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 1,901–2,000 of 3,144
VIPHY: Probing “Visible” Physical Commonsense Knowledge
Singh, S., Qasemi, E., & Chen, M. (2023) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2023.findings-emnlp.473 · Cited by 9
Deep Learning-Based Consistent Object Detection in Distance on Highly Perspective Region
Lee, K. B., Gong, J., Ryu, B. H., & Shin, H. (2023) · Applied Sciences · doi:10.3390/app132413169 · Cited by 1
Semi-Supervised Deep Learning for Estimating Fur Seal Numbers
Chen, R., Ghobakhlou, A., Narayanan, A., Pérez, M., Chávez, R. O., & Borras‐Chavez, R. (2023) · International Conference on Image and Vision Computing New Zealand (IVCNZ) · doi:10.1109/ivcnz61134.2023.10343918 · Cited by 2
“CNN-based large-scale object detection methods have been used to estimate the number of buildings [5], cars [6], crowds [7] and many other objects [8].”
BackgroundMethodDistance Estimation Based on Computer Vision
Zhou, T. (2023) · International Conference on Data Analytics, Computing and Artificial Intelligence (ICDACAI) · doi:10.1109/icdacai59742.2023.00144 · Cited by 2
“Object detection could be divided into two categories in this era: "two-stage detection" and "one-stage detection," where the former frames the detection as a "coarse-to-fine" process while the latter frames it as something that can be "completed in one step" [2].”
BackgroundImproved YOLOv5 for Aerial Images Object Detection with the Introduction of Attention Mechanism
Xu, L. (2023) · International Conference on Data Analytics, Computing and Artificial Intelligence (ICDACAI) · doi:10.1109/icdacai59742.2023.00159 · Cited by 1
“All of these issues make object detection in aerial scsnes very challenging. object detection models were constructed using sliding windows for region selection and then by integrating a series of hand-designed feature extractors, using machine learning methods for classification [2].”
BackgroundMethodObject Detection Using TensorFlow
Sharma, A., Mishra, T., Kukade, J., Golwalkar, A., & Tomar, H. (2023) · Lecture notes in networks and systems · doi:10.1007/978-981-99-6568-7_31 · Cited by 1
Ma, S., Bie, Z., & Liang, X. (2023) · International Conference on Integrated Circuits and Microsystems (ICICM) · doi:10.1109/icicm59499.2023.10366042 · Cited by 2
“Object detection algorithms are mainly divided into two classes: One-Stage and Two-Stage [2].”
BackgroundA Hierarchical Theme Recognition Model for Sandplay Therapy
Feng, X., Hu, S., Chen, X., & Huang, K. (2023) · Lecture notes in computer science · doi:10.1007/978-981-99-8462-6_20 · Cited by 7
Multi-Sensor Object Detection System for Real-Time Inferencing in ADAS
Mandumula, S. R., Park, J., Asolkar, R. P., et al. (2023) · IEEE Symposium Series on Computational Intelligence (SSCI) · doi:10.1109/ssci52147.2023.10371789 · Cited by 1
“Recently, camera-based Deep Neural Networks (DNNs) have achieved state-of-the-art performances in computer vision [1-3].”
BackgroundOne model, two brains: Automatic fetal brain extraction from MR images of twins
Chen, J., Lu, R., Jing, B., Zhang, H., Shen, D. G., & Shen, D. G. (2024) · Computerized Medical Imaging and Graphics · doi:10.1016/j.compmedimag.2024.102330 · Cited by 1
Fast Object Detection Leveraging Global Feature Fusion in Boundary-Aware Convolutional Networks
Fan, W., Yu, J., & Ju, Z. (2024) · Information · doi:10.3390/info15010053 · Cited by 2
STDG: Fast and Lightweight SNN Training Technique Using Spike Temporal Locality
Cai, Z., Kalatehbali, H. R., Walters, B., Azghadi, M. R., Amirsoleimani, A., & Genov, R. (2023) · IEEE Biomedical Circuits and Systems Conference (BioCAS) · doi:10.1109/biocas58349.2023.10388882 · Cited by 1
“In recent years, there has been remarkable progress in neural networks with outstanding accomplishments in tasks such as object detection [1] and image classification [2].”
BackgroundMTANet: Multi-Type Attention Ensemble for Malaria Parasite Detection
Zedda, L., Loddo, A., & Ruberto, C. D. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-51026-7_6 · Cited by 1
Estimating Water Storage from Images
Shahbaz, A., Yunas, S., Smith, L. N., et al. (2023) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata59044.2023.10386262 · Cited by 1
“Object detection stands as a foundational task within computer vision, involving the identification and precise localization of objects within images or video frames, as elaborated in [1].”
BackgroundGordienko, N., Gordienko, Y. G., Rokovyi, O., Alienin, O., Polukhin, A., & Stirenko, S. (2023) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata59044.2023.10386393 · Cited by 1
“This approach combines information from various sources, such as optical, infrared, and radar data, to enhance the accuracy and robustness of object detection in remote sensing applications [4]–[6].”
BackgroundDetecting Vehicles using YOLOv8n in Edge Computing Dashcam
Radim, A. S. A., Rusydi, M. ’. C., Nasution, S. M., & Setianingsih, C. (2023) · International Conference on Intelligent Cybernetics Technology & Applications (ICICyTA) · doi:10.1109/icicyta60173.2023.10428952 · Cited by 2
“Object detection has undergone many changes and developments in the past twenty years [9].”
BackgroundLow-light Road Target Detection based on Lightweight Generative Adversarial Networks
Wei, X., Yu, S., & He, S. (2023) · International Conference on Electronic Information Engineering and Computer Science (EIECS) · doi:10.1109/eiecs59936.2023.10434282 · Cited by 1
“…region selection, manual feature extraction, and classifier classification, and the traditional methods have never been able to solve the problems encountered in target detection well because it is often difficult to obtain the diverse features of the target by manual feature extraction [2].”
MethodBoosting Noise Reduction Effect via Unsupervised Fine-Tuning Strategy
Jiang, X., Xu, S., Wu, J., Zhou, C., & Ji, S. (2024) · Applied Sciences · doi:10.3390/app14051742 · Cited by 3
Human Action Recognition Based on YOLOv7
Liang, C., & Yan, W. Q. (2024) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3693-1738-9.ch006 · Cited by 2
Collaborative Intelligent Industrial Robots (CIIR) Framework
Alremeithi, K., Giri, P., & Sealy, W. (2023) · 2023 International Conference on Electrical, Communication and Computer Engineering (ICECCE) · doi:10.1109/icecce61019.2023.10442250 · Cited by 3
“Furthermore, Zhengxia et al. [23] conducted a survey on notable object detection methodologies, highlighting the widespread use of OpenCV, an open-source computer vision software detailed by Bradski et al. [24].”
MethodAn Improved YOLOv5s Algorithm and its Application for Object Detection
Chang, T., Niu, Z., & Wang, Y. (2023) · IEEE International Conference on Electrical, Automation and Computer Engineering (ICEACE) · doi:10.1109/iceace60673.2023.10442853 · Cited by 1
“However, due to the complex road background and the lack of small target information, existing object detection algorithms have the problem of low detection accuracy [2].”
BackgroundReal-Time Object Detection and Tracking Using Deep Learning
Soumyadeep, M., Singh, A. P., Sharma, A. J., et al. (2023) · International Conference on Intelligent Systems and Embedded Design (ISED) · doi:10.1109/ised59382.2023.10444534 · Cited by 1
“One of the primary objectives is to develop generic medication object detection pipelines that can effectively handle tasks such as object detection, face detection, and pedestrian detection[11].”
BackgroundGraph-based geometric structure line parsing
Li, F., Li, G., He, B., Lu, P., & Cheng, B. (2024) · Neurocomputing · doi:10.1016/j.neucom.2024.127481 · Cited by 1
Scale and spatial awareness-based prohibited item detection in X-ray image
Wang, S., Yang, K.-Q., Ye, X.-C., et al. (2024) · J. Electronic Imaging · doi:10.1117/1.jei.33.2.023027 · Cited by 1
“14 And with their fixed geometric configurations, they struggle to adapt to objects varying in scale and shape.”
BackgroundJung, Y.-H., & Seo, S. (2024) · Journal of Digital Art Engineering and Multimedia · doi:10.29056/jdaem.2024.03.05 · Cited by 1
SAR Ship Detection based on Deep Learning using Class Activation Map
Kim, B., Moon, H., Lee, J., & Kim, S. (2024) · Journal of Broadcast Engineering · doi:10.5909/jbe.2024.29.2.198 · Cited by 1
Research on an improved yolov5s algorithm for detecting helmets on construction sites
Liu, Q., & Han, F. (2023) · International Conference on Electronic Information Technology and Computer Engineering (EITCE) · doi:10.1145/3650400.3650418 · Cited by 1
“In addition, classifiers such as support vector machines [4] can classify and predict the extracted image features, effectively reducing the difficulty of feature selection.”
BackgroundResearch of an Enhanced YOLOv5-Based Algorithm for Garbage Detection in Service Areas
Zhang, Q., & He, H. (2024) · doi:10.1109/nnice61279.2024.10499157 · Cited by 1
“Although deep learning has advanced substantially in object detection[2], practical applications, such as detecting small waste in service areas, present significant challenges.”
BackgroundSlavuljica, A., Bektaş, K., Strecker, J., & Mayer, S. (2024) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3655599 · Cited by 1
Amin, R. M., Chen, F., Hirsch, L. S., Ou, C., La, T. V., & Butz, A. M. (2024) · International Conference on Advanced Visual Interfaces (AVI) · doi:10.1145/3656650.3656680 · Cited by 2
Construction of Three-Dimensional Semantic Maps of Unstructured Lawn Scenes Based on Deep Learning
Xie, X., Yan, Z., Zhang, Z., et al. (2024) · Applied Sciences · doi:10.3390/app14114884 · Cited by 1
Aras, K., Saif, S. S., Giuseppi, A., & Coşkun, V. (2024) · International Congress on Human-Computer Interaction, Optimization and Robotic Applications (ICHORA) · doi:10.1109/hora61326.2024.10550768 · Cited by 2
“This problem definition is quite similar to the ones found in object detection and pose estimation algorithms [11-13].”
MethodResultOpen Set Object Detection in Complex Petrochemical Scenes
Li, X., Chen, X., Qu, C., Yu, B., Liu, F., Hu, X., Zhu, D., Lu, F., Chen, R., Yu, G., et al. (2024) · International Symposium on Autonomous Systems (ISAS) · doi:10.1109/isas61044.2024.10552488 · Cited by 1
“After traditional artificial intelligence [3,4] is deployed to the scene, due to the complexity and variability of the industrial scene, there will be untrained anomalous data, resulting in the inability to accurately recognize.”
BackgroundResearch on Mask-Wearing Detection Algorithm Based on Improved YOLOv7-Tiny
Min, G. A. O., Gaohua, C. H. E. N., Jiaxin, G. U., et al. (2024) · IEICE Transactions on Information and Systems · doi:10.1587/transinf.2023edp7254 · Cited by 1
“In the past twenty years, the development of target detection has roughly experienced the evolution from traditional methods to detection methods based on deep learning [3].”
MethodMultiagent Detection System Based on Spatial Adaptive Feature Aggregation
Wang, H., Wang, H., Zhang, X., Ruan, R., Wang, Y.-Y., & Yin, Y. (2024) · IEEE Systems Journal · doi:10.1109/jsyst.2024.3423752 · Cited by 1
Vision-based hybrid object tracking for autonomous vehicles
Chuang, H.-M., Tsuchiya, M., Araki, S., Inoue, R., Ariyoshi, T., & Yasui, Y. (2024) · IEEE Intelligent Vehicles Symposium · doi:10.1109/iv55156.2024.10588487 · Cited by 1
“These features facilitate a range of tasks, including object detection, tracking, and ego-motion estimation [1], [2].”
BackgroundYOLOv8-CAS: An improvement of multi-class target detection algorithm based on YOLO
Du, Y., Guo, J., Yang, S., & Li, F. (2024) · IEEE International Conference on Electronic Technology, Communication and Information (ICETCI) · doi:10.1109/icetci61221.2024.10594299 · Cited by 1
“Furthermore, it imposes high standards on the real-time performance and robustness of the underlying algorithm[1].”
BackgroundMACRO: Incentivizing Multi-Leader Game-Based Pareto-Efficient Crowdsourcing for Video Analytics
Chen, Y., Zhang, S., Zhou, Z., Wang, X., Liang, Y., Chen, N., Yan, Y., Xiao, M., Wu, J., Qian, Z., et al. (2024) · IEEE International Conference on Data Engineering (ICDE) · doi:10.1109/icde60146.2024.00029 · Cited by 1
“Hence, each platform cannot improve its own utility unless others’ utility is reduced, and it is consistent with the definition of PE.”
BackgroundDLS-YOLO: An improved Detector based on YOLOv8n for UAV remote sensing detection
Zhang, Y. (2024) · International Conference on Computer Information and Big Data Applications (CIBDA) · doi:10.1145/3671151.3671171 · Cited by 1
“Object detection in the scenario [ 1 ] aims to swiftly identify specific objects amidst the intricate remote sensing backdrop, enabling precise localization and labeling to guide subsequent operations.”
Introducing Deep Learning to Undergraduate Engineering
Zhang, L. (2024) · ASEE Midwest Section Conference · doi:10.18260/1-2-530-46352 · Cited by 1
Zhang, O. (2024) · International Conference on Computer Vision, Image and Deep Learning (CVIDL) · doi:10.1109/cvidl62147.2024.10604097 · Cited by 1
“This makes them particularly effective for tasks like image classification [5], object detection [6], and image style transfer [7].”
BackgroundTowards Robust Object Detection in Unseen Catheterization Laboratories
Wang, Z., Butler, R., van den Dobbelsteen, J. J., Hendriks, B. H. W., van der Elst, M., & Dauwels, J. (2024) · IEEE International Symposium on Medical Measurements and Applications (MeMeA) · doi:10.1109/memea60663.2024.10596906 · Cited by 2
“Object detection stands as a cornerstone task in computer vision, critical for understanding images and videos [8].”
BackgroundImproving Replenishment for Retail: Utilizing Planogram Information
Topçu, B., Göksu, D., Aşkın, N., YILDIRIM, M. C., Aktaş, T., & Menteş, B. U. (2024) · Lecture notes in networks and systems · doi:10.1007/978-3-031-66329-1_11 · Cited by 1
A novel model selection and ensemble approach for tree species recognition using UAV images
Ye, Z., Zhu, S., Ma, Y., & Shen, Q. (2024) · International Conference on Computer, Artificial Intelligence and Control Engineering (CAICE) · doi:10.1145/3672758.3672834 · Cited by 2
“We reviewed the current status of Object Detection research domain [ 11 , 12 ] and selected several representative object detection models as our candidate models, including: atss, detectoRS, detr, nas_fcos, paa, fcos, fovea and reppoints.”
Amultistage Approach For Object Detection And Efficient Parsing Of Video Content
Sharma, G., Jatain, D., Malik, S., et al. (2024) · International Conference on Knowledge Engineering and Communication Systems (ICKECS) · doi:10.1109/ickecs61492.2024.10617104 · Cited by 1
“The ability to highlight the parts of the video where a desired object [3] is present enhances situational awareness and aids in making informed decisions promptly.”
BackgroundProgress of Object Detection Based on Deep Learning
Zhang, A. (2024) · Transactions on Computer Science and Intelligent Systems Research · doi:10.62051/tjd37347 · Cited by 1
A streamlined framework for BEV-based 3D object detection with prior masking
Tong, Q., Zhang, J., Yan, C. C., & Zeng, D. (2024) · Image and Vision Computing · doi:10.1016/j.imavis.2024.105229 · Cited by 2
Deep Neural Networks for Automated Metadata Extraction
Omari, A. E., Antari, J., & Elkina, H. (2024) · Lecture notes in networks and systems · doi:10.1007/978-3-031-68675-7_7 · Cited by 1
Detecting Objects of Various Categories in Optical Remote Sensing Imagery Using Neural Networks
Madajczak, A., & Ciecholewski, M. (2024) · IEEE International Geoscience and Remote Sensing Symposium (IGARSS) · doi:10.1109/igarss53475.2024.10640694 · Cited by 1
“The literature includes many papers on detecting objects of a single category [7].”
BackgroundDMAC-YOLO: A High-Precision YOLO v5s Object Detection Model with a Novel Optimizer
Meng, C. H., Liu, S., & Yu, Y. (2024) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn60899.2024.10650645 · Cited by 5
“Lai Xiao and colleagues, in constructing deep learning models, selected optimizers such as Stochastic Gradient Descent (SGD), Stochastic Gradient Descent with Momentum (SGD-M)[18], and Adaptive Moment Estimation, ultimately demonstrating that Adam could find the optimal parameters[19].”
BackgroundWoodenCube: An Innovative Dataset for Object Detection in Concealed Industrial Environments
Wu, C., Li, S., Xie, T., Wang, X., & Zhou, J. (2024) · Sensors · doi:10.3390/s24185903 · Cited by 1
“Some researchers have attempted to directly apply existing object-detection algorithms [14,15], such as convolutional neural networks (CNNs [13]), to the task of object recognition for robotic arms, combined with hand–eye calibration techniques [16] (e.g., eye-in-hand or eye-on-hand) to facilitate…”
BackgroundFrom Purpose to Technology: A Requirements-Driven Approach to Designing Digital Twin Implementations
Noichl, F., Collins, F. C., Pan, Y., Mafipour, M. S., Mehranfar, M., & Borrmann, A. (2024) · American Society of Civil Engineers eBooks · doi:10.1061/9780784485606.ch5 · Cited by 1
Convolution Filter Compression via Sparse Linear Combinations of Quantized Basis
Lan, W., Cheung, Y., Lan, L., Jiang, J., & Hu, Z. (2024) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2024.3457943 · Cited by 2
“We adopt the mean average precision (mAP) as an evaluation metric, which is widely used to assess the model performance in object detection tasks [85].”
AdvDenoise: Fast Generation Framework of Universal and Robust Adversarial Patches Using Denoise
Li, J., Wang, Z., & Li, J. (2024) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw63382.2024.00352 · Cited by 3
“Following the comprehensive survey by Zou et al. [50] and considering the practical relevance of adversarial attacks, we selected a diverse set of target models for our experiments.”
Check-QZP: A Lightweight Checkpoint Mechanism for Deep Learning Frameworks
Lee, S., Moon, G., Lee, C., Kim, H., An, D., & Kang, D. H. (2024) · Applied Sciences · doi:10.3390/app14198848 · Cited by 1
Mei, S., Xiao, Z., Chen, J., Shan, S., & Shi, Z. (2024) · International Journal of Information Retrieval Research · doi:10.4018/ijirr.356489 · Cited by 3
“It is well known that there is a conflict between classification and regression tasks in object detection (Zou et al., 2023).”
Self-citationPneumonia Detection in Chest X-Rays Using Combined Approach of Deep Learning
Aditya Pai, H., Pareek, P. K., Guruprasad, M. S., Chandrappa, S., & Bhargava, K. (2024) · International Conference on Networks, Multimedia and Information Technology (NMITCON) · doi:10.1109/nmitcon62075.2024.10699169 · Cited by 1
Xu, P., Xu, H., Xiao, P., et al. (2024) · Journal of Circuits Systems and Computers · doi:10.1142/s0218126625501105 · Cited by 1
Classification of Deep Learning Techniques for Object Detection
Purushotham, A. A. R., Ravindra, M., & Ravindra, C. (2024) · BENTHAM SCIENCE PUBLISHERS eBooks · doi:10.2174/9789815223491124010015 · Cited by 1
Automated feature map padding and transfer circuit for CNN inference
Zhang, H., Chen, M., Ni, M., Chen, L., Zhang, Y., & Hao, X. (2024) · IEICE Electronics Express · doi:10.1587/elex.21.20240559 · Cited by 1
Song, G., Sun, Q., Wang, G., Jiao, H., Wang, Y., & Qiu, X. (2024) · International Conference on Advanced Robotics and Mechatronics (ICARM) · doi:10.1109/icarm62033.2024.10715897 · Cited by 1
“The purpose of object detection networks is to extract pertinent target information from images through deep learning methodologies [6].”
BackgroundPeak Identification in Evolutionary Multimodal Optimization: Model, Algorithms, and Metrics
Zhang, Y., & Wang, Z.-J. (2024) · Biomimetics · doi:10.3390/biomimetics9100643 · Cited by 1
“However, in some real-world applications (e.g., multi-object detection [46]), a redundant solution will result in a false-positive error.”
BackgroundShah, V., & Sardhara, R. (2024) · International Conference on Intelligent Algorithms for Computational Intelligence Systems (IACIS) · doi:10.1109/iacis61494.2024.10721820 · Cited by 1
“It keeps an eye on the way people behave in public to spot any unusual activity [29].”
BackgroundHighway Anomaly Detection Based on Deep Learning
Yan, Z., Yin, W., & Zhai, J. (2024) · Lecture notes in electrical engineering · doi:10.1007/978-981-97-8650-3_33 · Cited by 1
Penguin colony georegistration using camera pose estimation and phototourism
Wu, H., Flynn, C., Hall, C., Che‐Castaldo, C., Samaras, D., Schwaller, M. R., & Lynch, H. J. (2024) · PLoS ONE · doi:10.1371/journal.pone.0311038 · Cited by 1
Unsupervised Dense Prediction Using Differentiable Normalized Cuts
Liu, Y., & Gould, S. J. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-73661-2_16 · Cited by 8
“Dense prediction aims at understanding detailed aspects of an image, encompassing tasks such as object detection [52], segmentation [26, 37], and correspondence [18,29].”
Lee, J. H., Lee, Y., Son, Y. S., & Choi, W. Y. (2024) · Transactions of Korean Society of Automotive Engineers · doi:10.7467/ksae.2024.32.11.935 · Cited by 1
Freire, D. L., de Carvalho, A. C. P. L. F., Peterlevitz, A. J., et al. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-73500-4_16 · Cited by 1
An Image Processing Approach to Quality Control of Drop-on-Demand Electrohydrodynamic (EHD) Printing
Tawhari, Y., Shukla, C., & Ren, J. (2024) · Micromachines · doi:10.3390/mi15111376 · Cited by 1
Chouchene, S., Brochard, F., Desecures, M., Lemoine, N., & Cavalier, J. (2024) · Scientific Reports · doi:10.1038/s41598-024-79251-z · Cited by 2
Multi-Target Detection Method of Intelligent Driving Traffic Scene Based on Faster R-CNN++
Xu, Q., & Guo, J. (2024) · International Journal of Pattern Recognition and Artificial Intelligence · doi:10.1142/s0218001424590195 · Cited by 2
Römer, I., Schieck, M., Harnau, N., & Franczyk, B. (2024) · Procedia Computer Science · doi:10.1016/j.procs.2024.09.559 · Cited by 2
Adversarial Attacks to Manipulate Target Localization of Object Detector
Xu, K. M., Cheng, X. M., Ji, Q., et al. (2024) · IEEE Access · doi:10.1109/access.2024.3508760 · Cited by 1
“…expanded to more complex tasks, posing significant challenges to models such as object detection, semantic segmentation, and natural language processing [13], [14], [15], The associate editor coordinating the review of this manuscript and approving it for publication was Miguel López-Benítez .”
Intelligent Traffic Lane Management System
Thosar, M. R., Pampattiwar, S., Gidage, P., & Khakale, P. (2024) · International Journal of Advanced Research in Science Communication and Technology · doi:10.48175/ijarsct-22295 · Cited by 1
An Improved YOLOF for Scale Imbalance with Dilated Attention
Amarbayasgalan, T., Kim, M., & Jeong, C. Y. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-78447-7_11 · Cited by 2
Li, X., Kim, H., & Kim, H. (2024) · International Conference on Control, Automation and Systems (ICCAS) · doi:10.23919/iccas63016.2024.10773226 · Cited by 1
Applications of Knowledge-Integrated Machine Learning in Robotics
Goswami, C., Kumar, S. V., Hameed, N. S., Sugadev, T., Raghuram, K. S., & Sahu, D. N. (2024) · Advances in intelligent systems and computing · doi:10.1007/978-981-97-6352-8_44 · Cited by 1
Multiscale Information Fusion Based on Large Model Inspired Bacterial Detection
Liu, Z., Huang, Y. T., Wang, J., Yuan, G., & Pang, J. (2024) · Big Data Mining and Analytics · doi:10.26599/bdma.2024.9020078 · Cited by 2
Wang, T., Zhang, Z., Qi, W., Han, X., Wang, K., Liu, J., Lin, Y., & Wen, R. (2024) · Computers, materials & continua/Computers, materials & continua (Print) · doi:10.32604/cmc.2024.058952 · Cited by 3
“To overcome these shortcomings, oriented object detection has gained prominence as a promising paradigm with diverse applications [12].”
Evolving Safety Protocols: Deep Learning-Enabled Detection of Personal Protective Equipment
Alahmid, M., Bhimani, K., Saradva, K., Ghildiyal, S., Saeedi, S. A., Ali, S., Han, Y., & Filippov, E. (2024) · Lecture notes in electrical engineering · doi:10.1007/978-981-97-7794-5_7 · Cited by 2
MC-YOLO: Multi-scale Transmission Line Defect Target Recognition Network
Wang, J., Ding, X., & Meng, F. (2024) · Lecture notes in computer science · doi:10.1007/978-981-96-2061-6_24 · Cited by 1
A case for edge video processing with FPGA SoC: reversi board detection using Hough transform
Fujieda, N., & Ito, N. (2024) · International Symposium on Computing and Networking Workshops (CANDARW) · doi:10.1109/candarw64572.2024.00017 · Cited by 1
“Computer vision algorithms and their applications, such as object detection [21] and anomaly detection [14], have been surprisingly grown in recent 20 years.”
Si, T., & Kong, S. (2025) · IEEE Access · doi:10.1109/access.2025.3527881 · Cited by 3
“In this situation, existing object detectors are prone to overfitting, leading to a significant decrease in generalization performance [14], [15].”
Dual-Path Downsampling Algorithm Based on HWD-MP
Wang, Z., Bai, J., Zhang, Q., et al. (2024) · International Conference on Cloud Computing, Big Data Application and Software Engineering (CBASE) · doi:10.1109/cbase64041.2024.10824445 · Cited by 1
Yu, P., & Yang, Z. (2024) · International Conference on Pattern Recognition and Artificial Intelligence (PRAI) · doi:10.1109/prai62207.2024.10827680 · Cited by 1
“In recent years, semantic segmentation has been widely used in unmanned driving, medical images 3D reconstruction, object detection [2], street view image recognition [3] and other scenarios.”
Enhanced Deblurring for Smart Cabinets in Dynamic and Low-Light Scenarios
Sun, Y., Hu, S., Xie, K., et al. (2025) · Electronics · doi:10.3390/electronics14030488 · Cited by 1
Hansen, C. D., Le, T. T., & Campos, D. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-80856-2_9 · Cited by 1
Application of Augmented Reality in Waterway Traffic Management Using Sparse Spatiotemporal Data
Zhang, R., Ai, Y., Li, S., et al. (2025) · Applied Sciences · doi:10.3390/app15041710 · Cited by 1
Ren, J., Fisker‐Bødker, N., Güldenring, R., et al. (2025) · IEEE/SICE International Symposium on System Integration (SII) · doi:10.1109/sii59315.2025.10870899 · Cited by 1
PE-SSD: Improved SSD for Small Object Detection
Tang, Z., Zhu, L., Wang, W., et al. (2024) · China Automation Congress (CAC) · doi:10.1109/cac63892.2024.10865724 · Cited by 1
“Object detection [1]–[3] is a fundamental task in the field of computer vision, which is widely applied in various domains such as intelligent surveillance [4], autonomous driving [5], and medical image analysis [6].”
Defect Detection of Composite Insulators Based on the Improved Faster-RCNN Model
Lan, D., Wang, K., Wang, X., et al. (2024) · IEEE International Conference on Automation, Electronics and Electrical Engineering (AUTEEE) · doi:10.1109/auteee62881.2024.10869711 · Cited by 1
A Density-Guided Regional Object Detection Method for Satellite Videos
Wenliang, Z., Lü, M., Huisheng, W., et al. (2024) · International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP) · doi:10.1109/iccwamtip64812.2024.10873641 · Cited by 1
“In contrast, deep learning-based video object detection methods [5] significantly enhance detection accuracy and robustness in complex scenarios by learning object feature representations from large-scale datasets.”
GMDNet: Fusion Network Based on Global Multi-Scale Detailed Information
Zhang, Z., Sun, W., Sun, C., & He, R. (2025) · Remote Sensing · doi:10.3390/rs17050745 · Cited by 2
Lekha, J., & Vijayalakshmi, S. (2024) · Mechanical Engineering, Science and Technology International Conference (MEST) · doi:10.3390/ecsa-11-20380 · Cited by 1
Rao, W., Chen, S., & Li, D. (2025) · IEEE Access · doi:10.1109/access.2025.3547825 · Cited by 2
“However, traditional object detection algorithms have disadvantages such as limited feature representation, poor scale and rotation invariance processing, and difficulty in dealing with occlusions and complex backgrounds [12].”
Intelligent Analysis of Electrical CAD Drawings for Robotic Services
Hu, L., Xu, N., Sun, H., Liu, X., Guo, W., & Yin, J. (2024) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio64047.2024.10907332 · Cited by 1
Liang, H., Dingqian, 邱. Q., Shiyu, 丁. D., & Kuan, 栾. L. (2025) · Chinese Journal of Lasers · doi:10.3788/cjl241265 · Cited by 2
Enhancing Table Recognition Model by Synthetic Image Generation
Vo-Le, C., Vo, H. S., Bui, A. V., & Truong, H. Q. (2024) · International Conference on Advanced Technologies for Communications · doi:10.1109/atc63255.2024.10908269 · Cited by 1
“OD involves locating and identifying visual objects of a specific class in digital images [9].”
SRS-YOLO: Improved YOLOv8-Based Smart Road Stud Detection
Mao, G., Wang, K., Du, H., Huang, B., Ren, X., Fu, T., & Zhang, Z. (2025) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2025.3545942 · Cited by 4
“Traditional object detection algorithms based on handcrafted features struggle to address the aforementioned challenges in achieving accurate and robust smart road stud detection [17], [18].”
LTOS: Layout-controllable Text-object Synthesis via Adaptive Cross-attention Fusions
Zhao, X., Wu, T., Lai, Y., Tian, Z., Huang, Z., Liu, Y., He, Z., & Li, D. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10890356 · Cited by 2
“To mitigate this challenge, we integrate the aforementioned two mainstream tasks - text rendering and layout-to-image generation - into a singular task: layout-controllable text-object synthesis (LTOS).”
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.