ROCVLGNov 20, 2019

A Human Action Descriptor Based on Motion Coordination

arXiv:1911.08928v19 citations
Originality Incremental advance
AI Analysis

This work addresses action recognition for computer vision applications, but it appears incremental as it builds on known principles of motion coordination.

The paper tackles human action recognition by introducing a coordination-based descriptor (CODE) that identifies informative joints and incorporates joint velocities and correlations, achieving recognition results on HDM05 and Berkeley MHAD datasets.

In this paper, we present a descriptor for human whole-body actions based on motion coordination. We exploit the principle, well known in neuromechanics, that humans move their joints in a coordinated fashion. Our coordination-based descriptor (CODE) is computed by two main steps. The first step is to identify the most informative joints which characterize the motion. The second step enriches the descriptor considering minimum and maximum joint velocities and the correlations between the most informative joints. In order to compute the distances between action descriptors, we propose a novel correlation-based similarity measure. The performance of CODE is tested on two public datasets, namely HDM05 and Berkeley MHAD, and compared with state-of-the-art approaches, showing recognition results.

Foundations

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

Your Notes