Efficient Annotation and Learning for 3D Hand Pose Estimation: A Survey

被引:9
|
作者
Ohkawa, Takehiko [1 ]
Furuta, Ryosuke [1 ]
Sato, Yoichi [1 ]
机构
[1] Univ Tokyo, Inst Ind Sci, 4-6-1 Komaba,Meguro Ku, Tokyo 1538505, Japan
关键词
Hand pose estimation; Efficient annotation; Learning with limited labels; TRACKING;
D O I
10.1007/s11263-023-01856-0
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In this survey, we present a systematic review of 3D hand pose estimation from the perspective of efficient annotation and learning. 3D hand pose estimation has been an important research area owing to its potential to enable various applications, such as video understanding, AR/VR, and robotics. However, the performance of models is tied to the quality and quantity of annotated 3D hand poses. Under the status quo, acquiring such annotated 3D hand poses is challenging, e.g., due to the difficulty of 3D annotation and the presence of occlusion. To reveal this problem, we review the pros and cons of existing annotation methods classified as manual, synthetic-model-based, hand-sensor-based, and computational approaches. Additionally, we examine methods for learning 3D hand poses when annotated data are scarce, including self-supervised pretraining, semi-supervised learning, and domain adaptation. Based on the study of efficient annotation and learning, we further discuss limitations and possible future directions in this field.
引用
收藏
页码:3193 / 3206
页数:14
相关论文
共 50 条
  • [1] Efficient Annotation and Learning for 3D Hand Pose Estimation: A Survey
    Takehiko Ohkawa
    Ryosuke Furuta
    Yoichi Sato
    International Journal of Computer Vision, 2023, 131 : 3193 - 3206
  • [2] A survey on 3D hand pose estimation: Cameras, methods, and datasets
    Li, Rui
    Liu, Zhenyu
    Tan, Jianrong
    PATTERN RECOGNITION, 2019, 93 : 251 - 272
  • [3] Lightweight 3D hand pose estimation by cascading CNNs with reinforcement learning
    Chen, Mingqi
    Li, Shaodong
    Shuang, Feng
    Liu, Xi
    Luo, Kai
    He, Wenbo
    PATTERN RECOGNITION LETTERS, 2023, 174 : 137 - 144
  • [4] 3D Hand Pose Estimation with Neural Networks
    Antonio Serra, Jose
    Garcia-Rodriguez, Jose
    Orts-Escolano, Sergio
    Manuel Garcia-Chamizo, Juan
    Angelopoulou, Anastassia
    Psarrou, Alexandra
    Mentzelopoulos, Markos
    Montoyo-Bojo, Javier
    Dominguez, Enrique
    ADVANCES IN COMPUTATIONAL INTELLIGENCE, PT II, 2013, 7903 : 504 - +
  • [5] Learning a deep network with spherical part model for 3D hand pose estimation
    Chen, Tzu-Yang
    Ting, Pai-Wen
    Wu, Min-Yu
    Fu, Li-Chen
    PATTERN RECOGNITION, 2018, 80 : 1 - 20
  • [6] Recurrent 3D Hand Pose Estimation Using Cascaded Pose-Guided 3D Alignments
    Deng, Xiaoming
    Zuo, Dexin
    Zhang, Yinda
    Cui, Zhaopeng
    Cheng, Jian
    Tan, Ping
    Chang, Liang
    Pollefeys, Marc
    Fanello, Sean
    Wang, Hongan
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2023, 45 (01) : 932 - 945
  • [7] CASCADED POINT NETWORK FOR 3D HAND POSE ESTIMATION
    Dou, Yikun
    Wang, Xuguang
    Zhu, Yuying
    Deng, Xiaoming
    Ma, Cuixia
    Chang, Liang
    Wang, Hongan
    2019 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2019, : 1982 - 1986
  • [8] 3D Hand Pose Estimation with a Single Infrared Camera via Domain Transfer Learning
    Park, Gabyong
    Kim, Tae-Kyun
    Woo, Woontack
    2020 IEEE INTERNATIONAL SYMPOSIUM ON MIXED AND AUGMENTED REALITY (ISMAR 2020), 2020, : 588 - 599
  • [9] ASCS-Reinforcement Learning: A Cascaded Framework for Accurate 3D Hand Pose Estimation
    Chen, Mingqi
    Shuang, Feng
    Li, Shaodong
    Liu, Xi
    PROCEEDINGS OF THE 2023 ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA RETRIEVAL, ICMR 2023, 2023, : 335 - 342
  • [10] Attention-Based Pose Sequence Machine for 3D Hand Pose Estimation
    Guo, Fangtai
    He, Zaixing
    Zhang, Shuyou
    Zhao, Xinyue
    Tan, Jianrong
    IEEE ACCESS, 2020, 8 : 18258 - 18269