MIP-GAF: A MLLM-annotated Benchmark for Most Important Person Localization and Group Context Understanding
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914946055405568 |
|---|---|
| author | Madan, Surbhi Ghosh, Shreya Sookha, Lownish Rai Ganaie, M. A. Subramanian, Ramanathan Dhall, Abhinav Gedeon, Tom |
| author_facet | Madan, Surbhi Ghosh, Shreya Sookha, Lownish Rai Ganaie, M. A. Subramanian, Ramanathan Dhall, Abhinav Gedeon, Tom |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_06224 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | MIP-GAF: A MLLM-annotated Benchmark for Most Important Person Localization and Group Context Understanding Madan, Surbhi Ghosh, Shreya Sookha, Lownish Rai Ganaie, M. A. Subramanian, Ramanathan Dhall, Abhinav Gedeon, Tom Computer Vision and Pattern Recognition Machine Learning Multimedia 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. |
| title | MIP-GAF: A MLLM-annotated Benchmark for Most Important Person Localization and Group Context Understanding |
| topic | Computer Vision and Pattern Recognition Machine Learning Multimedia |
| url | https://arxiv.org/abs/2409.06224 |