A survey of VQA datasets and models with new experiments showing Teney et al.'s 2017 model outperforms Vanilla VQA and Stacked Attention Networks on two datasets.
MemexQA: Visual Memex Question Answering
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
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.
fields
cs.CV 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Visual Question Answering using Deep Learning: A Survey and Performance Analysis
A survey of VQA datasets and models with new experiments showing Teney et al.'s 2017 model outperforms Vanilla VQA and Stacked Attention Networks on two datasets.