Skip to main navigation Skip to search Skip to main content

Int&Int: A Two-Pathway Network for Skeleton-Based Action Recognition

  • Harbin Institute of Technology

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Human action recognition has recently attracted a lot of researchers, while most of them mainly focus on the local dynamics or global information alone and cannot focus on both the intensity and the integrity of the action. In this work, we propose a two-pathway Int&Int network(Intensity&Integrity) for skeleton-based action recognition to satisfy both aspects, where the great complementarity between the two pathways further enhances the performance. Besides, for Integrity pathway, we apply the uniform sampling strategy. For Intensity pathway, we introduce the intensity-dependent sampling, where a clip composed of consecutive frames around the frame with the largest motion intensity is sampled. Moreover, we explain various definitions of the motion intensity containing different semantic information based on the extracted 2D human poses. For each pathway, the poses are represented by a 3D heatmap volume and 3D-CNNs of both pathways have the same architecture. Late fusion is used to ensemble them. The model is evaluated on two action recognition datasets, FineGYM-99 and HMDB-51, and it achieves superior performance on both of them. The code has been shown at https://github.com/SarahQi666/Int-and-Int.

Original languageEnglish
Title of host publicationProceedings of the 18th IEEE Conference on Industrial Electronics and Applications, ICIEA 2023
EditorsWenjian Cai, Guilin Yang, Jun Qiu, Tingting Gao, Lijun Jiang, Tianjiang Zheng, Xinli Wang
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1477-1482
Number of pages6
ISBN (Electronic)9798350312201
DOIs
StatePublished - 2023
Event18th IEEE Conference on Industrial Electronics and Applications, ICIEA 2023 - Ningbo, China
Duration: 18 Aug 202322 Aug 2023

Publication series

NameProceedings of the 18th IEEE Conference on Industrial Electronics and Applications, ICIEA 2023

Conference

Conference18th IEEE Conference on Industrial Electronics and Applications, ICIEA 2023
Country/TerritoryChina
CityNingbo
Period18/08/2322/08/23

Keywords

  • Intensity-dependent sampling
  • Skeleton-based action recognition
  • Two-pathway network

Fingerprint

Dive into the research topics of 'Int&Int: A Two-Pathway Network for Skeleton-Based Action Recognition'. Together they form a unique fingerprint.

Cite this