In the few-shot scenario, a learner must effectively generalize to unseen
classes given a small support set of labeled examples. While a relatively large
amount of research has gone into few-shot learning for image classification,
little work has been done on few-shot video classification. In this work, we
address the task of few-shot video action recognition with a set of two-stream
models. We evaluate the performance of a set of convolutional and recurrent
neural network video encoder architectures used in conjunction with three
popular metric-based few-shot algorithms. We train and evaluate using a
few-shot split of the Kinetics 600 dataset. Our experiments confirm the
importance of the two-stream setup, and find prototypical networks and pooled
long short-term memory network embeddings to give the best performance as
few-shot method and video encoder, respectively. For a 5-shot 5-way task, this
setup obtains 84.2% accuracy on the test set and 59.4% on a special "challenge"
test set, composed of highly confusable classes.

本研究介绍了针对少样本学习的视频动作识别任务，采用双流模型和三种常见的基于度量的算法，通过一组卷积和递归神经网络视频编码器进行训练和评估，证实了双流设置的重要性，并发现原型网络和池化长短期记忆网络嵌入为少样本方法和视频编码器提供了最佳性能。在 Kinetics 600 数据集上进行的 5-shot、5-way 任务中，该设置在测试集上获得了 84.2% 的准确度，而在混淆度较高的 “挑战” 测试集上获得了 59.4% 的准确度。