Few-shot action recognition, i.e. recognizing new classes given only a few examples, benefits from incorporating temporal information. Prior work either encodes such information in the representation itself and learns classifiers at test time, or obtains frame-level features performs pairwise matching. We first evaluate number of matching-based approaches using spatio-temporal backbones, compar...

Person-person mutual action recognition (also referred to as interaction recognition) is an important research branch of human activity analysis. Current solutions in the field – mainly dominated by CNNs, GCNs and LSTMs often consist complicated architectures mechanisms embed relationships between two persons on architecture itself, ensure patterns can be properly learned. Our main contribution...