paper-with-me

Papers

Seeing the World through Text: Evaluating Image Descriptions for Commonsense Reasoning in Machine Reading Comprehension

2020-12-01 · LANTERN (COLING) 2020 12 · Diana Galvan-Sosa, Jun Suzuki, Kyosuke Nishida, Koji Matsuda, Kentaro Inui

Despite recent achievements in natural language understanding, reasoning over commonsense knowledge still represents a big challenge to AI systems. As the name suggests, common sense is related to perception and as such, humans derive it from experience rather than from literary education. Recent works in the NLP and the computer vision field have made the effort of making such knowledge explicit using written language and visual inputs, respectively. Our premise is that the latter source fits better with the characteristics of commonsense acquisition. In this work, we explore to what extent the descriptions of real-world scenes are sufficient to learn common sense about different daily situations, drawing upon visual information to answer script knowledge questions.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Common Sense ReasoningMachine Reading ComprehensionNatural Language UnderstandingReading Comprehension

Similar Papers 제목 키워드 기반

The All-Seeing Project V2: Towards General Relation Comprehension of the Open World

2024-02-29 · Weiyun Wang, Yiming Ren, Haowen Luo, Tiantong Li 외

We present the All-Seeing Project V2: a new model and dataset designed for understanding object relations in images. Specifically, we propose the All-Seeing Model V2 (ASMv2) that integrates the formulation of text genera…

AllHallucinationObject LocalizationRelation+2

Seeing and Seeing Through the Glass: Real and Synthetic Data for Multi-Layer Depth Estimation

2025-03-14 · Hongyu Wen, Yiming Zuo, Venkat Subramanian, Patrick Chen 외

Transparent objects are common in daily life, and understanding their multi-layer depth information -- perceiving both the transparent surface and the objects behind it -- is crucial for real-world applications that inte…

Depth EstimationTransparent objects

Seeing The Words: Evaluating AI-generated Biblical Art

2025-04-23 · Hidde Makimei, Shuai Wang, Willem van Peursen

The past years witnessed a significant amount of Artificial Intelligence (AI) tools that can generate images from texts. This triggers the discussion of whether AI can generate accurate images using text from the Bible w…

Visual Room 2.0: Seeing is Not Understanding for MLLMs

2025-11-17 · Haokun Li, Yazhou Zhang, Jizhi Ding, Qiuchi Li 외 arxiv

Can multi-modal large language models (MLLMs) truly understand what they can see? Extending Searle's Chinese Room into the multi-modal domain, this paper proposes the Visual Room argument: MLLMs may describe every visual…

Scene Understanding

The All-Seeing Project: Towards Panoptic Visual Recognition and Understanding of the Open World

2023-08-03 · Weiyun Wang, Min Shi, Qingyun Li, Wenhai Wang 외

We present the All-Seeing (AS) project: a large-scale data and model for recognizing and understanding everything in the open world. Using a scalable data engine that incorporates human feedback and efficient models in t…

AllQuestion AnsweringRetrievalText Retrieval