Neuron: Learning Context-Aware Evolving Representations for Zero-Shot Skeleton Action Recognition

TL;DR

This paper introduces Neuron, a novel framework for zero-shot skeleton action recognition that dynamically evolves representations to better capture fine-grained cross-modal relationships, improving unseen class generalization.

Contribution

The paper proposes a dual skeleton-semantic synergistic framework with context-aware guidance, incorporating spatial-temporal prototypes and memory mechanisms for enhanced zero-shot recognition.

Findings

Outperforms existing methods on benchmark datasets.

Effectively captures fine-grained skeleton-semantic correlations.

Demonstrates strong generalization to unseen action categories.

Abstract

Zero-shot skeleton action recognition is a non-trivial task that requires robust unseen generalization with prior knowledge from only seen classes and shared semantics. Existing methods typically build the skeleton-semantics interactions by uncontrollable mappings and conspicuous representations, thereby can hardly capture the intricate and fine-grained relationship for effective cross-modal transferability. To address these issues, we propose a novel dyNamically Evolving dUal skeleton-semantic syneRgistic framework with the guidance of cOntext-aware side informatioN (dubbed Neuron), to explore more fine-grained cross-modal correspondence from micro to macro perspectives at both spatial and temporal levels, respectively. Concretely, 1) we first construct the spatial-temporal evolving micro-prototypes and integrate dynamic context-aware side information to capture the intricate and synergistic skeleton-semantic correlations step-by-step, progressively refining cross-model alignment; and 2) we introduce the spatial compression and temporal memory mechanisms to guide the growth of spatial-temporal micro-prototypes, enabling them to absorb structure-related spatial representations and regularity-dependent temporal patterns. Notably, such processes are analogous to the learning and growth of neurons, equipping the framework with the capacity to generalize to novel unseen action categories. Extensive experiments on various benchmark datasets demonstrated the superiority of the proposed method.