BriefGPT.xyz
Apr, 2022
AGQA 2.0：用于组合时空推理的更新基准
AGQA 2.0: An Updated Benchmark for Compositional Spatio-Temporal Reasoning
HTML
PDF
Madeleine Grunde-McLaughlin, Ranjay Krishna, Maneesh Agrawala
TL;DR
介绍了AGQA 2.0，这是一个改进版的模型问答基准测试，通过更严格的平衡程序来减少语言偏倚，实验结果表明这个改进版的基准测试可以更好地衡量视觉组合推理
Abstract
Prior benchmarks have analyzed models' answers to questions about videos in order to measure
visual compositional reasoning
.
action genome question answering
(
→