论文标题
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
论文作者
论文摘要
精确地命名视频中描绘的动作可能是一项具有挑战性的，通常是模棱两可的任务。与代表名词（例如狗，猫，椅子等）表示的对象实例相反，在行动的情况下，人类注释者通常对构成特定动作的什么（例如慢跑而不是跑步）缺乏共识。实际上，给定的视频可以包含相同动作的多个有效的正面注释。结果，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，我们应对仅来自单个积极培训标签的培训多标签动作识别模型的挑战。我们提出了两种基于生成从火车组中类似实例采样的伪训练示例的方法。与使用模型衍生的伪标签的其他方法不同，我们的伪标签来自人类注释，并根据特征相似性选择。为了验证我们的方法，我们通过手动注释带有多个动词标签的Epic-Kitchens-100验证集的子集来创建一个新的评估基准。我们在此新测试集上介绍了结果，并在新版本的HMDB-51（称为Cystusion-HMDB-102）上提供了其他结果，在这种情况下，我们在这种情况下均超过了现有的方法。数据和代码可从https://github.com/kiyoon/verb_ambiguity获得
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
