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 1,401–1,500 of 3,144
Yolo-Mif: Improved Yolov8 with Multi-Information Fusion for Object Detection in Gray-Scale ImagesPreprint
Wan, D., Lu, R., Hu, B., et al. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4767026 · Cited by 3
Exploring deep learning strategies for intervertebral disc herniation detection on veterinary MRI
Huang, S., Deng, G., Kang, Y., Li, J., Li, J., & Lyu, M. (2024) · Scientific Reports · doi:10.1038/s41598-024-67749-5 · Cited by 3
Zhao, C., Ling, H., Guo, J., & He, Z. (2024) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2024.104269 · Cited by 2
Research on Object Detection Algorithm Based on Twin Attention and Adaptive Feature Fusion
Liu, Y., Luo, L., Wang, X., & Zheng, Y. (2024) · International Conference on Communications, Information System and Computer Engineering (CISCE) · doi:10.1109/cisce62493.2024.10653276 · Cited by 2
Multi-Scale Position-Aware Cell Nucleus Mask Attention for Tumor Budding Detection
Zhang, W., Lian, J., & Dong, B. (2024) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme57554.2024.10688170 · Cited by 3
“Liu et al. [19] conduct a [20].”
Multi-Scale Expression of Coastal Landform in Remote Sensing Images Considering Texture Features
Zhang, R., & Shen, Y. (2024) · Remote Sensing · doi:10.3390/rs16203862 · Cited by 2
Río-Álvarez, Á., Marcos, P. G., González, P. P., Serrano‐Pertierra, E., Novelli, A., Fernández‐Sánchez, M. T., & González, V. M. (2024) · Medical & Biological Engineering & Computing · doi:10.1007/s11517-024-03202-z · Cited by 2
High Quality Fire Smoke Dataset: A Benchmark for Fire and Smoke Detection
Qian, J., Hong, C., Zhang, K., & Huang, J. (2024) · International Workshop on Multimedia Content Generation and Evaluation: New Methods and Practice (McGE) · doi:10.1145/3688867.3690170 · Cited by 4
“Detectors during this period can be roughly divided into two categories: two-stage detectors and single-stage detectors[64].”
Inter-Class Correlation-Based Online Knowledge Distillation
Zhu, H., Gou, J., Du, L., & Ou, W. (2024) · Lecture notes in computer science · doi:10.1007/978-981-97-8487-5_14 · Cited by 2
Enhanced soft domain adaptation for object detection in the dark
Bai, Y., Liu, C., Yang, R., & Li, X. (2024) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2024.104337 · Cited by 2
Rao, K. M., Agrawal, D., Reyya, S., & Varma, P. (2024) · Lecture notes in electrical engineering · doi:10.1007/978-981-97-6714-4_6 · Cited by 3
Cui, J., Shi, J., Liu, C., Bai, S., Shu, X., Zuo, X., Qian, Q., Xu, D., & Deng, H. (2025) · Neurocomputing · doi:10.1016/j.neucom.2024.129215 · Cited by 5
ACTIVE: A Deep Network for Sperm and Impurity Detection in Microscopic Videos
Chen, A., Fan, F., Zhang, J., Rahaman, M. M., Li, R., Tao, J., Zeng, T., Grzegorzek, M., & Li, C. (2024) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm62325.2024.10822549 · Cited by 4
“…models have been proposed, such as Region-based Convolutional Neural Networks (RCNNs) [15], [17], You Only Look Once (YOLO) series [20], [21], Single Shot Multibox Detector (SSD) [22], and Effi-cientdet [26], which outperform classical image processing algorithms in most object detection tasks [27].”
Efficient Selective Pre-Training for Imbalanced Fine-Tuning Data in Transfer Learning
Chowdhury, S., Tisha, S. N., Rahman, M., & Hamerly, G. (2024) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata62323.2024.10825627 · Cited by 2
Object Detection Approaches to Identifying Hand Images with High Forensic Values
Nguyen, T. T., Wilson, C., Khan, I., & Dalins, J. (2024) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc54092.2024.10831640 · Cited by 3
“Artificial intelligence technologies such as object detection methods [8] can be used to locate and isolate fingerprints, palm prints, or other unique features within a hand image.”
Jin, C., Zheng, A., Wu, Z., & Tong, C. (2025) · International Journal of Machine Learning and Cybernetics · doi:10.1007/s13042-025-02582-4 · Cited by 3
“Although many targeted approaches have been proposed, recent studies [21, 23, 24] investigating the upper limits of object detection performance reveal a substantial room for improvement between the present achievements and the theoretical peak of detecting tiny objects.”
Ureña-Pliego, M., Marín, R. M., Shi, N., Shibayama, T., Leth, U., & Marchamalo, M. (2025) · Remote Sensing Applications Society and Environment · doi:10.1016/j.rsase.2025.101503 · Cited by 3
“Machine learning has seen extensive application in remote sensing and object detection over the last decade [13].”
Augmenting atmospheric turbulence effects on thermal-adapted deep object detection models
Uzun, E., & Akagündüz, E. (2025) · Scientific Reports · doi:10.1038/s41598-025-86830-1 · Cited by 4
“For a survey on the subject, readers may refer to 90,91 .”
Noise-Aware Evaluation of Object Detectors
Murrugarra-Llerena, J., & Jung, C. R. (2025) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61041.2025.00903 · Cited by 8
“The literature on object detection is vast, and a recent survey can be found in [34].”
Bai, F., Wei, R., Bai, X., Jin, D., Ye, X., Lü, L., Yan, K., & Meng, M. Q. ‐. (2025) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2025.3558861 · Cited by 3
SODU2-NET: a novel deep learning-based approach for salient object detection utilizing U-NET
Abbas, H., Ren, S. B., Asim, M., Hassan, S. I., & El‐Latif, A. A. A. (2025) · PeerJ Computer Science · doi:10.7717/peerj-cs.2623 · Cited by 2
“…of a saliency object detection model is a map that highlights the most salient regions, which can be useful for various computer vision tasks such as object recognition ( Zou et al., 2023 ), image segmentation ( Tajbakhsh et al., 2021 ), and attention-based visual recognition ( Yuan et al., 2022 ).”
VISLIX: An XAI Framework for Validating Vision Models with Slice Discovery and Analysis
Yan, X., Xuan, X., Ono, J. P., Guo, J., Mohanty, V., Shekar, A. K., Gou, L., Wang, B., & Ren, L. (2025) · Computer Graphics Forum · doi:10.1111/cgf.70125 · Cited by 7
“See [ZCS ∗ 23] for a complete survey.”
Huang, Q., Fan, C., Sun, Y., Huang, J., & Jiang, W. (2025) · IEEE Access · doi:10.1109/access.2025.3575952 · Cited by 2
“Recent significant advances [4] in object detection algorithms have been made, primarily driven by increased computational power and the rapid development of deep neural networks.”
Fan, J., Shen, J., Zhao, Z., Xu, G., & Wu, D. (2025) · Sensors and Actuators B Chemical · doi:10.1016/j.snb.2025.138123 · Cited by 2
Intelligent Building Fire Evacuation Indication System Based on Edge Computing Devices
Wang, P., Liu, J., Peng, Y., et al. (2024) · Asian Conference on Artificial Intelligence Technology (ACAIT) · doi:10.1109/acait63902.2024.11022193 · Cited by 2
“Commonly used object detection algorithms include the YOLO series [11, 12], known for their speed, real-time capability, and ease of deployment.”
STF-Net: a model for detecting transmission line fittings in UAV images
Lv, W., Nie, M., Yue, Y., et al. (2025) · Electrical Engineering · doi:10.1007/s00202-025-03198-1 · Cited by 2
“Traditional object detection techniques, which rely on hand-crafted features such as shape and texture, often struggle to maintain robustness when applied to aerial imagery with complex backgrounds [5].”
Chrintz-Gath, G., Daivadanam, M., Matta, L., & McKeever, S. (2025) · JMIR Formative Research · doi:10.2196/70124 · Cited by 4
“However, due to the limited quality of image representations at the time, no major models were constructed [5].”
GSTD-DETR: A Detection Algorithm for Small Space Targets Based on RT-DETR
Zhang, Y., Guo, H., Zhao, Y., Zhang, L., Luan, C., Li, Y., & Zhang, X. (2025) · Electronics · doi:10.3390/electronics14122488 · Cited by 2
Comparative analysis of attentional mechanisms in rice pest identification
Xiao, Y., Zhang, X., Chen, Z., et al. (2025) · Scientific Reports · doi:10.1038/s41598-025-08869-4 · Cited by 2
“The task of target detection is to accurately and efficiently identify and localize many object instances of predefined categories from an image 12 .”
Ren, D., Shu, X., Li, Y., et al. (2025) · International Journal of Computer Vision · doi:10.1007/s11263-025-02522-3 · Cited by 2
“1 : Misalignment issues in the pairs of ground-truth sharp image I S and defocus blurry image I B in DPDD [1], RealDOF [2] and our SDD datasets.”
Exploring the Synergies Between Industrial Green TFP and Circular Economy: A Systematic Review
Mushtaq, B., Halog, A., & Hussain, S. (2025) · Circular Economy and Sustainability · doi:10.1007/s43615-025-00645-w · Cited by 4
“…for geographical externalities and market imperfections, particularly in regions with significant industrial disparities such as Asia to raise concerns about measurement precision, especially in capturing the intricate interrelations between technological advancement and ecological factors [89 ].”
Computational intelligence in rock engineering management systems
Lenji, A. R., Mehmandari, T. A., Ranjbar, S., Tee, K. F., & Fahimifar, A. (2025) · Elsevier eBooks · doi:10.1016/b978-0-443-23663-1.00001-x · Cited by 3
CaMuViD: Calibration-Free Multi-View Detection
Daryani, A. E., Bhutta, M. U. M., Hernandez, B., & Medeiros, H. P. (2025) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52734.2025.00122 · Cited by 18
“Many state-of-the-art monocular object detection meth-ods adopt a two-stage approach [48].”
A Two-stage Faster R-CNN Approach for Road Surface Damage Detection
Le, V. T. V., Keivanmarz, A., & Sharifzadeh, H. (2025) · IEEE Annual Computers, Software, and Applications Conference (COMPSAC) · doi:10.1109/compsac65507.2025.00077 · Cited by 2
Sarı, F., & Sarvia, F. (2025) · Earth · doi:10.3390/earth6030107 · Cited by 3
Category-Aware Dynamic Label Assignment With High-Quality Proposals for Oriented Object Detection
Feng, M., Yu, H., Dang, X., & Zhou, M. Q. (2025) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2025.3607785 · Cited by 7
Al-Tarawneh, Z. A., Tarawneh, A. S., Mbaidin, A., et al. (2025) · Electronics · doi:10.3390/electronics14183705 · Cited by 2
Tao, T., Li, Z., Zhang, J., Yu, Y., Wang, P., Lv, A., Tang, M., & Xu, L. (2025) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2025.3612651 · Cited by 2
“With the rise of deep learning, significant progress has been made in object detection [10], [11].”
Wang, Q., Wang, Y., Ma, L., et al. (2025) · IEEE Access · doi:10.1109/access.2025.3616365 · Cited by 2
“As the foundation for automated information extraction, symbol recognition represents a typical computer vision target detection task [9], [10], [15].”
LA‐YOLO: Location Refinement and Adjacent Feature Fusion‐Based Infrared Small Target Detection
Liu, S., Luo, C., Yan, K., Qin, F., Ge, R., Peng, Y. K., Huang, J., Zheng, N., Zhang, Y., & Wang, C. (2025) · CAAI Transactions on Intelligence Technology · doi:10.1049/cit2.70070 · Cited by 5
Unified Open-Set Recognition and Novel Class Discovery via Prototype-Guided Representation
Dong, J., Wang, S., Xue, J., et al. (2025) · Applied Sciences · doi:10.3390/app152111468 · Cited by 2
Sha, P., Lu, S., Xu, Z., Yu, J., Li, L., Zou, Y., & Zhao, L. (2025) · Journal of Marine Science and Engineering · doi:10.3390/jmse13112124 · Cited by 3
“In the realm of ocean engineering applications, HBB techniques can be categorized into Convolutional Neural Network (CNN)-based and Transformer-based methodologies [12–14].”
ConvNextV2X: Road Microcrack Detection Algorithm Based on Improved Multiscale Feature Fusion
Xing, Y., Han, X., An, D., Yao, G., Shi, H., & Liu, W. (2025) · Journal of Computing in Civil Engineering · doi:10.1061/jccee5.cpeng-6358 · Cited by 2
ACS-YOLO: a lightweight bearing surface defect detection algorithm
Ding, L., Xu, H. M., Du, P., et al. (2025) · Journal of Engineering and Applied Science · doi:10.1186/s44147-025-00818-2 · Cited by 2
“Existing approaches can be boardly categorized into two categories: two-stage algorithms [2, 13–16] and one-stage algorithms [3–12].”
Zhong, Y., Wan, J., Cao, M., et al. (2025) · Scientific Reports · doi:10.1038/s41598-025-31043-9 · Cited by 2
TCQI-YOLOv5: A Terminal Crimping Quality Defect Detection Network
Yu, Y., Ren, D., & Meng, L. (2025) · Sensors · doi:10.3390/s25247498 · Cited by 2
“Additionally, bounding box localization shows deviations; the overlap between predicted and ground-truth boxes is suboptimal, especially for small targets like insulation edges [23,24].”
Visual SLAM in the era of heterogeneous intelligence coexistence: A survey
Su, S., He, X., Meng, X., Zhang, Y., Yin, W., Mo, L., & Yu, F. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.132458 · Cited by 4
Bai, Y., Li, Y., Di, R., Liu, J., Wang, X., Li, C., & gao, P. (2025) · Agriculture · doi:10.3390/agriculture16010035 · Cited by 2
“Currently, there are three ways to collect livestock data: through hardware [8], image-or video-based techniques [9], or a combination of both methods [10].”
Zhang, Q., Hang, Y., Zhang, H. D., Lu, X., & Qiu, J. (2025) · Scientific Reports · doi:10.1038/s41598-025-28677-0 · Cited by 2
Dong, X., Cappuccio, M. L., Alnajjar, F., Ali, L., Jassmi, H. A., Debie, E., Ghasrikhouzani, M., Lanteri, A., McGregor, T., Molloy, О., et al. (2025) · Journal of Field Robotics · doi:10.1002/rob.70108 · Cited by 32
Steindl, G., Baca, A., & Kornfeind, P. (2025) · Sensors · doi:10.3390/s26010190 · Cited by 2
“…is an increasingly popular field within Deep Learning (DL) and has applications in various fields such as autonomous vehicles, robotics, augmented reality, medical fields, security systems and in sports, including recent approaches that explore contextual and multimodal object understanding [1–3].”
CORAL-EMH: an enhanced multi-module framework for improved underwater object detection
ANTWI, S. A., Zhou, Z., & Enyan, M. (2025) · Engineering Research Express · doi:10.1088/2631-8695/ae3278 · Cited by 2
Generative adversarial translation of RGB to thermal infrared images for enhanced multimodal data
Zhu, H., Zhu, Q., Ding, K., Tang, H., & Li, Y. (2026) · Infrared Physics & Technology · doi:10.1016/j.infrared.2026.106367 · Cited by 3
Efficient Object Detection in Smart Cities Using a Lightweight DETR Model
Javaid, A., Sattar, M. U., & Ilchenko, O. (2025) · IEEE International Conference on Cloud Computing Technology and Science · doi:10.1109/cloudcom67567.2025.11331493 · Cited by 2
“Recent surveys have further summarized the trajectory of object detection, from classical handcrafted methods to CNN-based pipelines and more recent transformer-based models, underscoring open challenges in scalability, efficiency, and explainability [9], [11], [19], [20].”
Small PCB Defect Detection Based on Convolutional Block Attention Mechanism and YOLOv8
Sun, Z., Ma, R., & Lei, Q. (2026) · Applied Sciences · doi:10.3390/app16021078 · Cited by 5
“For PCBs, research has transitioned from early classification-based networks [20] to two-stage and one-stage detectors such as Faster R-CNN [21] and SSD [22].”
Robot Object Detection and Tracking Based on Image–Point Cloud Instance Matching
Wang, H., Zhu, R., Ye, Z., & Li, Y. (2026) · Sensors · doi:10.3390/s26020718 · Cited by 4
“With the rapid advancement of deep learning, object detection [1], instance segmentation [2], and multimodal perception techniques [3] have achieved substantial progress in the field of robotic perception.”
Reddy, S., Reddy, N. C., Kommidi, H. R., & Rajula, S. (2025) · International Conference on Communication and Electronics Systems (ICCES) · doi:10.1109/icces67310.2025.11337102 · Cited by 2
“Architectures like YOLOv5n, MobileNet-SSD, and EfficientDet-D0 prioritize minimal storage requirements, low-latency inference, and reduced energy consumption without excessively compromising detection accuracy [2].”
LDFENet: A Lightweight Dilated Feature Enhanced Network for SAR Ship Detection
Zheng, Y., Lang, F., Zhao, J., Chen, Z. D., & Wang, Z. (2026) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2026.3656551 · Cited by 4
“These factors can obscure target features and reduce image contrast, making it prone to false alarms or missed detections, especially in scenarios with densely distributed ships or low signal-to-noise ratios [14].”
Yu, C., & Shin, Y. (2026) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2026.3657379 · Cited by 5
Zia, M. B., Zhou, X., Gururajan, R., et al. (2026) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2026.110978 · Cited by 2
Using Machine Learning to Support Behavioral Data Analysis in Physical Education
Leukel, C., Leuders, T., & Ward, P. (2026) · Journal of Teaching in Physical Education · doi:10.1123/jtpe.2025-0392 · Cited by 5
Li, X., Hu, E., Xue, C., et al. (2026) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2026.3666275 · Cited by 2
“…approaches, deep learning-based methods can extract high-level semantic features from training data in an end-to-end manner so that the target can be e ff ectively separated from background [17], which has greater potential in IRSTD tasks facing complex and volatile scenarios [18], [19].”
Jo, S., & Cho, Y. (2026) · Cybersecurity · doi:10.1186/s42400-025-00477-z · Cited by 3
“Moreover, object detection includes classification tasks and is widely applicable across various domains (Zou et al. 2023; Redmon et al. 2016).”
Wang, Q., Ye, G., Li, F., Chen, Q., Jiang, J., Zhang, S., & Ullah, F. (2026) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2026.3665257 · Cited by 2
“However, the large number of parameters and high computational costs associated with YOLO models present a few challenges [6].”
An intelligent approach for early smoke/fire detection using vision sensors in smart cities
Abozeid, A., & Alanazi, R. (2026) · Scientific Reports · doi:10.1038/s41598-026-42762-y · Cited by 5
“This, therefore, calls for intelligent detection to give ample warnings with adequate accuracy while having zero false alarms within the challenging urban dynamic environment 14 .”
DeCenter: Density-Center Guided Perception Enhancement for UAV Object Detection
Shi, Z., Wu, Z., Wen, J., Li, M., Xiaopeng Fan, B., Wang, Y., & Shen, L. (2026) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2026.3672818 · Cited by 4
“Early meth-ods based on handcrafted features and traditional classifiers (e.g., Viola-Jones and HOG) make notable progress but are limited by weak feature representation and poor adaptability to complex scenes [13].”
Self-citationDTA-YOLO: A small sample transfer learning method for substation cabinet screw status detection
Zhang, T.-X., Xie, H., Liu, L., Wang, H., & Li, J.-Y. (2026) · Electric power systems research · doi:10.1016/j.epsr.2026.112790 · Cited by 3
Ren, J., Yang, C., & Miao, K. (2026) · Engineering Research Express · doi:10.1088/2631-8695/ae52a3 · Cited by 2
The use of the Simplex architecture to enhance safety in deep-learning-powered autonomous systems
Nesti, F., Salamini, N., Marinoni, M., Cicero, G., Serra, G., Biondi, A., & Buttazzo, G. (2026) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2026.114583 · Cited by 4
GEM-YOLO: A Lightweight and Real-Time RGBT Object Detector with Gated Multimodal Fusion
Wang, L., Bao, Z., & Lu, D. (2026) · Sensors · doi:10.3390/s26072035 · Cited by 6
Wang, Y., Zhang, Y., Li, X., & Chen, Z. (2026) · Measurement Science and Technology · doi:10.1088/1361-6501/ae5730 · Cited by 2
Abdulfattah, M. H., Sheikh, U. U., Othman, M. A., Khamis, N., & Shugaba, F. A. (2026) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2026.114619 · Cited by 2
An accurate, generalized, and efficient detection framework for steel surface defect inspection
Yan, H., Chen, L., Zhang, H., et al. (2026) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2026.114690 · Cited by 2
SST-YOLO: An Improved Autonomous Driving Object Detection Algorithm Based on YOLOv8
Du, Q., Zhang, N., Bi, W., Zhu, R., Liu, Y., Shen, C., Zhang, S., & Zhao, J. (2026) · Applied Sciences · doi:10.3390/app16073456 · Cited by 4
DSF-Net: A directional spatial-frequency fusion network for accurate metal surface defect detection
Zuo, Y., Qu, Z., Zhang, S.-S., Yu, Z., Cai, X., Yang, Y., Yang, Y., Jiang, X., & Lin, C. (2026) · Expert Systems with Applications · doi:10.1016/j.eswa.2026.132378 · Cited by 3
Silva, C. J. F., Del-Valle-Soto, C., Mostafa, S. M., & Varela-Aldás, J. (2026) · Algorithms · doi:10.3390/a19040249 · Cited by 3
Hybrid YOLOv5s-faster R-CNN detector for complex road-scene object detection
Byenkya, N. L., Rose, N., & Taremwa, D. (2026) · Discover Artificial Intelligence · doi:10.1007/s44163-026-01253-9 · Cited by 3
VCR: Variance-Driven Channel Recalibration for Robust Low-Light Enhancement
Cheng, Z., Zhang, F., Yin, X., Yin, B., & Wang, H. (2026) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2026.3689584 · Cited by 2
“As a fundamental preprocessing step, low-light enhancement can benefit a wide range of downstream vision tasks such as object detection [7], [8], [50], instance segmentation [51], and image matching [6], [9].”
Zhong, M., Zhou, Y., Wang, Y., Mei, Y., Zhang, Y., & Xue, H. (2026) · Applied Intelligence · doi:10.1007/s10489-026-07268-0 · Cited by 3
“However, the absence of a dedicated proposal mechanism makes them less effective at detecting small or overlapping objects [ 13 ].”
LWF-YOLO: a lightweight framework based YOLO for blood cell detection
Mao, R., Huang, D., Wu, Y., & Cai, B. (2026) · Biomedical Physics & Engineering Express · doi:10.1088/2057-1976/ae7d2f · Cited by 2
“While these early methods, often paired with classifiers like SVMs (Platt 1998), struggled with complex scenes (Zou et al 2023), convolutional neural networks (CNNs) have enabled robust, end-to-end feature extraction (Alzubaidi et al 2021).”
Negrini, J., Palade, V., Sedighi, T., & Daneshkhah, A. (2022) · Advances in Artificial Intelligence and Machine Learning · doi:10.54364/aaiml.2022.1121 · Cited by 4
Enhanced CT Image Generation by GAN for Improving Thyroid Anatomy Detection
Shi, J., Liu, X., Yang, G., & Wang, G. (2022) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm55620.2022.9995366 · Cited by 2
“The object detection task [10] is to find objects of interest in an image or video and detect their position and size at the same time.”
BackgroundPemanfaatan Algoritma Faster R-CNN ResNet-101 Untuk Deteksi Potongan Tubuh Manusia
Hanun, N., Sarosa, M., & Asmara, R. A. (2023) · Jurnal Elektronika dan Otomasi Industri · doi:10.33795/elkolind.v10i1.2754 · Cited by 5
“Model deteksi yang memberikan kinerja tinggi dan akurasi untuk data citra memberrikan solusi pada permasalahn seperti pengawasan, deteksi wajah, dan lain – lain [4] .”
BackgroundFeature Attention as a Control Mechanism for the Balance of Speed and Accuracy in Visual Search
Griffith, T., Townend, F. J., Baker, S.-A., & Lepora, N. F. (2023) · Computational Brain & Behavior · doi:10.1007/s42113-023-00171-8 · Cited by 2
“Traditional computer vision methods for visual search, such as instance segmentation and object detection, require meticulously labelled training data sets to localise objects in images (Hariharan et al., 2014; Dai et al., 2016; Zou et al., 2023).”
Semantic‐guided fusion for multiple object tracking and RGB‐T tracking
Liu, X., Luo, Y., Zhang, Y., & Lei, Z. (2023) · IET Image Processing · doi:10.1049/ipr2.12861 · Cited by 2
NamGung, D.-H., & Kim, D. (2023) · Journal of Digital Contents Society · doi:10.9728/dcs.2023.24.7.1575 · Cited by 2
A Flexible Machine Vision AI System for Edge-Oriented Deep Learning Accelerators
Song, J. B., Kim, Y.-M., Lee, M., et al. (2023) · International Technical Conference on Circuits/Systems, Computers and Communications (ITC-CSCC) · doi:10.1109/itc-cscc58803.2023.10212811 · Cited by 2
Dutra, E. F., de Oliveira, T. R. C., & Rodriguês, M. A. F. (2023) · SeGAH ... IEEE ... International Conference on Serious Games and Applications for Health/IEEE International Conference on Serious Games and Applications for Health · doi:10.1109/segah57547.2023.10253813 · Cited by 3
“Essential information, such as the bounding geometries of objects of interest, which demarcate their location within the environment [3], [4], is typically either not included or inadequately represented in these datasets.”
BackgroundIqbal, N., Niemeyer, M., Krause, J. C., & Hertzberg, J. (2023) · European Conference on Mobile Robots · doi:10.1109/ecmr59166.2023.10256352 · Cited by 3
Improved YOLOv4-Based Object Detection Method for UAVs
Ke, H., Zhang, F., Yafeng, S., et al. (2023) · doi:10.1109/icsip57908.2023.10270983 · Cited by 2
“…enemy drones or preventing "black flight" and "indiscriminate flight" of civil drones from causing public safety risks, etc., meanwhile, fast and efficient object detection is an important part of the anti-UAV system, as well as the most basic and challenging task in computer vision tasks [1].”
BackgroundFu, S.-Y., Wei, D., & Zhou, L.-Y. (2023) · Communications in computer and information science · doi:10.1007/978-981-99-7593-8_5 · Cited by 2
Ding, N., Bao, X., Sun, S., & Wang, Y. (2023) · International Journal of Imaging Systems and Technology · doi:10.1002/ima.22999 · Cited by 2
“According to the survey paper, 17,18 after the introduction of regions with CNN features (R-CNN) by Girshick et al., 19 object detection entered the deep learning-based detection era and witnessed unprecedented advancements.”
BackgroundPerson Identification with Voice and Ear-print in Degraded Conditions for Smart Home Access
Boujnah, S., Ferjaoui, R., & Khalifa, A. B. (2023) · International Conference on Cyberworlds (CW) · doi:10.1109/cw58918.2023.00071 · Cited by 3
“The first successes of this theory emerged during the 1980s with the development of high capacity calculators [4].”
BackgroundShort-term Power Load Forecasting Based on a New Efficient Deep Learning Framework
Wang, L. (2023) · Academic Journal of Computing & Information Science · doi:10.25236/ajcis.2023.061102 · Cited by 2
“Deep learning methodologies, including convolutional neural networks, recurrent neural networks, and self-attention mechanisms, have demonstrated remarkable capabilities in various domains such as image recognition [4] , object detection [5] , and natural language processing [6] .”
BackgroundMohammadi, H., Thirunarayan, K., & Chen, L. (2023) · Sensors · doi:10.3390/s23249893 · Cited by 2
Rotating Object Detection for Cranes in Transmission Line Scenarios
Xia, L., Cao, S., Yang, C., Niu, L., Zhang, J., & Bao, H. (2023) · Electronics · doi:10.3390/electronics12245046 · Cited by 3
Feng, Z. H., Dong, C., Xu, X., Liu, Y., & Wang, S. (2023) · 3D Printing and Additive Manufacturing · doi:10.1089/3dp.2023.0208 · Cited by 5
“30 The network architecture consists of a backbone network, neck, and a detection head, as shown in Figure 9.”
Adversarial example generation for object detection using a data augmentation framework and momentum
Ding, Z., Sun, L., Mao, X., et al. (2023) · Signal Image and Video Processing · doi:10.1007/s11760-023-02924-1 · Cited by 2
“Object detection is also a fundamental element in computer vision research and forms the basis for advanced tasks such as instance segmentation, object tracking, and image description [21].”
Mögliche Einsatzgebiete von Künstlicher Intelligenz im Verlagswesen: Zur Einführung
Klotz, D. (2024) · Springer eBooks · doi:10.1007/978-3-658-43037-5_1 · Cited by 3
Tumor detection based on deep mutual learning in automated breast ultrasound
Li, Y., Zhang, Z., Sun, J., et al. (2024) · Multimedia Tools and Applications · doi:10.1007/s11042-024-18377-8 · Cited by 2
“According to whether the anchor is pre-set or not, the regression-based methods contain two types: anchor-based and anchor-free [21].”
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.