BriefGPT.xyz
Jun, 2018
DSTC7的音视频场景感知对话（AVSD）竞赛
Audio Visual Scene-Aware Dialog (AVSD) Challenge at DSTC7
HTML
PDF
Huda Alamri, Vincent Cartillier, Raphael Gontijo Lopes, Abhishek Das, Jue Wang...
TL;DR
该研究论文介绍了一种基于多个研究领域的技术相互整合的新型场景感知对话系统，同时提出了基于音视频的场景感知对话系统(AVSD)挑战与数据集，该挑战要求参赛者构建一个能够对输入视频进行对话响应的系统。
Abstract
scene-aware dialog systems
will be able to have conversations with users about the objects and events around them. Progress on such systems can be made by integrating state-of-the-art technologies from multiple research areas including
→