2 citations · 5 across the 7 of their papers we have counts for
4 papers · 1 filter
Trying Bilinear Pooling in Video-QA
Thomas Winterbottom, Sarah Xiao, Alistair McLean +1
Bilinear pooling (BLP) refers to a family of operations recently developed for fusing features from different modalities predominantly developed for VQA models. A bilinear (outer-p…
On Modality Bias in the TVQA Dataset
Thomas Winterbottom, Sarah Xiao, Alistair McLean +1
TVQA is a large scale video question answering (video-QA) dataset based on popular TV shows. The questions were specifically designed to require "both vision and language understan…
Bilinear Fusion of Commonsense Knowledge with Attention-Based NLI Models
Amit Gajbhiye, Thomas Winterbottom, Noura Al Moubayed +1
We consider the task of incorporating real-world commonsense knowledge into deep Natural Language Inference (NLI) models. Existing external knowledge incorporation methods are limi…
Exploring Racial Bias within Face Recognition via per-subject Adversarially-Enabled Data Augmentation
Seyma Yucer, Samet Akçay, Noura Al-Moubayed +1
Whilst face recognition applications are becoming increasingly prevalent within our daily lives, leading approaches in the field still suffer from performance bias to the detriment…