paper-with-me

Visual Commonsense Tests

1개 벤치마크 · 논문 2편 · 이 태스크의 논문 보기 →

Benchmarks

ViComTe-color

결과 2개

Most implemented

Papers

Z-LaVI: Zero-Shot Language Solver Fueled by Visual Imagination

2022-10-21 · Yue Yang, Wenlin Yao, Hongming Zhang, Xiaoyang Wang 외

Large-scale pretrained language models have made significant advances in solving downstream language understanding tasks. However, they generally suffer from reporting bias, the phenomenon describing the lack of explicit…

Image GenerationLanguage ModelingLanguage ModellingRetrieval+3

Visual Commonsense in Pretrained Unimodal and Multimodal Models

2022-05-04 · NAACL 2022 7 · Chenyu Zhang, Benjamin Van Durme, Zhuowan Li, Elias Stengel-Eskin

Our commonsense knowledge about objects includes their typical visual attributes; we know that bananas are typically yellow or green, and not purple. Text and image corpora, being subject to reporting bias, represent thi…

AttributeVisual Commonsense TestsWorld Knowledge