2 papers
cs.CV2024
MUSTAN: Multi-scale Temporal Context as Attention for Robust Video Foreground Segmentation
Praveen Kumar Pokala, Jaya Sai Kiran Patibandla, Naveen Kumar Pandey +1
Video foreground segmentation (VFS) is an important computer vision task wherein one aims to segment the objects under motion from the background. Most of the current methods are i…
cs.CL2023
AQUALLM: Audio Question Answering Data Generation Using Large Language Models
Swarup Ranjan Behera, Krishna Mohan Injeti, Jaya Sai Kiran Patibandla +2
Audio Question Answering (AQA) constitutes a pivotal task in which machines analyze both audio signals and natural language questions to produce precise natural language answers. T…