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

arXiv: https://arxiv.org/abs/2409.06224 · HTML: https://mlsanity.com/paper/2409.06224/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 44 references that are in the map.
- First posted on arXiv 10 Sep 2024.

## Builds on (most cited first, 24 of 24)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond](https://mlsanity.com/paper/2308.12966/) (2023)
- [A Survey on Evaluation of Large Language Models](https://mlsanity.com/paper/2307.03109/) (2023)
- [Kosmos-2: Grounding Multimodal Large Language Models to the World](https://mlsanity.com/paper/2306.14824/) (2023)
- [CogAgent: A Visual Language Model for GUI Agents](https://mlsanity.com/paper/2312.08914/) (2023)
- [Context-Aware Emotion Recognition Networks](https://mlsanity.com/paper/1908.05913/) (2019)
- [CLIP4Caption: CLIP for Video Caption](https://mlsanity.com/paper/2110.06615/) (2021)
- [Actor-Transformers for Group Activity Recognition](https://mlsanity.com/paper/2003.12737/) (2020)
- [Future Person Localization in First-Person Videos](https://mlsanity.com/paper/1711.11217/) (2017)
- [Egocentric Audio-Visual Object Localization](https://mlsanity.com/paper/2303.13471/) (2023)
- [Referring Image Segmentation Using Text Supervision](https://mlsanity.com/paper/2308.14575/) (2023)
- [Detecting events and key actors in multi-person videos](https://mlsanity.com/paper/1511.02917/) (2015)
- [Towards Local Visual Modeling for Image Captioning](https://mlsanity.com/paper/2302.06098/) (2023)
- [A Domain Based Approach to Social Relation Recognition](https://mlsanity.com/paper/1704.06456/) (2017)
- [Background Activation Suppression for Weakly Supervised Object Localization and Semantic Segmentation](https://mlsanity.com/paper/2309.12943/) (2023)
- [Learning to Learn Relation for Important People Detection in Still Images](https://mlsanity.com/paper/1904.03632/) (2019)
- [Learning to Detect Important People in Unlabelled Images for Semi-supervised Important People Detection](https://mlsanity.com/paper/2004.07568/) (2020)
- [PersonRank: Detecting Important People in Images](https://mlsanity.com/paper/1711.01984/) (2017)
- [Most Important Person-guided Dual-branch Cross-Patch Attention for Group Affect Recognition](https://mlsanity.com/paper/2212.07055/) (2022)
- [Head Matters: Explainable Human-centered Trait Prediction from Head Motion Dynamics](https://mlsanity.com/paper/2112.08068/) (2021)
- [MAGIC-TBR: Multiview Attention Fusion for Transformer-based Bodily Behavior Recognition in Group Settings](https://mlsanity.com/paper/2309.10765/) (2023)

## Built on by (most cited first, 3 of 3)

- [Enhancing Sports Strategy with Video Analytics and Data Mining: Assessing the effectiveness of Multimodal LLMs in tennis video analysis](https://mlsanity.com/paper/2507.02904/) (2025)
- [Mining Multi-Modality Spatio-Temporal Cues for Video Important Person Identification](https://mlsanity.com/paper/2605.28604/) (2026)
- [A Survey of Large Models in Sports](https://mlsanity.com/paper/2608.14377/) (2026)

## Abstract (arXiv)

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.