论文标题
更快的tad：在统一网络中使用提案生成和分类的时间动作检测
Faster-TAD: Towards Temporal Action Detection with Proposal Generation and Classification in a Unified Network
论文作者
论文摘要
时间动作检测（TAD）旨在检测未修剪视频中动作实例的语义标签和边界。当前的主流方法是多步解决方案，其效率和灵活性不足。在本文中，我们通过重新设置更快的rcnn架构来提出一个统一的TAD网络，称为更快的TAD。为了解决TAD的独特难度，我们对原始框架进行了重要改进。我们提出了一个新的上下文自适应提案模块和创新的假港口生成块。更重要的是，我们使用原子动作功能来提高性能。更快的TAD简化了TAD的管道，并在许多基准测试中获得了出色的性能，即ActivityNet-1.3（40.01％地图），HACS段（38.39％地图），Soccernet-action-action Spotion发现（54.09％的地图）。它的表现可以超过现有的单网络检测器的幅度很大。
Temporal action detection (TAD) aims to detect the semantic labels and boundaries of action instances in untrimmed videos. Current mainstream approaches are multi-step solutions, which fall short in efficiency and flexibility. In this paper, we propose a unified network for TAD, termed Faster-TAD, by re-purposing a Faster-RCNN like architecture. To tackle the unique difficulty in TAD, we make important improvements over the original framework. We propose a new Context-Adaptive Proposal Module and an innovative Fake-Proposal Generation Block. What's more, we use atomic action features to improve the performance. Faster-TAD simplifies the pipeline of TAD and gets remarkable performance on lots of benchmarks, i.e., ActivityNet-1.3 (40.01% mAP), HACS Segments (38.39% mAP), SoccerNet-Action Spotting (54.09% mAP). It outperforms existing single-network detector by a large margin.
