• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops >Cross-Stream Selective Networks for Action Recognition
【24h】

Cross-Stream Selective Networks for Action Recognition

机译：用于动作识别的跨流选择性网络

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

摘要

Combining multiple information streams has shown obvious improvements in video action recognition. Most existing works handle each stream independently or perform a simple combination on temporally simultaneous samples in multi-streams, which fails to make full use of the streamwise complementary property due to the negligence of the temporal pattern gaps among streams. In this paper, we propose a cross-stream selective network (CSN) to properly integrate and evaluate information in multi-streams. The proposed CSN first introduces a local selective-sampling module (LSM), which can find asynchronous correspondences among streams and construct high-correlated sample groups across multiple information streams. This LSM can effectively deal with the temporal dis-alignment among different streams, leading to a better integration of cross-stream information. We further introduce a global adaptive-weighting module (GAM). It adaptively evaluates the importance weights for each cross-stream sample group and selects temporally more important ones in action recognition. With the integration of cross-stream information, our GAM can obtain more reasonable importance than the existing single-stream weighting schemes. Extensive experiments on benchmark datasets of UCF101 and HMDB51 demonstrate the effectiveness of our approach over previous state-of-the-art methods.
机译：组合多个信息流已经显示了视频动作识别的显而易见。大多数现有的作品独立处理每个流或在多流中的时间上同时进行简单的组合，这不能由于流在流之间的时间模式间隙的疏忽而无法充分利用流动互补特性。在本文中，我们提出了一种跨流选择性网络（CSN），以适当地集成和评估多流中的信息。所提出的CSN首先介绍了局部选择性采样模块（LSM），其可以在流之间找到异步对应关系，并在多个信息流中构建高相关的样本组。该LSM可以有效地处理不同流之间的时间分数对齐，从而更好地集成了跨流信息。我们进一步介绍了全局自适应加权模块（GAM）。它自适应地评估每个跨流样本组的重要性权重，并且在动作识别中选择时间上更重要的重量。随着跨流信息的集成，我们的游戏可以获得比现有的单流加权方案更合理的重要性。关于UCF101和HMDB51的基准数据集的广泛实验证明了我们对先前最先进的方法的效果。

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