., Guo, P., & Yang, J. (2026) · Signal Processing Image Communication · doi:10.1016/j.image.2026.117654
RFA-Tex: Range-Flexible Adaptive Physical Adversarial Texture Against Real-World Person Detectors
Zhu, M., Li, X., Liu, D., Zhang, H., Yuan, S. W., Li, Y. F., Miao, Y., & Deng, R. H. (2026) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2026.3712205 · Cited by 1
“The security and reliability of object detection have drawn considerable attention from researchers [17], [18], [19].”
Structure-aware feature enhancement for real-time fabric defect detection in industrial inspection
Zhang, X., Xie, H., Lu, J., Ji, Z., Zhou, J., Xiang, J., & Pan, R. (2026) · Journal of Intelligent Manufacturing · doi:10.1007/s10845-026-02924-1
Deep Learning-Based Ripeness Detection for Smart Refrigerators
Καραγιάννης, Γ., Bompotas, A., Kalogeropoulos, N.-R., & Makris, C. H. (2026) · IFIP advances in information and communication technology · doi:10.1007/978-3-032-30801-6_14
FFEF-YOLO: a fine-grained feature extraction and fusion network for UAV small object detection
Yang, B., Jin, P., Ren, G., & Xu, S. (2026) · The Journal of Supercomputing · doi:10.1007/s11227-026-08703-2
Avhad, M., Kamat, P. V., Kumar, S., & Sayyad, S. (2026) · Discover Artificial Intelligence · doi:10.1007/s44163-026-01751-w · Cited by 2
Xie, W., & Lu, Y. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-3441-7_40
Det-PaCo: Active Camera Imaging Parameter Control Aiming at Object Detection Performance
Pu, Y., Hao, X., Yang, S. Y., et al. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-3504-9_7
From keywords to context: A relation-centric framework for automated image dataset preparation
Lu, J., Xu, W., Wu, Y., & Wang, Z. (2026) · Neurocomputing · doi:10.1016/j.neucom.2026.134487
EAM-YOLO: Adaptive Feature Aggregation and Refined Regression for Robust Fall Detection
Li, Y., Wang, Y., Meng, G., et al. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-3504-9_26
Wang, A., Qin, L., Huang, Q., & Zou, Q. (2026) · Journal of Real-Time Image Processing · doi:10.1007/s11554-026-01904-1
Dual-Domain Imitation with Normalization: Enhancing Feature Distillation for Object Detection
Zhang, M., Cheng, Z., Wang, J., He, X., He, T., & Lu, G. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-3504-9_27
Baishemirov, Z., Kazhimova, R., & Amirgaliyev, B. (2026) · IEEE International Conference on Smart Information Systems and Technologies (SIST) · doi:10.1109/sist61674.2026.11596310
“This approach is fragile; it often triggers false alarms due to camera perspective shifts, slight "jitter" in the detector's output, or vehicles momentarily blocking each other from view [1][3].”
Consistency-guided model-contrastive federated learning for scalable road damage detection
Xiong, Z., & Jia, G. (2026) · Automation in Construction · doi:10.1016/j.autcon.2026.107140
Effective Computer Vision Approach for Surveillance Systems to Detect Stone Crushers
Harichandan, A. K., Harichandan, S., Kumar, R. R., & Muduli, D. (2025) · Springer proceedings in mathematics & statistics · doi:10.1007/978-981-95-3841-6_24
Bao, J., Zhang, Z., Petropoulos, G. P., Fang, Z., Shen, J., & Li, J. (2026) · Remote Sensing Applications Society and Environment · doi:10.1016/j.rsase.2026.102168
Cheng, X., Liu, Y., Zhang, H., Liu, H., Wu, Y., Hu, Z., & Xu, N. (2026) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2026.3714489
“Early sliding-window approaches with handcrafted features struggled with limited representation in remote sensing imagery, failing to handle object diversity in complex backgrounds [20].”
Hu, J., Jia, L., Liu, J., et al. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-3513-1_31
R 2 -Net: A Hybrid Meta-Learning Framework for Cross-Domain Few-Shot Industrial Defect Detection
Huang, Z., Ouyang, X., Zhang, H., & Yang, J. (2026) · Journal of Advanced Computational Intelligence and Intelligent Informatics · doi:10.20965/jaciii.2026.p1138
VPDL: Visual Prompt-Guided Differential Learning for Generalizable Scene Text Recognition
Niu, Y., An, J., & Zou, S. (2026) · Journal of Advanced Computational Intelligence and Intelligent Informatics · doi:10.20965/jaciii.2026.p1306
Edge-guided transformer network for small object detection in UAV imagery
Fang, X., Fang, C., Tie, Z., et al. (2026) · Digital Signal Processing · doi:10.1016/j.dsp.2026.106432
A Comprehensive Review on Hardware Accelerator for YOLO Model Using Sparse Data
Endrawati, D. N., Syafalni, I., Sutisna, N., & Adiono, T. (2026) · IEEE Access · doi:10.1109/access.2026.3715073
“…the review of this manuscript and approving it for publication was Syed Islam . object detection techniques relied on handcrafted features and classical detectors, such as the Viola Jones detector, histogram of oriented gradients (HOG), and deformable part models (DPM) [1], [2], [3], [4].”
Wang, B., Leng, C., Fang, Y., et al. (2026) · Digital Signal Processing · doi:10.1016/j.dsp.2026.106408
A Lightweight Ship Target Detection Algorithm Based on Improved RT-DETR
Zheng, R., & Duan, X. (2026) · International Conference on Electrical, Control and Information Technology (ECITech) · doi:10.1109/ecitech69277.2026.11601881
“Lately, optical remote sensing has emerged as a key data provider for extensive ocean observation [1], [2].”
Irrahman, A., Arief, M., Iskandar, A., Saddami, K., Afdhal, A., Sugiarto, S., & Nasaruddin, N. (2026) · Franklin Open · doi:10.1016/j.fraope.2026.100720
Art Beyond Semantics: Sheaf-Informed Contrastive Learning for Multi-relational Representations
Schaerf, L., Purificato, A., Riccio, P., Silvestri, F., & García, N. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37324-3_15 · Cited by 1
DSAF-YOLOv8: A Behavior Detection Algorithm for Dense and Occluded Multi-Person Scenes
Zhang, Y., Chen, Q., Xu, F., Chen, M., Wang, Q. L., & Duan, Z. (2026) · IEEE International Conference on Pattern Recognition, Machine Vision and Artificial Intelligence (PRMVAI) · doi:10.1109/prmvai70103.2026.11605562
“Early studies on behavior-aware visual analysis mainly relied on handcrafted features and traditional machine learning, which were sensitive to environmental disturbance and lacked robust generalization [1], [5].”
Tian, J., Ma, C., Li, J., Sun, M., & Zhou, H. (2026) · Journal of Stored Products Research · doi:10.1016/j.jspr.2026.103183
PST-PFN: A Parallel Spatiotemporal Network with Progressive Fusion for Raw Meal Fineness PredictionPreprint
Liu, G., Cao, M., Zhai, S., et al. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7158736
YOLOv11n-SSS: A dynamic dual-branch attention detection model for sea urchins in marine ranching
Qiao, L., & Wang, J. (2026) · Ocean Engineering · doi:10.1016/j.oceaneng.2026.127181
Kishore, T., Ramana, K. S., Mayee, M. K., Kumar, P. H., & Alluraiah, N. C. (2026) · Next research. · doi:10.1016/j.nexres.2026.102222
MarineRT-DETR: A Lightweight Real-Time Detector for Small Maritime Targets in UAV Search and Rescue
Jiang, C., Zhang, G., Zou, C., Li, W., Wang, T., & Zhou, Z. (2026) · International Conference on Image and Graphics Processing (ICIGP) · doi:10.1109/icigp68997.2026.11619677
“However, such approaches typically rely on non-maximum suppression (NMS) to discard inaccurate boxes, which not only introduces an efficiency bottleneck but also tends to miss small objects, limiting robustness in complex scenes [12], [13].”
Zhang, L., & Xiong, Z. (2026) · Algorithms · doi:10.3390/a19080620
Solving Imbalanced Problems With Multilayer Ensemble Balanced Fuzzy Inference Broad Network
Chen, W., Yu, Z., Yang, K., Jiang, J., Zhang, F., & Chen, C. L. P. (2026) · IEEE Transactions on Fuzzy Systems · doi:10.1109/tfuzz.2026.3717303
Toward LLM-Based Evaluation of Hybrid Object Detection Models
Qu, Z. (2026) · International Conference on Artificial Intelligence, Big Data and Algorithms (CAIBDA) · doi:10.1109/caibda70336.2026.11621388
“It aims to identify object categories in an image or video and localize their positions, typically by predicting class labels and bounding boxes [1][3].”
InfluentialA Semantic Understanding Method for Dimension Information in Electronic Component Packaging Drawings
Qi, X., Wu, L., Li, N., & Xu, N. (2026) · International Conference on Computer and Communication Systems (ICCCS) · doi:10.1109/icccs69761.2026.11613419
“…extraction technology of engineering drawings, in addition to the improvement of deep learning models : text detection, target detection [2]-[4] and OCR [5] [6], Kashevnik [7] proposed an engineering drawing border detection method based on YOLOv5, which achieved 99% accurate detection…”
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.