This paper proposes a new task, MemexQA: given a collection of photos or videos from a user, the goal is to automatically answer questions that help users recover their memory about events captured in the collection. Towards solving the task, we 1) present the MemexQA dataset, a large, realistic multimodal dataset consisting of real personal photos and crowd-sourced questions/answers, 2) propose MemexNet, a unified, end-to-end trainable network architecture for image, text and video question answering. Experimental results on the MemexQA dataset demonstrate that MemexNet outperforms strong baselines and yields the state-of-the-art on this novel and challenging task. The promising results on TextQA and VideoQA suggest MemexNet's efficacy and scalability across various QA tasks.
@article{arxiv.1708.01336,
title = {MemexQA: Visual Memex Question Answering},
author = {Lu Jiang and Junwei Liang and Liangliang Cao and Yannis Kalantidis and Sachin Farfade and Alexander Hauptmann},
journal= {arXiv preprint arXiv:1708.01336},
year = {2017}
}