Loose Social-Interaction Recognition in Real-world Therapy Scenarios

TL;DR

This paper introduces a novel dual-path neural network architecture for recognizing loose social interactions in real-world therapy scenarios, demonstrating state-of-the-art results on autism-related datasets and exploring interaction-specific network designs.

Contribution

The paper proposes a new dual-path CNN with a Global-Layer-Attention module for recognizing loose social interactions, addressing a gap in complex dyadic activity analysis.

Findings

Achieves baseline results on the Loose-Interaction dataset.

Attains state-of-the-art results on autism datasets.

Incorporating time information improves performance on tight interactions.

Abstract

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.