research
∙
06/15/2023
Revealing the Illusion of Joint Multimodal Understanding in VideoQA Models
While VideoQA Transformer models demonstrate competitive performance on ...
share
research
∙
11/30/2022
A Probabilistic-Logic based Commonsense Representation Framework for Modelling Inferences with Multiple Antecedents and Varying Likelihoods
Commonsense knowledge-graphs (CKGs) are important resources towards buil...
research
∙
11/26/2021
TDAN: Top-Down Attention Networks for Enhanced Feature Selectivity in CNNs
Attention modules for Convolutional Neural Networks (CNNs) are an effect...
research
∙
07/17/2017