CVCLAug 4, 2017

MemexQA: Visual Memex Question Answering

arXiv:1708.01336v128 citations
Originality Incremental advance
AI Analysis

It addresses the problem of memory recovery from personal media for users, but is incremental as it builds on existing QA methods.

The paper introduces MemexQA, a task for answering questions about personal photo/video collections to aid memory recall, and presents MemexNet, an end-to-end multimodal network that achieves state-of-the-art results on this new dataset.

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes