Pedestrians are vulnerable participants on streets and their actions serve as important cues for motion prediction so as to avoid collision. In this paper, we address the problem of pedestrian action recognition for the first time. We first introduce a new dataset namely Pedestrian Action Recognition Dataset (PARD) which serves as the database for experiments, and provide an efficient baseline MFVGG, reaching comparable performance to previous methods at lower costs. To better handle the

more »

... al problem, we further improve the baseline from the following two aspects: first, we leverage pose prior to enrich the feature representations; second, we propose a two-stream neural architecture search (NAS) method to obtain the optimal network architecture tailored to our task. From the experimental results on PARD, our method outperforms previous top performing action recognition methods. The dataset and code will be made publicly available.