Skip to content
conftrace_
2021 IJCAI IJCAI 2021

Learning from Multimedia Data with Incomplete Information

Abstract

Traditional deep learning methods are based on the condition that the data is of high-quality, which means the data information is highly available. However, data in these scenes often have the characteristics of large background noise, lack of sample content, small target, serious occlusion and a small number of samples. The application of related tasks in real open scenarios is very important, so it is urgent to make full use of these incomplete information data accurately.

Authors

Renshuai Tao

Topics

Machine Learning > Learning Types > Semi-Supervised Learning Machine Learning > Learning Types > Unsupervised Learning Deep Learning > Architectures > Neural Networks

Keywords

semi-supervised learning multimodal learning incomplete information noisy label
Download PDF

More from IJCAI 2021

All IJCAI 2021 papers →
Inter-Task Similarity for Lifelong Reinforcement Learning in Heterogeneous Tasks
A Human-AI Teaming Approach for Incremental Taxonomy Learning from Text
Continual Lifelong Learning for Intelligent Agents
Data Efficient Algorithms and Interpretability Requirements for Personalized Assessment of Taskable AI Systems
Adversarial Examples in Physical World
Learning and Planning Under Uncertainty for Green Security