Deep learning (DL) applications are prevalent nowadays as they can help ...
Semantic segmentation based on sparse annotation has advanced in recent
...
Large Language Models pre-trained with self-supervised learning have
dem...
Weakly supervised object localization is a challenging task which aims t...
We introduce temporal multimodal multivariate learning, a new family of
...
Recent research has achieved impressive progress in the session-based
re...
Recent advancements in open-domain question answering (ODQA), i.e., find...
This paper proposes a new problem of complementary evidence identificati...
For many new application domains for data-to-text generation, the main
o...
Electroencephalogram (EEG) is a prominent way to measure the brain activ...
Existing deep learning based facial landmark detection methods have achi...
Recently, a more challenging state tracking task, Audio-Video Scene-Awar...
A lot of progress has been made to improve question answering (QA) in re...
Neural network-based sequence-to-sequence (seq2seq) models strongly suff...
The neural attention model has achieved great success in data-to-text
ge...
We explore trust in a relatively new area of data science: Automated Mac...
Many text generation tasks naturally contain two steps: content selectio...
Recent research has made impressive progress in single-turn dialogue
mod...
We introduce Reagent, a technology that readily converts ordinary webpag...
Sequence-to-Sequence (seq2seq) models have become overwhelmingly popular...
We propose a cost-effective framework for preference elicitation and
agg...
Variational encoder-decoders (VEDs) have shown promising results in dial...
We develop a high-quality multi-turn dialog dataset, DailyDialog, which ...
As computational power has continued to increase, and sensors have becom...
Deep latent variable models have been shown to facilitate the response
g...