A Unified Framework for Real-world Skeleton-based Action Recognition
(BMVC'2021 Oral Presentation)

Di Yang*      Yaohui Wang*      Antitza Dantcheva      Lorenzo Garattoni      Gianpiero Francesca      François Brémond

Inria,    Université Côte d'Azur,    Toyota Motor Europe


Abstract

In this work, we introduce UNIK, a novel topology-free skeleton-based action recognition method that is not only effective to learn spatio-temporal features on human skeleton sequences but also able to generalize across datasets. This is achieved by learning an optimal dependency matrix from the uniform distribution based on a multi-head attention mechanism. Moreover, to study the cross-domain generalizability of skeleton-based action recognition in real-world videos, we re-evaluate state-of-the-art approaches as well as the proposed UNIK in light of a novel Posetics dataset. This dataset is created from Kinetics-400 videos by estimating, refining and filtering poses. We provide an analysis on how much performance improves on the smaller benchmark datasets after pre-training on Posetics for the action classification task. Experimental results show that the proposed UNIK, with pre-training on Posetics, generalizes well and outperforms state-of-the-art when transferred onto four target action classification datasets: Toyota Smarthome, Penn Action, NTU-RGB+D 60 and NTU-RGB+D 120.

[Paper]      [Code]      [Posetics Dataset]