Cross-Domain Micro-Action Learning via Inter-Space Alignment and Prototype Calibration

Prototype distances learned independently on heterogeneous datasets are defined relative to dataset-specific geometries, so the same class-relative score need not carry the same meaning across datasets. We study cross-dataset anchor generality: whether one fixed class-reference system can provide a common class-reference coordinate for SMG and iMiGUE under a prespecified binary polarity ontology while retaining recognition utility. This is a reference-comparability problem rather than a prototype-storage or unseen-domain generalization claim. We realize it through three coupled requirements: a domain-shared class geometry is constructed, frozen source features are aligned to that reference geometry, and residual sample-level deviations are calibrated with the same fixed anchors. Cross-domain Class-conditional Shared Geometry (CCSG), a soft-gated source-to-reference mapper, and Prototype-Guided Anchor-Pair Calibration (PG-APC) implement these roles. On SMG, dataset-specific PG-APC obtains $69.00\pm 2.79\%/68.69\pm 3.12\%$ Accuracy/Macro-F1, while CCSG-PG-APC obtains $68.00\pm 4.31\%/67.65\pm 4.48\%$. On iMiGUE, the same five seeds fixed a priori give $70.38\pm 1.58\%/69.73\pm 2.18\%$ for CCSG-PG-APC and $68.65\pm 1.46\%/68.09\pm 1.92\%$ for PG-APC, a descriptive $+1.73$-point Accuracy gap. Naive pooling also degrades substantially, consistent with reference-geometry mismatch.