Improved Spatio-temporal Action Localization for Surveillance Videos
2021 Digital Image Computing: Techniques and Applications (DICTA)(2021)
摘要
We present an improved spatiotemporal action localization framework that operates in an online manner. Current state of the art approaches have achieved remarkable results mainly due to the advancements in action recognition models. These approaches have commonly followed a two-stage pipeline consisting of a region proposal stage and an action classification stage. Recently, the improvement in spa...
更多查看译文
关键词
Location awareness,Surveillance,Digital images,Pipelines,Benchmark testing,Spatiotemporal phenomena,Proposals
AI 理解论文
溯源树
样例
![](https://originalfileserver.aminer.cn/sys/aminer/pubs/mrt_preview.jpeg)
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要