CVApr 20

Beyond Binary Contrast: Modeling Continuous Skeleton Action Spaces with Transitional Anchors

arXiv:2604.1791480.8h-index: 2Has Code
Predicted impact top 41% in CV · last 90 daysOriginality Incremental advance
AI Analysis

For skeleton-based action recognition, this work addresses the limitation of binary contrastive objectives by modeling motion continuity, leading to improved representation quality.

TranCLR introduces a contrastive learning framework with transitional anchors to model continuous skeleton action spaces, achieving superior accuracy and calibration on NTU RGB+D, NTU RGB+D 120, and PKU-MMD datasets.

Self-supervised contrastive learning has emerged as a powerful paradigm for skeleton-based action recognition by enforcing consistency in the embedding space. However, existing methods rely on binary contrastive objectives that overlook the intrinsic continuity of human motion, resulting in fragmented feature clusters and rigid class boundaries. To address these limitations, we propose TranCLR, a Transitional anchor-based Contrastive Learning framework that captures the continuous geometry of the action space. Specifically, the proposed Action Transitional Anchor Construction (ATAC) explicitly models the geometric structure of transitional states to enhance the model's perception of motion continuity. Building upon these anchors, a Multi-Level Geometric Manifold Calibration (MGMC) mechanism is introduced to adaptively calibrate the action manifold across multiple levels of continuity, yielding a smoother and more discriminative representation space. Extensive experiments on the NTU RGB+D, NTU RGB+D 120 and PKU-MMD datasets demonstrate that TranCLR achieves superior accuracy and calibration performance, effectively learning continuous and uncertainty-aware skeleton representations. The code is available at https://github.com/Philchieh/TranCLR.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes