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 1,301–1,400 of 3,144
Improving generalization capability of object detectors via efficient global attention
Chen, J., & Er, M. J. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.130287 · Cited by 3
An improved and lightweight small-scale foreign object debris detection model
Zhang, H., Fu, W., Wang, X., Li, D., Zhu, D., & Su, X. (2025) · Cluster Computing · doi:10.1007/s10586-024-05002-4 · Cited by 6
“Nonetheless, this technology heavily depended on manually designed feature extractors, demanding substantial prior knowledge and skills to ensure effectiveness, and exhibited poor generalization [6].”
Liu, H., Liu, X., Huang, K., & Guo, D. (2025) · Machine learning · doi:10.1007/978-981-96-5871-8_1 · Cited by 4
Nguyen, P. T., & Nguyen, L. H. (2025) · Neural Computing and Applications · doi:10.1007/s00521-025-11305-3 · Cited by 5
A multi-model approach for distance and angle estimation using a custom-designed tag
Erkan, E. (2025) · Engineering Science and Technology an International Journal · doi:10.1016/j.jestch.2025.102076 · Cited by 3
Li, G., Lian, A., Yao, Z., Hu, Y., Pang, G., Yuan, T., Li, Z., Huang, X., & Wang, G. (2025) · Frontiers in Marine Science · doi:10.3389/fmars.2025.1619457 · Cited by 6
Wang, L., Wu, H., Yu, Y., Yu, W., Chen, S., & Wang, J. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3591635 · Cited by 6
“For instance, a Transformer-based self-supervised model has enhanced image anomaly recognition ACC and efficiency [6], and a novel segmentation approach has effectively handled complex anatomical structures with minimal labeled data [7].”
Qu, L., Wen, F., Huang, H., & Peng, F. (2025) · Signal Image and Video Processing · doi:10.1007/s11760-025-04548-z · Cited by 3
“DETR [12] is an end-to-end Transformer-based detection network that eliminates NMS but suffers from high computational costs [20].”
YOLOv8-C2fSE- An Improved Accuracy Model for Object Detection
Modupalli, B. M., & Prithvi, P. (2025) · International Conference on Recent Advances in Information Technology · doi:10.1109/rait65068.2025.11089214 · Cited by 3
“The survey provides a comprehensive overview of this revolutionary area of visual computing by examining datasets, measurements, speedup strategies, and future problems [6].”
Yi, P., Cao, K., Wei, C., Liang, L., & Gao, Z. (2025) · Measurement Science and Technology · doi:10.1088/1361-6501/adf136 · Cited by 3
Detection of Maize Pathogenic Fungal Spores Based on Deep Learning
Ren, Y., Xu, Y., Tian, H., Zhang, Q., Ming-xiu, Y., Zhu, R., Xin, D., Chen, Q., Wei, Q., & Song, S. (2025) · Agriculture · doi:10.3390/agriculture15151689 · Cited by 7
Diversifying Human Pose In Synthetic Data For Aerial-View Human Detection
Shen, Y., Lee, H., Kwon, H., & Bhattacharyya, S. S. (2025) · Proceedings - International Conference on Image Processing · doi:10.1109/icip55913.2025.11084750 · Cited by 6
CCANet: A Cross-scale Context Aggregation Network for UAV object detection
Shang, L., He, Q., Lei, H., & Yang, W. (2025) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2025.104472 · Cited by 5
B., C. E. P., R., O. I. I., A., M. D. L., & M., C. G. Q. (2025) · Systems · doi:10.3390/systems13090753 · Cited by 5
“The effectiveness of object detection is evaluated using metrics such as precision, recall and the mean average precision (mAP), which summarizes precision and recall across all object classes to provide a single performance score [10].”
Qiu, H., Wang, J., Lin, Z., et al. (2025) · Measurement Science and Technology · doi:10.1088/1361-6501/ae0aeb · Cited by 3
“…simple structures and efficient inference; two-stage detectors (e.g. Faster R-CNN [14], Mask R-CNN [15]), on the other hand, use a sequential process of region proposal followed by refined classification and regression to improve detection accuracy, but at the cost of real-time performance [16].”
From Blurry to Brilliant Detection: YOLO-Based Aerial Object Detection with Super Resolution
Nihal, R. A., Yen, B., Ashizawa, T., Itoyama, K., & Nakadai, K. (2025) · Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) · doi:10.1109/apsipaasc65261.2025.11249079 · Cited by 20
“Aerial object detection presents challenges including small object sizes, high density clustering, and complex backgrounds [15], [16].”
Ma, Y., & Zhi, Z. (2022) · Advances in Multimedia · doi:10.1155/2022/1239337 · Cited by 3
“It is a basic problem in the field of computer vision and has a wide range of applications in the fields of autonomous driving, image understanding, and video surveillance [1].”
BackgroundRetractedObject detection algorithm based on cosine similarity IoU
Ma, S., Li, N., Guansheng, P., Chen, Y., Wang, Y., & Zhiqiang, H. (2022) · International Conference on Networking and Network Applications (NaNA) · doi:10.1109/nana56854.2022.00077 · Cited by 4
“SSD proposed multi-scale feature prediction for the first time, mapping objects of different sizes to feature maps of different resolutions for detection [11].”
BackgroundMethodInfluentialThe Study of Light-weight YOLOv4 Model for Rice Seedling and Counting
Li, L.-H., Chung, K.-L., Jiang, L.-Q., et al. (2022) · doi:10.1109/ccat56798.2022.00008 · Cited by 3
“Object detection is an important technology for the research of computer vision [14].”
BackgroundAI-based Endpoint Detection for Surface Defect Removal on Aircraft Components
Kähler, F., Shetty, A. C. K., & Schüppstuhl, T. (2023) · IEEE/SICE International Symposium on System Integration (SII) · doi:10.1109/sii55687.2023.10039239 · Cited by 5
“Object detection is a computer vision task to detect the object instances of a certain category (similar to classification tasks) along with its location in an image [12].”
BackgroundMutually Distilled Sparse RCNN for Few-Shot Object Detection
Jiang, X., Yu, H.-C., Lv, Y., & Zhu, X. F. (2022) · IEEE International Conference on Frontiers Technology of Information and Computer (ICFTIC) · doi:10.1109/icftic57696.2022.10075197 · Cited by 2
“INTRODUCTION With the research of generations of researchers, deep neural networks[1, 2, 3] have achieved state-of-art on speech recognition[4, 5], image classification[6, 7, 8] and object detection[9, 10, 11, 12].”
BackgroundThe PSG challenge: towards comprehensive scene understanding
Yang, J., Ma, Z., Wang, Q., Guo, X., Wang, H., Liu, Z., Zhang, W., Xu, X., & Zhang, H. F. (2023) · National Science Review · doi:10.1093/nsr/nwad126 · Cited by 3
Flower classification Model based on improved attention
Tang, Y., Yang, J., Xu, Q., et al. (2023) · IEEE International Conference on Information Technology, Big Data and Artificial Intelligence (ICIBA) · doi:10.1109/iciba56860.2023.10165230 · Cited by 3
“In recent years, with the continuous development of deep convolutional neural network, it has also promoted the progress in the field of computer vision, showing great advantages in the field of classification [1], detection [2], segmentation [3] and other tasks.”
Backgroundda Silva, D. D. A., Bomfim, I. G. A., Braga, A. R., & Gomes, D. G. (2023) · doi:10.5753/wcama.2023.230588 · Cited by 4
“These models can be divided into two basic groups: single-stage models and multi-stage models (two or more) [Zou et al. 2023].”
MethodRecognition and Semantic Information Extraction for Map Based on Deep Learning
Wang, Y., Du, K., Che, X., Ma, R., & Ren, F. (2023) · Proceedings of the ICA · doi:10.5194/ica-proc-5-25-2023 · Cited by 2
Jia, N., Zhang, H., Gao, H., & Liu, J. (2023) · Forests · doi:10.3390/f14091874 · Cited by 3
Shakirzyanov, R. M., Shleymovich, M. P., & Новикова, С. В. (2023) · Automation and Remote Control · doi:10.1134/s000511792307010x · Cited by 3
“So, in [27] the so-called two-pass algorithms of the FASTER RCNN type are described, reaching an accuracy of 73.2% (VOC07 1 dataset).”
MethodInfluentialA Bolt Rust Detection System for Smart Construction Sites
Sun, Y., Zheng, L., Lu, Z., Lian, Q., & Zhou, L. (2023) · International Conference on Image, Vision and Computing (ICIVC) · doi:10.1109/icivc58118.2023.10270376 · Cited by 4
Information extraction from operator interface images using computer vision and machine learning
Illing, E., Skeie, N., & Brastein, O. M. (2023) · Linköping electronic conference proceedings · doi:10.3384/ecp200031 · Cited by 3
“This paper explores the field of image classification [3] and object detection [4] for the purpose of extracting information from complex operator interface images.”
BackgroundNovel methods for locating and matching IC cells based on standard cell libraries
Liu, C., Wang, K., Li, Q., Zhao, F., Zhao, K., & Ma, H. (2023) · Microelectronic Engineering · doi:10.1016/j.mee.2023.112107 · Cited by 6
Height Restriction Bar Detection via Deformable YOLOv5s
Wang, W., Li, Q., Li, B., & Liu, X. (2023) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2023.3332603 · Cited by 4
“More algorithms about object detection can be found in [26] and [27].”
MethodResearch on a lightweight electronic component detection method based on knowledge distillation
Xia, Z., Gu, J., Wang, W., & Huang, Z. (2023) · Mathematical Biosciences & Engineering · doi:10.3934/mbe.2023928 · Cited by 3
Design and Implementation of a Camera-Based Tracking System for MAV Using Deep Learning Algorithms
Hensel, S., Marinov, M. B., & Panter, R. (2023) · Computation · doi:10.3390/computation11120244 · Cited by 3
“The detection of objects provides a basis for further computer vision tasks, especially instance segmentation, image recognition, and tracking of objects [16].”
BackgroundMethodScAR: Scaling Adversarial Robustness for LiDAR Object Detection
Lu, X., & Radha, H. (2023) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros55552.2023.10341583 · Cited by 3
“Deep neural networks have demonstrated remarkable power in solving various computer vision problems, including image classification [4], object detection [5], semantic segmentation [6], and more.”
BackgroundA practical guide to (successfully) collect and process images through online surveys
Iglesias, P. A., Ochoa, C., & Revilla, M. (2023) · Social Sciences & Humanities Open · doi:10.1016/j.ssaho.2023.100792 · Cited by 3
Deep Learning-Based Object Detection Techniques for Self-Driving Cars: an in-Depth Analysis
Isong, B., Mashego, T., Moemi, T. J., & Dladlu, N. (2023) · International Conference on Electrical, Computer and Energy Technologies (ICECET) · doi:10.1109/icecet58911.2023.10389376 · Cited by 3
“…prominent architectures, and class imbalance as well as explores various detectors and advancements and optimization of deep CNNs. Authors in [31] surveyed object detection techniques over two decades, tracing the shift from handcrafted to DL-based detectors, covering milestones, datasets,…”
BackgroundInfluentialDetecting Non-Injured and Injured Humans in Thermal Imaging using YOLOv8
Tham, M., Cham, T. H., & Kwan, B.-H. (2023) · International Conference on Computer and Applications (ICCA) · doi:10.1109/icca59364.2023.10401590 · Cited by 3
“Existing CNN-based object detection methods can be categorized into two types: one-stage and two-stage detectors [4].”
MethodYOLO, Faster R-CNN, and SSD for cloud detection
Yu, F. (2024) · Applied and Computational Engineering · doi:10.54254/2755-2721/37/20230514 · Cited by 3
RZUD: A Novel Hybrid Model for Small Sized Handgun Detection
Warsi, A., Abdullah, M., Jawaid, N., Khan, S., & Yahya, M. (2024) · International Conference on Ubiquitous Information Management and Communication (IMCOM) · doi:10.1109/imcom60618.2024.10418397 · Cited by 4
“One of the primary issues with existing object detection models is their limited ability to recognize small-sized objects adequately [24].”
BackgroundObject Detection-Based Knowledge Graph Creation: Enabling Insight into Construction Processes
Pfitzner, F., Braun, A., & Borrmann, A. (2024) · ASCE International Conference on Computing in Civil Engineering (i3CE) · doi:10.1061/9780784485224.023 · Cited by 4
“One of the object detection development milestones was CNN-based One-stage Detectors, e.g., You Only Look Once (YOLO), allowing extremely fast prediction speed (Zou et al., 2019).”
BackgroundMethodModel-agnostic progressive saliency map generation for object detector
Yan, Y., Jiang, T., Li, X., Sun, L., Zhu, J., & Lin, J. (2024) · Image and Vision Computing · doi:10.1016/j.imavis.2024.104988 · Cited by 3
Speaker Nonverbal Unintentionality: An OpenPose Intervention for Engineering Students
LeFebvre, L., Jaromczyk, J. W., Allen, M. R., LeFebvre, L. E., Tan, G. Z., & Tapia, A. C. (2024) · ASEE Southeast Section Conference · doi:10.18260/1-2--45559 · Cited by 3
An Improved YOLOv5 Multi-Scale Object Detection Method
Liu, X., Wang, Y., Chen, X., & Chen, F. (2023) · International Conference on Artificial Intelligence, Human-Computer Interaction and Robotics (AIHCIR) · doi:10.1109/aihcir61661.2023.00014 · Cited by 3
“In the experiments, we chose the mean Average Precision (mAP) [17] as the evaluation metric.”
MethodDetection of Crabs and Lobsters Using a Benchmark Single-Stage Detector and Novel Fisheries Dataset
Iftikhar, M., Neal, M., Hold, N., Toé, S. G. D., & Tiddeman, B. (2024) · Computers · doi:10.3390/computers13050119 · Cited by 3
Object and Event Detection Pipeline for Rink Hockey Games
Lopes, J. M., Mota, L. P., Mota, S. M., Torres, J. M., Moreira, R. S., Soares, C. P. D. A., Pereira, I. F., Gouveia, F. R., & Sobral, P. (2024) · Future Internet · doi:10.3390/fi16060179 · Cited by 7
“The latest innovations in object detection techniques have resulted in considerable increases in both the accuracy and speed of object detection [1].”
BackgroundSemantic-alignment transformer and adversary hashing for cross-modal retrieval
Sun, Y., Wang, M., & Ma, Y. (2024) · Applied Intelligence · doi:10.1007/s10489-024-05501-2 · Cited by 5
FEF-Net: feature enhanced fusion network with crossmodal attention for multimodal humor prediction
Gao, P., Tao, C., & Guan, D. (2024) · Multimedia Systems · doi:10.1007/s00530-024-01402-z · Cited by 7
“Additionally, current feature fusion methods can be categorized into two main types: bottom-up fusion and top-down fusion [52].”
RegionFilter: Region-aware video filtering mechanism on resource-constrained edge nodes
Chen, T., Bu, Y., Zeng, Y. W., Xie, L., & Lu, S. (2024) · Computer Networks · doi:10.1016/j.comnet.2024.110624 · Cited by 5
Online Scene Semantic Understanding Based on Sparsely Correlated Network for AR
Wang, Q., Song, J., Du, C., & Wang, C. (2024) · Sensors · doi:10.3390/s24144756 · Cited by 3
“In recent years, convolutional neural network architectures have significantly advanced object detection [14] and instance segmentation [15].”
BackgroundWang, Y., Liu, H., Zhao, Y., et al. (2024) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-031-67162-3_23 · Cited by 3
PMLPNet: Classifying Multi-Class Pests in Wild Environment via a Novel Convolutional Neural Network
Liu, L., Chang, J., Qiao, S., Xie, J., Xu, X., & Qiao, H. (2024) · Agronomy · doi:10.3390/agronomy14081729 · Cited by 3
Orientation-Aware Multi-Modal Learning for Road Intersection Identification and Mapping
He, Q., Xiao, Z., Huang, Z., Yuan, H., & Sun, L. (2024) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra57147.2024.10610015 · Cited by 4
“Specifically, we adopt the multi-task loss function [31] frequently used in object detection as our learning objective: where N represents the total number of anchors in the batch, and i indexes each anchor. coordinates of the predicted and ground truth bounding boxes, respectively, while p i and p…”
MethodA High-Frame-Rate-Imaging-Based Framework for Moving Point Target Detection in Very Low SNR
Niu, W., Guo, Y., Han, X., et al. (2024) · IEEE Transactions on Aerospace and Electronic Systems · doi:10.1109/taes.2024.3449270 · Cited by 3
Self-citationYinzheng, 张. Z., Hongjiang, 刘. L., Runlin, 朱. Z., Yifei, 刘. L., & Fuxing, 谷. G. (2024) · Chinese Journal of Lasers · doi:10.3788/cjl240564 · Cited by 3
Guo, D., Zhao, C., Shuai, H., Zhang, J., & Zhang, X. (2024) · Sustainability · doi:10.3390/su16177539 · Cited by 3
AIDCON: An Aerial Image Dataset and Benchmark for Construction Machinery
Ersöz, A. B., Pekcan, O., & Akbaş, E. (2024) · Remote Sensing · doi:10.3390/rs16173295 · Cited by 3
Cross-pollination of knowledge for object detection in domain adaptation for industrial automation
Rehman, A. U., & Gallo, I. (2024) · International Journal of Intelligent Robotics and Applications · doi:10.1007/s41315-024-00372-9 · Cited by 4
“Modern OD algorithms are mostly trained on domain-specific tasks and perform exceptionally well when trained on images with the same distribution as the test images (Zou et al. 2023).”
QYOLO: Contextual Query-Assisted Object Detection in High-Resolution Images
Gao, M., Wang, W., Mao, J., Xiong, J., Wang, Z., & Wu, B. (2024) · Information · doi:10.3390/info15090563 · Cited by 3
YOLO-LRHG: Long Range Hand Gesture detection using YOLO with attention mechanism
Yang, Y.-Y., Yang, H.-H., & Yang, J.-K. (2024) · IEEE International Conference on Electronic Information and Communication Technology (ICEICT) · doi:10.1109/iceict61637.2024.10671140 · Cited by 3
“The application of Convolutional Neural Networks (CNNs) in object detection has gradually replaced traditional handcrafted feature methods and machine learning-based approaches [1, 2].”
BackgroundPoTATO: A Dataset for Analyzing Polarimetric Traces of Afloat Trash Objects
Batista, L. F. W., Khazem, S., Adibi, M., et al. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-91569-7_13 · Cited by 3
Applications of Computer Vision, 2nd Edition
Cernadas, E. (2024) · Electronics · doi:10.3390/electronics13183779 · Cited by 8
Revising the Problem of Partial Labels from the Perspective of CNNs' Robustness
Zhang, X., Song, Y., McCurdy, W., Wang, X., & Zuo, F. (2024) · IEEE/ACIS International Conference on Software Engineering Research, Management and Applications (SERA) · doi:10.1109/sera61261.2024.10685603 · Cited by 4
“…(CNNs), with the ability to extract and learn features automatically from raw data have revolutionized the field of computer vision and have achieved state-of-the-art results on various tasks, including image classification [1], object detection [2], semantic segmentation [3], and so on [4]–[6].”
BackgroundMask-Based Invisible Backdoor Attacks on Object Detection
Shin, J. (2024) · Proceedings - International Conference on Image Processing · doi:10.1109/icip51287.2024.10647450 · Cited by 10
Cho, C., Song, H. M., & Youn, T.-Y. (2024) · Computer Modeling in Engineering & Sciences · doi:10.32604/cmes.2024.053430 · Cited by 4
A divide-and-conquer reconstruction method for defending against adversarial example attacks
Liu, X., Hu, J., Yang, Q., Jiang, M. Y., He, J., & Fang, H. (2024) · Visual Intelligence · doi:10.1007/s44267-024-00061-y · Cited by 8
“In recent years, deep neural networks (DNNs) have experienced rapid growth and achieved significant break-throughs in areas such as image classification [1, 2] and object detection [3, 4], resulting in remarkable outcomes.”
TraceGuard: Fine-Tuning Pre-Trained Model by Using Stego Images to Trace Its User
Zhou, L., Ren, X., Qian, C., & Sun, G. (2024) · Mathematics · doi:10.3390/math12213333 · Cited by 3
SES-ReNet: Lightweight deep learning model for human detection in hazy weather conditions
Bouafia, Y., Allili, M. S., Hebbache, L., & Guezouli, L. (2024) · Signal Processing Image Communication · doi:10.1016/j.image.2024.117223 · Cited by 5
Improved Squeeze and Excitation-Based YOLOv8-SE for Object Detection
Chauhan, R., Deshmukh, M., & Singh, A. (2024) · International Conference on Computing, Communication and Networking Technologies (ICCCNT) · doi:10.1109/icccnt61001.2024.10725047 · Cited by 4
“Object detection has garnered significant attention in computer vision research due to its wide-ranging applications, including surveillance, autonomous vehicles, and image retrieval[ [1], [2]].”
BackgroundVIMVA: Innovative Multimodal Recognition in Vietnamese Folk Dance Video Analysis
Ma, T.-T., Ngo, T., Tran, H.-N., Ton, M.-L., Ha, N. T., Phan, B.-C., & Do, T. (2024) · Communications in computer and information science · doi:10.1007/978-981-96-0437-1_21 · Cited by 5
Domain adaptation with temporal ensembling to local attention region search for object detection
Shi, H., He, Z., & Hwang, K. (2024) · Knowledge-Based Systems · doi:10.1016/j.knosys.2024.112846 · Cited by 3
Antonazzi, M., Luperto, M., Borghese, N. A., & Basilico, N. (2024) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros58592.2024.10802847 · Cited by 5
“Deep learning is today the leading approach to building detectors, which are typically based on architectures that analyze the input image through different stages to ensure its comprehensive coverage [23].”
Wang, S., Yu, Z., Han, G.-S., & Sun, X.-G. (2025) · International Journal of Biological Macromolecules · doi:10.1016/j.ijbiomac.2025.139519 · Cited by 3
Cross-View Detection of Crowded Objects Based on Multi-Sensor Fusion
Gu, Z., Peng, G., Yun, Y., Liu, Y., Wu, Z., Zhang, J., Li, Z., Suo, X., & Wang, D. (2024) · International Conference on Control, Automation, Robotics and Vision (ICARCV) · doi:10.1109/icarcv63323.2024.10821686 · Cited by 3
“Object detection [1]–[3] in the field of computer vision is a critical task that requires computer systems to not only recognize objects in an image, but also determine the precise location and bounding box of those objects.”
Bütler, R. M., Frassini, E., Vijfvinkel, T. S., van Riel, S., Bachvarov, C., Constandse, J. C., van der Elst, M., van den Dobbelsteen, J. J., & Hendriks, B. H. W. (2025) · Medical Engineering & Physics · doi:10.1016/j.medengphy.2025.104289 · Cited by 3
SA-LfV: self-annotated labeling from videos for object detection
Sivapuram, A. K., Komuravelli, P., & Gorthi, R. K. (2025) · Machine Learning · doi:10.1007/s10994-024-06676-y · Cited by 3
“There has been extensive research in architectural design, exploring/ proposing different loss functions, and the development of post-processing methods (Zou et al., 2023) in the last 15 years in object detection.”
Performance Comparison of MobileNet SSD and YOLO v4 in Object Detection
Manju, D., Gollapalli, B., Benarji, P. S., Pooja, K. S. M., & Made, A. (2024) · IEEE International Conference on Cybernetics, Cognition and Machine Learning Applications (ICCCMLA) · doi:10.1109/icccmla63077.2024.10871895 · Cited by 3
Mishchuk, V., & Podorozhniak, A. (2024) · IEEE KhPI Week on Advanced Technology (KhPIWeek) · doi:10.1109/khpiweek61434.2024.10878035 · Cited by 3
Optimizing Real-Time Object Detection in a Multi-Neural Processing Unit System
Oh, S., Kwon, Y., & Lee, J. (2025) · Sensors · doi:10.3390/s25051376 · Cited by 16
“Recent advancements in artificial intelligence have increased demand for real-time video analysis and object detection applications [1,2].”
Zhang, W., Shi, H., Qiu, J. W., et al. (2025) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2025.3547481 · Cited by 4
“L 2 loss is very sensitive to these outliers, and using L 2 loss to constrain the model generates overfitting [26].”
Wang, L., Yang, Z., & Gu, J. (2025) · Journal of Engineering Design · doi:10.1080/09544828.2025.2467003 · Cited by 3
Lightweight traffic sign detection algorithm based on improved YOLOv5 in snowy environments
Wang, Z., Qu, M., Wang, N., et al. (2025) · Signal Image and Video Processing · doi:10.1007/s11760-025-03998-9 · Cited by 3
“The deep learning based traffic sign recognition technique is mainly divided into one-stage detection and recognition algorithm [4] and two-stage detection and recognition algorithm [5].”
Bird Detection Method for Airport Perimeters Based on an Improved YOLOv8
Zhang, Y., & Shi, Y. (2024) · International Conference on Artificial Intelligence and Computer Engineering (ICAICE) · doi:10.1145/3716895.3716964 · Cited by 3
SPPNet: Single-Person Human Parsing and Pose Estimation in RGB Videos
Verma, A., Tiwari, V., & Lovanshi, M. (2025) · Journal of Social Computing · doi:10.23919/jsc.2024.0031 · Cited by 3
Dong, C., Zeng, H., Li, Y., et al. (2025) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2025.3558167 · Cited by 3
“Currently, object detection is a prominent research topic in computer vision, which has gained widespread attention and development in recent years [13].”
Enhancing Novel Object Detection via Cooperative Foundational Models
Bharadwaj, R., Naseer, M., Khan, S. A., & Khan, F. S. (2025) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61041.2025.00876 · Cited by 7
Deepfake Image Classification Using Decision (Binary) Tree Deep Learning
Alrajeh, M., & Al‐Samawi, A. (2025) · Journal of Sensor and Actuator Networks · doi:10.3390/jsan14020040 · Cited by 6
“Object detection: Object detection tasks in computer vision [17–21] have been a cornerstone of Artificial Intelligence (AI), with early works laying the foundation for object recognition and feature extraction using classical methods [22].”
Zhang, C., Qin, Q., Zhao, B., Yu, C., Wang, S., Chai, J. S., & Jiang, F. (2025) · Humanities and Social Sciences Communications · doi:10.1057/s41599-025-04936-3 · Cited by 6
Qi, S., Liu, B., Zhou, Y., Liu, P., Zhang, C. G., & Chen, S. (2025) · Image and Vision Computing · doi:10.1016/j.imavis.2025.105640 · Cited by 5
Sikdar, A., Igamberdiev, A. U., Sun, S., & Debnath, S. C. (2025) · Smart Agricultural Technology · doi:10.1016/j.atech.2025.101388 · Cited by 4
Development and Adaptation of Robotic Vision in the Real World: The Challenge of Door Detection
Antonazzi, M., Luperto, M., Borghese, N. A., & Basilico, N. (2025) · Journal of Field Robotics · doi:10.1002/rob.70084 · Cited by 8
“This conclusion is further supported by observing the significant performance improvements achieved when transitioning from training with iG to DD2 (among our training datasets, the one that maximizes photorealism).”
Face Mask Detection using Deep Learning to Manage Pandemic Guidelines
Singh, A., & Singh, P. (2021) · Journal of Management and Service Science (JMSS) · doi:10.54060/jmss/001.02.003 · Cited by 3
“[6] The algorithm applies a single neural network to the full image, and then divides the image into regions and predicts bounding boxes and probabilities for each region.”
MethodUnsupervised and Adaptive Perimeter Intrusion Detector
Lohani, D., Crispim-Junior, C. F., Barthélemy, Q., Bertrand, S., Robinault, L., & Tougne, L. (2022) · Proceedings - International Conference on Image Processing · doi:10.1109/icip46576.2022.9897472 · Cited by 3
“In the past few years, deep learning has shown tremendous achievements on video surveillance tasks like object detection [4], tracking [5], anomaly detection [6], etc.”
BackgroundJYOLO: Joint Point Cloud for Autonomous Driving 3D Object Detection
Tian, H., & Guo, L. (2022) · IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC) · doi:10.1109/icspcc55723.2022.9984261 · Cited by 3
“As the performance of hand-crafted features becomes saturated[5].”
BackgroundDeep Learning Based Real-time Visual Inspection for Harvesting Apples
Matsui, A., Iinuma, M., & Meng, L. (2022) · International Conference on Advanced Mechatronic Systems · doi:10.1109/icamechs57222.2022.10003376 · Cited by 3
“It uses image processing to detect objects and deep learning to determine the type of objects [13], [14].”
MethodA Lightweight Pedestrian Intrusion Detection and Warning Method for Intelligent Traffic Security
Yan, X., He, Z., Huang, Y., Xu, X., Wang, J., Zhou, X., Wang, C., & Lu, Z. (2022) · KSII Transactions on Internet and Information Systems · doi:10.3837/tiis.2022.12.007 · Cited by 4
Long-Tailed Metrics and Object Detection in Camera Trap Datasets
He, W., Luo, Z., Tong, X., Hu, X., Chen, C., & Shu, Z. (2023) · Applied Sciences · doi:10.3390/app13106029 · Cited by 8
Liao, B. H.-C., Cheng, C., Esen, H., & Knoll, A. (2024) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc58415.2024.10919937 · Cited by 5
“2 depicts, we transform them into the PV and BEV planes, which are easier to handle than the direct 3D world.”
InfluentialSpatio-temporal Attention Network for Student Action Recognition in Classroom Teaching VideosPreprint
Huang, Y., & Liang, M. (2021) · Research Square · doi:10.21203/rs.3.rs-1022972/v1 · Cited by 4
Er, M. J., Chen, J., Zhang, Y., & Gao, W. (2022) · doi:10.36227/techrxiv.19350389.v1 · Cited by 3
Biofouling Detection in Fish Farming Nets Using Neural NetworksPreprint
Paraskevas, K., & Kavallieratou, E. (2022) · SSRN Electronic Journal · doi:10.2139/ssrn.4144161 · Cited by 3
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.