arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1908.00943cs.CV
收藏

视频中近期活动的预测和描述

Prediction and Description of Near-Future Activities in Video

University of California, Riverside(加州大学河滨分校);Comcast AI(康卡斯特人工智能实验室)

Tahmida Mahmud, Mohammad Billah, Mahmudul Hasan, Amit K. Roy-Chowdhury

摘要:

现有的人类活动分析的工作大多集中在识别或早期识别的活动标签从完整或部分的观察。类似地,几乎所有现有的视频描述方法都关注视频中观察到的事件。在没有观察到预测活动的帧的情况下预测未来活动的标签和标题是一个具有挑战性的问题,具有需要预期响应的重要应用。在这项工作中,我们提出了一个系统,可以推断的标签和标题的一系列未来的活动。我们提出的用于未来活动序列的标签预测的网络有三个分支,其中第一个分支从场景中存在的对象中获取视觉特征,第二个分支获取观察到的连续活动特征,第三个分支捕获最后观察到的活动特征。然后,使用基于序列到序列学习的方法将预测的标签和观察到的场景上下文映射到有意义的字幕。在四个具有挑战性的活动分析数据集和视频描述数据集上的实验表明,我们的标签预测方法实现了与最先进技术相当的性能,我们的字幕框架优于最先进技术。

英文摘要:

Most of the existing works on human activity analysis focus on recognition or early recognition of the activity labels from complete or partial observations. Similarly, almost all of the existing video captioning approaches focus on the observed events in videos. Predicting the labels and the captions of future activities where no frames of the predicted activities have been observed is a challenging problem, with important applications that require anticipatory response. In this work, we propose a system that can infer the labels and the captions of a sequence of future activities. Our proposed network for label prediction of a future activity sequence has three branches where the first branch takes visual features from the objects present in the scene, the second branch takes observed sequential activity features, and the third branch captures the last observed activity features. The predicted labels and the observed scene context are then mapped to meaningful captions using a sequence-to-sequence learning-based method. Experiments on four challenging activity analysis datasets and a video description dataset demonstrate that our label prediction approach achieves comparable performance with the state-of-the-arts and our captioning framework outperform the state-of-the-arts.

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。

↑