Object Detection With Deep Learning: A Review
Open accessThe DOI matches its Crossref record; 252 of the 252 references it cites were found in a registry or an index.
Abstract
Due to object detection's close relationship with video analysis and image understanding, it has attracted much research attention in recent years. Traditional object detection methods are built on handcrafted features and shallow trainable architectures. Their performance easily stagnates by constructing complex ensembles that combine multiple low-level image features with high-level context from object detectors and scene classifiers. With the rapid development in deep learning, more powerful tools, which are able to learn semantic, high-level, deeper features, are introduced to address the problems existing in traditional architectures. These models behave differently in network architecture, training strategy, and optimization function. In this paper, we provide a review of deep learning-based object detection frameworks. Our review begins with a brief introduction on the history of deep learning and its representative tool, namely, the convolutional neural network. Then, we focus on typical generic object detection architectures along with some modifications and useful tricks to improve detection performance further. As distinct specific detection tasks exhibit different characteristics, we also briefly survey several specific tasks, including salient object detection, face detection, and pedestrian detection. Experimental analyses are also provided to compare various methods and draw some meaningful conclusions. Finally, several promising directions and tasks are provided to serve as guidelines for future work in both object detection and relevant neural network-based learning systems.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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
“We ensure that these “hard” candidate genes are included in the candidate list for each patient during training, as using such “hard” examples tends to improve the efficiency of training113.”
From Few shot learning for phenotype-driven diagnosis of patients with rare genetic diseases (2025) · cites this paper as [113]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“This capability makes YOLO exceptionally well-suited for applications requiring rapid decision-making, such as autonomous driving, medical diagnostics, and surveillance systems [8,9].”
From The YOLO Framework: A Comprehensive Review of Evolution, Applications, and Benchmarks in Object Detection (2024) · cites this paper as [8]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“Although great progress has been reported with respect to accuracy in object detection and recognition [173], current systems are mainly designed to calculate 2D or 3D bounding boxes for a couple of trained object classes, or to provide a segmented image of the driving environment.”
From A survey of deep learning techniques for autonomous driving (2020) · cites this paper as [173]
The cited source says what the claim attributes to it.
In the citing paper
“Deep learning methods are more effective and accurate, and they perform better in complex environments to detect objects [11].”
From Fusion of Deep Sort and Yolov5 for Effective Vehicle Detection and Tracking Scheme in Real-Time Traffic Management Sustainable System (2023) · cites this paper as [11]
In the citing paper
“Deep Compression uses three steps, prunning, quantization, and Huffman Encoding, to compress over-parameterized DNN models, such as VGG [77], AlexNet [1].”
From Bringing ai to edge: from deep learning’s perspective (2022) · cites this paper as [75]
2 more claims about this paper
Create a free account to see every claim other papers make about this one.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Items 201–252 of 252
Hao, Z., Liu, Y., Qin, H., Yan, J., Li, X., & Hu, X. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.207 · Cited by 134 · cited 2×
“efficient CNN to predict the scale distribution histogram of the faces and took this histogram to guide the zoom-in and zoomout of the image [171].”
MethodPedestrian Detection with Spatially Pooled Features and Structured Ensemble Learning
Paisitkriangkrai, S., Shen, C., & Hengel, A. V. D. (2016) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2015.2474388 · Cited by 130 · cited 2×
“To this end, spatiotemporal tubelets [230], optical flow [199] and LSTM [107] should be considered to fundamentally model object associations”
BackgroundMethodsegDeepM: Exploiting segmentation and context in deep neural networks for object detection
Zhu, Y., Urtasun, R., Salakhutdinov, R., & Fidler, S. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7299102 · Cited by 129 · cited 1×
“proposed the SegDeepM to exploit object segmentation which reduces the dependency on initial candidate boxes with Markov Random Field [106].”
MethodFace Detection through Scale-Friendly Deep Convolutional NetworksPreprint
Yang, S., Xiong, Y., Loy, C. C., & Tang, X. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1706.02863 · Cited by 129 · cited 5×
“The evaluated models cover DDFD [168], Cascade-CNN [180], aggregate channel features (ACF)-multiscale [181], Pico [182], Head-Hunter [183], Joint Cascade [31], SURF-multiview [184], Viola–Jones [166], NPDFace [185], Faceness [169], convolutional channel features (CCF) [186], MTCNN [176], Conv3-D [175], Hyperface [187]…”
BackgroundInfluentialEdge Preserving and Multi-Scale Contextual Neural Network for Salient Object Detection
Wang, X., Ma, H., Chen, X., & You, S. (2018) · IEEE Transactions on Image Processing · doi:10.1109/tip.2017.2756825 · Cited by 123 · cited 1×
“[144] proposed the RegionNet by performing salient object detection with end-to-end edge”
MethodMultiple Representations-Based Face Sketch–Photo Synthesis
Peng, C., Gao, X., Wang, N., Tao, D., Li, X., & Li, J. (2015) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2015.2464681 · Cited by 122
Embedded Streaming Deep Neural Networks Accelerator With Applications
Dundar, A., Jin, J., Martini, B., & Culurciello, E. (2017) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2016.2545298 · Cited by 120 · cited 5×
“But unlike R-CNN, the fine-tuning algorithm proposed in [11] cannot update the convolutional layers that precede the spatial pyramid pooling.”
BackgroundMethodInfluentialYang, B., Yan, J., Lei, Z., & Li, S. Z. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.650 · Cited by 120 · cited 1×
“detectors are built in different stages or layers [180], [220].”
BackgroundScale-aware Fast R-CNN for Pedestrian DetectionPreprint
Li, J., Liang, X., Shen, S., et al. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1510.08160 · Cited by 114 · cited 4×
“SA-FastRCNN extends Fast R-CNN to automatically detecting pedestrians according to their different scales, which has trouble when there are partial occlusions.”
InfluentialTraining Object Class Detectors with Click Supervision
Papadopoulos, D. P., Uijlings, J. R. R., Keller, F., & Ferrari, V. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.27 · Cited by 113
Pushing the Limits of Deep CNNs for Pedestrian Detection
Hu, Q., Wang, P., Shen, C., van den Hengel, A., & Porikli, F. (2017) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2017.2648850 · Cited by 103
Detection of spicules on mammogram based on skeleton analysis
Kobatake, H., & Yoshinaga, Y. (1996) · IEEE Transactions on Medical Imaging · doi:10.1109/42.500062 · Cited by 99 · cited 5×
“1) The emergence of large-scale annotated training data, such as ImageNet [39], to fully exhibit its very large learning capacity.”
BackgroundMethodInfluentialJung, C., & Kim, C. (2011) · IEEE Transactions on Image Processing · doi:10.1109/tip.2011.2164420 · Cited by 95 · cited 1×
“Numerous applications incorporate the visual saliency to improve their performance, such as image cropping [125] and segmentation [126], image retrieval [57] and object detection [66].”
BackgroundA multi-scale cascade fully convolutional network face detector
Yang, Z., & Nevatia, R. (2016) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2016.7899705 · Cited by 94 · cited 6×
“Yang and Nevatia [8] proposed a three-stage cascade structure based on FCNs, while in each stage, a multiscale FCN is utilized to refine the positions of possible faces.”
BackgroundMethodInfluentialFace R-CNNPreprint
Wang, H., Li, Z., Ji, X., & Wang, Y. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1706.01061 · Cited by 89 · cited 3×
“Joint Cascade [30], SURF-multiview [184], Viola-Jones [166], NPDFace [185], Faceness [169], CCF [186], MTCNN [176], Conv3D [175], Hyperface [187], UnitBox [167], LDCF+ [S2], DeepIR [173], HR-ER [188], Face-R-CNN [172] and ScaleFace [170].”
Discriminatively Trained And-Or Graph Models for Object Shape Detection
Lin, L., Wang, X., Yang, W., & Lai, J.-H. (2015) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2014.2359888 · Cited by 86 · cited 1×
“At the same time, to explicitly model the deformation and occlusion, part-based models [200] and”
BackgroundSaliency Detection via Combining Region-Level and Pixel-Level Predictions with CNNs
Tang, Y., & Wu, X. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-46484-8_49 · Cited by 85 · cited 6×
“proposed a novel saliency detection framework (CRPSD) [142], which combines region-level saliency estimation and pixel-level saliency prediction together with three closely related CNNs.”
BackgroundInfluentialSelf-citationEfficient and robust Pedestrian Detection using Deep Learning for Human-Aware Navigation
Mateus, A., Ribeiro, D. A., Miraldo, P., & Nascimento, J. C. (2018) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2018.12.007 · Cited by 80 · cited 2×
“[33] addressed the problem of human-aware navigation and proposed a vision-based person tracking system guided by multiple camera sensors.”
BackgroundReal Time Image Saliency for Black Box Classifiers
Dabkowski, P., & Gal, Y. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1705.07857 · Cited by 77 · cited 1×
“and couple them with the global structure in a joint-learning manner [226].”
BackgroundPVANet: Lightweight Deep Neural Networks for Real-time Object Detection
Hong, S., Roh, B., Kim, K.-H., Cheon, Y., & Park, M. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1611.08588 · Cited by 76 · cited 7×
“The PVANET achieves the state-of-the-art performance and can be processed in real time on Titan X GPU (21 FPS).”
BackgroundMethodInfluentialWeakly supervised object recognition with convolutional neural networks
Oquab, M., Bottou, L., Laptev, I., & Šivic, J. (2014) · Cited by 76
Lenc, K., & Vedaldi, A. (2015) · Procedings of the British Machine Vision Conference 2015 · doi:10.5244/c.29.5 · Cited by 73
Multistage Object Detection With Group Recursive Learning
Li, J., Liang, X., Li, J., Wei, Y., Xu, T., Feng, J., & Yan, S. (2018) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2017.2772796 · Cited by 59
Object Detection with Pixel Intensity Comparisons Organized in Decision TreesPreprint
Markuš, N., Frljak, M., Pandzic, I. S., Ahlberg, J., & Forchheimer, R. (2013) · arXiv (Cornell University) · doi:10.48550/arxiv.1305.4537 · Cited by 55
Pedestrian Detection Based on Fast R-CNN and Batch Normalization
Zhao, Z., Bian, H., Hu, D., Cheng, W., & Glotin, H. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-63309-1_65 · Cited by 55 · cited 1×
“Due to these advantages, CNN has been widely applied into many research fields, such as image super-resolution reconstruction [54], [55], image classification [5], [56], image retrieval [57], [58], face recognition [8][S5], pedestrian detection [59]–[61] and video analysis [62], [63].”
MethodSelf-citationLow-Complexity Approximate Convolutional Neural Networks
Cintra, R. J., Duffner, S., García, C., & Leite, A. (2018) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2018.2815435 · Cited by 54 · cited 1×
“But if we look at performance on the canonical visual recognition task, PASCAL VOC object detection [12], it is generally acknowledged that progress has been slow during 2010-2012, with small gains obtained by building ensemble systems and employing minor variants of successful methods.”
BackgroundMultispectral Deep Neural Networks for Pedestrian DetectionPreprint
Liu, J., Zhang, S., Wang, S., et al. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1611.02644 · Cited by 53 · cited 2×
“a specific application, the information from different modalities, such as text [212], thermal data [205], and images [65], can be fused together to achieve a more discriminant network.”
BackgroundUnsupervised Learning from Video to Detect Foreground Objects in Single Images
Croitoru, I., Bogolin, S.-V., & Leordeanu, M. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.465 · Cited by 53 · cited 1×
“To release this burden, semantic prior [55], unsupervised object discovery [221], multiple instance learning [222] and deep neural network prediction [47] can be integrated to make best use of image-level supervision to”
MethodDeeply-Supervised Recurrent Convolutional Neural Network for Saliency Detection
Tang, Y.-B., Wu, X., & Bu, W. (2016) · ACM Multimedia · doi:10.1145/2964284.2967250 · Cited by 51 · cited 5×
“DSR and MT act in different ways by introducing a recurrent network and semantic segmentation, which provide insights for future improvements.”
BackgroundMethodInfluentialSelf-citationVisual-Inertial-Semantic Scene Representation for 3D Object Detection
Dong, J., Fei, X., & Soatto, S. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.380 · Cited by 48 · cited 1×
“To achieve better bounding results, multi-view representation [181] and 3D proposal network [228] may provide some guidelines to encode depth information with the aid of inertial sensors (accelerometer and gyrometer) [229].”
BackgroundLearning invariance through imitation
Taylor, G. W., Spiro, I., Bregler, C., & Fergus, R. (2011) · CVPR 2011 · doi:10.1109/cvpr.2011.5995538 · Cited by 45 · cited 1×
“Among the pre-related works [44], [75], [76], the most representative one is Overfeat [44].”
BackgroundMultiple Pedestrian Tracking From Monocular Videos in an Interacting Multiple Model Framework
Jiang, Z., & Huynh, D. Q. (2017) · IEEE Transactions on Image Processing · doi:10.1109/tip.2017.2779856 · Cited by 39 · cited 1×
“Recently, pedestrian detection has been intensively studied, which has a close relationship to pedestrian tracking [189],”
BackgroundCompact Convolutional Neural Network Cascade for Face DetectionPreprint
Kalinovskii, I., & Спицын, В. Г. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1508.01292 · Cited by 34 · cited 2×
“To achieve real-time detection on the mobile platform, Kalinovskii and Spitsyn [177] proposed a new solution of frontal face detection based on compact CNN cascades.”
MethodCholakkal, H., Johnson, J., & Rajan, D. (2018) · IEEE Transactions on Image Processing · doi:10.1109/tip.2018.2864891 · Cited by 32
Plant Leaf Identification via a Growing Convolution Neural Network with Progressive Sample Learning
Zhao, Z., Xie, B.-J., Cheung, Y., & Wu, X. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-16808-1_24 · Cited by 30 · cited 1×
“Due to these advantages, CNN has been widely applied into many research fields, such as image super-resolution reconstruction [54], [55], image classification [5], [56], image retrieval [57], [58], face recognition [8][S5], pedestrian detection [59]–[61] and video analysis [62], [63].”
MethodSelf-citationTwo-Stream Convolutional Networks for Dynamic Saliency PredictionPreprint
Bak, Ç., Erdem, A., & Erdem, E. (2016) · arXiv.org · doi:10.48550/arxiv.1607.04730 · Cited by 28 · cited 1×
“fused two static saliency models, namely spatial stream net and temporal stream net, into a two-stream framework with a novel empirically grounded data augmentation technique [139].”
BackgroundFace Detection using Deep Learning: An Improved Faster RCNN ApproachPreprint
Sun, X., Wu, P., & Hoi, S. C. H. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1701.08289 · Cited by 27 · cited 4×
“From Figure 13(b), it can be observed that most of CNN based methods earn similar true positive rates between 60% and 70% while DeepIR and HR-ER perform much better than them.”
BackgroundInfluentialStuffNet: Using ‘Stuff’ to Improve Object Detection
Brahmbhatt, S., Christensen, H. I., & Hays, J. (2017) · 2017 IEEE Winter Conference on Applications of Computer Vision (WACV) · doi:10.1109/wacv.2017.109 · Cited by 24 · cited 3×
“S-CNN [105], Faster R-CNN [17], HyperNet [101], ION [95], MS-GR [104], StuffNet [100], SSD300 [71], SSD512 [71], OHEM [113], SDP+CRC [34], G-CNN [70], SubCNN [60], GBD-Net [109], PVANET [116], YOLO [18], YOLOv2 [72], R-FCN [65], FPN [66], Mask R-CNN [67], DSSD [73],”
BackgroundLearning Detection with Diverse Proposals
Azadi, S., Feng, J., & Darrell, T. (2017) · 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/cvpr.2017.779 · Cited by 23 · cited 1×
“To solve these problems, we can refer to diverse subset selection [217] and sequential reasoning tasks [218] for possible solutions.”
MethodSaliency-based Sequential Image Attention with Multiset PredictionPreprint
Welleck, S., Mao, J., Cho, K., & Zhang, Z. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1711.05165 · Cited by 22 · cited 1×
“For scale-adaptive detectors, it is useful to combine knowledge graph [215], attentional mechanism [216], cascade network [180] and scale distribution estimation [171] to detect objects adaptively.”
MethodFace Recognition from Multiple Stylistic Sketches: Scenarios, Datasets, and Evaluation
Peng, C., Wang, N., Gao, X., & Li, J. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-46604-0_1 · Cited by 21
(2015) · arXiv (Cornell University) · Cited by 14 · cited 2×
“[88] provided an analysis on the role of proposal generation in CNN-based detectors and tried to replace this stage with a constant and trivial region generation”
MethodReduced memory region based deep Convolutional Neural Network detection
Tomè, D., Bondi, L., Baroffio, L., Tubaro, S., Plebani, E., & Pau, D. (2016) · IEEE International Conference on Consumer Electronics - Berlin (ICCE-Berlin) · doi:10.1109/icce-berlin.2016.7684706 · Cited by 13 · cited 2×
“However, despite that detection accuracy is reduced, it is more meaningful to learn compact models with fewer number of parameters [209].”
BackgroundReduced memory region based deep Convolutional Neural Network detection
Tomè, D., Luca, B., Baroffio, L., Tubaro, S., Plebani, E., & Danilo, P. (2016) · UCL Discovery (University College London) · Cited by 10
Learning to detect and localize many objects from few examplesPreprint
Moysset, B., Kermorvant, C., & Wolf, C. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1611.05664 · Cited by 7 · cited 1×
“[108] took advantage of four directional 2-D long short-term memories (LSTMs) [107] to convey global context between different local regions and reduced trainable parameters with local parameter sharing.”
BackgroundMulti-stage Object Detection with Group Recursive LearningPreprint
Li, J., Liang, X., Li, J., et al. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1608.05159 · Cited by 6 · cited 1×
“S-CNN [105], Faster R-CNN [17], HyperNet [101], ION [95], MS-GR [104], StuffNet [100], SSD300 [71], SSD512 [71], OHEM [113], SDP+CRC [34], G-CNN [70], SubCNN [60], GBD-Net [109], PVANET [116], YOLO [18], YOLOv2 [72], R-FCN [65], FPN [66], Mask R-CNN [67], DSSD [73],”
A MultiPath Network for Object Detection
Zagoruyko, S., Lerer, A., Lin, T.-Y., et al. (2016) · arXiv · doi:10.48550/arxiv.1604.02135 · cited 2×
“R-CNN [112], including multi-scale skip connections [95], a modified foveal structure [110] and a novel loss function summing different IoU losses.”
MethodEfficient and Robust Pedestrian Detection using Deep Learning for Human-Aware Navigation
Mateus, A., Ribeiro, D., Miraldo, P., & Nascimento, J. C. (2016) · arXiv · doi:10.48550/arxiv.1607.04441 · cited 2×
“addressed the problem of Human-Aware Navigation [32] and proposed a vision-based person tracking system guided by multiple camera sensors.”
BackgroundCholakkal, H., Johnson, J., & Rajan, D. (2016) · arXiv · doi:10.48550/arxiv.1611.05345
Edge Preserving and Multi-Scale Contextual Neural Network for Salient Object Detection
Wang, X., Ma, H., Chen, X., & You, S. (2016) · arXiv · doi:10.48550/arxiv.1608.08029 · cited 1×
“[144] proposed the RegionNet by performing salient object detection with end-to-end edge”
MethodDeeply supervised salient object detection with short connections
Hou, Q., Cheng, M.-M., Hu, X.-W., Borji, A., Tu, Z., & Torr, P. (2016) · arXiv · doi:10.48550/arxiv.1611.04849 · cited 5×
“regional feature integration (DRFI) [152], MC [138], multiscale deep CNN features (MDF) [146], local estimation and global search (LEGS) [136], DSR [149], multi-task deep neural network [141], CRPSD [142], deep contrast learning (DCL) [143], encoded low level distance (ELD) [153], nonlocal deep features (NLDF) [154],…”
BackgroundInfluentialRanjan, R., Patel, V. M., & Chellappa, R. (2016) · arXiv · doi:10.48550/arxiv.1603.01249 · cited 3×
“The outstanding performance of MTCNN, Conv3D and Hyperface proves the effectiveness of multi-task learning.”
Background
Research works printed but not linked: 4
- wang, 2017, Face R-CNN
- 10.1109/ICCV.2015.221 · DOI · Paper page
- 10.1109/TPAMI.2009.167 · DOI · Paper page
- everingham, 2011, The pascal visual object classes challenge 2012 (voc2012) results (2012)
Cited by
Review of deep learning: concepts, CNN architectures, challenges, applications, future directions
Alzubaidi, L., Zhang, J., Humaidi, A. J., Al-Dujaili, A., Duan, Y., Al-Shamma, O., Santamaría, J., Fadhel, M. A., Al-Amidie, M., & Farhan, L. (2021) · Journal of Big Data · doi:10.1186/s40537-021-00444-8 · Cited by 7,906
Object Detection in 20 Years: A Survey
Zou, Z., Chen, K., Shi, Z., Guo, Y., & Ye, J. (2023) · Proceedings of the IEEE · doi:10.1109/jproc.2023.3238524 · Cited by 3,689
“SPPNet [17], Fast RCNN [18], Faster RCNN [19], YOLO [20], [21], [22], SSD [23], FPN [24], Retina-Net [25], CornerNet [26], CenterNet [27], and”
A Review of Yolo Algorithm Developments
Jiang, P., Ergu, D., Liu, F., Cai, Y., & Ma, B. (2022) · Procedia Computer Science · doi:10.1016/j.procs.2022.01.135 · Cited by 2,783
A Survey of Autonomous Driving: Common Practices and Emerging Technologies
Yurtsever, E., Lambert, J., Carballo, A., & Takeda, K. (2020) · IEEE Access · doi:10.1109/access.2020.2983149 · Cited by 1,889
A survey of deep learning techniques for autonomous driving
Grigorescu, S., Trasnea, B., Cocias, T., & Macesanu, G. (2020) · Journal of Field Robotics · doi:10.1002/rob.21918 · Cited by 1,809
“Although great progress has been reported with respect to accuracy in object detection and recognition [173], current systems are mainly designed to calculate 2D or 3D bounding boxes for a couple of trained object classes, or to provide a segmented image of the driving environment.”
Background
Metadata
- Authors
- Zhao, Z.-Q., Zheng, P., Xu, S.-T., & Wu, X.
- Affiliations
- Hefei University of Technology (CN)
- University of Louisiana at Lafayette (US)
- Venue
- IEEE Transactions on Neural Networks and Learning Systems
- Published
- 2019-11
- Volume
- 30
- Issue
- 11
- Pages
- 3212-3232
- ISSN
- 2162-237X (ISSN-L)
- 2162-2388
- OpenAlex
- W2884367402
- Cited by
- 5,545
- References
- 241
- Citations by year
- 2026: 418 · 2025: 752 · 2024: 866 · 2023: 921 · 2022: 997 · 2021: 887 · 2020: 548 · 2019: 149
- FWCI
- 288.39
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- IEEE Transactions on Neural Networks and Learning Systems (publishedVersion)
- PubMed (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- National Natural Science Foundation of China (61672203, 61375047, 91746209)
- National Key Research and Development Program of China (2016YFB1000901)
- Anhui Natural Science Funds for Distinguished Young Scholar (170808J08)
- 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, deep learning, convolutional neural networks, salient object detection, face detection, pedestrian detection, training strategies, optimization functions, image understanding
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.
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.