TY -的A2 -卡索拉,Miguel AU - Maraghi Vali Ollah AU -法耶兹,可并卡里姆PY - 2021 DA - 2021/06/10 TI -扩展人造物交互识别的视频通过Zero-Shot学习SP - 9922697六世- 2021 AB -承认人类活动是一个重要的在计算机视觉领域。最人类活动包括人类和对象之间的交互。许多成功的作品在人造物交互(海)近年来识别,取得了可接受的结果。不过,他们完全有监督和所有海需要训练带安全标签的数据。由于人造物的巨大空间交互,清单,并提供所有可能的类别的训练数据是昂贵的和不切实际的。我们提出一个方法扩展人造物交互识别的视频数据通过zero-shot学习技术来解决这个问题。我们的方法识别一个动词和一个对象的视频,使一个海类。识别的动词和对象,而不是海下允许确定一个新的动词和对象的组合。所以,新海类可以被识别,未见的识别器系统。我们引入神经网络架构,可以理解和表示视频数据。 The proposed system learns verbs and objects from available training data at the training phase and can identify the verb-object pairs in a video at test time. So, the system can identify the HOI class with different combinations of objects and verbs. Also, we propose to use lateral information for combining the verbs and the objects to make valid verb-object pairs. It helps to prevent the detection of rare and probably wrong HOIs. The lateral information comes from word embedding techniques. Furthermore, we propose a new feature aggregation method for aggregating extracted high-level features from video frames before feeding them to the classifier. We illustrate that this feature aggregation method is more effective for actions that include multiple subactions. We evaluated our system by recently introduced Charades challengeable dataset, which has lots of HOI categories in videos. We show that our proposed system can detect unseen HOI classes in addition to the acceptable recognition of seen types. Therefore, the number of classes identifiable by the system is greater than the number of classes used for training. SN - 1687-5265 UR - https://doi.org/10.1155/2021/9922697 DO - 10.1155/2021/9922697 JF - Computational Intelligence and Neuroscience PB - Hindawi KW - ER -