Modality attention fusion model with hybrid multi-head self-attention for video understanding

Video question answering (Video-QA) is a subject undergoing intense study in Artificial Intelligence, which is one of the tasks which can evaluate such AI abilities. In this paper, we propose a Modality Attention Fusion framework with Hybrid Multi-head Self-attention (MAF-HMS). MAF-HMS focuses on th...

Full description

Saved in:
Bibliographic Details
Published in:PloS one 2022-10, Vol.17 (10), p.e0275156-e0275156
Main Authors: Zhuang, Xuqiang, Liu, Fang'ai, Hou, Jian, Hao, Jianhua, Cai, Xiaohong
Format: Article
Language:English
Subjects:
Ablation
Analysis
Artificial intelligence
Attention
Biology and Life Sciences
Comprehension
Computer and Information Sciences
Datasets
Feature extraction
Hypotheses
Multiple choice
Natural language
Neural networks
Questions
Representations
Semantics
Social Sciences
Subtitles & subtitling
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Video question answering (Video-QA) is a subject undergoing intense study in Artificial Intelligence, which is one of the tasks which can evaluate such AI abilities. In this paper, we propose a Modality Attention Fusion framework with Hybrid Multi-head Self-attention (MAF-HMS). MAF-HMS focuses on the task of answering multiple-choice questions regarding a video-subtitle-QA representation by fusion of attention and self-attention between each modality. We use BERT to extract text features, and use Faster R-CNN to ex-tract visual features to provide a useful input representation for our model to answer questions. In addition, we have constructed a Modality Attention Fusion (MAF) framework for the attention fusion matrix from different modalities (video, subtitles, QA), and use a Hybrid Multi-headed Self-attention (HMS) to further determine the correct answer. Experiments on three separate scene datasets show our overall model outperforms the baseline methods by a large margin. Finally, we conducted extensive ablation studies to verify the various components of the network and demonstrate the effectiveness and advantages of our method over existing methods through question type and required modality experimental results.
ISSN:1932-6203
1932-6203
DOI:10.1371/journal.pone.0275156