Humans exhibit complex motions that vary depending on the task that they...
Heatmaps are widely used to interpret deep neural networks, particularly...
Automatic labelling of anatomical structures, such as coronary arteries,...
Advances in machine learning and contactless sensors have enabled the
un...
High-quality saliency maps are essential in several machine learning
app...
With tremendous advancements in low-power embedded computing devices and...
With advances in data-driven machine learning research, a wide variety o...
Recently, in-bed human pose estimation has attracted the interest of
res...
Medical applications have benefited from the rapid advancement in comput...
This paper presents a novel lightweight COVID-19 diagnosis framework usi...
With the remarkable success of representation learning for prediction
pr...
This paper proposes a novel framework for lung sound event detection,
se...
With the advances of data-driven machine learning research, a wide varie...
Recent advances in deep learning have enabled the development of automat...
In a real world environment, person re-identification (Re-ID) is a
chall...
Person re-identification (re-ID) concerns the matching of subject images...
Large-scale trademark retrieval is an important content-based image retr...
Recently, Zero-shot Sketch-based Image Retrieval (ZS-SBIR) has attracted...
Machine learning-based medical anomaly detection is an important problem...
Image convolutions have been a cornerstone of a great number of deep lea...
Objective: Epilepsy is one of the most prevalent neurological diseases a...
Objective: When training machine learning models, we often assume that t...
Neural Memory Networks (NMNs) have received increased attention in recen...
Gesture recognition is a much studied research area which has myriad
rea...
Deep learning has emerged as a powerful alternative to hand-crafted meth...
The use of multi-modal data for deep machine learning has shown promise ...
Automating the analysis of imagery of the Gastrointestinal (GI) tract
ca...
Deep learning has been widely adopted in automatic emotion recognition a...
Traditionally, abnormal heart sound classification is framed as a three-...
Person re-identification (re-ID) remains challenging in a real-world
sce...
The temporal segmentation of events is an essential task and a precursor...
This paper presents a novel framework for Speech Activity Detection (SAD...
This paper proposes a novel framework for the segmentation of phonocardi...
Deep learning has been applied to achieve significant progress in emotio...
Off-the-shelf convolutional neural network features achieve state-of-the...
A precise, controllable, interpretable and easily trainable text removal...
Inspired by human neurological structures for action anticipation, we pr...
Classification of seizure type is a key step in the clinical process for...
Classification of seizure type is a key step in the clinical process for...
Advances in computer vision have brought us to the point where we have t...
In the domain of machine learning, Neural Memory Networks (NMNs) have
re...
We propose a novel conditional GAN (cGAN) model for continuous fine-grai...
We propose a novel neural memory network based framework for future acti...
In this paper we address the problem of continuous fine-grained action
s...
Humans tend to learn complex abstract concepts faster if examples are
pr...
We present a novel learning framework for vehicle recognition from a sin...
We present a novel learning framework for vehicle recognition from a sin...
Text removal algorithms have been proposed for uni-lingual scripts with
...
This paper presents a novel framework for predicting shot location and t...
State-of-the-art person re-identification systems that employ a triplet ...