A Novel Infogain and Multi-Axial Wavelet-based Transformer for Personality Traits Question Answering

Biswas, Kunal; Palaiahnakote, Shivakumara; Bhattacharya, Saumik; Pal, Umapada; Sarkar, Ram

Abstract

Visual Question Answering (VQA) is one of the attractive topics in the field of multimedia, affective,
and empathic computing to garner user interest. Unlike existing models which aim at addressing chal-
lenges of VQA for the scene images, this work aims at developing a new model for Personality Traits
Question Answering (PQA). It uses Twitter account information, which includes shared images, pro-
file pictures, banners, text in the images, and descriptions of the images. Motivated by the accomplish-
ments of the transformer, for encoding visual features of the images, a new InfoGain Multi-Axial
Wavelet Vision Transformer (IgMaWaViT) is explored here. For encoding textual features in the im-
ages and descriptions, a new Information Gain BERT (InfoBert) method is introduced, which can
handle the variable length encoding of text by choosing the optimal discriminator. Furthermore, the
model fuses encodings of images and text according to the questions on different personality traits for
question answering. The model is called InfoGain Multi-Axial Wavelet Vision Transformer for Per-
sonality Traits Question Answering (IgMaWaViT-PQA). To validate the efficacy of the proposed
model, a dataset has been constructed, and it is used along with standard datasets for experimentation.

Citation

Biswas, K., Palaiahnakote, S., Bhattacharya, S., Pal, U., & Sarkar, R. (2024). A Novel Infogain and Multi-Axial Wavelet-based Transformer for Personality Traits Question Answering. International Journal of Pattern Recognition and Artificial Intelligence, https://doi.org/10.1142/S0218001424510236

• Journal Article Type: Article
• Acceptance Date: Nov 2, 2024
• Publication Date: Nov 15, 2024
• Deposit Date: Nov 15, 2024
• Publicly Available Date: Nov 16, 2025
• Journal: International Journal of Pattern Recognition and Artificial Intelligence
• Print ISSN: 0218-0014
• Electronic ISSN: 1793-6381
• Publisher: World Scientific Publishing
• Peer Reviewed: Peer Reviewed
• DOI: https://doi.org/10.1142/S0218001424510236