MemexQA: Visual Memex Question Answering

By Lu Jiang, Junwei Liang, Liangliang Cao, Yannis Kalantidis, Sachin Farfade, Alexander G. Hauptmann. 2017

29 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Multimodal Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Multimodal Learning

Citations in the corpus

Towards VQA Models That Can Read (2019, background): “MemexQA [16] introduces a VQA task which involves reasoning about the time and date at which a photo/video was taken, but this information is structured and is part of the meta data.”
Memory Grounded Conversational Reasoning (2019, background): “Jiang et al. (2018) propose the visual memex QA task which addresses similar domains given a dataset composed of multiple photo albums.”
Progressive Attention Memory Network for Movie Story Question Answering (2019, background): “To this end, various video story QA benchmarks such as PororoQA [16], MeMexQA [12], TVQA [17] and MovieQA [26] have been suggested.”