Local Self-Expression Subspace Learning Network for Motion Capture Data

Guiyu Xia

doi:10.1109/TIP.2022.3189822

Local Self-Expression Subspace Learning Network for Motion Capture Data

2022-01-01

2

PRE

AI

DOI：10.1109/TIP.2022.3189822

Original

Original request for help

Save

Abstract

En 中文

Deep subspace learning is an important branch of self-supervised learning and has been a hot research topic in recent years, but current methods do not fully consider the individualities of temporal data and related tasks. In this paper, by transforming the individualities of motion capture data and segmentation task as the supervision, we propose the local self-expression subspace learning network. Specifically, considering the temporality of motion data, we use the temporal convolution module to extract temporal features. To implement the local validity of self-expression in temporal tasks, we design the local self-expression layer which only maintains the representation relations with temporally adjacent motion frames. To simulate the interpolatability of motion data in the feature space, we impose a group sparseness constraint on the local self-expression layer to impel the representations only using selected keyframes. Besides, based on the subspace assumption, we propose the subspace projection loss, which is induced from distances of each frame projected to the fitted subspaces, to penalize the potential clustering errors. The superior performances of the proposed model on the segmentation task of synthetic data and three tasks of real motion capture data demonstrate the feature learning ability of our model.

Keywords:

Task analysis

Feature extraction

Motion segmentation

Data models

Kernel

Motion capture

Sun

Temporal self-supervised learning

subspace learning

local self-expression

subspace projection

motion capture data

Local Self-Expression Subspace Learning Network for Motion Capture Data

Abstract

Journal

Organization