Hyperbolic space is becoming a popular choice for representing data due ...
Models capable of leveraging unlabelled data are crucial in overcoming l...
Visual Question Answering (VQA) models aim to answer natural language
qu...
Purpose: A fundamental problem in designing safe machine learning system...
Annotating new datasets for machine learning tasks is tedious,
time-cons...
Despite considerable recent progress in Visual Question Answering (VQA)
...
Semantic segmentation has made significant progress in recent years than...
Modern sky surveys are producing ever larger amounts of observational da...
Visual Question Answering (VQA) models take an image and a natural-langu...
Unsupervised out-of-distribution (U-OOD) detection has recently attracte...
Cataract surgery is a sight saving surgery that is performed over 10 mil...
Given an image sequence featuring a portion of a sports field filmed by ...
Optical Coherence Tomography (OCT) is the primary imaging modality for
d...
Multi-label classification (MLC) problems are becoming increasingly popu...
The finite element method (FEM) is among the most commonly used numerica...
We present a method to train self-binarizing neural networks, that is,
n...
Delineation of curvilinear structures is an important problem in Compute...
Detection of surgical instruments plays a key role in ensuring patient s...
Imposing constraints on the output of a Deep Neural Net is one way to im...
Size uniformity is one of the main criteria of superpixel methods. But s...
Most recent approaches to monocular 3D human pose estimation rely on Dee...