CVAIMay 27

Multimodal Group Emotion Recognition In-the-Wild Towards a Privacy-Safe Non-Individual Approach

arXiv:2606.075859.5h-index: 2
Predicted impact top 53% in CV · last 90 daysOriginality Synthesis-oriented
AI Analysis

For researchers in affective computing and privacy, this work provides a privacy-preserving approach to group emotion recognition, though it is incremental as it builds on existing multimodal fusion and representation learning techniques.

This thesis tackles group emotion recognition in-the-wild while preserving privacy by using collective audio-video signals instead of individual cues. It proposes two frameworks achieving competitive performance without individual features, demonstrating that group-level emotion inference is feasible and privacy-safe.

This thesis addresses group emotion recognition (GER) in-the-wild with a focus on privacy preservation. Unlike traditional emotion recognition methods that rely on individual-level cues such as face, gaze, or voice analysis, this work uses collective audio-video signals to infer emotions at the group level, reducing risks of individual monitoring and surveillance. Two complementary frameworks are proposed. The first is a cross-attention multimodal architecture for audio-video fusion, combined with Frames Attention Pooling (FAP) for temporal aggregation. It is supported by synthetic data augmentation and validated through ablation studies, demonstrating robustness in real-world GER conditions. The second framework, Variational Encoder Multi-Decoder (VE-MD), learns a shared latent space for emotion classification and structural representation prediction, including body and face cues. Two decoding strategies, DETR-based and heatmap-based, are explored to analyze the role of structural representations in group and individual settings. The thesis makes three main contributions: it clarifies the role of multimodality and structural cues in group-level affective computing; introduces two architectures for privacy-preserving multimodal GER; and shows that competitive performance can be achieved without using individual features as input data.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes