Continuous Gesture Recognition from Articulated Poses

@inproceedings{Evangelidis2014ContinuousGR,
  title={Continuous Gesture Recognition from Articulated Poses},
  author={Georgios D. Evangelidis and Gurkirt Singh and R. Horaud},
  booktitle={ECCV Workshops},
  year={2014}
}
  • Georgios D. Evangelidis, Gurkirt Singh, R. Horaud
  • Published in ECCV Workshops 2014
  • Computer Science
  • This paper addresses the problem of continuous gesture recognition from articulated poses. Unlike the common isolated recognition scenario, the gesture boundaries are here unknown, and one has to solve two problems: segmentation and recognition. This is cast into a labeling framework, namely every site (frame) must be assigned a label (gesture ID). The inherent constraint for a piece-wise constant labeling is satisfied by solving a global optimization problem with a smoothness term. For… CONTINUE READING
    Nonparametric Gesture Labeling from Multi-modal Data
    32
    Exploring 3D Human Action Recognition: from Offline to Online
    1
    Hands, face and joints for multi-modal human-action temporal segmentation and recognition
    3
    A Unified Framework for Multi-Modal Isolated Gesture Recognition
    28
    Discriminative training of hidden Markov Models for gesture recognition
    1

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 42 REFERENCES
    Nonparametric Gesture Labeling from Multi-modal Data
    32
    Human Action Segmentation and Recognition Using Discriminative Semi-Markov Models
    133
    Multi-modal Gesture Recognition Using Skeletal Joints and Motion Trail Model
    15
    Deep Dynamic Neural Networks for Gesture Segmentation and Recognition
    34
    Recognition and Segmentation of 3-D Human Action Using HMM and Multi-class AdaBoost
    379
    Hidden Conditional Random Fields for Gesture Recognition
    508
    Continuous Action Recognition Based on Sequence Alignment
    34
    A Multi-scale Boosted Detector for Efficient and Robust Gesture Recognition
    48
    Joint Angles Similiarities and HOG 2 for Action Recognition
    42