arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1706.04122cs.CV
收藏

基于最大间隔和语义特征的复杂场景连续事件检测

Joint Max Margin and Semantic Features for Continuous Event Detection in Complex Scenes

Queensland University of Technology(昆士兰科技大学);Carnegie Mellon University(卡内基梅隆大学)

Iman Abbasnejad, Sridha Sridharan, Simon Denman, Clinton Fookes, Simon Lucey

摘要:

在本文中,复杂的事件检测在连续域(即未知的开始和结束位置的事件)的问题得到解决。现有的事件检测方法仅限于从视频的局部空间或时空补丁中提取的特征。然而,这使得模型容易受到具有类似概念的事件的影响,例如“打开抽屉”和“打开橱柜”。在这项工作中,为了解决上述限制,我们提出了一种新的模型的基础上结合的语义和时间特征提取的视频帧。我们训练的最大利润分类器上提取的功能,在一个自适应的框架,能够检测未知的开始和结束位置的事件。我们的模型是基于双向区域神经网络和大间隔结构输出支持向量机。我们的模型的通用性允许它简单地应用于不同的标记和未标记的数据集。最后,我们在三个具有挑战性的数据集上测试了我们的算法,“UCF 101-动作识别”,“MPII烹饪活动”和“好莱坞”,我们报告了最先进的性能。

英文摘要:

In this paper the problem of complex event detection in the continuous domain (i.e. events with unknown starting and ending locations) is addressed. Existing event detection methods are limited to features that are extracted from the local spatial or spatio-temporal patches from the videos. However, this makes the model vulnerable to the events with similar concepts e.g. "Open drawer" and "Open cupboard". In this work, in order to address the aforementioned limitations we present a novel model based on the combination of semantic and temporal features extracted from video frames. We train a max-margin classifier on top of the extracted features in an adaptive framework that is able to detect the events with unknown starting and ending locations. Our model is based on the Bidirectional Region Neural Network and large margin Structural Output SVM. The generality of our model allows it to be simply applied to different labeled and unlabeled datasets. We finally test our algorithm on three challenging datasets, "UCF 101-Action Recognition", "MPII Cooking Activities" and "Hollywood", and we report state-of-the-art performance.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑