arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2006.07520cs.CV
收藏

用于时间动作定位的时间融合网络:提交ActivityNet挑战赛2020(任务E)

Temporal Fusion Network for Temporal Action Localization:Submission to ActivityNet Challenge 2020 (Task E)

Huazhong University of Science and Technology(华中科技大学);DAMO Academy, Alibaba Group(阿里巴巴集团达摩院)

Zhiwu Qing, Xiang Wang, Yongpeng Sang, Changxin Gao, Shiwei Zhang, Nong Sang

摘要:

该技术报告分析了我们在Activitynet Challenge 2020举办的HACS竞赛中使用的一种时间动作定位方法。我们的任务目标是在未经裁剪的视频中定位动作的开始时间和结束时间,并预测动作类别。首先,我们利用视频级特征信息训练多个视频级动作分类模型。其次,本文着重于生成高质量的时态建议,为此,我们应用BMN生成大量的建议,以获得高召回率。然后,我们使用一种称为Refine Network的级联结构网络来细化这些建议,该网络可以在地面实况的监督下预测位置偏移和新的IOU。为了使建议更加准确,我们使用双向LSTM,Nonlocal和Transformer来捕获每个建议的局部特征与视频数据的全局特征之间的时间关系。最后,通过融合多个模型的结果,在mAP方面,我们的方法在验证集上获得40.55%,在测试集上获得40.53%,并且在该挑战中达到Rank 1。

英文摘要:

This technical report analyzes a temporal action localization method we used in the HACS competition which is hosted in Activitynet Challenge 2020.The goal of our task is to locate the start time and end time of the action in the untrimmed video, and predict action category.Firstly, we utilize the video-level feature information to train multiple video-level action classification models. In this way, we can get the category of action in the video.Secondly, we focus on generating high quality temporal proposals.For this purpose, we apply BMN to generate a large number of proposals to obtain high recall rates. We then refine these proposals by employing a cascade structure network called Refine Network, which can predict position offset and new IOU under the supervision of ground truth.To make the proposals more accurate, we use bidirectional LSTM, Nonlocal and Transformer to capture temporal relationships between local features of each proposal and global features of the video data.Finally, by fusing the results of multiple models, our method obtains 40.55% on the validation set and 40.53% on the test set in terms of mAP, and achieves Rank 1 in this challenge.

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。

↑