Domain-adaptive discriminative one-shot learning of gestures

<p>The objective of this paper is to recognize gestures in videos &ndash; both localizing the gesture and classifying it into one of multiple classes.</p> <p>We show that the performance of a gesture classifier learnt from a single (strongly supervised) training example can be...

Mô tả đầy đủ

Chi tiết về thư mục
Những tác giả chính: Pfister, T, Charles, J, Zisserman, A
Định dạng: Conference item
Ngôn ngữ:English
Được phát hành: Springer 2014