Search Results for author: Shailaja Keyur Sampat

Found 12 papers, 9 papers with code

VL-GLUE: A Suite of Fundamental yet Challenging Visuo-Linguistic Reasoning Tasks

1 code implementation17 Oct 2024 Shailaja Keyur Sampat, Mutsumi Nakamura, Shankar Kailas, Kartik Aggarwal, Mandy Zhou, Yezhou Yang, Chitta Baral

We show that this benchmark is quite challenging for existing large-scale vision-language models and encourage development of systems that possess robust visuo-linguistic reasoning capabilities.

Natural Language Understanding

ActionCOMET: A Zero-shot Approach to Learn Image-specific Commonsense Concepts about Actions

1 code implementation17 Oct 2024 Shailaja Keyur Sampat, Yezhou Yang, Chitta Baral

We present baseline results of ActionCOMET over the collected dataset and compare them with the performance of the best existing VQA approaches.

Visual Question Answering (VQA)

Help Me Identify: Is an LLM+VQA System All We Need to Identify Visual Concepts?

1 code implementation17 Oct 2024 Shailaja Keyur Sampat, Maitreya Patel, Yezhou Yang, Chitta Baral

An ability to learn about new objects from a small amount of visual data and produce convincing linguistic justification about the presence/absence of certain concepts (that collectively compose the object) in novel scenarios is an important characteristic of human cognition.

Language Modeling Language Modelling +4

Cannot find the paper you are looking for? You can Submit a new open access paper.