# MemexQA: Visual Memex Question Answering

Source: [MemexQA: Visual Memex Question Answering](<https://www.sota2.com/research/paper/68fa638b1e209131ce9ff73f>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T20:44:17.219Z

Authors: Lu Jiang, Junwei Liang, Liangliang Cao, Yannis Kalantidis, Sachin Farfade, Alexander Hauptmann

Published: 2017-08-04T00:17:48.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Visual Question Answering on MemexQA (test)](<https://www.sota2.com/research/sota/visual-question-answering-on-memexqa-test.md>): Visual Question Answering; MemexQA (test); Accuracy (How Many): 64.5.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1708.01336>)

[PDF](<https://arxiv.org/pdf/1708.01336.pdf>)