MVP-Shot: Multi-Velocity Progressive-Alignment Framework for Few-Shot Action Recognition

arXiv:2405.02077v1 Announce Type: new
Abstract: Recent few-shot action recognition (FSAR) methods achieve promising performance by performing semantic matching on learned discriminative features. However, most FSAR methods focus on single-scale (e.g., frame-level, segment-level, \etc) feature alignment, which ignores that human actions with the same semantic may appear at different velocities. To this end, we develop a novel Multi-Velocity Progressive-alignment (MVP-Shot) framework to progressively learn and align semantic-related action features at multi-velocity levels. Concretely, a Multi-Velocity Feature Alignment (MVFA) module is designed …

abstract action recognition alignment arxiv cs.cv etc feature features few-shot focus framework however human mvp performance recognition scale segment semantic type