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 2,801–2,900 of 3,144
Introduction of Video Analytics
Bai, T. (2025) · Textbooks in telecommunication engineering · doi:10.1007/978-3-032-14764-6_1
SCS-YOLO: An Occlusion-Robust Object Detection Algorithm Based on YOLO12
Liu, D., Ren, C., Ma, H., et al. (2026) · Communications in computer and information science · doi:10.1007/978-981-95-6736-2_3
A Metrics-Based Framework for Model Selection in Object Detection Systems
Ngammongkolwong, S., & Saosing, R. (2026) · Journal of Advances in Information Technology · doi:10.12720/jait.17.4.636-647
“…AHP strikes a pragmatic balance between rigor and usability, making the approach applicable to diverse AI use cases, such as surveillance, industrial inspection, and embedded/edge systems, where priorities differ across recall-critical, precision-critical, and latency-constrained deployments [8–11”
Credible early fire detection via intelligent pan–tilt-zoom camera
Deng, T., Qiu, P., Lv, X., Tarambiwa, E., Luo, Y., Xu, W., Bian, A., & Nienkötter, A. (2026) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2026.114891
Li, X., Zhai, D., & Xia, Y. (2025) · China Automation Congress (CAC) · doi:10.1109/cac67268.2025.11487434 · Cited by 1
“Separate Detection and Embedding (SDE) [6] paradigm has seen significant performance improvements due to advances in the detection [4] and ReID [5] algorithms.”
Zhang, Y., Chen, Z., Long, D., & Zuo, R. (2026) · Mathematical Geosciences · doi:10.1007/s11004-026-10297-7
An Improved Object Detection Method Based on YOLO for Airborne Scenario
Guo, C., Tang, B., Yan, W., et al. (2026) · Lecture notes in electrical engineering · doi:10.1007/978-981-95-7656-2_27
CD-DETR: Compensate for the Positioning Deviation of the Transform
Wei, X., & Wu, J. (2025) · China Automation Congress (CAC) · doi:10.1109/cac67268.2025.11486592
“Object detection is one of the core tasks in the field of computer vision [1].”
Luan, Y., Lv, B., Guo, Y., et al. (2026) · Lecture notes in electrical engineering · doi:10.1007/978-981-95-6553-5_16
Self-citationBionic Corner Detection Based on Cooperative Processing of Simple Cells and End-Stopped Cells
Sun, S., & Yu, H. (2026) · Algorithms · doi:10.3390/a19050343
Improvement of Road Traffic Accident Detection Based on YOLOv11
Zhang, X., & Zhai, J. (2026) · Lecture notes in electrical engineering · doi:10.1007/978-981-95-6553-5_8
Xue, D., Li, B., Li, Y., Sun, F., & Zhang, X. (2026) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2026.3689768 · Cited by 1
“Currently, Transformers and their various improved models have shown substantial potential in tasks such as image classification [21], object detection [22], and semantic segmentation [23].”
Zhang, L., & Li, Y. (2026) · Sensors · doi:10.3390/s26092793 · Cited by 2
“Deep neural network detectors have progressed rapidly on natural images [1,2] and been extended to aerial imagery.”
Underwater garbage detection method for environmental protection
Chen, Y., Ning, H., Hao, P., et al. (2026) · Discover Applied Sciences · doi:10.1007/s42452-026-08752-5
“The former follows a cascaded processing paradigm of “region proposal–feature classification”,with typical representatives including RCNN [2], Fast R-CNN [3], and Faster R-CNN [4].”
EV Charging Socket Detection using YOLO for High Precision Robot Manipulation
Zaw, N. H., & Wang, Q. (2026) · IEEE International Conference on Industrial Technology (ICIT) · doi:10.1109/icit64854.2026.11491131
“[5] Choosing an object detection algorithm for an electric vehicle (EV) charging robot arm depends on several factors including the environment the robot will operate in indoor or outdoor, the types of objects the robot needs to detect (charging ports, cables, vehicles) and the need for real-time…”
Luan, W., Lu, S., Zheng, Y., Xu, W., Nie, L., Zhou, Z., & Liao, K. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.02368 · Cited by 1
“This phenomenon harms the model performance at the data level, making it difficult to provide accurate scene perception information for downstream vision tasks, such as object detection[5, 52], image segmentation[9, 19, 47], and SLAM[6, 12].”
Yang, Y., & Chen, D. (2025) · International Conference on Industrial Automation, Robotics and Control Engineering (IARCE) · doi:10.1109/iarce68366.2025.11485770
“Consequently, leveraging advanced technological solutions to enhance operational monitoring has become a critical research imperative for ensuring mining safety and optimizing production efficiency [3, 4].”
Zhang, Y., & Liu, C. (2026) · Elsevier eBooks · doi:10.1016/b978-0-443-45022-8.00004-8
Liao, X., Wei, X., Leung, W. K., Yuen, Y. F., Yang, S., Wang, D., Zhou, Z., Xiao, X., Chen, Y., Huang, Y., et al. (2026) · IEEE Systems Man and Cybernetics Magazine · doi:10.1109/msmc.2025.3634086 · Cited by 1
Zhang, C.-L., Zhang, J.-M., Liu, H.-L., Qin, S.-Y., & Wang, J.-Q. (2026) · Nuclear Science and Techniques · doi:10.1007/s41365-026-01919-0
Ahsan, M. M., Liu, Y.-T., Raman, S., & Siddique, Z. (2026) · Next Materials · doi:10.1016/j.nxmate.2026.102174 · Cited by 2
A Bandwidth-Efficient Bit-Serial Systolic Accelerator with Bit-Matrix Based Dataflow
Wu, J., Li, W., Deng, S., He, W., & Li, Y. (2026) · International Conference on Electronics Technology and Artificial Intelligence (ETAI) · doi:10.1109/etai68332.2026.11485450
“With the rapid development of AI technology, AI has achieved remarkable results in various fields [1]–[4], reaching accuracy close to or even exceeding that of humans.”
Unseen things: Computer vision and the uneven geographies of AI failure
Cinnamon, J., & Dai, J. (2026) · Digital Geography and Society · doi:10.1016/j.diggeo.2026.100173
He, T., Wang, L., & Deng, M. (2026) · Frontiers in Earth Science · doi:10.3389/feart.2026.1689915
Multiple similar radioactive source detection using deep learning
Liu, M., Xu, P. F., Yang, X., et al. (2026) · Nuclear Technology and Radiation Protection · doi:10.2298/ntrp2601001l
Kwak, S., & Shin, E. (2026) · The Korean Society of Costume · doi:10.7233/jksc.2026.76.2.020
Santos, B. (2026) · Journal of Artificial Intelligence & Control Systems · doi:10.66967/jaics.2026.v2i105
BAD: Bidirectional Attention-Guided Distillation for Object Detection
Zhang, C., Wang, N., & Zhou, H. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-7084-3_28
SFNet: Sparse Fusion Network for Object Detection of Cross-Modal Images
Xiao, H., Ren, Z., Li, Z., Zeng, Z., Yang, S., Teng, Z., Wang, Y., Cai, S., Xu, C., & Wu, Z. (2026) · IEEE Sensors Journal · doi:10.1109/jsen.2026.3689924
“The subject of object detection has always been of fundamental importance in the field of computer vision, and extensive research has led to its remarkable development over the years [24].”
PFENet: Physics-Informed Frequency-Enhanced YOLO for Object Detection in Hazy Scenes
Bai, K., Zhou, Z., Yang, J., & Zhang, W. (2026) · Applied Sciences · doi:10.3390/app16104635
YOLO-FR: An enhanced object detector for small object detection in complex scenes
Fan, R., Jiao, R., Nan, W., Dang, J., Wang, Z., Ge, X., Dong, B., & Luo, X. (2026) · Remote Sensing Applications Society and Environment · doi:10.1016/j.rsase.2026.102059 · Cited by 1
StratiFormer: Stratified Temporal Transformer for video object detection
Zheng, W., Zheng, H., Sun, Y., & Jing, Y. (2026) · Knowledge-Based Systems · doi:10.1016/j.knosys.2026.116117 · Cited by 1
Liu, M., Hou, Y., Duan, X., Feng, B., Hou, H., Yang, M., Dai, X., & Gu, L. (2026) · Journal of Real-Time Image Processing · doi:10.1007/s11554-026-01892-2 · Cited by 2
Vision-based Crowd Density Monitoring and Automated Emergency Alert System using YOLO Deep Learning
Pujitha, M., Tanmayi, M., & Varshitha, T. V. L. (2026) · International Congress on Information and Communication Technology · doi:10.1109/icict68280.2026.11510723
“Object detection methods have undergone significant advancements in the past two decades, and these methods are highly efficient for accuracy [23].”
Cao, Y., He, Z., Liang, H., He, Z., Lin, Z., Shi, M., & Xie, S. (2026) · IEEE Sensors Journal · doi:10.1109/jsen.2026.3690187
“Object detection is one of the fundamental tasks in computer vision, involving the detection and classification of all objects within an image [28], [29].”
MBF-DETR: a lightweight real-time detector with multi-backbone hybrid attention for ship detection
Fan, X., Xing, B., Wang, X., Liu, H., Yan, C., & Zhi, P. (2026) · Journal of Real-Time Image Processing · doi:10.1007/s11554-026-01896-y
“Object detection, a fundamental computer vision task, aims to identify and localize objects within images [15, 16].”
Head Protective Equipment Detection in VideoSurveillance via Flow-Guided Spatiotemporal Fusion
Liu, Y., Zhang, S. T., Shu, S., & Xie, W. (2026) · Journal of Computing in Civil Engineering · doi:10.1061/jccee5.cpeng-7260
Shinichi, Y., Taiki, K., Taku, N., et al. (2026) · Institutional Repositories DataBase (IRDB)
Multimodal Fusion with External Knowledge (MFEK)
Lin, Z., & Li, Q. (2026) · Wireless networks · doi:10.1007/978-3-032-20416-5_3
Lightweight YOLOv5 with Wavelet Convolution and Attention for Waste Detection
Wang, S., & Chen, Z. (2026) · International Conference on Generative Artificial Intelligence and Information Security (GAIIS) · doi:10.1109/gaiis69281.2026.11519247
“Deep convolutional neural networks have achieved remarkable progress in visual recognition tasks by learning hierarchical feature representations from large-scale data [2] .”
YOLO-MSFF: An Improved YOLO11-Based Multispectral Feature Fusion Method for Object Detection
Guo, C., Zhao, T., & Zhang, Z. (2026) · International Conference on Generative Artificial Intelligence and Information Security (GAIIS) · doi:10.1109/gaiis69281.2026.11519149
“Owing to its capability of integrating complementary information from different spectra, multispectral detection has shown great potential in practical applications such as autonomous driving, surveillance systems, and UAV-based monitoring [1].”
Lee, K., Hong, J., Kim, B.-S., Song, Y., & Lee, D.-H. (2026) · Algorithms · doi:10.3390/a19050409 · Cited by 1
“Object detection, a core area of computer vision, has seen continuous technological advancement and practical application driven by industrial demands [1–4].”
Zhao, C. (2026) · International Conference on Advanced Electronic Materials, Computers and Software Engineering (AEMCSE) · doi:10.1109/aetcse69203.2026.11503938
“However, existing studies often rely on limited evaluation indicators or single weighting strategies, and a unified framework that integrates subjective preferences with objective data remains insufficiently explored in object detection evaluation [9].”
Intelligent Recognition of Chinese Pangolin Stereotyped Pacing
Tang, P., Chen, M., Chen, B., Wang, K., Jia, G., Hua, Y., & Gao, Y. (2026) · Journal of Applied Animal Welfare Science · doi:10.1080/10888705.2026.2673921
Low-Altitude Object Detection Based on Multi-Scale Feature Global Interaction
Ma, M., Wu, Y., & Wang, J. (2025) · Asian Conference on Artificial Intelligence Technology (ACAIT) · doi:10.1109/acait67930.2025.11522602
“The perspective of drone imagery [4] is different from that of regular imagery [5]–[8], often presenting an oblique top-down view.”
SSL-OTA: Unveiling backdoor threats in self-supervised learning for object detection
Yin, C., Wang, Q., Yang, H., Fang, L., Zhou, L., & Liu, Z. (2026) · Applied Soft Computing · doi:10.1016/j.asoc.2026.115524 · Cited by 2
RAME: Runtime-adaptive model evolution system for video perception pipelines
Chen, T. Y., Zeng, Y., Zhou, W., et al. (2026) · Journal of Systems Architecture · doi:10.1016/j.sysarc.2026.103846
Chu, W. C.-C., Hsu, T.-C., Cheng, Y., & Qu, W. (2026) · IEEE Transactions on Reliability · doi:10.1109/tr.2026.3695615
“Therefore, image-based automated measurement technology is gaining increasing attention [2].”
Multi-sensor fusion on autonomous driving perception: A comprehensive survey
Jiang, M., Chu, Z., Pan, Y., Yuan, H., Han, Q., Zou, J., Zhang, Y., Zhu, X., Zhang, C., Zhou, X., et al. (2026) · Multimodal Transportation · doi:10.1016/j.multra.2026.100325 · Cited by 4
Shang, S., Fu, Y., Huang, L., Liu, D., & Li, J. (2026) · Advanced Engineering Informatics · doi:10.1016/j.aei.2026.104840 · Cited by 1
A Guided Fusion Network based on Cross-Scale Semantic Alignment for multi-spectral object detection
Wu, H., Rong, J., Zhou, Q., et al. (2026) · Pattern Recognition · doi:10.1016/j.patcog.2026.114024
Intelligent Object Detection in Remote Sensing Images
Feng, P., Chen, Y., Lan, H., He, G., Li, Y., & Guan, J. (2026) · Springer eBooks · doi:10.1007/978-981-95-5879-7_4
EAFE‐OSOD: Efficient Attention Fusion Encoder for Open‐Set Object Detection in UAV Applications
Wang, Z., Pan, Z., Cai, Z., Zhou, H., Tang, Y., & Mao, Y. (2026) · IET Image Processing · doi:10.1049/ipr2.70396
MLS-YOLO : Remote sensing target detection for multi-scale craters
Zhu, L., Lu, B., Yao, H., Ren, S., Chen, Z., & Liu, X. (2026) · Expert Systems with Applications · doi:10.1016/j.eswa.2026.132952
An Improved YOLOv8 Model for Pavement Distress Detection Under Low-Computing-Power Conditions
Tang, Y., Yang, Z., Xu, Z., Zhou, Y., & Wang, H. (2026) · Sensors · doi:10.3390/s26113373
“Convolutional neural network (CNN)-based target detection methods can be broadly classified into two categories: two-stage models and one-stage models [15].”
Ad Keyframe Extraction and Product Detection Framework in Short Video Advertising
Wang, H., Sheng, H., Hong, M., & Liu, Y. (2026) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.70771
Development of a Dual-Arm Autonomous Mobile Robot for Fig Harvesting in Open-Field Environments
Kim, S.-S., & Lee, Y.-H. (2026) · Journal of the Korean Society of Manufacturing Process Engineers · doi:10.14775/ksmpe.2026.25.5.084
Inter-Class Enhanced Feature Correlation for Adaptive Online Knowledge Distillation
Gou, J., Zhu, H., Du, L., Ou, W., Chen, W., & Zhang, Y. (2026) · IEEE Transactions on Big Data · doi:10.1109/tbdata.2026.3695374 · Cited by 1
“D EEP convolutional neural networks (CNNs) have made significant strides in various computer vision tasks over the past decade, encompassing image classification [1], [2], [3], object detection [4], [5], [6], and semantic segmentation [7], [8], [9].”
Kang, S., Cai, Y., Zhong, T., Liu, Y., Yang, S., & Ye, Y. (2026) · Sustainable Cities and Society · doi:10.1016/j.scs.2026.107550
Sewick, M., Bondarenko, T., Hromovych, K., & Tkachuk, P. (2026) · Intelligent systems reference library · doi:10.1007/978-3-032-13497-4_16
Jadhav, S., Kulkarni, Y. C., Jadhav, P. A., Patil, V., & Kadam, A. K. (2026) · International Journal of Recent Technology and Engineering (IJRTE) · doi:10.35940/ijrte.b8366.15010526 · Cited by 1
DeepGrounder: Generalized Reasoning for MLLM-Based Remote Sensing Visual Grounding
Zhang, J. Q., Chen, K., Liu, C., Lin, B., Zou, Z., & Shi, Z. (2026) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2026.3697769 · Cited by 1
“This capability supports a wide range of applications, including target search [4], [5], disaster response [6], [7], and urban management [8], [9], [10].”
Self-citationNeural Audio-based Detection of Occluding andOccluded ObjectsPreprint
Saha, A., Yen, B., Bauer-Wersing, U., Ashizawa, T., Kojima, R., & Nakadai, K. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6861720
Song, Y., Zuo, X., Qu, C., et al. (2026) · Journal of Imaging · doi:10.3390/jimaging12060246
“Although object detection has achieved remarkable progress in recent years [8], detectors relying solely on RGB images still suffer from degraded performance in adverse environments such as nighttime scenes, fog, and abrupt illumination changes [9].”
CDS-YOLOv11:vehicle detection in low-light scenarios via a lightweight YOLOv11
Zheng, S., Tan, B.-H., Yu, R., et al. (2026) · Engineering Research Express · doi:10.1088/2631-8695/ae76f2
“We use a series of standard object detection metrics, such as precision ( P ), recall ( R ), mean precision (mAP) [40], and FLOPs, to evaluate the performance of the model.”
Robustness Analysis of Translation Tampering in Multi-sensor Object Detection
Safarzadehvahed, M., & Zulkernine, M. (2026) · IFIP advances in information and communication technology · doi:10.1007/978-3-032-27993-4_16
Vision-based early fault diagnosis and self-recovery for strawberry harvesting robots
Sun, M., Zhao, C., Yang, L., et al. (2026) · Artificial Intelligence in Agriculture · doi:10.1016/j.aiia.2026.05.009
“For the detection and segmentation tasks, precision and recall were used to evaluate performance, following the definitions in [25].”
SD-YOLO: An Efficient Deep Learning Framework for Real-Time and Multiscale Pavement Crack Detection
Zhang, H., Liu, P., Zhang, X., Yang, Y., Liu, Y., & Wang, Q. (2026) · Journal of Infrastructure Systems · doi:10.1061/jitse4.iseng-2864
Han, J. (2026) · International Conference on Intelligent Computing and Signal Processing (ICSP) · doi:10.1109/icsp69961.2026.11540985
“Furthermore, Average Precision ( AP ) measures the area under the Precision-Recall curve for a specific defect [19], and mAP is the unweighted mean of the AP across all target classes.”
Cao, Q., Xia, Y., & Li, Z. (2026) · International Conference on Intelligent Computing and Signal Processing (ICSP) · doi:10.1109/icsp69961.2026.11540762 · Cited by 1
“Object detection in Very High-Resolution (VHR) remote sensing imagery is fundamental to applications such as urban planning, traffic surveillance, and disaster assessment [1,2].”
Liu, Z., Zhang, Y., Yang, Y., et al. (2026) · Research Square · doi:10.21203/rs.3.rs-9756311/v1
Machine Vision for Recognizing the Syllabograms of Linear-A Script
Mavridaki, A., Samoladas, C., Giachos, I., et al. (2026) · WSEAS Transactions on Computers archive · doi:10.37394/23205.2026.25.2
ContinualCropBank: Object-Level Replay for Semi-supervised Online Continual Object Detection
da Silva, L. T., & Batista, G. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-1462-4_37
CMNet: coordinated multi-granularity feature learning for efficient UAV small object detection
Liu, Y., & Wenzhu, Y. (2026) · Multimedia Systems · doi:10.1007/s00530-026-02399-3
“Object detection [ 1 , 2] is a core task in computer vision, aiming to accurately localize and classify targets within input images.”
Suyeni, N., & Indrabayu (2026) · International Conference on Pervasive Computing and Social Networking (ICPCSN) · doi:10.1109/icpcsn68523.2026.11543957
“Deep learning has transformed object detection in precision farming [7, 8], with prior work demonstrating its effectiveness for fruit detection in apple orchards [9, 10], coconut shell quality assessment [11], and UAV-based cacao pod counting in outdoor plantation conditions [21], while targeted…”
Improving Interoperability in Object Detection across Diverse Datasets
Jo, G. D., Jeong, K., Seo, H., et al. (2026) · ACM/SIGAPP Symposium on Applied Computing (SAC) · doi:10.1145/3748522.3779951
“Object detection is a fundamental task in the field of computer vision [24], with wide-ranging applications in areas such as au-tonomousdriving[6]andmedicalimaging[10].”
A Survey on High-Value Target Reasoning for Computer Vision
Tang, X., Zhuang, Z., Xiao, Y., Wang, Y., & Yin, G. (2026) · International Symposium on Intelligent Robotics and Systems (ISoIRS) · doi:10.1109/isoirs70157.2026.11545312
“…on autonomous driving perception predominantly focus on standalone tasks such as object detection[29], trajectory prediction[30], or risk assessment[11] yet none systematically delineate the full detection-anchored High-Value Target Reasoning (HVTR) chain from fine-grained semantic inference to…”
InfluentialAccuracy-First Improved YOLOv8 for Industrial Fastener Detection on MVTec Screws
Wu, M. (2026) · International Conference on Information Science, Electrical and Automation Engineering (ISEAE) · doi:10.1109/iseae69422.2026.11544438
“Among various detection frameworks, the YOLO (You Only Look Once) series [2], particularly YOLOv8 [3], has achieved remarkable success due to its optimal balance between real-time processing speed and detection accuracy [4], [5].”
Ning, D., & Han, D. S. (2026) · ICT Express · doi:10.1016/j.icte.2026.05.020 · Cited by 2
MDA-YOLO: A fine-grained ship detection model under complex water conditionsPreprint
Jiang, L., & Lu, D. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6913243
Sahoo, N., Kar, A., & Khemchandani, V. (2026) · Discover Oncology · doi:10.1007/s12672-026-04746-2
“DL is better suited to object detection algorithms that have demonstrated exceptional performance in real-time object detection and localisation [37–39].”
A multitask method for parking slot and obstacle detection using YOLO
Zhang, B., Zheng, D., Wang, Y., Shen, G., & Zhang, C. (2026) · Journal of Engineering Research · doi:10.1016/j.jer.2026.06.013
Fog-Adaptive-YOLO: A lightweight model for insulator defect detection
Jin, X., Zhao, Y., Shen, W., et al. (2026) · PLoS ONE · doi:10.1371/journal.pone.0351054
Huang, J., He, W., Gou, L., Ren, L., & Bryan, C. (2026) · Computer Graphics Forum · doi:10.1111/cgf.70472
Chu, Z., Liu, W. Y., Zhang, M., et al. (2026) · Next research. · doi:10.1016/j.nexres.2026.102011
SSANet: A Scale and Shape Awareness Network for Ship Detection in Remote Sensing Scenes
Cheng, C., Jin, F., & Chang, M. (2026) · Lecture notes in electrical engineering · doi:10.1007/978-981-95-8232-7_20
Gao, G., Zhou, F., Xu, L., Zhang, J., & Li, X. (2026) · Agronomy · doi:10.3390/agronomy16121156
Shan, W., Liu, N., Jiang, Y., Wu, H., Xiao, H., & Li, X. (2026) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2026.104845
Characterization of Mobile Augmented Reality Tasks Supported by Edge Computing Resources
Rodrigues, K. B. C., Cardoso, K. V., & Corrêa, S. L. (2026) · doi:10.5753/sbrc.2026.19355
“Object detection extracts high-level semantic information from visual data by identifying objects present in a scene and estimating their spatial extent, typically represented by bounding boxes and associated confidence scores [Zou et al. 2023].”
Wen, T., & Hu, Y. (2026) · International Conference on Image, Signal Processing and Pattern Recognition (ISPP) · doi:10.1109/ispp69262.2026.11543075
“With the rapid advancement of object detection algorithms—most notably the YOLO series [3]–[5]—behavior recognition in classroom environments has attracted considerable research attention [6]– [9].”
AIM-Net: Adaptive Multispectral Fusion for Pedestrian Detection
Zhao, S., & Ren, J. (2026) · International Seminar on Artificial Intelligence, Networking and Information Technology (AINIT) · doi:10.1109/ainit70033.2026.11557883
“Multispectral (RGB-T) pedestrian detection effectively overcomes the limitations of a single modality under adverse conditions by combining the texture details of visible light with the thermal radiation information of long-wave infrared (LWIR) [6].”
CPM-DETR: A Lightweight Multi-Scale Object Detector for Autonomous Driving
Mu, F., Yang, G., & Zou, L. (2026) · International Seminar on Artificial Intelligence, Networking and Information Technology (AINIT) · doi:10.1109/ainit70033.2026.11558088
“Object detection is a fundamental task in autonomous driving and traffic-scene understanding, since the accurate perception of vehicles and pedestrians directly affects subsequent decision-making and safety monitoring [1].”
SmartVision Path: An Edge-Intelligence-Driven Vision Assistance System for the Visually Impaired
Wei, W., Zhao, J., Zhang, W., Hua, Y., & Ji, C. (2026) · International Conference on Image, Signal Processing and Pattern Recognition (ISPP) · doi:10.1109/ispp69262.2026.11542997
“Meanwhile, lightweight object detectors represented by the YOLO series have shown strong real-time performance [5]-[7], while multi-object tracking methods provide temporal continuity in dynamic scenes.”
Van, T. T., Hasegawa, H., & Bui, N.-T. (2026) · Journal of Real-Time Image Processing · doi:10.1007/s11554-026-01908-x
“As a leading solution for real-time detection, YOLO has evolved substantially [28–30], with recent releases—namely YOLOv11 (September 2024), YOLOv12 (February 2025), and YOLOv13 (June 2025)—establishing new state-of-the-art (SOTA) benchmarks on the COCO dataset.”
SHWDPPNet: Safety Helmet Wearing Detection in Power Production Environments Based on YOLOv8
Huang, L., Zeng, C., Wang, L. W., et al. (2026) · Lecture notes in electrical engineering · doi:10.1007/978-981-95-5304-4_7
VMCM: Vision-Aided Multi-Modal Channel Measurement and Modeling in Terahertz Urban Macrocell
Li, Y., Yu, Z., & Han, C. Z. (2026) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2026.3701744
“Vision sensing data offers new dimensions that are missing in RF data to capture the characteristics in realistic environments, such as object positions, material types, environment shapes, human movements, etc [40], [41], [42].”
An Improved YOLOv11-Based Approach for Hard Hat Detection in Construction Environments
He, D., Duan, Y.-N., Zhu, N., et al. (2026) · International Conference on Image, Signal Processing and Pattern Recognition (ISPP) · doi:10.1109/ispp69262.2026.11543063
“Current deep learning–based object detection algorithms can be broadly categorized into two groups: two-stage detectors and one-stage detectors [3].”
Real-Time Object Detection of Visible-Infrared Feature Fusion for UAV Platform
Li, Y., Liu, K., Zheng, C., et al. (2026) · Lecture notes in electrical engineering · doi:10.1007/978-981-95-7660-9_58
Detail-Semantic Fusion and Information Loss Suppression for Small Object Detection in UAV ImagesPreprint
Liu, X., Zhu, J., Huang, L., et al. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6964219
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.