Action Recognition by Hierarchical Mid-level Action Elements

2015 IEEE International Conference on Computer Vision (ICCV)(2015)

引用 94|浏览129
暂无评分
摘要
Realistic videos of human actions exhibit rich spatiotemporal structures at multiple levels of granularity: an action can always be decomposed into multiple finer-grained elements in both space and time. To capture this intuition, we propose to represent videos by a hierarchy of mid-level action elements (MAEs), where each MAE corresponds to an action-related spatiotemporal segment in the video. We introduce an unsupervised method to generate this representation from videos. Our method is capable of distinguishing action-related segments from background segments and representing actions at multiple spatiotemporal resolutions. Given a set of spatiotemporal segments generated from the training data, we introduce a discriminative clustering algorithm that automatically discovers MAEs at multiple levels of granularity. We develop structured models that capture a rich set of spatial, temporal and hierarchical relations among the segments, where the action label and multiple levels of MAE labels are jointly inferred. The proposed model achieves state-of-the-art performance in multiple action recognition benchmarks. Moreover, we demonstrate the effectiveness of our model in real-world applications such as action recognition in large-scale untrimmed videos and action parsing.
更多
查看译文
关键词
action recognition,MAE label,action label,hierarchical relation,temporal relation,spatial relation,structured models,discriminative clustering algorithm,training data,spatiotemporal resolution,action representation,background segments,unsupervised method,video,action-related spatiotemporal segment,spatiotemporal structures,human action,hierarchical mid-level action elements
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要