• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>IEEE International Conference on Image Processing >INTRODUCING TEMPORAL ORDER OF DOMINANT VISUAL WORD SUB-SEQUENCES FOR HUMAN ACTION RECOGNITION
【24h】

INTRODUCING TEMPORAL ORDER OF DOMINANT VISUAL WORD SUB-SEQUENCES FOR HUMAN ACTION RECOGNITION

机译：介绍人类行动识别的主导视觉词子序列的时间顺序

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

We present a novel video representation for human action recognition by considering temporal sequences of visual words. Based on state-of-the-art dense trajectories, we introduce temporal bundles of dominant, that is most frequent, visual words. These are employed to construct a complementary action representation of ordered dominant visual word sequences, that additionally incorporates fine grained temporal information. We exploit the introduced temporal information by applying local sub-sequence alignment that quantifies the similarity between sequences. This facilitates the fusion of our representation with the bag-of-visual-words (BoVW) representation. Our approach incorporates sequential temporal structure and results in a low-dimensional representation compared to the BoVW, while still yielding a descent result when combined with it. Experiments on the KTH, Hollywood2 and the challenging HMDB51 datasets show that the proposed framework is complementary to the BoVW representation, which discards temporal order.
机译：我们通过考虑视觉词的时间序列，为人类行动识别提供了一种新的视频表示。基于最先进的密集轨迹，我们介绍了时间束的主导，最常见的，视觉词语。这些用于构造有序显性视觉词序列的互补动作表示，其另外包含细粒度的时间信息。我们通过应用局部子序列对齐来利用引入的时间信息，该对齐量量化序列之间的相似性。这有助于与视觉文字（BOVW）表示的融合我们的代表。我们的方法包含顺序时间结构并导致与BOVW相比的低维表示，同时与其结合时仍然产生下降结果。 Kth，Hollywood2和挑战HMDB51数据集的实验表明，所提出的框架与BOVW表示互补，丢弃时间顺序。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号