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 3,101–3,143 of 3,143
A metamorphic testing technique for object detection networks
Wang, Z., Ma, S., Guo, J., et al. (2026) · Information and Software Technology · doi:10.1016/j.infsof.2026.108330
DECA-YOLO: Dual-pooling efficient channel attention for real-time pedestrian detection
S, S. B. V., & Raman, R. (2026) · Multimedia Tools and Applications · doi:10.1007/s11042-026-21903-5
“Object detection [1] is a crucial task in computer vision that focuses on identifying and localizing instances of objects within an image.”
Remote Sensing Techniques and Applications for Port Management: A Review
Yuan, Q., Yan, Q., Mei, Q., et al. (2026) · Lecture notes in electrical engineering · doi:10.1007/978-981-92-3574-2_13
Yang, F., Wang, J., Cui, W., et al. (2026) · Sensors · doi:10.3390/s26185854
MSN-TE: a network for multi-scale object detection in turbid environments
Xu, H., & Zhang, W. (2026) · Ships and Offshore Structures · doi:10.1080/17445302.2026.2731429
Deng, X., Yuan, H., & Liang, S. (2026) · Measurement Science and Technology · doi:10.1088/1361-6501/ae9ab8
A Real-Time High Sensitivity Signals Detection Method for ELF Wireless Communication
Du, Y., Dou, Z., & Jiang, H. (2026) · IEEE/CIC International Conference on Communications in China (ICCC) · doi:10.1109/iccc70295.2026.11680110
“From the computer vision perspective, Zou et al. summarized that object detection has matured into an end-to-end paradigm for simultaneous localization and recognition of structured targets [10].”
Wang, H., Mu, C., Liu, Y., & Abbasi, A. N. (2026) · Measurement · doi:10.1016/j.measurement.2026.123220
Guo, R., & He, Y. (2026) · Journal of Imaging · doi:10.3390/jimaging12090449
“Zou et al. [20] systematically reviewed the development of object detection from handcrafted features and convolutional neural networks to Transformer-based detectors, and pointed out that small objects, occlusion, long-tailed categories, and complex backgrounds remain major factors limiting…”
UAV Object Detection with High-Frequency Augmentation and Adaptive Multi-Scale Fusion
Zhu, G., Chen, H., Chen, Y., et al. (2026) · International Conference on Image, Vision and Computing (ICIVC) · doi:10.1109/icivc70586.2026.11686620
“To cope with complex and volatile aerial environments, deep learning-based object detection algorithms have comprehensively replaced traditional hand-crafted feature operators due to their powerful feature modeling capabilities, becoming the mainstream solution in this domain [3].”
Xu, G., & Dong, Y. (2026) · Sensors · doi:10.3390/s26185877
Gu, Q., Yang, M., Chen, Y., Zhang, Y., Zhang, J., & Jiang, L. (2026) · International Conference on Electronic Packaging Technology (ICEPT) · doi:10.1109/icept71373.2026.11690178
“Powered by deep learning [2], smart manufacturing increasingly adopts diverse object detection paradigms [1].”
Chen, H., Huang, K., Hu, H., et al. (2026) · doi:10.1145/3829441.3829489
Lee, D., Kim, J.-S., Moon, H. J., & Chae, Y. T. (2026) · Building and Environment · doi:10.1016/j.buildenv.2026.115274 · Cited by 1
Unified Cross-Model Credibility Modeling for Heterogeneous Object Detector FusionPreprint
Xiong, A., Li, Y., Feng, Y., Tao, X., & Yong, J. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7506857
CASR: Correlation-Aware Support Resampling for Few-Shot Learning with Prototypical Networks
Yıldız, U., Yazıcıoğlu, İ. K., Küçük, K., & Akbulut, O. (2026) · Applied Sciences · doi:10.3390/app16199456
Sampling-Free Universal Domain Adaptive Object Detection with Synergistic Optimization Alignment
Zheng, Y., Wu, J., Li, W., et al. (2026) · International Journal of Computer Vision · doi:10.1007/s11263-026-03047-z
Jang, H.-S., Cha, Y., & Choi, S. (2026) · Mathematics · doi:10.3390/math14193455
Tefera, M. A., Xiao, J.-J., Lin, P. T., et al. (2026) · Optics & Laser Technology · doi:10.1016/j.optlastec.2026.116449
Adversarial Patch and Camouflage Attacks on Aerial Object Detection: A Geometry-Aware Review
Shrestha, S., Mahima, K. T. Y., & Perera, A. G. (2026) · Sensors · doi:10.3390/s26196057
Ding, X., Jiao, N., Chi, Y., Jiang, R., Xie, Z., Wang, K., Cao, H. V., Shang, C., & Wang, Z. (2026) · Displays · doi:10.1016/j.displa.2026.103708
Liu, J., Yao, R., Yang, Q., Liu, R., Hu, J., Lyu, J., Wang, Z., Zhang, Z., Feng, M., & Wei, F. (2026) · Plants · doi:10.3390/plants15192927
Jian, G., Zhang, S., Chongnian, Q., Li, H., & Wang, Y. (2026) · Signal Image and Video Processing · doi:10.1007/s11760-026-05736-1
“Model-oriented approaches reduce per-stream computational cost through quantization, pruning, knowledge distillation, and lightweight architecture design [5–10].”
Kim, Y., Kim, C., Yun, C., & Joo, G. (2026) · Ecological Solutions and Evidence · doi:10.1002/2688-8319.70322
Jiang, C., Song, Q., Liu, W., Dapeng, T., Liu, B., & Wang, Y. (2026) · International Journal of Remote Sensing · doi:10.1080/01431161.2026.2735048
Wei, P., Jia, C., Liu, Y., Zhu, X., Li, L., Wu, Z., & Yu, Q. (2026) · Electronics · doi:10.3390/electronics15194479
COF-YOLO: A Contour-Oriented Framework for Rocket Detection Under Visual Degradation Conditions
Liu, B., Li, X., Cao, R., Zhang, Z., Guo, K., & Yue, C. (2026) · IEEE Access · doi:10.1109/access.2026.3737519
“The dilation ratios for P3, P4, and P5 are set to [1, 2, 3], [1, 3, 5], and [2, 4, 6], respectively.”
Hybrid clustering framework for large-scale scientific literature structuring
Teplov, D., Radzivil, A., & Bugajev, A. (2026) · New Trends in Computer Sciences · doi:10.3846/ntcs.2026.26284
“Zou et al. (2023) split the field into traditional feature-based detectors, region-based deep detectors (R-CNN family), single-shot deep detectors (SSD and YOLO families), transformer-based detectors, detection datasets and evaluation metrics, and speedup and efficiency techniques; our Cluster 0…”
Zhang, M.-H., Yang, L.-X., Song, W., et al. (2026) · Expert systems with applications · doi:10.1016/j.eswa.2026.134590
A Retinex-based iterative network with adversarial discrimination for low-light image enhancement
Shen, L., Xuanqi, W., Ni, W., et al. (2026) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2026.104982
MAREA: Active Learning for Object Detection Using Nested Local Embeddings
Sokolov, V. A., Teplyakov, L., & Matveev, I. A. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-39382-1_12
Zhang, Z., Du, L., Zhang, X., Jiang, S., & Ma, J. (2026) · International Conference on Advanced Algorithms and Neural Networks (AANN) · doi:10.1109/aann71145.2026.11709354
“With the advancement of deep learning, object detection technology has undergone a paradigm shift from traditional handcrafted feature methods to deep convolutional neural networks and subsequently to Transformer architectures, with continuous improvements in both detection accuracy and speed [1].”
Distilling adaptive scale knowledge for remote sensing object detection
Kim, S., Yoon, D., & Sung, Y.-H. (2026) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2026.09.033
An Improved Mask R-CNN and Concentric Double-Circle Fitting-Based Method for Coil Length Measurement
Du, Y., & Liu, X. (2026) · International Conference on Advanced Algorithms and Neural Networks (AANN) · doi:10.1109/aann71145.2026.11709301
“Recent object-detection reviews emphasize multiscale representation, localization quality, and task-specific adaptation [10] .”
An IoT-Edge Smart Glass Prototype for Object Identification Assistance Using YOLO26
Ravi, V., Ganesalingam, V., Сысоев, А., et al. (2026) · doi:10.1109/iceece71300.2026.11710100
“YOLO-based detectors are widely used for real-time object detection because they perform single-stage object localization and classification [7], [8].”
A cross-guided and dynamic adaptive convolutional network for ancient city wall defect detection
Zhao, S., Chen, Z., Zhang, Y., et al. (2026) · Image and Vision Computing · doi:10.1016/j.imavis.2026.106223
Juarto, B., & Widianto, M. H. (2026) · International Conference on ICT for Smart Society (ICISS) · doi:10.1109/iciss71466.2026.11715060
“Deep-learning object detection has advanced rapidly, with surveys documenting large gains in accuracy and robustness, two decades of architectural progress, and the efficiency, complexity, and generalization trade-offs that matter for deployment on portable hardware [11], [12].”
Gunawan, E. (2026) · International Conference on ICT for Smart Society (ICISS) · doi:10.1109/iciss71466.2026.11715547
HMA-YOLO: Hypergraph-guided multi-scale feature interaction for remote sensing object detection
Zhang, Z., Qian, Y., & Bie, Q. (2026) · Digital Signal Processing · doi:10.1016/j.dsp.2026.106549
Data-Augmented Visual Positioning Method for Train Static Weighing
Zuo, L., Chen, Z., Chen, J., et al. (2026) · Asian Control Conference (ASCC) · doi:10.1109/ascc70886.2026.11702272
“To address the complex lighting issues in the aforementioned few cases, this paper employs the CLAHE (Contrast Limited Adaptive Histogram Equalization) [9] algorithm as the pre-processing module before target detection.”
Reverse Procedure for Lost Track Recovery in Multi-Object Tracking
Hiek, L., Valy, D., & Nou, S. (2026) · Journal of Intelligent Media Computing · doi:10.47836/jimc.1.1.09
Modification of the YOLOv8 Detection Head for Nested Object Embeddings
Matveev, I. A., & Sokolov, V. A. (2026) · Journal of Computer and Systems Sciences International · doi:10.1134/s1064230726700437
“At present, applied computer vision problems are usually most successfully solved using deep neural networks [1]; in this case, the problem of detection (localization and classification) of objects is one of the most common in practice [2].”
Gupta, A., & Engineer, P. (2026) · International Symposium on VLSI Design and Test (VDAT) · doi:10.1109/vdat72243.2026.11704573
“Object detection has improved a lot in recent years [14], but most systems only answer: what objects are present?”
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.