ARN-LSTM: A Multi-Stream Fusion Model for Skeleton-based Action Recognition
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917850789183488 |
|---|---|
| author | Wang, Chuanchuan Mohmamed, Ahmad Sufril Azlan Noor, Mohd Halim Bin Mohd Yang, Xiao Yi, Feifan Li, Xiang |
| author_facet | Wang, Chuanchuan Mohmamed, Ahmad Sufril Azlan Noor, Mohd Halim Bin Mohd Yang, Xiao Yi, Feifan Li, Xiang |
| contents | This paper presents the ARN-LSTM architecture, a novel multi-stream action recognition model designed to address the challenge of simultaneously capturing spatial motion and temporal dynamics in action sequences. Traditional methods often focus solely on spatial or temporal features, limiting their ability to comprehend complex human activities fully. Our proposed model integrates joint, motion, and temporal information through a multi-stream fusion architecture. Specifically, it comprises a jointstream for extracting skeleton features, a temporal stream for capturing dynamic temporal features, and an ARN-LSTM block that utilizes Time-Distributed Long Short-Term Memory (TD-LSTM) layers followed by an Attention Relation Network (ARN) to model temporal relations. The outputs from these streams are fused in a fully connected layer to provide the final action prediction. Evaluations on the NTU RGB+D 60 and NTU RGB+D 120 datasets outperform the superior performance of our model, particularly in group activity recognition. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_01769 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | ARN-LSTM: A Multi-Stream Fusion Model for Skeleton-based Action Recognition Wang, Chuanchuan Mohmamed, Ahmad Sufril Azlan Noor, Mohd Halim Bin Mohd Yang, Xiao Yi, Feifan Li, Xiang Computer Vision and Pattern Recognition This paper presents the ARN-LSTM architecture, a novel multi-stream action recognition model designed to address the challenge of simultaneously capturing spatial motion and temporal dynamics in action sequences. Traditional methods often focus solely on spatial or temporal features, limiting their ability to comprehend complex human activities fully. Our proposed model integrates joint, motion, and temporal information through a multi-stream fusion architecture. Specifically, it comprises a jointstream for extracting skeleton features, a temporal stream for capturing dynamic temporal features, and an ARN-LSTM block that utilizes Time-Distributed Long Short-Term Memory (TD-LSTM) layers followed by an Attention Relation Network (ARN) to model temporal relations. The outputs from these streams are fused in a fully connected layer to provide the final action prediction. Evaluations on the NTU RGB+D 60 and NTU RGB+D 120 datasets outperform the superior performance of our model, particularly in group activity recognition. |
| title | ARN-LSTM: A Multi-Stream Fusion Model for Skeleton-based Action Recognition |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2411.01769 |