ADR Awareness Centre

In this paper, the authors propose a lightweight neural network architecture that extracts and performs the analysis of multimodal information using the same audio and visual networks across multiple temporal segments.

This paper introduces a multilingual, multispeaker dataset composed of synthetic and natural speech, designed to foster research and benchmarking in synthetic speech detection.

Code for Word-Class Embeddings (WCEs), a form of supervised embeddings especially suited for multiclass text classification.

A novel unsupervised domain adaptation approach for action recognition from videos, inspired by recent literature on contrastive learning.

A holistic learning framework for Novel Class Discovery (NCD), which adopts contrastive learning to learn discriminate features with both the labeled and unlabeled data.

we study the task of synthetic-to-real domain generalized semantic segmentation, which aims to learn a model that is robust to unseen real-world scenes using only synthetic data.