Saved in:
Bibliographic Details
Main Authors: Ali, Abid, Dai, Rui, Marisetty, Ashish, Astruc, Guillaume, Thonnat, Monique, Odobez, Jean-Marc, Thümmler, Susanne, Bremond, Francois
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2409.20270
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909368739430400
author Ali, Abid
Dai, Rui
Marisetty, Ashish
Astruc, Guillaume
Thonnat, Monique
Odobez, Jean-Marc
Thümmler, Susanne
Bremond, Francois
author_facet Ali, Abid
Dai, Rui
Marisetty, Ashish
Astruc, Guillaume
Thonnat, Monique
Odobez, Jean-Marc
Thümmler, Susanne
Bremond, Francois
contents The computer vision community has explored dyadic interactions for atomic actions such as pushing, carrying-object, etc. However, with the advancement in deep learning models, there is a need to explore more complex dyadic situations such as loose interactions. These are interactions where two people perform certain atomic activities to complete a global action irrespective of temporal synchronisation and physical engagement, like cooking-together for example. Analysing these types of dyadic-interactions has several useful applications in the medical domain for social-skills development and mental health diagnosis. To achieve this, we propose a novel dual-path architecture to capture the loose interaction between two individuals. Our model learns global abstract features from each stream via a CNNs backbone and fuses them using a new Global-Layer-Attention module based on a cross-attention strategy. We evaluate our model on real-world autism diagnoses such as our Loose-Interaction dataset, and the publicly available Autism dataset for loose interactions. Our network achieves baseline results on the Loose-Interaction and SOTA results on the Autism datasets. Moreover, we study different social interactions by experimenting on a publicly available dataset i.e. NTU-RGB+D (interactive classes from both NTU-60 and NTU-120). We have found that different interactions require different network designs. We also compare a slightly different version of our method by incorporating time information to address tight interactions achieving SOTA results.
format Preprint
id arxiv_https___arxiv_org_abs_2409_20270
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Loose Social-Interaction Recognition in Real-world Therapy Scenarios
Ali, Abid
Dai, Rui
Marisetty, Ashish
Astruc, Guillaume
Thonnat, Monique
Odobez, Jean-Marc
Thümmler, Susanne
Bremond, Francois
Computer Vision and Pattern Recognition
The computer vision community has explored dyadic interactions for atomic actions such as pushing, carrying-object, etc. However, with the advancement in deep learning models, there is a need to explore more complex dyadic situations such as loose interactions. These are interactions where two people perform certain atomic activities to complete a global action irrespective of temporal synchronisation and physical engagement, like cooking-together for example. Analysing these types of dyadic-interactions has several useful applications in the medical domain for social-skills development and mental health diagnosis. To achieve this, we propose a novel dual-path architecture to capture the loose interaction between two individuals. Our model learns global abstract features from each stream via a CNNs backbone and fuses them using a new Global-Layer-Attention module based on a cross-attention strategy. We evaluate our model on real-world autism diagnoses such as our Loose-Interaction dataset, and the publicly available Autism dataset for loose interactions. Our network achieves baseline results on the Loose-Interaction and SOTA results on the Autism datasets. Moreover, we study different social interactions by experimenting on a publicly available dataset i.e. NTU-RGB+D (interactive classes from both NTU-60 and NTU-120). We have found that different interactions require different network designs. We also compare a slightly different version of our method by incorporating time information to address tight interactions achieving SOTA results.
title Loose Social-Interaction Recognition in Real-world Therapy Scenarios
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2409.20270