Temporal Action Localization Based on Temporal Evolution Model and Multiple Instance Learning.
MMM(2019)
摘要
Temporal action localization in untrimmed long videos is an important yet challenging problem. The temporal ambiguity and the intra-class variations of temporal structure of actions make existing methods far from being satisfactory. In this paper, we propose a novel framework which firstly models each action clip based on its temporal evolution, and then adopts a deep multiple instance learning (MIL) network for jointly classifying action clips and refining their temporal boundaries. The proposed network utilizes a MIL scheme to make clip-level decisions based on temporal-instance-level decisions. Besides, a temporal smoothness constraint is introduced into the multi-task loss. We evaluate our framework on THUMOS Challenge 2014 benchmark and the experimental results show that it achieves considerable improvements as compared to the state-of-the-art methods. The performance gain is especially remarkable under precise localization with high tIoU thresholds, e.g. mAP@tIoU=0.5 is improved from 31.0% to 35.0%.
更多查看译文
关键词
Temporal action localization, Temporal evolution model, Multiple instance learning
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