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 1,701–1,800 of 3,144
Data-Driven Anchor Box Optimization Using Genetic Algorithm
Nam, E., Wang, S., & Kim, W. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-0692-4_35 · Cited by 1
Estimation of Object Grounding Surface Using RGB-D Cameras
Natori, N., Iwasawa, H., Mikuriya, M., Ogino, F., & Nakayama, Y. (2025) · IEEE Sensors Journal · doi:10.1109/jsen.2025.3541254 · Cited by 1
“D object detection has emerged as a prominent research area, driven by its growing relevance in applications such as autonomous driving and robotics [25], [26].”
Improved YOLOv8 algorithm for student behavior detection in a smart classroom
He, L., & Han, P. (2024) · doi:10.1109/icairc64177.2024.10900276 · Cited by 1
“Object detection represents a fundamental task in the field of computer vision, with the objective of identifying and locating specific classes of objects within an image or video sequence [3].”
AILDP: a research on ship number recognition technology for complex scenarios
Wei, T., Hu, Z., Zhao, Y., & Fan, X. (2025) · Complex & Intelligent Systems · doi:10.1007/s40747-025-01820-0 · Cited by 1
“The task not only requires the sys-tem to effectively deal with the tiny size of the target, but Over the past 2 decades, the progress of target detection can be roughly categorized into two phases: the “traditional object detection period” and the “deep learning based detection period” [16].”
Safarzadehvahed, M., Zulkernine, M., de Araujo, P. R. M., & Givigi, S. N. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3550048 · Cited by 1
“This limitation stems from the fundamental purpose of vision-based object detection algorithms, which revolves around accurately identifying all objects, irrespective of their authenticity [62].”
GDP-YOLO: Incorporating Gather-and-Distribute Mechanism into Pruning Strategy for Object Detection
Yuan, Z., Zhang, F., Tang, P., et al. (2024) · doi:10.1145/3700003.3700008 · Cited by 1
TrainNet for locking state recognition of side door of railway freight car
Xing, N., Kangcheng, C., Shumin, Z., et al. (2025) · International Journal of Advanced Robotic Systems · doi:10.1177/17298806251326420 · Cited by 1
CSS-YOLOv8: an efficient detection model for printed circuit boards with tiny defects
Li, S., Wang, W., & Lu, Q. (2025) · Engineering Research Express · doi:10.1088/2631-8695/adc542 · Cited by 1
Oladive, K. A., Alampay, R., & Abu, P. A. R. (2024) · International Conference on Control and Robotics (ICCR) · doi:10.1109/iccr64365.2024.10927516 · Cited by 1
SD-YOLOv8: SAM-Assisted Dual-Branch YOLOv8 Model for Tea Bud Detection on Optical Images
Zhang, X., Wu, D., & Xu, F. (2025) · Agriculture · doi:10.3390/agriculture15070712 · Cited by 1
Accurately Estimate and Analyze Human Postures in Classroom Environments
Shou, Z., YU, Y., Li, D., Mo, J., Zhang, H., Zhang, J., & Wu, Z. (2025) · Information · doi:10.3390/info16040313 · Cited by 4
Improving Plastic Waste Segregation with Deep Learning Techniques
Kumar, E. S., Mehta, Z., & Basu, D. (2024) · doi:10.1109/i3ceet61722.2024.10994048 · Cited by 1
A Novel Deep Learning-Based Compressed Image Enhancement Method for Machine Consumption
Ma, Z., Paul, F., Zhang, S., Chen, H., Tohidypour, H. R., & Nasiopoulos, P. (2025) · 2012 International Conference on Computing, Networking and Communications (ICNC) · doi:10.1109/icnc64010.2025.10993636 · Cited by 2
“Many modern applications such as object detection [4], image classification [5], and autonomous driving systems [6] rely on visual data to perform critical tasks.”
Deep Learning Based Supermarket Product Detection and Recognition with Rectified Images
Sah, M., & Mathew, J. (2025) · Procedia Computer Science · doi:10.1016/j.procs.2025.03.287 · Cited by 1
Deep Learning-Based Algorithm for Robust Object Detection in Flooded and Rainy Environments
Wang, P., Sun, J., Lu, L., Li, H., Liu, H., Xu, C., & Liu, Y. (2025) · Computers, materials & continua/Computers, materials & continua (Print) · doi:10.32604/cmc.2025.065267 · Cited by 3
“In this study, to quantify the performance of vehicle detection algorithms in flooding scenarios, three standard performance evaluation metrics are used: Precision, Recall, and mean Average Precision (mAP) [25].”
Lan, N. T., Tran, C. T., Dang, N. H., & Toi, T. T. (2024) · RIVF International Conference on Computing and Communication Technologies (RIVF) · doi:10.1109/rivf64335.2024.11009090 · Cited by 1
“These challenges are exacerbated by the high resolution and complexity of remote sensing images, requiring a careful balance between computational efficiency and detection accuracy [5] [21].”
Zocco, F., Lake, D. R., McLoone, S., & Rahimifard, S. (2025) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2025.3574911 · Cited by 8
“The second period is ongoing and is based on the end-to-end deep learning of features [15].”
Anchor-Free SNR-Aware Signal Detector for Wideband Signal Detection Framework
Li, C., Xiang, X., Hu, M., et al. (2025) · Electronics · doi:10.3390/electronics14112260 · Cited by 1
Hybrid Tunnel Entrance Detection via Multiple Morphological Component-Based Texture Enhancement
Huang, H., Chen, J., Chen, T., Li, J., & Plaza, A. (2025) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2025.3577214 · Cited by 1
“A MONG remote sensing imagery (RSI) analysis techniques, object detection (OD) involves analyzing image data to accurately identify and locate specific objects or entities [1].”
VIL-PPGen: A Novel Pseudo Point Generator Based on Visible Light Camera, Infrared Camera and Lidar
Ai, F., Amjad, H., Li, Z., Song, Y., Song, C., & Xu, Z. (2025) · IEEE Transactions on Intelligent Vehicles · doi:10.1109/tiv.2024.3511923 · Cited by 1
“O BJECT detection [1] is a fundamental task in the field of perceptiontechnology,withdiverseapplicationsspanning autonomous driving [2], [3], [4], augmented reality [5], smart cities [6] and other domains.”
A Lightweight Network for Vehicle and Pedestrian Object Detection in Autonomous Driving Scenarios
Zhu, Y., Zhang, Y., & Sun, K. (2025) · International Journal of Image and Graphics · doi:10.1142/s0219467827500434 · Cited by 1
A Cloud-Edge Collaborative Framework for Object Detection Using Kubeedge
Qing, C., Zhang, L., Gao, Y., & Zhang, W. (2025) · International Conference on Cloud Computing and Big Data Analytics (ICCCBDA) · doi:10.1109/icccbda64898.2025.11030479 · Cited by 1
Solving the Lunar Lander Problem with Spiking Neural Networks and One-Hot Encoding
Hansert, J., Offermann, P., & Gechter, F. (2025) · IFIP advances in information and communication technology · doi:10.1007/978-3-031-96239-4_3 · Cited by 1
Behavioral Anomalies Detection via Human Pose Estimation: A Study on Cheating Detection
Doshi, V., Sheikh, D., Sharma, N., et al. (2025) · Lecture notes in networks and systems · doi:10.1007/978-981-96-2179-8_26 · Cited by 1
Exploring Objectness Information via Progressively Decoupled Adaptation for Cross-Domain Detection
Ge, Y., Liu, H., Shang, E., Du, J., Zhao, J., & Niu, Z. (2025) · International Conference on Multimedia Retrieval · doi:10.1145/3731715.3733333 · Cited by 2
“It is crucial in various applications, including multimedia retrieval, autonomous driving, and surveillance [9, 58].”
A Multi-Scale Unsupervised Feature Extraction Network with Structured Layer-Wise Decomposition
Günaydın, Y. Ş., & Şen, B. (2025) · Applied Sciences · doi:10.3390/app15137194 · Cited by 1
Small Target Detection Algorithm for UAV aerial images based on YOLOv8s-SSB
Wang, J., & Qi, J. (2024) · doi:10.1145/3703935.3704034 · Cited by 1
Learning Case Features with Proxy-Guided Deep Neural Networks
Vats, V., Wilkerson, Z., Sato, H., Leake, D. B., & Crandall, D. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-96559-3_21 · Cited by 1
Recycling/upcycling graphic design: automatic design elements extraction and vectorization
Qu, H., Chau, K. P., & Mok, P. Y. (2025) · The Visual Computer · doi:10.1007/s00371-025-04039-9 · Cited by 1
“State-of-the-art (SOTA) object detection methods are supervised learning based [15, 16], where pixels in natu-ral scene images are labeled with known categories such as road, mountain, sky, and sea.”
MRTMD: A Multi-Resolution Dataset for Evaluating Object Detection in Traffic Monitoring Systems
Bugeja, M., Bartolo, M., Montebello, M., & Seychell, D. (2025) · IEEE Access · doi:10.1109/access.2025.3585986 · Cited by 1
“Computer vision, particularly object detection, has witnessed remarkable advancements in recent years, primarily driven by the development of deep learning techniques [5].”
Bilozerskyi, V., Dergachov, K., & Hurtovyi, O. (2025) · Lecture notes in networks and systems · doi:10.1007/978-3-031-94845-9_7 · Cited by 1
Exploiting Gaussian based effective receptive fields for object detection
Qi, X., Johar, M. G. M., Khatibi, A., & Tham, J. (2025) · Scientific Reports · doi:10.1038/s41598-025-10548-3 · Cited by 4
Anchor-Free Signal Detector Based on Center Frequency Axis Learning in Wideband Spectrogram
Li, C., Xiang, X., Li, Q., et al. (2025) · IEEE Wireless Communications Letters · doi:10.1109/lwc.2025.3589489 · Cited by 1
“To our knowledge, only limited efforts [1], [14] have attempted anchor-free detectors to eliminate anchors, all adopting a keypoint prediction fashion [15].”
Dual radar vision: A feature fusion approach for advanced object detection in IoT radar networks
Reitz, P., Veihelmann, T., Franchi, N., et al. (2025) · Machine Learning with Applications · doi:10.1016/j.mlwa.2025.100703 · Cited by 1
Li, T., Li, N., & Nie, Y. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-9869-1_8 · Cited by 1
Cross-modality-enhanced visual Scene Graph Generation
Yu, F., Ji, H., & Li, Y. (2025) · Information Fusion · doi:10.1016/j.inffus.2025.103430 · Cited by 3
Designing a Lightweight Network for Object Detection in Drone-Based Surveillance
Rastogi, A., Aggarwal, Y., & Guha, P. (2025) · Communications in computer and information science · doi:10.1007/978-3-031-93694-4_16 · Cited by 1
Detecting Planting Holes Using Improved YOLO-PH Algorithm with UAV Images
Long, K., Jiangping, L., Chao, F., Lin, H., Hui, L., & Yang, Y. (2025) · Remote Sensing · doi:10.3390/rs17152614 · Cited by 1
Chen, Q., Liu, R., Yan, Q., Xu, Y., Liu, Y., Huang, X., & Zhang, Y. (2025) · Remote Sensing · doi:10.3390/rs17152627 · Cited by 2
Vision-based detection of bent circular tubes with ball joints
Xu, X., Ren, J., Dong, G.-S., et al. (2025) · Structural Health Monitoring · doi:10.1177/14759217251351556 · Cited by 1
Tang, X., Deng, H., & Dong, L. (2025) · Measurement · doi:10.1016/j.measurement.2025.118619 · Cited by 1
Assessing the Object-Detection Skills of Modern Vision Language Models
Fernández, P. T., García, L. D., Mendes, A. S., & Murciego, Á. L. (2025) · Advances in intelligent systems and computing · doi:10.1007/978-3-031-99474-6_26 · Cited by 1
Ji, J., Zhao, Y., Zhang, Y., Zuo, X., Wang, C., & Shi, F. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2025.3596581 · Cited by 2
“O BJECT detection, as a core task in the field of computer vision, has the core mission of accurately identifying and locating object instances in images or videos [1], [2].”
Integrating Camera Technology and Sound Frequencies to Mitigate Wildlife-Caused Crop Damage
Arun, R., Usha, L. J., Sharma, A., & Jha, L. (2025) · International Conference on Emerging Technologies in Engineering Applications (ICETEA) · doi:10.1109/icetea64585.2025.11099772 · Cited by 1
“Moreover, while promising for certain types of pests, they may not be effective against larger or more resilient wildlife species that threaten crop fields[10-15].”
Uses of Metaverse Recordings in Multimedia Information Retrieval
Steinert, P., Wagenpfeil, S., Frommholz, I., & Hemmje, M. (2025) · Multimedia · doi:10.3390/multimedia1010002 · Cited by 1
GEE-UOD: An Underwater Object Detection Network Based on Global and Edge Information Enhancement
Na, W., Wang, Y., Xu, C., et al. (2025) · Proceedings - International Conference on Image Processing · doi:10.1109/icip55913.2025.11084525 · Cited by 1
Fine-Grained Spatial-Temporal Perception for Gas Leak Segmentation
Zhao, X., & Du, S. (2025) · Proceedings - International Conference on Image Processing · doi:10.1109/icip55913.2025.11084304 · Cited by 3
“Recently, deep-learning techniques have shown robustness in object segmentation [4].”
The Motion Picture: Leveraging Movement to Enhance AI Object Detection in Ecology
Maslen, B., Popovic, G. C., Wang, D., Jansen, A., & Warton, D. I. (2025) · Ecology and Evolution · doi:10.1002/ece3.71996 · Cited by 3
Managing Computation Offloading from Edge Devices to a Reconfigurable Edge Cloud
Zhang, Z., Madabhushi, B., Kundu, S. K., & Tessier, R. (2025) · IEEE International Conference on Application-specific Systems, Architectures and Processors (ASAP) · doi:10.1109/asap65064.2025.00029 · Cited by 1
“A. Applications and Datasets 1) Applications: We consider two classes of edge device-based applications: ( i ) image classification [31], ( ii ) and object detection [32].”
Xu, X., Zhang, H., Lu, J., et al. (2025) · Plant Methods · doi:10.1186/s13007-025-01433-1 · Cited by 1
Chen, X., Xu, S., Hu, S., & Ma, X. (2025) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2025.3596132 · Cited by 2
Ferreira, G., Viveiros, J. M. S. M., Santoro, G. B., et al. (2025) · Journal for Nature Conservation · doi:10.1016/j.jnc.2025.127066 · Cited by 1
Efficient Object Detection Using Total Energy Function: An Alternative to Anchor Box
Dang, D. T., Nguyen, K. T., & Huynh, H. X. (2025) · International Conference on Intelligent Information Technology (ICIIT) · doi:10.1145/3731763.3731782 · Cited by 1
“This evolved to deep learning [4, 5], which utilized CNN networks and region proposals achieving 0.89 mAP, followed by the modern era with anchor-based methods [6], which introduced Region Proposal Networks (RPN) integrated with CNN, improving both speed and accuracy .”
InfluentialComputer Vision-Based Environmental Perception for a Collaborative Robot
Rieder, J. S. I., Kollmann, D., Khoury, R. E., & Aschenbrenner, D. (2025) · IFIP advances in information and communication technology · doi:10.1007/978-3-032-03515-8_38 · Cited by 1
Aircraft Detection Based on Improved YoloV11
Zhang, C., & Wang, R. (2025) · International Conference on Computer Information and Big Data Applications (CIBDA) · doi:10.1145/3746709.3746872 · Cited by 1
Identification of Facial Countenance Established by Local Monotonic Pattern and Support Vector
Kshatri, S. S., Prasad, S., Bhagat, P. N., et al. (2024) · International Conference on Innovative Sustainable Computational Technologies (CISCT) · doi:10.1109/cisct62494.2024.11134267 · Cited by 1
“Even though the significance of facial expressions is poised to increase further, the two most common computer vision approaches for facial expression recognition [3] are incredibly different.”
Region-aware unknown information enhancement for open world object detection
Su, S., Wang, C., Zhu, Y., & Xu, Y. (2025) · Cluster Computing · doi:10.1007/s10586-025-05161-y · Cited by 1
Jin, H., Chen, J., Zhang, Y., Su, H., & Wang, B. (2025) · Remote Sensing · doi:10.3390/rs17173029 · Cited by 1
Sun, M., Liu, P., Han, X., et al. (2025) · Signal Image and Video Processing · doi:10.1007/s11760-025-04593-8 · Cited by 1
“Image processing techniques typically utilize threshold segmentation, edge detection, and other methods for preliminary screening [1 , 2 , 3].”
A Novel Underwater Blurred Target Detection Algorithm Based on RT ‐ DETR
Chen, X., Ge, X., Yang, Q. Z., & Wang, H. (2025) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.70267 · Cited by 1
Li, M.-D., Xiao, S., & Chen, S.-W. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2025.3607102 · Cited by 1
“Four commonly used evaluation criteria [62] are employed to assess the accuracy and completeness of the recognition Authorized licensed use limited to the terms of the applicable license agreement with IEEE.”
CrackNet-Weather: An Effective Pavement Crack Detection Method Under Adverse Weather Conditions
Wang, W., Yu, X., Jing, B., Tang, Z., Zhang, W., Wang, S., Xiao, Y., Li, S., & Yang, L. (2025) · Sensors · doi:10.3390/s25175587 · Cited by 3
“Object detection constitutes a cornerstone of computer vision research and continues to evolve rapidly, which is propelled by the growing demand for high-precision and real-time automated inspection systems [21,22].”
Discriminative Latent-Space Learning for Fine-Grained Object Detection in Remote Sensing Images
Liu, Y., Hu, X., Liu, W., Wang, X., Chen, C., Wan, P., Jiang, Y., & Zhong, P. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2025.3608706 · Cited by 3
“It has achieved rapid technological evolution and has profoundly impacted the entire computer vision field [16].”
Gilpin, Y., Lin, C.-Y., & Dandin, M. P. (2025) · Review of Scientific Instruments · doi:10.1063/5.0271101 · Cited by 1
Barbier, C., Abeloos, B., & Herbin, S. (2025) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw67362.2025.00288 · Cited by 1
“Object detection typically involves two main sub-tasks: localization and classification of target objects [33].”
Fusion or Confusion? A Look at Dataset Pooling for Infrared Object Detection
Becker, S., Grosselfinger, A.-K., Bayer, J., Münch, D., Hübner, W., & Arens, M. (2025) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw67362.2025.00428 · Cited by 2
“For a more detailed description of the reference detector, we refer to the original paper [35] and for a comparison to other YOLO variants or alternative detection approaches to these surveys [14, 21, 34, 36, 37, 42, 43].”
An Attention-Enhanced YOLOv8 Architecture for Leakage Detection in Building Systems
Yang, K., Tan, M., Liao, H., Azucena, J., Yuan, J., & Ham, R. (2025) · Journal of Performance of Constructed Facilities · doi:10.1061/jpcfev.cfeng-5264 · Cited by 1
Chen, J., Liu, B., & Zuo, H. (2025) · Journal of Intelligent Manufacturing · doi:10.1007/s10845-025-02684-4 · Cited by 1
Kong, L. (2025) · IEEE Joint International Information Technology and Artificial Intelligence Conference (ITAIC) · doi:10.1109/itaic64559.2025.11163094 · Cited by 1
“Compared to traditional methods, object detection algorithms based on neural networks possess more parameters and can characterize and describe more complex features [3].”
ERBW-bolt: A high-accuracy model for train underbody bolts detection in complex background
Yang, Y., Zong, J., Dong, H., et al. (2025) · Transactions of the Institute of Measurement and Control · doi:10.1177/01423312251364330 · Cited by 1
“The object detection technology based on deep learning has been widely used, which can be divided into two-stage detection and one-stage detection (Zou et al., 2023).”
Vessel detection leveraging satellite imagery and YOLO in maritime surveillance
Magalhães, R., Falcão, A. P., & Barbosa, A. (2025) · Remote Sensing Applications Society and Environment · doi:10.1016/j.rsase.2025.101730 · Cited by 3
Machine learning-aided differential-linear attacks with applications to Des and Speck32/64
Hou, Z., Ren, J., & Chen, S. (2025) · Journal of King Saud University - Computer and Information Sciences · doi:10.1007/s44443-025-00241-w · Cited by 1
Enhancing Tomato Leaf Disease Detection with Deep Learning and Augmentation Techniques
Tarek, S., & Hamdi, A. (2025) · Intelligent Methods, Systems, and Applications (IMSA) · doi:10.1109/imsa65733.2025.11167453 · Cited by 1
“Among deep learning techniques [7], object detection [8] models such as the You Only Look Once (YOLO) [9] family and the Real-Time Detection Transformer (RT-DETR) [10] have shown remarkable performance in real-time applications been adapted to tomato disease datasets, yielding better accuracy with…”
Instance mask alignment for object detection knowledge distillation
Guo, Z., Zhang, P., & Liang, P. (2025) · Scientific Reports · doi:10.1038/s41598-025-03100-w · Cited by 3
Matalia, K., Patel, D., Kheni, H., Patel, H., Navadiya, K., & Rahevar, M. L. (2025) · Lecture notes in networks and systems · doi:10.1007/978-981-96-4536-7_9 · Cited by 1
A deep learning-based pin precision weeding machine with densely placed needle nozzles
Jin, H., Arsa, D. M. S., Ilyas, T., Lee, J., Won, O., Park, S.-H., Sandesh, K., Kim, S. C., & Kim, H. (2025) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2025.110990 · Cited by 2
Global impact and thematic evolution of object detection in the deep learning era
Roslin, A. H., & Muhammad, N. (2025) · Discover Artificial Intelligence · doi:10.1007/s44163-025-00528-x · Cited by 1
“Zou et al. [2] assembled principal ODM milestones, datasets, evaluation metrics, break-throughs and research trends.”
InfluentialADA-Net: A Lightweight Model for Apple Flower Maturity Detection in Horticultural Plant Monitoring
Xu, R., Jia, W., Yan, J., et al. (2025) · IEEE Transactions on AgriFood Electronics · doi:10.1109/tafe.2025.3615644 · Cited by 1
“…enhancing the model’s stability and accuracy across various scenarios, and the deep learning model demonstrates stronger generalization ability by adapting to different lighting conditions, backgrounds, and object shapes, which leads to improved detection precision and robustness [18], [19].”
Xuan, J., Li, X., Mao, F., Wang, J., Zhang, B., Gong, Y., Huang, Z., Chen, C., Lv, L., Zhao, Y., et al. (2025) · Urban forestry & urban greening · doi:10.1016/j.ufug.2025.129119 · Cited by 1
A road damage detection model based on improved YOLOv11s
Ma, H., & Dong, J. (2025) · Engineering Research Express · doi:10.1088/2631-8695/ae1279 · Cited by 1
Zhao, Y., Li, Z., Jin, Z. G., Zhang, F., Wang, Z., Wu, L., Dou, C., Zhao, H., & Xu, X. (2025) · Science China Information Sciences · doi:10.1007/s11432-024-4416-8 · Cited by 4
Continual Learning for Multimodal Data Fusion of a Soft Gripper
Kushawaha, N., & Falotico, E. (2025) · Advanced Robotics Research · doi:10.1002/adrr.202500126 · Cited by 2
DSRIR: Dynamic spatial refinement learning for progressive all-in-one image restoration
Wang, X., Liu, X., Yang, Y., Wang, Z., He, X., Chen, H., Li, Y., & Wang, P. (2025) · Information Processing & Management · doi:10.1016/j.ipm.2025.104380 · Cited by 4
Jin, Y., Liu, X., & Liu, J. (2025) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3746027.3758149 · Cited by 3
“In this method, task-specific models, such as object detection [79] or scene classification [7], are applied to both the original and reconstructed content.”
Pei, G., Ma, K., Zhang, D., Sun, C., Xu, Q., & Huang, Q. (2025) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3746027.3761985 · Cited by 3
“Deep neural networks (DNNs), despite their superior performance across diverse tasks [22, 26, 32, 41], remain highly vulnerable to adversarial examples—inputs crafted by adding imperceptibly small perturbations that can cause models to make erroneous predictions [1, 4, 11, 20, 30].”
Progressive Representation Learning for Weakly-Supervised Camouflaged Object Detection
Gao, S., Guo, Q., Feng, Y., Chen, C., Wei, X., Wang, Y., & Zhang, W. (2025) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3746027.3754737 · Cited by 5
“Unlike traditional object detection [47] and semantic segmentation [22] , COD presents unique challenges because camou-flaged objects are intentionally designed to blend indistinguish-ably into their surroundings.”
Aligned Pseudo Feature Generation for Zero-Shot Object Detection
Dai, X., Li, Z.-H., Wang, C., Lu, Y., Chen, Y., Qian, J.-B., & Wu, J.-F. (2026) · IEEE Transactions on Cognitive and Developmental Systems · doi:10.1109/tcds.2025.3625782 · Cited by 1
“O BJECT detection [1], [2], [3], [4], [5], as one of the three main tasks in computer vision, has wide applications in various fields.”
Zhang, X., Chen, Y., Yao, R., et al. (2025) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme59968.2025.11210191 · Cited by 1
“The core idea of this loss function is that we regard the localization and detection on the 2D plane as a task like object detection [27], [28].”
Ocholla, I. A., Heiskanen, J., Karanja, F., Boitt, M. K., & Pellikka, P. (2025) · ISPRS Open Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.ophoto.2025.100106 · Cited by 2
AI-Driven PPE Detection and Human Access Monitoring in Manufacturing Zones for Safety Compliance
Kumar, K., Verma, K., Tiwari, N., et al. (2025) · doi:10.1109/icoeit63558.2025.11211593 · Cited by 1
Deep Learning for Recognition of Object Manipulation Hand Gestures using Wearable Sensor Data
Sharples, J., & Martínez-Hernández, U. (2025) · IEEE RO-MAN · doi:10.1109/ro-man63969.2025.11217817 · Cited by 1
“For example, computer vision may be susceptible to occlusion and changes in lighting conditions [4], while wearable sensors may be less effective if any of them compromised due to prolonged use, as wearable sensors are susceptible to factors such as sweat and muscle fatigue impairing readings over…”
Liang, D., Zhang, H., Yao, Z., et al. (2025) · doi:10.1109/mcte67374.2025.11213772 · Cited by 1
“To address these challenges, researchers have explored various strategies, including hardware optimization [12], feature selection [13], algorithmic optimization [14], model compression [15], and lightweight model design [16].”
You, D., Bingbing, Z., Lei, D., & Mao, Y. (2025) · The Journal of Supercomputing · doi:10.1007/s11227-025-08026-8 · Cited by 4
“These approaches are mostly grouped into two branches: two-stage detectors and single-stage detectors [37].”
Nguyen, N. M., & Nguyen, V. D. (2025) · Signal Image and Video Processing · doi:10.1007/s11760-025-04954-3 · Cited by 1
Adaptive Capsule Graph Neural Network with Attention Mechanism for Parathyroid Glands Detection
Liu, W., Lu, W., Chen, F., Cai, J., Wang, B., & Zhao, W. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-3058-8_10 · Cited by 1
RDD-DETR: lightweight road damage detection with hierarchical feature interaction
Sun, B., Liu, J., Gao, L., et al. (2025) · Engineering Research Express · doi:10.1088/2631-8695/ae2117 · Cited by 1
Jayathunga, D. P., Ramashini, M., Zaini, J., Müller, R., & Silva, L. C. D. (2025) · Applied AI Letters · doi:10.1002/ail2.70014 · Cited by 1
LPC-SYS: AI-Powered Laryngo-Pharyngeal Cancer Diagnosing System
Li, Y., Chen, H., Zhou, P., et al. (2025) · doi:10.1109/embc58623.2025.11251675 · Cited by 1
“Object detection methods can be classified into two main categories: single-stage detection and two-stage detection [4], [5].”
Wang, Z., Ramli, N., & Thio, T. H. G. (2025) · Sensors · doi:10.3390/s25237283 · Cited by 3
“Object detection models based on deep learning now dominate state-of-the-art PCB inspection research [6].”
Energy-Efficient Video Analytics with Edge Computing and Machine Learning
Elbatrawy, M. T., Waref, D., Alayary, Y., Ghany, M. A. A. E., & Salem, M. A. ‐. (2025) · IEEE International Conference on Electronics, Circuits and Systems (ICECS) · doi:10.1109/icecs66544.2025.11270558 · Cited by 1
“Zou et al. [15] review object detection evolution from 1990–2022, noting accuracy and efficiency gains but persistent small-object and domain adaptation issues.”
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.