Self-Supervised Learning for Visual Tracking and Recognition of Human Hand

DMCA

Self-Supervised Learning for Visual Tracking and Recognition of Human Hand (2000)

Cached

Download Links

Other Repositories/Bibliography

DBLP

by Ying Wu , Thomas S. Huang

Venue:	in Proc. AAAI National Conf. on Artificial Intelligence
Citations:	7 - 2 self

BibTeX

@INPROCEEDINGS{Wu00self-supervisedlearning,
    author = {Ying Wu and Thomas S. Huang},
    title = {Self-Supervised Learning for Visual Tracking and Recognition of Human Hand},
    booktitle = {in Proc. AAAI National Conf. on Artificial Intelligence},
    year = {2000},
    pages = {243--248}
}

OpenURL

Abstract

Due to the large variation and richness of visual inputs, statistical learning gets more and more concerned in the practice of visual processing such as visual tracking and recognition. Statistical models can be trained from a large set of training data. However, in many cases, since it is not trivial to obtain a large labeled and representative training data set, it would be difficult to obtain a satisfactory generalization. Another difficulty is how to automatically select good features for representation. By combining both labeled and unlabeled training data, this paper proposes a new learning paradigm, selfsupervised learning, to investigate the issues of learning bootstrapping and model transduction. Inductive learning and transductive learning are the two main cases of self-supervised learning, in which the proposed algorithm, Discriminant-EM (D-EM), is a specific learning technique. Vision-based gesture...

Keyphrases

visual tracking self-supervised learning human hand main case new learning paradigm training data satisfactory generalization visual processing unlabeled training data many case statistical model large set representative training data set inductive learning transductive learning visual input good feature vision-based gesture model transduction specific learning technique large variation

DMCA