Systematic generalization is a crucial aspect of intelligence, which ref...
By default neural networks are not robust to changes in data distributio...
Human-Object Interaction (HOI) detection is a task to predict interactio...
Deep Neural Networks (DNNs) often fail in out-of-distribution scenarios....
Recent rapid developments in reinforcement learning algorithms have been...
Transformer-based models achieve great performance on Visual Question
An...
The insideness problem is an aspect of image segmentation that consists ...
Symmetry is omnipresent in nature and perceived by the visual system of ...
The training data distribution is often biased towards objects in certai...
Stream-based active learning (AL) is an efficient training data collecti...
Datasets often contain input dimensions that are unnecessary to predict ...
Neural networks are susceptible to small transformations including 2D
ro...
Neural Module Networks (NMNs) aim at Visual Question Answering (VQA) via...
Reinforcement learning (RL) provides a model-free approach to designing ...
In reinforcement learning (RL) algorithms, exploratory control inputs ar...
Recognizing an object's category and pose lies at the heart of visual
un...