8 citations · 49 across the 40 of their papers we have counts for
8 papers · 1 filter
Imperial College London Submission to VATEX Video Captioning Task
Ozan Caglayan, Zixiu Wu, Pranava Madhyastha +2
This paper describes the Imperial College London team's submission to the 2019' VATEX video captioning challenge, where we first explore two sequence-to-sequence models, namely a r…
On Model Stability as a Function of Random Seed
Pranava Madhyastha, Rishabh Jain
In this paper, we focus on quantifying model stability as a function of random seed by investigating the effects of the induced randomness on model performance and the robustness o…
Probing Representations Learned by Multimodal Recurrent and Transformer Models
Jindřich Libovický, Pranava Madhyastha
Recent literature shows that large-scale language modeling provides excellent reusable sentence representations with both recurrent and self-attentive architectures. However, there…
Predicting Actions to Help Predict Translations
Zixiu Wu, Julia Ive, Josiah Wang +2
We address the task of text translation on the How2 dataset using a state of the art transformer-based multimodal approach. The question we ask ourselves is whether visual features…
VIFIDEL: Evaluating the Visual Fidelity of Image Descriptions
Pranava Madhyastha, Josiah Wang, Lucia Specia
We address the task of evaluating image description generation systems. We propose a novel image-aware metric for this task: VIFIDEL. It estimates the faithfulness of a generated c…
Distilling Translations with Visual Awareness
Julia Ive, Pranava Madhyastha, Lucia Specia
Previous work on multimodal machine translation has shown that visual information is only needed in very specific cases, for example in the presence of ambiguous words where the te…
Model Explanations under Calibration
Rishabh Jain, Pranava Madhyastha
Explaining and interpreting the decisions of recommender systems are becoming extremely relevant both, for improving predictive performance, and providing valid explanations to use…
Probing the Need for Visual Context in Multimodal Machine Translation
Ozan Caglayan, Pranava Madhyastha, Lucia Specia +1
Current work on multimodal machine translation (MMT) has suggested that the visual modality is either unnecessary or only marginally beneficial. We posit that this is a consequence…