Modern day computer vision tasks requires efficient solution to problems such as image
recognition, natural language processing, object detection, object segmentation and …

Over the past few years, the computer vision domain has evolved and made a revolutionary
transition from human-engineered features to automated features to address challenging …

Abstract We introduce the Action Transformer model for recognizing and localizing human
actions in video clips. We repurpose a Transformer-style architecture to aggregate features …

Deep convolutional neural networks, assisted by architectural design strategies, make
extensive use of data augmentation techniques and layers with a high number of feature …

In this paper, we propose 3D point-capsule networks, an auto-encoder designed to process
sparse 3D point clouds while preserving spatial arrangements of the input data. 3D capsule …

During the past decade, deep learning is one of the essential breakthroughs made in
artificial intelligence. In particular, it has achieved great success in image processing …

Recent years have witnessed a big leap in automatic visual saliency detection attributed to
advances in deep learning, especially Convolutional Neural Networks (CNNs). However …

Spatiotemporal action localization requires the incorporation of two sources of information
into the designed architecture:(1) temporal information from the previous frames and (2) …

We introduce a new task, MultiMedia Event Extraction (M2E2), which aims to extract events
and their arguments from multimedia documents. We develop the first benchmark and …

Our work expands the use of capsule networks to the task of object segmentation for the first
time in the literature. This is made possible via the introduction of locally-constrained routing …