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 1,801–1,900 of 3,144
Zhu, Y., Zhu, W., & Wang, L. (2025) · International Conference on Artificial Intelligence, Automation and High Performance Computing (AIAHPC) · doi:10.1109/aiahpc66801.2025.11290184 · Cited by 1
“YOLOv2–v3 enhanced multiscale prediction, YOLOv4–v5 introduced CSPNet and augmentation, YOLOv6–v8 improved lightweight design and small-object detection, while YOLOv9– v11 further optimized representation learning, efficiency, and robustness [13][14] .”
An energy-efficient data-reused on-the-fly Im2col for OS-dataflow systolic array-based accelerator
Wu, J., Fan, J., Wang, X., Chen, J., & Li, W. (2025) · Microelectronics Journal · doi:10.1016/j.mejo.2025.106831 · Cited by 1
Research on automatic adjustment system for curved reflector of ultra-short-focus lenses
Ma, X., Wang, S., Yu, P., et al. (2025) · Measurement · doi:10.1016/j.measurement.2025.118823 · Cited by 1
Multi-scale feature enhancement for pedestrian detection in complex events: the elephant in the room
Wen, Y., Xu, P., & Li, Z. (2025) · Soft Computing · doi:10.1007/s00500-025-10941-0 · Cited by 1
Unsupervised adaptive learning method for salient object detection under weak observation conditions
Tong, Y., Luo, X., Ma, L., et al. (2025) · Applied Intelligence · doi:10.1007/s10489-025-07005-z · Cited by 1
“As one of the important computer vision tasks, object detection has always been valued by people [10, 38, 44, 62], but there are relatively few algorithms for object detection under weak observation conditions.”
Hardware Trojan Object Detection Based on Bidirectional Graph Neural Networks
Cheng, D., Lin, X., Dong, C., et al. (2025) · IEEE Transactions on Computers · doi:10.1109/tc.2025.3642575 · Cited by 1
“Inspired by object detection in the field of computer vision [33], this paper develops a method for HTOD based on bidirectional jumping knowledge network (Bi-JKNet), named HTOD-BGNN, which covers the entire process from modeling to HT localization and behavior recognition.”
Zhang, N., Zhao, H., Jing, P., Gao, Y. F., Liu, S., Shen, J., Huang, S., Zeng, Q., Liu, Y., & Huang, M. (2025) · Processes · doi:10.3390/pr14010028 · Cited by 1
Egi, Y., Oter, T., Hajyzadeh, M., & Çatak, M. (2025) · Plants · doi:10.3390/plants15010047 · Cited by 1
“For this reason, anchor-free segmentation frameworks show the most promise for biological imaging [11].”
Multispectral Object Detection via Edge-Enhanced and Frequency-Aware Fusion Network
Peng, S., Xue, R., Tong, Y., Wang, Z., & Yang, H. (2025) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2025.3648007 · Cited by 6
Abdulaziz, S., & Bondarev, E. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-07343-3_14 · Cited by 1
RTLUD-DETR: A High-precision and Lightweight DETR for UAV Detection
Feng, Z., Liu, J., & Wu, Y. (2025) · 2022 IEEE 20th International Conference on Industrial Informatics (INDIN) · doi:10.1109/indin64977.2025.11279509 · Cited by 1
“Breakthroughs in deep learning have provided innovative solutions to the challenges outlined above [5].”
ESS-DETR: A Lightweight and High-Accuracy UAV-Deployable Model for Surface Defect Detection
Wang, Y., Yao, Y., Zheng, H., & Han, Y. (2026) · Drones · doi:10.3390/drones10010043 · Cited by 3
Guo, H., & Liu, S. (2026) · Image and Vision Computing · doi:10.1016/j.imavis.2026.105897 · Cited by 2
Multi-scale object detection with feature enhancement for traffic scenes
Chuai, Q., Zhu, T., Wang, X., Wang, Z., & Fu, X. (2026) · International Journal of Multimedia Information Retrieval · doi:10.1007/s13735-025-00396-2 · Cited by 1
“One of the vital branches in automatic driving systems is vision recognition, including object detection [1], object tracking[2],imagesegmentation[3],andsoon.”
MGLoc: A Wi-Fi Indoor Localization Method Based on Multi-Task Learning and Geographical Correlation
Ma, C., Liang, W. G., Zheng, M., et al. (2026) · IEEE Transactions on Consumer Electronics · doi:10.1109/tce.2026.3652034 · Cited by 1
“This labeling method is efficient for traditional deep learning applications (e.g., sentiment analysis [43], object detection [44] and semantic segmentation [45]).”
Federated Learning with Large Language Models
Wu, X., Zhang, C., & Lin, W. (2025) · IEEE Intl Conf on Dependable, Autonomic and Secure Computing, Intl Conf on Pervasive Intelligence and Computing, Intl Conf on Cloud and Big Data Computing, Intl Conf on Cyber Science and Technology Congress (DASC/PiCom/CBDCom/CyberSciTech) · doi:10.1109/cyberscitech68397.2025.00129 · Cited by 1
“Because of superior performance in tasks like image classification [4], object detection [5], optical character recognition [6], etc., deep learning has been widely applied to various domains, such as medical diagnosis [7], autonomous driving [8], and text generation [9].”
Zhang, M., Wu, Z., Li, H., Li, J., Pang, L., & Qian, C. (2025) · IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom) · doi:10.1109/trustcom66490.2025.00171 · Cited by 1
“Deep neural networks have made remarkable achievements in computer vision, approaching or surpassing human performance across various tasks such as image classification [1], object detection [2], and semantic segmentation [3].”
Lightweight target detection based on improved YOLOv5n for unmanned aerial vehicle infrared imagery
Xue, W., Zhang, X., Yan, J., Chen, D., & Wang, Y. (2026) · Engineering Research Express · doi:10.1088/2631-8695/ae408c · Cited by 1
Baydilli, Y. Y. (2026) · The Journal of Supercomputing · doi:10.1007/s11227-026-08244-8 · Cited by 1
The enhanced EME-YOLOv11 for real-time polarizer defect detection
Liu, R., Jing, C., Zhang, T., & Zhang, J. (2026) · Scientific Reports · doi:10.1038/s41598-026-37884-2 · Cited by 1
“…deep learning detection algorithms fall into two categories: two-stage detection algorithms, which first generate candidate regions and then perform classification, and one-stage detection algorithms, which simultaneously predict category and location of the target through regression 18 .”
Noise-Robust Object Detection for Forward-Looking Sonar Imagery
Wang, Z., Guo, Q., & Luo, J. (2026) · IEEE Sensors Journal · doi:10.1109/jsen.2026.3661175 · Cited by 2
“In recent years, with advancements in computer vision [4], [5], [6], [7] and robotics technology [8], [9], [10], autonomous underwater vehicles (AUVs) equipped with object detection capabilities have Zichen Wang and Jianbin Luo are with the Department of Mechanical Engineering, Tsinghua University,…”
Tiny object detection: An in-depth survey of techniques, challenges, and future directions
Nautiyal, R., & Deshmukh, M. (2026) · Digital Signal Processing · doi:10.1016/j.dsp.2026.105995 · Cited by 4
Stream-DINO: exploring DETR-based online object detection with streaming perception
Zhang, M., Zhang, Y., Tian, R., Zhang, Y., Zhang, Z., & Sun, J. (2026) · Applied Intelligence · doi:10.1007/s10489-026-07139-8 · Cited by 1
“…toward practical applications, more researchers are emphasizing the importance of robustness, real-time performance, and stability in these models [47], while those post-processing operations have a significant impact on the robustness [48] and real-time performance of object detection models.”
AEWD: A weakly observable object detection benchmark for UAV-based endangered wildlife monitoring
Ma, M., Liu, L., Han, B., Yang, L., Gao, X., Chang, R., Wang, S., & Xu, F. X. F. (2026) · Ecological Informatics · doi:10.1016/j.ecoinf.2026.103662 · Cited by 1
See Hidden Insight From Transposition: Multiaxis Feature Aggregation for Aerial Object Detection
Zheng, S., Xu, Y., Zheng, P., Wei, Z., & Wu, Z. (2026) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2026.3665585 · Cited by 3
“D IFFERENT from object detection in natural images [1], [2], [3], aerial object detection is much more challenging due to the extremely small resolution and arbitrary orientations of instances.”
YOLO-RECAP: reassembly with channel attention for perception
Kim, H.-J., Park, S.-W., Sim, C.-B., et al. (2026) · Journal of King Saud University - Computer and Information Sciences · doi:10.1007/s44443-026-00525-9 · Cited by 1
“Various architectures have been proposed depending on the implementation approach (Girshick 2015; Lin et al. 2017a; Zhao et al. 2023; Zou et al. 2023).”
Enhancing object detection in complex lighting conditions via illumination-guided feature fusion
Xu, L., Zhu, L., Hu, J., & Guo, B. (2026) · Cluster Computing · doi:10.1007/s10586-026-05976-3 · Cited by 1
S, S. B. V., & Raman, R. (2026) · Image and Vision Computing · doi:10.1016/j.imavis.2026.105942 · Cited by 1
Mai, A.-T., Nicolas, M. M., Ladret, P., & Caplier, A. (2025) · IEEE International Conference on Visual Communications and Image Processing (VCIP) · doi:10.1109/vcip67698.2025.11396834 · Cited by 2
“While existing methods address some issues, they often fail to handle multiple challenges or provide the transparency needed to build trust in high-stakes decisions [2].”
Wang, K. J., & Tang, Y.-C. (2026) · Journal of Intelligent Manufacturing · doi:10.1007/s10845-026-02807-5 · Cited by 1
Ko, J., Kim, Y.-W., & Byun, Y.-C. (2026) · PeerJ Computer Science · doi:10.7717/peerj-cs.3665 · Cited by 1
Application Design of a Wide-Angle and Zoom Collaborative Visual Perception Device
刘, 德. (2026) · Instrumentation and Equipments · doi:10.12677/iae.2026.141004 · Cited by 1
KD-DETR: multi-scale lightweight DETR based on knowledge distillation for road crack detection
Cheng, J., Li, Y., Zhong, L., & Li, D. (2026) · Nondestructive Testing And Evaluation · doi:10.1080/10589759.2026.2637845 · Cited by 1
MCS-YOLO: A novel remote sensing image segmentation algorithm for mountain crops
Chen, K., Li, Y., Quan, H., Liu, J., & Xiao, W. (2026) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2026.111592 · Cited by 1
Self-citationLiu, P., Wu, Y., & Song, Y. (2025) · International Conference on Virtual Reality and Visualization · doi:10.1109/icvrv67992.2025.00097 · Cited by 1
“Deep learning has achieved remarkable success in various computer vision and language tasks, such as image classification [1], object detection [2], image segmentation [3], and vision-language understanding [4].”
Black-box physical adversarial stripes for hiding from infrared detectors at multiple views
Zheng, Z., Liu, G., Dang, M., & Luo, J. (2026) · Neural Networks · doi:10.1016/j.neunet.2026.108821 · Cited by 2
Liang, X., Xu, P., Cao, F., & Kong, Q. (2026) · International Journal of Machine Learning and Cybernetics · doi:10.1007/s13042-026-03028-1 · Cited by 1
Container Damage Detection Based on SelfContrastive Learning and Deep Convolutional Neural Networks
Zhang, L. (2025) · International Conference on Electronic Communication, Computer Science and Technology (ECCST) · doi:10.1109/eccst68196.2025.11441171 · Cited by 2
“…effectively solve the gradient disappearance problem of deep networks through residual connections, and have excellent performance in image classification tasks [10] ; YOLO series models achieve efficient unification of object localization and classification based on the end-to-end detection idea.”
Scalable One-Pixel Attacks on Deep Neural Networks for High-Resolution Images
Nam, W., Moon, H., Kim, K., & Kil, H. (2026) · Mathematics · doi:10.3390/math14071095 · Cited by 1
Li, H., Tao, H., Qiu, J., et al. (2026) · Engineering Research Express · doi:10.1088/2631-8695/ae590f · Cited by 1
MBS-YOLOv11: a lightweight network for real-time detection of tea plant diseases
Yang, S., Huang, D., Liu, D., & Zhu, L. (2026) · Journal of Real-Time Image Processing · doi:10.1007/s11554-026-01867-3 · Cited by 2
“To ensure an accurate assessment, we use the precision (P), recall (R)[26], and mean average precision (mAP)[27] as these metrics to evaluate the model: In the formula, TP and FP denote true positive samples and false positive samples; FN denotes false negative samples; M denotes total number of…”
RT-FCOSH: bridging accuracy and efficiency in low-resolution object detection for autonomous driving
Mboutayeb, S., Majda, A., & Zenkouar, K. (2026) · Multimedia Tools and Applications · doi:10.1007/s11042-026-21520-2 · Cited by 1
Multi-Task Unified Domain Incremental Learning With Domain Difference Adapters
Song, X. R., He, Y., Peng, L., & Gong, Y. (2026) · IEEE Transactions on Image Processing · doi:10.1109/tip.2026.3678033 · Cited by 1
“A RTIFICIAL intelligence technology has brought substantial improvements in various visual tasks, including object detection [1], instance segmentation [2], and image classification [3], etc .”
A wavelet-fusion attention prior network for low-light image enhancement
Li, Y., Wang, R., Yan, H., Luo, H., & Yin, J. (2026) · Digital Signal Processing · doi:10.1016/j.dsp.2026.106132 · Cited by 2
Shen, Z., Lv, Y., Yuan, R. B., et al. (2026) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2026.3687972 · Cited by 1
“Early research by Zou et al. [28] identified SWR damage by extracting smoothness and entropy values and comparing them with classification thresholds.”
LiteUAV-Det: A lightweight network for robust small-object detection in complex aerial scenes
Jobaer, S., Muzahid, A. A. M., Hussain, M. A. I., Ahmed, F., Bai, X., Han, H., & Sohel, F. A. (2026) · Neurocomputing · doi:10.1016/j.neucom.2026.133782 · Cited by 3
Acknowledging Focus Ambiguity in Visual Questions
Chen, C., Tseng, Y., Li, Z., Venkatesh, A., & Gurari, D. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.00122 · Cited by 16
“More generally, this work contributes to existing literature on locating linguistic expressions in an image, which is already explored for tasks like object detection [56], instance segmentation [18, 23], referring expression comprehension [8, 41], and described object detection [44, 52].”
Lei, Z., Dong, Z., Xu, H., Xiao, X., & Xin’an, Q. I. U. (2026) · Sensors · doi:10.3390/s26092844 · Cited by 1
Gradient-Reweighted Adversarial Camouflage for Physical Object Detection Evasion
Liang, J.-J., Liang, S., Lou, T., Zhang, M., Wenjin, L., Fan, D., & Cao, X. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01288 · Cited by 5
“Object Detection: Object detection is a core task in computer vision and has evolved through multiple methodologies [49].”
Delving Into the Devils of Knowledge Distillation for Object Detection: A Survey
Shi, Q., Zhang, G., Liu, Y., Liu, Y., Zhang, W., Ze, T., & Hou, Y. (2026) · IET Computer Vision · doi:10.1049/cvi2.70067 · Cited by 1
YOLOv12-VSD: A Transfer-Learning-Assisted Real-Time Detection Algorithm for Vehicle Surface Defects
Liu, H., Zhao, D., & Li, Y. (2026) · Sensors · doi:10.3390/s26092905 · Cited by 1
“Two-stage detectors such as Faster R-CNN achieve high accuracy through region pro-Sensors posal and refinement [4], and recent variants have introduced deformable convolutions [5] and multi-scale attention [6] to improve boundary regression for irregular defect shapes.”
Zhang, X., Jiang, H., Han, D., Guo, H., Zhang, X., & Sun, K. (2026) · Machines · doi:10.3390/machines14050527 · Cited by 1
Zhang, S., Tang, R., Mu, J., et al. (2026) · Frontiers in Medicine · doi:10.3389/fmed.2026.1850116 · Cited by 1
“Object detection is one of the core tasks in computer vision, aiming to locate and identify objects of interest in images (10).”
MD-YOLO: A Multi-Scale Adaptive and Dual-Attention Enhanced YOLOv11 for Small Object Detection
Zhou, W., & Gong, G. (2026) · Electronics · doi:10.3390/electronics15102099 · Cited by 1
Qian, W., Coutinho, R. W. L., & Boukerche, A. (2026) · Computer Networks · doi:10.1016/j.comnet.2026.112380 · Cited by 1
Alsaidalani, B. A., & Yafooz, W. M. S. (2026) · International Conference on Smart Electronic Devices and Intelligent Systems (ICSEDIS) · doi:10.1109/icsedis68157.2026.11517991 · Cited by 1
Meng, L. Y., Wu, M., Gao, J., et al. (2026) · Remote Sensing · doi:10.3390/rs18101663 · Cited by 1
Yuan, X., Liu, W., Ma, Y., Wang, Y., & Liu, B. (2026) · PLoS ONE · doi:10.1371/journal.pone.0341210 · Cited by 1
“The performance of the fastener detection model was evaluated using standard object detection metrics including recall, precision, and mean Average Precision (mAP) [35], while the performance of the PointNet++ network was evaluated using the Intersection over Union (IoU) metric [36].”
EAGLE-DET: Edge-Aware Global–Local Enhancement for Small Object Detection in UAV Aerial Imagery
Tao, Y., Ding, Y., Mo, B., Zhang, B., Zhao, C., & Li, D. (2026) · Sensors · doi:10.3390/s26113554 · Cited by 2
“Unmanned aerial vehicle (UAV)-based object detection has emerged as crucial technology with diverse applications, including traffic monitoring, disaster rescue, and urban surveillance [1].”
Zhang, X., Kang, W., Peng, Y., et al. (2026) · Drones · doi:10.3390/drones10060447 · Cited by 1
Khujamatov, H., Abdullayevich, S. R., Jumanov, I., et al. (2026) · Mathematics · doi:10.3390/math14132345 · Cited by 1
FAN: A Frequency-Adaptive network for tiny object detection in complex backgrounds
Lv, Y., Jin, C., Liu, S., 文, 冬., & Song, X. (2026) · Image and Vision Computing · doi:10.1016/j.imavis.2026.106100 · Cited by 1
You only look at manga faces: a YOLOv12-based approach on manga datasets and benchmark
Fargetta, G., Fiorito, E. R., Licciardello, R., et al. (2026) · PeerJ Computer Science · doi:10.7717/peerj-cs.3787 · Cited by 1
Saffron harvestability detection with deep neural networks for just-in-time harvesting
Noh, C. T., Jones, N., & Cook, D. D. (2026) · Biosystems Engineering · doi:10.1016/j.biosystemseng.2026.104546 · Cited by 3
Zhang, A., Cao, H., Shan, N., Wang, J., Pu, M., & Song, Y. (2025) · Intelligent Opto-Electronics · doi:10.67704/ioe.2025.250007 · Cited by 7
Hussain, S., Mumtaz, I., Ahmad, U., Li, L., Jia, Z., Lv, M., Zhao, X., Ma, H., & Wang, C. (2026) · Remote Sensing · doi:10.3390/rs18162715 · Cited by 1
Research on Neural Networks Integration for Object Classification in Video Analysis Systems
Fomin, I., Burin, V., & Bakhshiev, A. V. (2020) · International Conference on Industrial Engineering, Applications and Manufacturing (ICIEAM) · doi:10.1109/icieam48468.2020.9112011 · Cited by 1
MOHE-NET: MONOCULAR OBJECT HEIGHT ESTIMATION NETWORK USING DEEP LEARNING AND SCENE GEOMETRY
Wei, J., Jiang, J., & Yılmaz, A. (2021) · The international archives of the photogrammetry, remote sensing and spatial information sciences/International archives of the photogrammetry, remote sensing and spatial information sciences · doi:10.5194/isprs-archives-xliii-b2-2021-557-2021 · Cited by 1
de Witte, B., Bouarfa, S., & Geradts, Z. (2022) · International Conference on Image Processing and Machine Vision (IPMV) · doi:10.1145/3529446.3529457 · Cited by 1
“This is particularly beneficial for areas such as image classification [19, 28] and object detection [38, 46] where Deep Learning (DL) plays a central role.”
Liu, Z., Chen, G., Wu, Y., Du, J., Conradt, J., & Knoll, A. (2022) · Journal of Advanced Transportation · doi:10.1155/2022/2673191 · Cited by 2
“A lot of work has been done in the fi eld of vehicle detection [57], and di ff erent studies in object detection clas-si fi cation [58] have also attempted to automatically detect and classify di ff erent classes of vehicles.”
2D Image Object Detection Aided by Generative Adversarial Networks: A Literature Review
Bertolini, C. V., & Monteiro, R. L. S. (2022) · Journal of Bioengineering, Technologies and Health · doi:10.34178/jbth.v5i3.228 · Cited by 1
“However, Deep Learning techniques, and the ones based on Convolutional Neural Networks (CNN), represented a big leap in accuracy and are the most used today [1].”
MethodDetecting Microatolls from Drone Images
Zhou, Z., Wang, L., & Hamylton, S. M. (2022) · International Conference on Digital Image Computing: Techniques and Applications (DICTA) · doi:10.1109/dicta56598.2022.10034596 · Cited by 1
“It maps an image to a set of bounding boxes indicating the location and category of objects of interest [1].”
BackgroundReal-Time Objects Detection, Tracking, and Counting Using Image Processing Techniques
Al-Hayani, M. H. A. (2023) · Al-Nahrain Journal for Engineering Sciences · doi:10.29194/njes.26010024 · Cited by 1
Mohanty, A., Balasundaram, A., & Shaik, A. (2022) · International Conference on Smart Technologies in Computing, Electrical and Electronics (ICSTCEE) · doi:10.1109/icstcee56972.2022.10100084 · Cited by 2
“Focal loss was introduced to emphasize hard, misclassified samples during training and helped one-stage detectors in achieving accurate detection results at a faster rate [4].”
BackgroundInfluentialUAV-YOLOX: An Accurate Object Detection Method for UAV Images
Wang, Q., Wang, F., Zhang, W., et al. (2023) · International Conference on Computer and Communication Systems (ICCCS) · doi:10.1109/icccs57501.2023.10150775 · Cited by 1
“Commonly, the accuracy of the two-stage object detection method is slightly higher than that of the one-stage object detection method, but the reasoning time is slightly lower than that of the one-stage detection algorithm [26].”
BackgroundResearch on Dynamic Image Segmentation Method Based on Detection Federated Learning Algorithm
Wang, B., Hua, Q., Zhang, S., et al. (2023) · IEEE International Conference on Electronic Technology, Communication and Information (ICETCI) · doi:10.1109/icetci57876.2023.10176831 · Cited by 1
Boosting Aerial Object Detection Performance via Virtual Reality Data and Multi-Object Training
Koutsoubis, N., Naddeo, K., Williams, G., Lecakes, G. D., Ditzler, G., Bouaynaya, N. C., & Kiel, T. (2023) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn54540.2023.10191223 · Cited by 1
“Modern object detection methods typically are categorized as: single-stage, or two-stage detectors [1].”
MethodBi, C., & He, S. (2023) · IEEE International Conference on Electronics Information and Emergency Communication · doi:10.1109/iceiec58029.2023.10199610 · Cited by 1
Accelerating sparse convolutional neural networks with systolic arrays on FPGA
Nehete, H., Verma, G., Yadav, S. S., et al. (2023) · SPIE Applications of Machine Learning · doi:10.1117/12.2676783 · Cited by 1
“They have evolved into the core of many applications, from classification 1 , object detection 2 and segmentation 3 to medical image analysis 4 and autonomous vehicles 5 .”
BackgroundAdvanced System for Enhancing Location Identification through Human Pose and Object Detection
Kevin, M. A., Crespo, J., Gómez, J., & Álfaro, C. (2023) · Machines · doi:10.3390/machines11080843 · Cited by 1
“Computer vision and machine learning have proven to be useful tools for understanding how the objects can be used to improve navigation systems [4,5], but there are still limitations in their ability to understand the complexity of human movement and interaction with objects.”
BackgroundA Deep Learning Ensemble for Ultrasonic Weld Quality Control
Moreno, R. A., Sanjuán, J. M., Cristóbal, M. D. R., Muthuselvam, R. S., & Wang, T. (2023) · Lecture notes in networks and systems · doi:10.1007/978-3-031-42536-3_14 · Cited by 1
Workload‐Aware Performance Tuning for Multimodel Databases Based on Deep Reinforcement Learning
Sun, J. C., Ye, F., Nedjah, N., Zhang, M., & Xu, D. Y. (2023) · International Journal of Intelligent Systems · doi:10.1155/2023/8835111 · Cited by 2
Enabling High-Resolution Pose Estimation in Real Time Using Active Perception
Manousis, T., Passalis, N., & Tefas, A. (2023) · Proceedings - International Conference on Image Processing · doi:10.1109/icip49359.2023.10223083 · Cited by 1
“The obtained results also highlight the potential of active perception approaches in HR analysis paving way for enabling HR analysis for other tasks, e.g. object detection [17], crowd counting [18], and others.”
Adversarial Example Generation Method Based on Probability Histogram Equalization
Fang, Y., Jia, J., Yang, Y., & Lyu, W. (2023) · Chinese Control Conference (CCC) · doi:10.23919/ccc58697.2023.10240834 · Cited by 4
Thai culture image classification with transfer learning
Rattaphun, M., & Songsri-in, K. (2023) · International Journal of Power Electronics and Drive Systems/International Journal of Electrical and Computer Engineering · doi:10.11591/ijece.v13i6.pp6259-6267 · Cited by 2
Comparative Study of Natural Replay and Experience Replay in Online Object Detection
Wagner, B., Pellerin, D., & Huet, S. (2023) · IEEE/CVF International Conference on Computer Vision Workshops (ICCVW) · doi:10.1109/iccvw60793.2023.00386 · Cited by 1
“Continual Object Detection Object detection has been extensively studied in the field of computer vision [30,32].”
BackgroundAn FMCW MIMO Radar-Vision Fusion Algorithm for Target Classification and Localization
Cai, G., Wang, X., Shi, J., Lan, X., Su, T., & Guo, Y. (2023) · IEEE Access · doi:10.1109/access.2023.3321271 · Cited by 1
“With the development of deep learning [7], [8], [9], [10], the emergence of network structures with continuously improving detection accuracy and detection speed proves the success of using deep learning networks for image target detection.”
BackgroundSelf-citationXie, Z., Fu, M., & Liu, X. (2023) · International Conference on Image, Vision and Computing (ICIVC) · doi:10.1109/icivc58118.2023.10270297 · Cited by 2
“In the early days, the detection algorithm for fittings relied primarily on traditional image processing methods that utilized artificially designed features, which process features in a relatively single manner, making them susceptible to interference from image background, lighting, angle, and other factors, resulti…”
MethodExpand Object Detection Dataset Automatically via Deep Learning Neural Networks
Liu, B., & Ganesan, S. (2023) · International Conference on Computing and Information Technology (ICCIT) · doi:10.1109/iccit58132.2023.10273981 · Cited by 1
Detecting individual dead trees using airborne laser scanning
Heinaro, E. (2023) · Dissertationes Forestales · doi:10.14214/df.343 · Cited by 2
Improved YOLOv5s Object Algorithm Based on Decoupled Head Module
Yan, X., & Hou, J. (2023) · International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD) · doi:10.1109/icnc-fskd59587.2023.10281088 · Cited by 1
“Object detection algorithm is a branch in the field of computer vision, and also a research hotspot in the field of computer vision, and its position in the field of computer vision is crucial [1] .”
BackgroundA Robust Multiple Honeybee Tracking Method from Videos Captured at Beehive Entrance
Le, T.-N., Tran, D.-N., Phan, T.-T.-H., Pham, H.-T., Le, T., & Vu, H. (2023) · International Conference on Multimedia Analysis and Pattern Recognition (MAPR) · doi:10.1109/mapr59823.2023.10289105 · Cited by 1
“According to surveys [5], [6], in recent years, many object detection and tracking methods have been proposed and successfully applied in many different object monitoring systems.”
BackgroundAutomatic Generation of Images Using Unreal Engine for Supervised Learning
Brasil, C. B., Oliveira, R. R., Oliveira, A. P., Braun, C., da Silva, L. F. M., Correa, I. S., & Klautau, A. (2023) · Anais de XXXV Simpósio Brasileiro de Telecomunicações e Processamento de Sinais · doi:10.14209/sbrt.2023.1570920088 · Cited by 1
Xia, L., Su, Y., Liu, R., Mi, S., & Yang, D. (2023) · Geocarto International · doi:10.1080/10106049.2023.2280549 · Cited by 1
“Conventional pixel-and object-level target detection techniques gradually lose target information as the image reaches deeper layers of the network after multiple convolutional pooling operations, effectively hindering target extraction (Xiao et al. 2020; Zou et al. 2023).”
BackgroundA Low-Latency Hardware Accelerator for YOLO Object Detection Algorithms
Wang, A., Ye, Y., Yu, P., et al. (2023) · Lecture notes in computer science · doi:10.1007/978-981-99-7872-4_15 · Cited by 1
Zhu, J., Ai, J., Shi, T., Zhang, C., & Wu, X. (2023) · International Conference on Dependable Systems and Their Applications (DSA) · doi:10.1109/dsa59317.2023.00121 · Cited by 3
“As a task in computer vision which aims to identify and locate objects, object detection requires algorithms or models to identify the coordinates of objects within an image and distinguish its category within the identified region, or Region of Interest (RoI) [20].”
BackgroundRemote Sensing Image Detection Algorithm Based on GhostNetv2 Improved YOLOv5s Algorithm
Li, R., Huang, W., Liu, C., et al. (2023) · International Conference on Information Systems Engineering (ICISE) · doi:10.1109/icise60366.2023.00047 · Cited by 1
“Two types of algorithms, two-stage algorithms and single-stage algorithms, are the two mainstream research algorithms in the field of target detection[2].”
Attention-Fused Shallow Network for Underwater Object Detection
Chourasia, A., Naosekpam, V., & Sahu, N. (2023) · IEEE Region 10 Conference (TENCON) · doi:10.1109/tencon58879.2023.10322535 · Cited by 1
“One of the most fundamental and challenging issues in computer vision is object detection [9], which has recently at-tracted much attention.”
Research Review of Autonomous Vehicle Detection Based on YOLO Algorithm
王, 树. (2023) · Computer Science and Application · doi:10.12677/csa.2023.1311212 · Cited by 1
Improved YOLOv5 Object Detection Algorithm for Remote Sensing Images
Duan, X., & Huang, W. D. (2023) · International Conference on Robotics and Computer Vision (ICRCV) · doi:10.1109/icrcv59470.2023.10329114 · Cited by 1
“Object detection is an important computer vision task [1].”
Background
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.