Adaptive Multimodal Person Recognition: A Robust Framework for Handling Missing Modalities

TL;DR

This paper introduces a robust multimodal person recognition framework that effectively handles missing modalities by combining feature-level and score-level fusion, achieving high accuracy on multiple datasets including a new interview-based dataset.

Contribution

The work presents a novel hybrid fusion strategy with dynamic adaptation mechanisms, and introduces a new dataset for benchmarking multimodal person recognition in interview scenarios.

Findings

Achieves 99.51% accuracy on CANDOR dataset

Reaches 99.92% accuracy on VoxCeleb1 in bimodal mode

Maintains high accuracy with missing modalities

Abstract

Person identification systems often rely on audio, visual, or behavioral cues, but real-world conditions frequently present with missing or degraded modalities. To address this challenge, we propose a multimodal person identification framework incorporating upper-body motion, face, and voice. Experimental results demonstrate that body motion outperforms traditional modalities such as face and voice in within-session evaluations, while serving as a complementary cue that enhances performance in multi-session scenarios. Our model employs a unified hybrid fusion strategy, fusing both feature-level and score-level information to maximize representational richness and decision accuracy. Specifically, it leverages multi-task learning to process modalities independently, followed by cross-attention and gated fusion mechanisms to exploit both unimodal information and cross-modal interactions. Finally, a confidence-weighted strategy and mistake-correction mechanism dynamically adapt to missing data, ensuring that our single classification head achieves optimal performance even in unimodal and bimodal scenarios. We evaluate our method on CANDOR, a newly introduced interview-based multimodal dataset, which we benchmark in this work for the first time. Our results demonstrate that the proposed trimodal system achieves 99.51% Top-1 accuracy on person identification tasks. In addition, we evaluate our model on the VoxCeleb1 dataset as a widely used evaluation protocol and reach 99.92% accuracy in bimodal mode, outperforming conventional approaches. Moreover, we show that our system maintains high accuracy even when one or two modalities are unavailable, making it a robust solution for real-world person recognition applications. The code and data for this work are publicly available.