Adaptive Local-Component-aware Graph Convolutional Network for One-shot Skeleton-based Action Recognition

09/21/2022
by   Anqi Zhu, et al.
0

Skeleton-based action recognition receives increasing attention because the skeleton representations reduce the amount of training data by eliminating visual information irrelevant to actions. To further improve the sample efficiency, meta-learning-based one-shot learning solutions were developed for skeleton-based action recognition. These methods find the nearest neighbor according to the similarity between instance-level global average embedding. However, such measurement holds unstable representativity due to inadequate generalized learning on local invariant and noisy features, while intuitively, more fine-grained recognition usually relies on determining key local body movements. To address this limitation, we present the Adaptive Local-Component-aware Graph Convolutional Network, which replaces the comparison metric with a focused sum of similarity measurements on aligned local embedding of action-critical spatial/temporal segments. Comprehensive one-shot experiments on the public benchmark of NTU-RGB+D 120 indicate that our method provides a stronger representation than the global embedding and helps our model reach state-of-the-art.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/19/2022

Part-aware Prototypical Graph Network for One-shot Skeleton-based Action Recognition

In this paper, we study the problem of one-shot skeleton-based action re...
research
06/27/2023

Multi-Dimensional Refinement Graph Convolutional Network with Robust Decouple Loss for Fine-Grained Skeleton-Based Action Recognition

Graph convolutional networks have been widely used in skeleton-based act...
research
03/17/2020

Feedback Graph Convolutional Network for Skeleton-based Action Recognition

Skeleton-based action recognition has attracted considerable attention i...
research
07/12/2022

Skeletal Human Action Recognition using Hybrid Attention based Graph Convolutional Network

In skeleton-based action recognition, Graph Convolutional Networks model...
research
12/24/2019

Focusing and Diffusion: Bidirectional Attentive Graph Convolutional Networks for Skeleton-based Action Recognition

A collection of approaches based on graph convolutional networks have pr...
research
10/20/2020

Stronger, Faster and More Explainable: A Graph Convolutional Baseline for Skeleton-based Action Recognition

One essential problem in skeleton-based action recognition is how to ext...
research
04/07/2020

SC4D: A Sparse 4D Convolutional Network for Skeleton-Based Action Recognition

In this paper, a new perspective is presented for skeleton-based action ...

Please sign up or login with your details

Forgot password? Click here to reset