论文标题
具有关系感知金字塔网络的准确时间动作提案生成
Accurate Temporal Action Proposal Generation with Relation-Aware Pyramid Network
论文作者
论文摘要
准确的时间动作建议在检测未修剪视频的动作中起着重要作用。现有的方法在捕获全球上下文信息和同时以不同持续时间的方式定位动作方面存在困难。为此，我们提出了一个关系感知的金字塔网络（RAPNET）来生成高度准确的时间动作建议。在Rapnet中，引入了一个新颖的关系感知模块，以利用本地特征之间的双向远程关系进行上下文提炼。这个嵌入式模块在给定预定义的锚点盒的情况下，根据其多粒性时间提案的产生能力增强了RAPNET。我们进一步介绍了一个两阶段的调整方案，以完善提案边界并衡量其对包含摘要级行动的动作的信心。关于具有挑战性的活动网和Thumos14基准的广泛实验表明，我们的RAPNET对现有最新方法产生了较高的准确建议。
Accurate temporal action proposals play an important role in detecting actions from untrimmed videos. The existing approaches have difficulties in capturing global contextual information and simultaneously localizing actions with different durations. To this end, we propose a Relation-aware pyramid Network (RapNet) to generate highly accurate temporal action proposals. In RapNet, a novel relation-aware module is introduced to exploit bi-directional long-range relations between local features for context distilling. This embedded module enhances the RapNet in terms of its multi-granularity temporal proposal generation ability, given predefined anchor boxes. We further introduce a two-stage adjustment scheme to refine the proposal boundaries and measure their confidence in containing an action with snippet-level actionness. Extensive experiments on the challenging ActivityNet and THUMOS14 benchmarks demonstrate our RapNet generates superior accurate proposals over the existing state-of-the-art methods.
