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 2106.10271cs.CV
收藏

基于Transformer的端到端瞬时动作检测

End-to-end Temporal Action Detection with Transformer

Huazhong University of Science and Technology(华中科技大学);Alibaba Group(阿里巴巴集团);ByteDance Inc.(字节跳动公司)

Xiaolong Liu, Qimeng Wang, Yao Hu, Xu Tang, Shiwei Zhang, Song Bai, Xiang Bai

摘要:

时序动作检测的目的是确定未裁剪视频中每个动作实例的语义标签和时间间隔。这是视频理解中一项基础性和挑战性的任务。以前的方法通过复杂的管道来解决这个任务。它们通常需要训练多个网络,并涉及手工设计的操作,例如非最大抑制和锚点生成,这限制了灵活性并阻止了端到端学习。在本文中,我们提出了一个端到端的基于transformer的方法,称为TadTR。给定一个称为动作查询的可学习嵌入的小集合,TadTR自适应地从每个查询的视频中提取时间上下文信息,并直接预测具有上下文的动作实例。为了使Transformer能够适应网络环境,我们提出了三点改进来增强其局部感知能力.核心是一个时间可变形的注意力模块,它有选择地关注视频中的一组稀疏的关键片段。分别设计了一个分段细化机制和一个动作性回归头来细化预测实例的边界和置信度。有了这样一个简单的管道,TadTR需要比以前的检测器更低的计算成本,同时保持显着的性能。作为一个独立的检测器,它在THUMOS 14(56.7% mAP)和HACS Segments(32.09% mAP)上实现了最先进的性能。结合额外的动作分类器,它在ActivityNet-1.3上获得了36.75%的mAP。代码可在https://github.com/xlliu7/TadTR上获得。

英文摘要:

Temporal action detection (TAD) aims to determine the semantic label and the temporal interval of every action instance in an untrimmed video. It is a fundamental and challenging task in video understanding. Previous methods tackle this task with complicated pipelines. They often need to train multiple networks and involve hand-designed operations, such as non-maximal suppression and anchor generation, which limit the flexibility and prevent end-to-end learning. In this paper, we propose an end-to-end Transformer-based method for TAD, termed TadTR. Given a small set of learnable embeddings called action queries, TadTR adaptively extracts temporal context information from the video for each query and directly predicts action instances with the context. To adapt Transformer to TAD, we propose three improvements to enhance its locality awareness. The core is a temporal deformable attention module that selectively attends to a sparse set of key snippets in a video. A segment refinement mechanism and an actionness regression head are designed to refine the boundaries and confidence of the predicted instances, respectively. With such a simple pipeline, TadTR requires lower computation cost than previous detectors, while preserving remarkable performance. As a self-contained detector, it achieves state-of-the-art performance on THUMOS14 (56.7% mAP) and HACS Segments (32.09% mAP). Combined with an extra action classifier, it obtains 36.75% mAP on ActivityNet-1.3. Code is available at https://github.com/xlliu7/TadTR.

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。

↑