HoME 智能问答数据集

HoME 全称 Household Multimodal Environment，是一个多模态环境数据集，旨在帮助智能主体 (artificial agent) 在现实环境中从视觉、音频、语义、物理学及与物体或其他主体的交互中学习。

HoME, short for Household Multimodal Environment, is a multimodal environment dataset designed to help artificial agents learn from visual, audio, semantic, and physical information, as well as interactions with objects or other agents in real-world environments.

搜集汇总

背景与挑战

背景概述

HoME（Household Multimodal Environment）是一个多模态环境数据集，旨在帮助智能主体从多模态交互中学习，包含基于SUNCG的4.5万多个3D房屋布局。它是一个开源且兼容OpenAI Gym的平台，适用于强化学习、语言基础等多种任务，由舍布鲁克大学发布。