标题：Learning action patterns in difference images for efficient action recognition
作者：Lu, Guoliang; Kudo, Mineichi
作者机构：[Lu, Guoliang; Kudo, Mineichi] Hokkaido Univ, Grad Sch Informat Sci & Technol, Sapporo, Hokkaido 0600814, Japan.; [Lu, Guoliang] Shandong Univ, Sch 更多
通讯作者地址：[Lu, GL]Hokkaido Univ, Grad Sch Informat Sci & Technol, Sapporo, Hokkaido 0600814, Japan.
关键词：Action patterns; Efficient action recognition; Temporal; self-similarities; Bag-of-words
摘要：A new framework is presented for single-person oriented action recognition. This framework does not require detection/location of bounding boxes of human body nor motion estimation in each frame. The novel descriptor/pattern for action representation is learned with local temporal self-similarities (LTSSs) derived directly from difference images. The bag-of-words framework is then employed for action classification taking advantages of these descriptors. We investigated the effectiveness of the framework on two public human action datasets: the Weizmann dataset and the KTH dataset In the Weizmann dataset, the proposed framework achieves a performance of 95.6% in the recognition rate and that of 91.1% in the KTH dataset, both of which are competitive with those of state-of-the-art approaches, but it has a high potential to achieve a faster execution performance. (C) 2013 Elsevier B.V. All rights reserved.