Class Incremental Learning (CIL) aims to sequentially learn new classes ...
Data-Free Class Incremental Learning (DFCIL) aims to sequentially learn ...
In this paper we propose a new method for exemplar-free class incrementa...
In class incremental learning (CIL) a model must learn new classes in a
...
In games, as in and many other domains, design validation and testing is...
This paper proposes a novel deep reinforcement learning algorithm to per...
Recent self-supervised learning methods are able to learn high-quality i...
In this article we study the problem of training intelligent agents usin...
In this paper we propose a method for improving pedestrian detection in ...
Recent advances in Deep Reinforcement Learning (DRL) have largely focuse...
Deep Reinforcement Learning achieves very good results in domains where
...
In this paper we introduce DeepCrawl, a fully-playable Roguelike prototy...
Research on continual learning has led to a variety of approaches to
mit...
Humans are capable of learning new tasks without forgetting previous one...
Technology and the fruition of cultural heritage are becoming increasing...
For many applications the collection of labeled data is expensive labori...
Word spotting in natural scene images has many applications in scene
und...
We propose a novel crowd counting approach that leverages abundantly
ava...
In this paper we propose an approach to avoiding catastrophic forgetting...
Deep Neural Networks trained on large datasets can be easily transferred...
In emergency situations, actions that save lives and limit the impact of...
We propose a no-reference image quality assessment (NR-IQA) approach tha...
In this paper we propose an approach to lexicon-free recognition of text...
This paper proposes a novel method to optimize bandwidth usage for objec...
Most approaches to human attribute and action recognition in still image...
In this paper we present the use of Sparse Radial Sampling Local Binary
...