Temporal Action Detection Using a Statistical Language Model
Temporal Action Detection Using a Statistical Language Model
复制标题
DOI：
10.1109/cvpr.2016.341
复制
发表时间：
2016-06
期刊：
影响因子：
--
通讯作者：
Alexander Richard;Juergen Gall
中科院分区：
文献类型：
--
作者：
Alexander Richard;Juergen Gall
虽然目前对预分割视频片段的动作识别方法已经达到了很高的精度，但时间动作检测仍然远没有达到相当好的效果。在不同长度的视频中自动定位和分类相关的动作片段是一项具有挑战性的任务。我们提出了一种新的时间动作检测方法，包括统计长度和语言建模来表示时间和上下文结构。我们的方法旨在全局优化三个组成部分的联合概率，一个长度和语言模型和一个判别行为模型，而不做中间决策。用动态规划方法解决了在指数级搜索空间中寻找最可能的动作序列和相应的段边界的问题。我们在Thumos 14（一个大型动作检测数据集）上对每个模型组件进行了广泛的评估，并在三个数据集上报告了最新的结果。
While current approaches to action recognition on presegmented video clips already achieve high accuracies, temporal action detection is still far from comparably good results. Automatically locating and classifying the relevant action segments in videos of varying lengths proves to be a challenging task. We propose a novel method for temporal action detection including statistical length and language modeling to represent temporal and contextual structure. Our approach aims at globally optimizing the joint probability of three components, a length and language model and a discriminative action model, without making intermediate decisions. The problem of finding the most likely action sequence and the corresponding segment boundaries in an exponentially large search space is addressed by dynamic programming. We provide an extensive evaluation of each model component on Thumos 14, a large action detection dataset, and report state-of-the-art results on three datasets.