VQA-MHUG: A Gaze Dataset to Study Multimodal Neural Attention in Visual Question Answering
Ekta Sood, Fabian Kögel, Florian Strohm, Prajit Dhar, Andreas Bulling
Abstract
We present VQA-MHUG – a novel 49-participant dataset of multimodal human gaze on both images and questions during visual question answering (VQA) collected using a high-speed eye tracker. We use our dataset to analyze the similarity between human and neural attentive strategies learned by five state-of-the-art VQA models: Modular Co-Attention Network (MCAN) with either grid or region features, Pythia, Bilinear Attention Network (BAN), and the Multimodal Factorized Bilinear Pooling Network (MFB). While prior work has focused on studying the image modality, our analyses show – for the first time – that for all models, higher correlation with human attention on text is a significant predictor of VQA performance. This finding points at a potential for improving VQA performance and, at the same time, calls for further research on neural text attention mechanisms and their integration into architectures for vision and language tasks, including but potentially also beyond VQA.- Anthology ID:
- 2021.conll-1.3
- Volume:
- Proceedings of the 25th Conference on Computational Natural Language Learning
- Month:
- November
- Year:
- 2021
- Address:
- Online
- Editors:
- Arianna Bisazza, Omri Abend
- Venue:
- CoNLL
- SIG:
- SIGNLL
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 27–43
- Language:
- URL:
- https://aclanthology.org/2021.conll-1.3
- DOI:
- 10.18653/v1/2021.conll-1.3
- Cite (ACL):
- Ekta Sood, Fabian Kögel, Florian Strohm, Prajit Dhar, and Andreas Bulling. 2021. VQA-MHUG: A Gaze Dataset to Study Multimodal Neural Attention in Visual Question Answering. In Proceedings of the 25th Conference on Computational Natural Language Learning, pages 27–43, Online. Association for Computational Linguistics.
- Cite (Informal):
- VQA-MHUG: A Gaze Dataset to Study Multimodal Neural Attention in Visual Question Answering (Sood et al., CoNLL 2021)
- PDF:
- https://preview.aclanthology.org/naacl-24-ws-corrections/2021.conll-1.3.pdf
- Data
- VQA-MHUG, SALICON, TDIUC, VQA-HAT, Visual Question Answering