Saved in:
Bibliographic Details
Main Authors: Ray, Abhisek, Raj, Ayush, Kolekar, Maheshkumar H.
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2411.05692
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916634691633152
author Ray, Abhisek
Raj, Ayush
Kolekar, Maheshkumar H.
author_facet Ray, Abhisek
Raj, Ayush
Kolekar, Maheshkumar H.
contents Extracting multiscale contextual information and higher-order correlations among skeleton sequences using Graph Convolutional Networks (GCNs) alone is inadequate for effective action classification. Hypergraph convolution addresses the above issues but cannot harness the long-range dependencies. The transformer proves to be effective in capturing these dependencies and making complex contextual features accessible. We propose an Autoregressive Adaptive HyperGraph Transformer (AutoregAd-HGformer) model for in-phase (autoregressive and discrete) and out-phase (adaptive) hypergraph generation. The vector quantized in-phase hypergraph equipped with powerful autoregressive learned priors produces a more robust and informative representation suitable for hyperedge formation. The out-phase hypergraph generator provides a model-agnostic hyperedge learning technique to align the attributes with input skeleton embedding. The hybrid (supervised and unsupervised) learning in AutoregAd-HGformer explores the action-dependent feature along spatial, temporal, and channel dimensions. The extensive experimental results and ablation study indicate the superiority of our model over state-of-the-art hypergraph architectures on the NTU RGB+D, NTU RGB+D 120, and NW-UCLA datasets.
format Preprint
id arxiv_https___arxiv_org_abs_2411_05692
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Autoregressive Adaptive Hypergraph Transformer for Skeleton-based Activity Recognition
Ray, Abhisek
Raj, Ayush
Kolekar, Maheshkumar H.
Computer Vision and Pattern Recognition
Extracting multiscale contextual information and higher-order correlations among skeleton sequences using Graph Convolutional Networks (GCNs) alone is inadequate for effective action classification. Hypergraph convolution addresses the above issues but cannot harness the long-range dependencies. The transformer proves to be effective in capturing these dependencies and making complex contextual features accessible. We propose an Autoregressive Adaptive HyperGraph Transformer (AutoregAd-HGformer) model for in-phase (autoregressive and discrete) and out-phase (adaptive) hypergraph generation. The vector quantized in-phase hypergraph equipped with powerful autoregressive learned priors produces a more robust and informative representation suitable for hyperedge formation. The out-phase hypergraph generator provides a model-agnostic hyperedge learning technique to align the attributes with input skeleton embedding. The hybrid (supervised and unsupervised) learning in AutoregAd-HGformer explores the action-dependent feature along spatial, temporal, and channel dimensions. The extensive experimental results and ablation study indicate the superiority of our model over state-of-the-art hypergraph architectures on the NTU RGB+D, NTU RGB+D 120, and NW-UCLA datasets.
title Autoregressive Adaptive Hypergraph Transformer for Skeleton-based Activity Recognition
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2411.05692