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 2210.04933cs.CV
收藏

一个动作值得多个词:处理动作识别中的歧义

An Action Is Worth Multiple Words: Handling Ambiguity in Action Recognition

University of Edinburgh(爱丁堡大学)

Kiyoon Kim, Davide Moltisanti, Oisin Mac Aodha, Laura Sevilla-Lara

摘要:

准确地命名视频中描述的动作可能是一项具有挑战性且经常模糊的任务。与表示为名词的对象实例(例如狗、猫、椅子等)相反,在动作的情况下,人类注释者通常缺乏关于什么构成特定动作(例如慢跑与跑步)的共识。在实践中,给定的视频可以包含针对同一动作的多个有效的积极注释。因此,视频数据集通常包含大量的标签噪声和原子动作类之间的重叠。在这项工作中,我们解决了仅从单个正训练标签训练多标签动作识别模型的挑战。我们提出了两种方法,是基于生成伪训练样本的训练集内类似的情况下。与其他使用模型衍生伪标签的方法不同,我们的伪标签来自人类注释,并基于特征相似性进行选择。为了验证我们的方法,我们创建了一个新的评估基准手动注释EPIC-Kitchen-100的验证集的一个子集,多个动词标签。我们在这个新的测试集上给出了结果,以及在新版本的HMDB-51上的其他结果,称为混淆-HMDB-102,在这两种情况下,我们都优于现有的方法。数据和代码可在https://github.com/kiyoon/verb_ambiguity上获得

英文摘要:

Precisely naming the action depicted in a video can be a challenging and oftentimes ambiguous task. In contrast to object instances represented as nouns (e.g. dog, cat, chair, etc.), in the case of actions, human annotators typically lack a consensus as to what constitutes a specific action (e.g. jogging versus running). In practice, a given video can contain multiple valid positive annotations for the same action. As a result, video datasets often contain significant levels of label noise and overlap between the atomic action classes. In this work, we address the challenge of training multi-label action recognition models from only single positive training labels. We propose two approaches that are based on generating pseudo training examples sampled from similar instances within the train set. Unlike other approaches that use model-derived pseudo-labels, our pseudo-labels come from human annotations and are selected based on feature similarity. To validate our approaches, we create a new evaluation benchmark by manually annotating a subset of EPIC-Kitchens-100's validation set with multiple verb labels. We present results on this new test set along with additional results on a new version of HMDB-51, called Confusing-HMDB-102, where we outperform existing methods in both cases. Data and code are available at https://github.com/kiyoon/verb_ambiguity

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。

↑