MIP-GAF: A MLLM-annotated Benchmark for Most Important Person Localization and Group Context Understanding

TL;DR

This paper introduces MIP-GAF, a large-scale annotated dataset for identifying the Most Important Person in social images, highlighting the challenges and benchmarking current methods which underperform on real-world data.

Contribution

The paper presents a new annotated dataset for MIP localization, a novel MLLM-based annotation strategy, and a comprehensive benchmark revealing the need for more robust algorithms.

Findings

Significant performance drop of existing methods on in-the-wild data

The proposed dataset highlights the complexity of real-world social scene understanding

Benchmark results indicate the necessity for improved MIP localization algorithms

Abstract

Estimating the Most Important Person (MIP) in any social event setup is a challenging problem mainly due to contextual complexity and scarcity of labeled data. Moreover, the causality aspects of MIP estimation are quite subjective and diverse. To this end, we aim to address the problem by annotating a large-scale `in-the-wild' dataset for identifying human perceptions about the `Most Important Person (MIP)' in an image. The paper provides a thorough description of our proposed Multimodal Large Language Model (MLLM) based data annotation strategy, and a thorough data quality analysis. Further, we perform a comprehensive benchmarking of the proposed dataset utilizing state-of-the-art MIP localization methods, indicating a significant drop in performance compared to existing datasets. The performance drop shows that the existing MIP localization algorithms must be more robust with respect to `in-the-wild' situations. We believe the proposed dataset will play a vital role in building the next-generation social situation understanding methods. The code and data is available at https://github.com/surbhimadan92/MIP-GAF.