CE-BART: Cause-and-Effect BART for Visual Commonsense Generation

Citations

WEB OF SCIENCE

2
Citations

SCOPUS

3

초록

"A Picture is worth a thousand words". Given an image, humans are able to deduce various cause-and-effect captions of past, current, and future events beyond the image. The task of visual commonsense generation has the aim of generating three cause-and-effect captions for a given image: (1) what needed to happen before, (2) what is the current intent, and (3) what will happen after. However, this task is challenging for machines, owing to two limitations: existing approaches (1) directly utilize conventional vision-language transformers to learn relationships between input modalities and (2) ignore relations among target cause-and-effect captions, but consider each caption independently. Herein, we propose Cause-and-Effect BART (CE-BART), which is based on (1) a structured graph reasoner that captures intra- and inter-modality relationships among visual and textual representations and (2) a cause-and-effect generator that generates cause-and-effect captions by considering the causal relations among inferences. We demonstrate the validity of CE-BART on the VisualCOMET and AVSD benchmarks. CE-BART achieved SOTA performance on both benchmarks, while an extensive ablation study and qualitative analysis demonstrated the performance gain and improved interpretability.

키워드

deep learning; visual-language reasoning; visual commonsense generation; video-grounded dialogue; VisualCOMET; AVSD
제목
CE-BART: Cause-and-Effect BART for Visual Commonsense Generation
저자
Kim, Junyeong; Hong, Ji Woo; Yoon, Sunjae; Yoo, Chang D.
DOI
10.3390/s22239399
발행일
2022-12
유형
Article
저널명
Sensors
권
22
호
23

파일 다운로드

Thumbnail