Catastrophic forgetting remains a critical challenge in the field of
con...
Recent breakthroughs in zero-shot voice synthesis have enabled imitating...
Given a limited labeling budget, active learning (AL) aims to sample the...
Zero-shot NL2SQL is crucial in achieving natural language to SQL that is...
Real-world graphs are often dynamic and evolve over time. To trace the
e...
Orchestrating a high-quality data preparation program is essential for
s...
In this paper, we research the new topic of object effects recommendatio...
Transaction processing technology has three important contents: data
ano...
Autonomous Driving and Simultaneous Localization and Mapping(SLAM) are
b...
Text analytics directly on compression (TADOC) has proven to be a promis...
Point cloud-based large scale place recognition is fundamental for many
...
Can AI help automate human-easy but computer-hard data preparation tasks...
This article provides a comprehensive description of Text Analytics Dire...
The proliferation of big data has brought an urgent demand for
privacy-p...
Deep learning methods have played a more and more important role in
hype...
Cross-modal associations between voice and face from a person can be lea...
Existing works, including ELMO and BERT, have revealed the importance of...
SimRank is a classic measure of the similarities of nodes in a graph.
G...
Analogical reasoning is effective in capturing linguistic regularities. ...
Despite the loss of semantic information, bag-of-ngram based methods sti...