BriefGPT.xyz
Mar, 2021
选择、替换、搜索:一种新的用于知识增强视觉问答的基准测试
Select, Substitute, Search: A New Benchmark for Knowledge-Augmented Visual Question Answering
HTML
PDF
Aman Jain, Mayank Kothyari, Vishwajeet Kumar, Preethi Jyothi, Ganesh Ramakrishnan...
TL;DR
该研究针对现有数据集中存在的限制,建立了一个新的基于结构模式的跨模态问答数据集和挑战,同时提出了一个基于神经网络的透明的 OKVQA 系统 S3,该系统在新数据集上实现了比较好的表现。
Abstract
multimodal ir
, spanning text corpus, knowledge graph and images, called outside knowledge visual question answering (
okvqa
), is of much recent interest. However, the popular data set has serious limitations. A su
→