Abstract: The Audio-Visual Question Answering (AVQA) task holds significant potential for applications. Compared to traditional unimodal approaches, the multi-modal input of AVQA makes feature ...
As gunshots rang out at Bondi, dozens of eyewitnesses risked their lives to film the horror. This is what they wanted you to see.
A new study finds that horse whinnies are made of both a high and a low frequency, generated by different parts of the vocal ...
Abstract: In real-world physiological and psychological scenarios, there often exists a robust complementary correlation between audio and visual signals. Audio-Visual Event Localization (AVEL) aims ...
Live music can engage more than just one sense, despite it being an auditory medium. Lighting and visual effects can enhance the listening experience, but it is unclear if they can also affect the ...
This repo is the implementation of a research project aimed at enhancing Acoustic Side-Channel Attacks (ASCAs) using a novel combination of Vision Transformers (VTs) and Large Language Models (LLMs).
Some results have been hidden because they may be inaccessible to you
Show inaccessible results