Memex Question Answering

3 papers with code • 1 benchmarks • 1 datasets

Question answering with real-world multi-modal personal collections, e.g., photo albums with visual, text, time and location information.


Most implemented papers

Focal Visual-Text Attention for Visual Question Answering

JunweiLiang/FVTA_MemexQA CVPR 2018

Recent insights on language and vision with neural networks have been successfully applied to simple single-image visual question answering.

MemexQA: Visual Memex Question Answering

JunweiLiang/FVTA_MemexQA 4 Aug 2017

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.