Challenges and Prospects in Vision and Language Research

2019/04/19 by Kafle, Kushal, Shrestha, Robik, Kanan, Christopher · 1 citation
#Computation and Language (cs.CL) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Neural and Evolutionary Computing (cs.NE)

paper · doi:10.48550/arxiv.1904.09317

Abstract

Language grounded image understanding tasks have often been proposed as a method for evaluating progress in artificial intelligence. Ideally, these tasks should test a plethora of capabilities that integrate computer vision, reasoning, and natural language understanding. However, rather than behaving as visual Turing tests, recent studies have demonstrated state-of-the-art systems are achieving good performance through flaws in datasets and evaluation procedures. We review the current state of affairs and outline a path forward.

Cited by

• Explain Before You Answer: A Survey on Compositional Visual Reasoning

Related

• A Survey of Current Datasets for Vision and Language Research
• Vision-Language Intelligence: Tasks, Representation Learning, and Large Models
• Position: Reasoning After Perception Means Reasoning Without Vision
• On Efficient Language and Vision Assistants for Visually-Situated Natural Language Understanding: What Matters in Reading and Reasoning
• Images in Language Space: Exploring the Suitability of Large Language Models for Vision & Language Tasks