Intrinsic susceptibility of deep learning to adversarial examples has le...
In line with the human capacity to perceive the world by simultaneously
...
The rise in popularity of text-to-image generative artificial intelligen...
Localization is a fundamental task in robotics for autonomous navigation...
Originally inspired by game-theory, path attribution framework stands ou...
Saliency methods provide post-hoc model interpretation by attributing in...
Deep visual models have widespread applications in high-stake domains. H...
Precise localization is critical for autonomous vehicles. We present a
s...
Annotating medical images for disease detection is often tedious and
exp...
Multiple object detection and pose estimation are vital computer vision
...
Vision transformers are emerging as a powerful tool to solve computer vi...
Currently, action recognition is predominately performed on video data a...
Point cloud scene flow estimation is of practical importance for dynamic...
Artificial Intelligence (AI) relies heavily on deep learning - a technol...
Geometric feature learning for 3D meshes is central to computer graphics...
Deep learning is gaining instant popularity in computer aided diagnosis ...
Deep Learning (DL) is the most widely used tool in the contemporary fiel...
Deep learning is found to be vulnerable to adversarial examples. However...
Backpropagation image saliency aims at explaining model predictions by
e...
Deep visual models are susceptible to adversarial perturbations to input...
We present Picasso, a CUDA-based library comprising novel modules for de...
COVID-19 classification using chest Computed Tomography (CT) has been fo...
Deep learning-based Multiple Object Tracking (MOT) currently relies on
o...
Deep learning has demonstrated state-of-the-art performance for a variet...
Contemporary deep learning based video captioning follows encoder-decode...
We propose a spherical kernel for efficient graph convolution of 3D poin...
Deep learning models achieve impressive performance for skeleton-based h...
Advances in Deep Learning have recently made it possible to recover full...
We introduce Label Universal Targeted Attack (LUTA) that makes a deep mo...
We propose an octree guided neural network architecture and spherical
co...
Automatic generation of video captions is a fundamental challenge in com...
Medical Image Analysis is currently experiencing a paradigm shift due to...
Multiple Object Tracking (MOT) plays an important role in solving many
f...
We propose a neural network for 3D point cloud processing that exploits
...
Real-time automatic counting of people has widespread applications in
se...
Hyperspectral cameras preserve the fine spectral details of scenes that ...
Deep learning is at the heart of the current rise of machine learning an...
Human skeleton joints are popular for action analysis since they can be
...
Recent advances in Deep Learning show the existence of image-agnostic
qu...
In video-based action recognition, viewpoint variations often pose major...
Many classification approaches first represent a test sample using the
t...
We propose a Bayesian approach to learn discriminative dictionaries for
...