Towards Generalized Action Recognition on Low-Resolutions with Domain-Invariant Representation

Abstract

This paper studies cross-domain/species action recognition from low-resolution videos with sharp appearance variations and domain-specific biases. Its attractive viewpoint is mining domain-invariant representations of cross-domain/species features under rough spatial details to enhance recognition and generalization, overcoming the significant decline of existing methods. To address this, we propose a generalized Action recognition framework for Low-resolution conditions with Domain-invariant Representation learning, named ActLDR, designed to learn domain-invariant representations. First, it decomposes video understanding into spatial and temporal pathways for explicitly separating domain-dependent appearance cues from robust motion dynamics; Second, it constructs a Spatial-Temporal Feature Exchange module to enable cross-branch refinement and suppress domain bias; Third, we inject Gaussian feature interference to simulate feature corruption and enforce prediction-level consistency to encourage stable representations. Empirical results demonstrate that our proposal outperforms previous methods, significantly improving robustness across resolutions, domains, and species, and demonstrating outstanding generalization and transferability.