Causal discovery is a powerful technique for identifying causal relation...
Recent advances in deep neural networks have achieved unprecedented succ...
Understanding causal relations is vital in scientific discovery. The pro...
There has been an increasing interest in enhancing the fairness of machi...
EXplainable AI (XAI) is an essential topic to improve human understandin...
Safeguarding personal information is paramount for healthcare data shari...
As the popularity of large language models (LLMs) soars across various
a...
We propose a hybrid neural network (NN) and PDE approach for learning
ge...
Exploring data is crucial in data analysis, as it helps users understand...
Recently reported state-of-the-art results in visual speech recognition ...
Audio-visual speech recognition has received a lot of attention due to i...
Cross-lingual self-supervised learning has been a growing research topic...
Recent progress in large language code models (LLCMs) has led to a drama...
We present RAVEn, a self-supervised multi-modal approach to jointly lear...
Recognizing a word shortly after it is spoken is an important requiremen...
Several training strategies and temporal models have been recently propo...
In light of the growing popularity of Exploratory Data Analysis (EDA),
u...
Debugging performance anomalies in real-world databases is challenging.
...
This work considers identifying parameters characterizing a physical sys...
Neural program embeddings have demonstrated considerable promise in a ra...
This paper presents a novel method for face clustering in videos using a...
Visual speech recognition (VSR) aims to recognise the content of speech ...
The high dimensionality of soft mechanisms and the complex physics of
fl...
Deep metric learning (DML) is a cornerstone of many computer vision
appl...
The large amount of audiovisual content being shared online today has dr...
Video-to-speech is the process of reconstructing the audio speech from a...
The computational design of soft underwater swimmers is challenging beca...
In this work, we present a hybrid CTC/Attention model based on a ResNet-...
For given multivariate functions specified by algebraic, differential or...
We present a novel, fast differentiable simulator for soft-body learning...
Text-to-SQL is a task to generate SQL queries from human utterances. How...
In this work, we present the Densely Connected Temporal Convolutional Ne...
Lipreading has witnessed a lot of progress due to the resurgence of neur...
Tasks in multi-task learning often correlate, conflict, or even compete ...
Style transfer has recently received a lot of attention, since it allows...
Lip-reading has attracted a lot of research attention lately thanks to
a...
Self supervised representation learning has recently attracted a lot of
...
Adversarial attacks pose a threat to deep learning models. However, rese...
3D CNN shows its strong ability in learning spatiotemporal representatio...
Lip-reading models have been significantly improved recently thanks to
p...
Speech is a means of communication which relies on both audio and visual...
Several audio-visual speech recognition models have been recently propos...
Traditional visual speech recognition systems consist of two stages, fea...
Recent years have witnessed a boom of connected medical devices, which b...
In the NeurIPS 2018 Artificial Intelligence for Prosthetics challenge,
p...
Recent works in speech recognition rely either on connectionist temporal...
Several end-to-end deep learning approaches have been recently presented...