Despite significant advances in deep learning, models often struggle to
...
Visual Question Answering (VQA) is a multi-modal task that involves answ...
Designing efficient and reliable VQA systems remains a challenging probl...
Detecting emotions in languages is important to accomplish a complete
in...
The problem of learning from few labeled examples while using large amou...
Sketches are a medium to convey a visual scene from an individual's crea...
FloodNet is a high-resolution image dataset acquired by a small UAV plat...
This paper describes our submissions for the Social Media Mining for Hea...