深度神经网络在人体姿态估计中的应用综述

doi:10.3778/j.issn.1002-8331.2409-0272

摘要/Abstract

摘要： 人体姿态估计是计算机视觉领域的重要研究方向，在教育教学、临床诊断、人机交互等多场景均有重要应用。随着深度神经网络提出及发展，其以强大的特征学习能力、大规模并行处理等优势，广泛应用于人体姿态估计，并大幅提高了估计结果准确度和识别效率。以人体姿态估计为研究对象，梳理近5年相关领域100篇包含RNN、CNN、GAN、前沿网络模型等深度神经网络及其变体架构的代表性文献；此外，汇总梳理近5年常用数据集，并阐释了模型常用评估指标。最后，总结现阶段人体姿态估计领域面临的挑战，并展望未来研究，以进一步探讨深度神经网络在人体姿态估计中的应用潜力。

关键词: 人体姿态估计, 计算机视觉, 深度神经网络, 评价指标

Abstract: Human pose estimation(HPE) is a critical research direction in the field of computer vision, with important applications in various scenarios such as education and training, clinical diagnosis, and human-computer interaction. The emergence and evolution of deep neural networks have profoundly influenced human pose estimation, harnessing their robust feature learning capabilities and leveraging large-scale parallel processing benefits. This has led to significant enhancements in the precision of estimation outcomes and recognition efficiency. Focusing on human pose estimation, more than 100 representative papers from the relevant field over the past five years are reviewed, covering deep neural network models and their variant architectures, including RNN, CNN, GAN, and state-of-the-art network models. In addition, a systematic review and summary of commonly used datasets over the past five years is provided, along with an explanation of the commonly used evaluation metrics for models. Finally, the challenges currently faced in the field of HPE are summarized, and future research is anticipated to further explore the potential applications of deep neural networks in human pose estimation.

Key words: human pose estimation(HPE), computer vision, deep neural networks, evaluation metrics

郝鹤菲, 张龙豪, 崔洪振, 朱宵月, 彭云峰, 李向晖. 深度神经网络在人体姿态估计中的应用综述[J]. 计算机工程与应用, 2025, 61(9): 41-60.

HAO Hefei, ZHANG Longhao, CUI Hongzhen, ZHU Xiaoyue, PENG Yunfeng, LI Xianghui. Review of Application of Deep Neural Networks in Human Pose Estimation[J]. Computer Engineering and Applications, 2025, 61(9): 41-60.

参考文献

[1] MUNEA T L, JEMBRE Y Z, WELDEGEBRIEL H T, et al. The progress of human pose estimation: a survey and taxonomy of models applied in 2D human pose estimation[J]. IEEE Access, 2020, 8: 133330-133348.
[2] CHEN H M, FENG R Y, WU S F, et al. 2D Human pose estimation: a survey[J]. Multimedia Systems, 2023, 29(5): 3115-3138.
[3] 苏妍妍, 邱志良, 李帼, 等. 基于深度学习的二维单人姿态估计综述[J]. 计算机工程与应用, 2024, 60(21): 18-37.
SU Y Y, QIU Z L, LI G, et al. Review on deep learning-based 2D single-person pose estimation[J]. Computer Engineering and Applications, 2024, 60(21): 18-37.
[4] DESMARAIS Y, MOTTET D, SLANGEN P, et al. A review of 3D human pose estimation algorithms for markerless motion capture[J]. Computer Vision and Image Understanding, 2021, 212: 103275.
[5] 王仕宸, 黄凯, 陈志刚, 等. 深度学习的三维人体姿态估计综述[J]. 计算机科学与探索, 2023, 17(1): 74-87.
WANG S C, HUANG K, CHEN Z G, et al. Survey on 3D human pose estimation of deep learning[J]. Journal of Frontiers of Computer Science and Technology, 2023, 17(1): 74-87.
[6] CHEN Y C, TIAN Y L, HE M Y. Monocular human pose estimation: a survey of deep learning-based methods[J]. Computer Vision and Image Understanding, 2020, 192: 102897.
[7] JANARDHANAN J, UMAMAHESWARI S. A comprehensive study on human pose estimation[C]//Proceedings of the 2022 8th International Conference on Advanced Computing and Communication Systems. Piscataway: IEEE, 2022: 535-541.
[8] ZHENG C, WU W H, CHEN C, et al. Deep learning-based human pose estimation: a survey[J]. ACM Computing Surveys, 2024, 56(1): 1-37.
[9] ELMAN J. Finding structure in time[J]. Cognitive Science, 1990, 14(2): 179-211.
[10] GRAVES A. Long short-term memory[M]//Supervised sequence labelling with recurrent neural networks. Berlin, Heidelber: Springer, 2012: 37-45.
[11] LEE K, KIM W, LEE S. From human pose similarity metric to 3D human pose estimator: temporal propagating LSTM networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023, 45(2): 1781-1797.
[12] JANG Y, JEONG I, YOUNESI HERAVI M, et al. Multi-camera-based human activity recognition for human-robot collaboration in construction[J]. Sensors, 2023, 23(15): 6997.
[13] CHUNG J, GULCEHRE C, CHO K, et al. Empirical evaluation of gated recurrent neural networks on sequence modeling[J]. arXiv:1412.3555, 2014.
[14] QIU S X, LI Z H, YE K L, et al. DSiaG: real-time pose estimation and recognition algorithm based on spatial and temporal information[C]//Proceedings of the 2024 4th International Conference on Computer Communication and Artificial Intelligence. Piscataway: IEEE, 2024: 41-45.
[15] DU S L, ZHANG Z W, IKENAGA T. AnatPose: bidirectionally learning anatomy-aware heatmaps for human pose estimation[J]. Pattern Recognition, 2024, 155: 110654.
[16] LECUN Y, BOTTOU L, BENGIO Y, et al. Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE, 1998, 86(11): 2278-2324.
[17] JAIN A, TOMPSON J, ANDRILUKA M, et al. Learning human pose estimation features with convolutional networks[J]. arXiv:1312.7302, 2013.
[18] SHELHAMER E, LONG J, DARRELL T. Fully convolutional networks for semantic segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(4): 640-651.
[19] RONNEBERGER O, FISCHER P, BROX T. U-Net: convolutional networks for biomedical image segmentation[C]//Proceedings of the18th International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI 2015). Cham: Springer International Publishing, 2015: 234-241.
[20] NEWELL A, YANG K, DENG J. Stacked hourglass networks for human pose estimation[C]//Proceedings of the European Conference on Computer Vision (ECCV), 2016:?483-499.
[21] WEI S H, RAMAKRISHNA V, KANADE T, et al. Convolutional pose machines[C]//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2016: 4724-4732.
[22] SUN K, XIAO B, LIU D, et al. Deep high-resolution representation learning for human pose estimation[C]//Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2019: 5693-5703.
[23] LI W W, DU R, CHEN S D. Skeleton-based spatio-temporal U-network for 3D human pose estimation in video[J]. Sensors, 2022, 22(7): 2573.
[24] GONG F M, MA Y H, ZHENG P, et al. A deep model method for recognizing activities of workers on offshore drilling platform by multistage convolutional pose machine[J]. Journal of Loss Prevention in the Process Industries, 2020, 64: 104043.
[25] DONG X N, YU J, ZHANG J. Joint usage of global and local attentions in hourglass network for human pose estimation[J]. Neurocomputing, 2022, 472: 95-102.
[26] FENG R Y, GAO Y X, MA X Q, et al. Mutual information-based temporal difference learning for human pose estimation in video[C]//Proceedings of the 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2023: 17131-17141.
[27] LUO W, XUE J Y. Human pose estimation based on improved HRNet model[C]//Proceedings of the 2023 IEEE 3rd International Conference on Computer Communication and Artificial Intelligence. Piscataway: IEEE, 2023: 153-157.
[28] BULAT A, KOSSAIFI J, TZIMIROPOULOS G, et al. Toward fast and accurate human pose estimation via soft-gated skip connections[C]//Proceedings of the 2020 15th IEEE International Conference on Automatic Face and Gesture Recognition. Piscataway: IEEE, 2020: 8-15.
[29] GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2014: 580-587.
[30] SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[J]. arXiv:1409.1556, 2014.
[31] HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition[C]//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2016: 770-778.
[32] CAO Z, SIMON T, WEI S H, et al. Realtime multi-person 2D pose estimation using part affinity fields[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2017: 1302-1310.
[33] SRIVASTAV V, GANGI A, PADOY N. Unsupervised domain adaptation for clinician pose estimation and instance segmentation in the operating room[J]. Medical Image Analysis, 2022, 80: 102525.
[34] HUANG Y, SHUM H P H, HO E S L, et al. High-speed multi-person pose estimation with deep feature transfer[J]. Computer Vision and Image Understanding, 2020, 197: 103010.
[35] OSOKIN D. Real-time 2D multi-person pose estimation on CPU: lightweight OpenPose[J]. arXiv:1811.12004, 2018.
[36] 方益, 石守东, 方靖森, 等. 基于空间交叉卷积的轻量级人体姿态估计算法[J]. 传感技术学报, 2024, 37(3): 439-445.
FANG Y, SHI S D, FANG J S, et al. Lightweight human pose estimation algorithm based on spatial cross convolution[J]. Chinese Journal of Sensors and Actuators, 2024, 37(3): 439-445.
[37] XIAO B, WU H P, WEI Y C. Simple baselines for human pose estimation and tracking[C]//Proceedings of the European Conference on Computer Vision. Cham: Springer International Publishing, 2018: 472-487.
[38] GAO S H, CHENG M M, ZHAO K, et al. Res2Net: a new multi-scale backbone architecture[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021, 43(2): 652-662.
[39] ZHANG H R, QI Y F, CHEN H L, et al. LSDNet: lightweight stochastic depth network for human pose estimation[J]. The Visual Computer, 2025, 41(1): 257-270.
[40] KOCABAS M, KARAGOZ S, AKBAS E. MultiPoseNet: fast multi-person pose estimation using pose residual network[C]//Proceedings of the European Conference on Computer VisioN (ECCV). Cham: Springer International Publishing, 2018: 437-453.
[41] ZHANG Z W, LIU M G, SHEN J Y, et al. Lightweight whole-body human pose estimation with two-stage refinement training strategy[J]. IEEE Transactions on Human-Machine Systems, 2024, 54(1): 121-130.
[42] GOODFELLOW I, POUGET-ABADIE J, MIRZA M, et al. Generative adversarial nets[C]//Advances in Neural Information Processing Systems, 2014: 2672-2680.
[43] MIRZA M, OSINDERO S. Conditional generative adversarial nets[J]. arXiv:1411.1784, 2014.
[44] GULRAJANI I, AHMED F, ARJOVSKY M, et al. Improved training of Wasserstein GANs[C]//Advances in Neural Information Processing Systems, 2017: 5767-5777.
[45] DAYARATHNA T, MUTHUKUMARANA T, RATHNAYAKA Y, et al. Privacy-preserving in-bed pose monitoring: a fusion and reconstruction study[J]. Expert Systems with Applications, 2023, 213: 119139.
[46] BARSOUM E, KENDER J, LIU Z C. HP-GAN: probabilistic 3D human motion prediction via GAN[C]//Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. Piscataway: IEEE, 2018: 1418-1427.
[47] RADFORD A, METZ L, CHINTALA S, et al. Unsupervised representation learning with deep convolutional generative adversarial networks[J]. arXiv:1511.06434, 2015.
[48] SHOMAN M, GHOUL T, LANZARO G, et al. Enforcing traffic safety: a deep learning approach for detecting motorcyclists’ helmet violations using YOLOv8 and deep convolutional generative adversarial network-generated images[J]. Algorithms, 2024, 17(5): 202.
[49] 姜友鹏, 华阳, 宋晓宁. 空间注意力与位置优化的三维人体姿态估计域适应算法[J]. 计算机科学与探索, 2024, 18(9): 2384-2394.
JIANG Y P, HUA Y, SONG X N. Domain adaptation algorithm for 3D human pose estimation with spatial attention and position optimization[J]. Journal of Frontiers of Computer Science and Technology, 2024, 18(9): 2384-2394.
[50] TIAN L, WANG P, LIANG G Q, et al. An adversarial human pose estimation network injected with graph structure[J]. Pattern Recognition, 2021, 115: 107863.
[51] REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once: unified, real-time object detection[C]//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2016: 779-788.
[52] SONG C Y, WANG S G, CHEN M M, et al. A multimodal discrimination method for the response to Name behavior of autistic children based on human pose tracking and head pose estimation[J]. Displays, 2023, 76: 102360.
[53] LIU L, DAI Y X, LIU Z H. Real-time pose estimation and motion tracking for motion performance using deep learning models[J]. Journal of Intelligent Systems, 2024, 33(1): 20230288.
[54] ZHANG Y T, WANG Z Y, LI M L, et al. SP-YOLO: an end-to-end lightweight network for real-time human pose estimation[J]. Signal, Image and Video Processing, 2024, 18(1): 863-876.
[55] DING J, NIU S W, NIE Z G, et al. Research on human posture estimation algorithm based on YOLO-pose[J]. Sensors, 2024, 24(10): 3036.
[56] DONG X Q, WANG X C, LI B J, et al. YH-Pose: human pose estimation in complex coal mine scenarios[J]. Engineering Applications of Artificial Intelligence, 2024, 127: 107338.
[57] VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[C]//Advances in Neural Information Processing Systems, 2017: 5998-6008.
[58] ZHENG C, ZHU S J, MENDIETA M, et al. 3D human pose estimation with spatial and temporal transformers[C]//Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision. Piscataway: IEEE, 2021: 11636-11645.
[59] LI W H, LIU H, TANG H, et al. MHFormer: multi-hypothesis transformer for 3D human pose estimation[C]//Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2022: 13137-13146.
[60] LI W H, LIU H, TANG H, et al. Multi-hypothesis representation learning for transformer-based 3D human pose estimation[J]. Pattern Recognition, 2023, 141: 109631.
[61] YANG S, QUAN Z B, NIE M, et al. TransPose: keypoint localization via transformer[C]//Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision. Piscataway: IEEE, 2021: 11782-11792.
[62] MAO W A, GE Y T, SHEN C H, et al. TFPose: direct human pose estimation with transformers[J]. arXiv:2103.15320, 2021.
[63] ALEXEY D. An image is worth 16×16 words: transformers for image recognition at scale[J]. arXiv:2010.11929, 2020.
[64] XU Y, ZHANG J, ZHANG Q, et al. ViTPose: simple vision transformer baselines for human pose estimation[C]//Advances in Neural Information Processing Systems, 2022: 38571-38584.
[65] LIU Z, LIN Y T, CAO Y, et al. Swin transformer: hierarchical vision transformer using shifted windows[C]//Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision. Piscataway: IEEE, 2021: 9992-10002.
[66] LI M Y, HU H N, XIONG J J, et al. TSwinPose: enhanced monocular 3D human pose estimation with JointFlow[J]. Expert Systems with Applications, 2024, 249: 123545.
[67] SCARSELLI F, GORI M, TSOI A C, et al. The graph neural network model[J]. IEEE Transactions on Neural Networks, 2009, 20(1): 61-80.
[68] KIPF T N, WELLING M. Semi-supervised classification with graph convolutional networks[J]. arXiv:1609.02907, 2016.
[69] ZHAO L, PENG X, TIAN Y, et al. Semantic graph convolutional networks for 3D human pose regression[C]//Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2019: 3425-3435.
[70] 马金林, 崔琦磊, 马自萍, 等. 预加权调制密集图卷积网络三维人体姿态估计[J]. 计算机科学与探索, 2024, 18(4): 963-977.
MA J L, CUI Q L, MA Z P, et al. Pre-weighted modulated dense graph convolutional networks for 3D human pose estimation[J]. Journal of Frontiers of Computer Science and Technology, 2024, 18(4): 963-977.
[71] CHEN Z M, DAI J, BAI J X, et al. DGFormer: dynamic graph transformer for 3D human pose estimation[J]. Pattern Recognition, 2024, 152: 110446.
[72] KAMEL A, SHENG B, LI P, et al. Hybrid refinement-correction heatmaps for human pose estimation[J]. IEEE Transactions on Multimedia, 2020, 23: 1330-1342.
[73] LI H R, YAO H X, HOU Y X. HPnet: hybrid parallel network for human pose estimation[J]. Sensors, 2023, 23(9): 4425.
[74] YUAN Z X, ZHANG X T, WU S P, et al. Multi hybrid extractor network for 3D human pose estimation[C]//Proceedings of the 2023 IEEE International Conference on Image Processing. Piscataway: IEEE, 2023: 3170-3174.
[75] GU A, DAO T. Mamba: linear-time sequence modeling with selective state spaces[J]. arXiv:2312.00752, 2023.
[76] ZHANG X Y, BAO Q Q, CUI Q P, et al. Pose magic: efficient and temporally consistent human pose estimation with a hybrid mamba-GCN network[J]. arXiv:2408.02922, 2024.
[77] JOHNSON S, EVERINGHAM M. Clustered pose and nonlinear appearance models for human pose estimation[C]//Proceedings of the British Machine Vision Conference, 2010: 1-11.
[78] JHUANG H, GALL J, ZUFFI S, et al. Towards understanding action recognition[C]//Proceedings of the 2013 IEEE International Conference on Computer Vision. Piscataway: IEEE, 2013: 3192-3199.
[79] SAPP B, TASKAR B. MODEC: multimodal decomposable models for human pose estimation[C]//Proceedings of the 2013 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2013: 3674-3681.
[80] ZHANG W Y, ZHU M L, DERPANIS K G. From actemes to action: a strongly-supervised representation for detailed action understanding[C]//Proceedings of the 2013 IEEE International Conference on Computer Vision. Piscataway: IEEE, 2013: 2248-2255.
[81] LIN T Y, MAIRE M, BELONGIE S, et al. Microsoft COCO: common objects in context[C]//Proceedings of the 13th European Conference on Computer Vision. Cham: Springer International Publishing, 2014: 740-755.
[82] ANDRILUKA M, PISHCHULIN L, GEHLER P, et al. 2D human pose estimation: new benchmark and state of the art analysis[C]//Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2014: 3686-3693.
[83] CHERIAN A, MAIRAL J, ALAHARI K, et al. Mixing body-part sequences for human pose estimation[C]//Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2014: 2361-2368.
[84] GONG K, LIANG X D, ZHANG D Y, et al. Look into person: self-supervised structure-sensitive learning and a new benchmark for human parsing[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2017: 6757-6765.
[85] XIA F T, WANG P, CHEN X J, et al. Joint multi-person pose estimation and semantic part segmentation[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2017: 6080-6089.
[86] LI J F, WANG C, ZHU H, et al. CrowdPose: efficient crowded scenes pose estimation and a new benchmark[C]//Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2019: 10863-10872.
[87] ZHANG S-H, LI R L, DONG X, et al. Pose2Seg: detection free human instance segmentation[C]//Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2019: 889-898.
[88] LIU H, CHEN Y, ZHAO W L, et al. Human pose recognition via adaptive distribution encoding for action perception in the self-regulated learning process[J]. Infrared Physics & Technology, 2021, 114: 103660.
[89] SIGAL L, BALAN A O, BLACK M J. HumanEva: synchronized video and motion capture dataset and baseline algorithm for evaluation of articulated HumanMotion[J]. International Journal of Computer Vision, 2010, 87(1): 4-27.
[90] KUEHNE H, JHUANG H, GARROTE E, et al. HMDB: a large video database for human motion recognition[C]//Proceedings of the 2011 International Conference on Computer Vision. Piscataway: IEEE, 2011: 2556-2563.
[91] IONESCU C, PAPAVA D, OLARU V, et al. Human3.6M: large scale datasets and predictive methods for 3D human sensing in natural environments[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2014, 36(7): 1325-1339.
[92] JOO H, SIMON T, LI X L, et al. Panoptic studio: a massively multiview system for social interaction capture[J]. arXiv:1612.03153, 2016.
[93] MEHTA D, RHODIN H, CASAS D, et al. Monocular 3D human pose estimation in the wild using improved CNN supervision[C]//Proceedings of the 2017 International Conference on 3D Vision. Piscataway: IEEE, 2017: 506-516.
[94] RHODIN H, MEYER F, SP?RRI J, et al. Learning monocular 3D human pose estimation from multi-view images[C]//Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2018: 8437-8446.
[95] MEHTA D, SOTNYCHENKO O, MUELLER F, et al. Single-shot multi-person 3D pose estimation from monocular RGB[C]//Proceedings of the 2018 International Conference on 3D Vision. Piscataway: IEEE, 2018: 120-130.
[96] LI T J, LIU J, ZHANG W, et al. UAV-human: a large benchmark for human behavior understanding with unmanned aerial vehicles[C]//Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2021: 16266-16275.
[97] LI R L, YANG S, ROSS D A, et al. AI choreographer: music conditioned 3D dance generation with AIST[C]//Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision. Piscataway: IEEE, 2021: 13381-13392.
[98] SONG I, LEE J, RYU M, et al. Motion-aware heatmap regression for human pose estimation in videos[C]//Proceedings of the 33rd International Joint Conference on Artificial Intelligence, 2024: 1245-1253.
[99] MUKHERJEE S S, ROBERTSON N M. Deep head pose: gaze-direction estimation in multimodal video[J]. IEEE Transactions on Multimedia, 2015, 17(11): 2094-2107.
[100] WANG C, LI J F, LIU W T, et al. HMOR: hierarchical multi-person ordinal relations for monocular multi-person 3D pose estimation[C]//Proceedings of the 16th European Conference on Computer Vision. Cham: Springer International Publishing, 2020: 242-259.
[101] NEUMANN L, VEDALDI A. Tiny people pose[C]//Proceedings of the 14th Asian Conference on Computer Vision. Cham:Springer International Publishing, 2019: 558-574.
[102] WANG C, ZHANG F, ZHU X T, et al. Low-resolution human pose estimation[J]. Pattern Recognition, 2022, 126: 108579.
[103] ZHENG Q H, TIAN X Y, YU Z G, et al. MobileRaT: a lightweight radio transformer method for automatic modulation classification in drone communication systems[J]. Drones, 2023, 7(10): 596.
[104] ZHAO S, GONG M, LIU T, et al. Domain generalization via entropy regularization[C]//Advances in Neural Information Processing Systems, 2020: 16096-16107.
[105] QIAO F C, ZHAO L, PENG X. Learning to learn single domain generalization[C]//Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2020: 12553-12562.
[106] XU D N, ZHANG R, GUO L J, et al. LDNet: lightweight dynamic convolution network for human pose estimation[J]. Advanced Engineering Informatics, 2022, 54: 101785.
[107] TAN M X, CHEN B, PANG R M, et al. MnasNet: platform-aware neural architecture search for mobile[C]//Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2019: 2820-2828.
[108] FANG H S, LI J F, TANG H Y, et al. AlphaPose: whole-body regional multi-person pose estimation and tracking in real-time[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023, 45(6): 7157-7173.