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 2008.11149cs.CVcs.AIcs.LGeess.IV
收藏

餐厅视频中的时空动作识别

Spatiotemporal Action Recognition in Restaurant Videos

Carnegie Mellon University(卡内基梅隆大学)

Akshat Gupta, Milan Desai, Wusheng Liang, Magesh Kannan

摘要:

时空动作识别是对视频中的动作进行定位和分类的任务。我们的项目将此任务应用于分析餐厅工作人员准备食物的视频片段,其潜在应用包括自动结账和库存管理。这些视频与研究人员习惯的标准化数据集截然不同,因为它们涉及小对象,快速动作和众所周知的不平衡数据类。我们探索两种方法。第一种方法涉及熟悉的对象检测器You Only Look Once,另一种方法应用最近提出的动作识别模拟,You Only Watch Once。首先,我们使用卷积LSTM设计并实现了一种新颖的、经常性的YOLO修改,并探索了这种网络训练中的各种微妙之处。在第二部分中,我们研究了YOWO三维卷积捕捉我们独特数据集的时空特征的能力

英文摘要:

Spatiotemporal action recognition is the task of locating and classifying actions in videos. Our project applies this task to analyzing video footage of restaurant workers preparing food, for which potential applications include automated checkout and inventory management. Such videos are quite different from the standardized datasets that researchers are used to, as they involve small objects, rapid actions, and notoriously unbalanced data classes. We explore two approaches. The first approach involves the familiar object detector You Only Look Once, and another applying a recently proposed analogue for action recognition, You Only Watch Once. In the first, we design and implement a novel, recurrent modification of YOLO using convolutional LSTMs and explore the various subtleties in the training of such a network. In the second, we study the ability of YOWOs three dimensional convolutions to capture the spatiotemporal features of our unique dataset

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。

↑