Multimodal Machine Learning: A Survey and Taxonomy
Multimodal Machine Learning: A Survey and Taxonomy
复制标题
DOI：
10.1109/tpami.2018.2798607
复制
发表时间：
2019-02-01
影响因子：
23.6
通讯作者：
Morency, Louis-Philippe
中科院分区：
文献类型：
--
作者：
Baltrusaitis, Tadas;Ahuja, Chaitanya;Morency, Louis-Philippe
我们对世界的经验是多模式的 - 我们看到物体，听到声音，感觉质地，气味和味道。模态是指发生或经历过的事情的方式，并且在包含多种此类方式时，研究问题被描述为多模式。为了使人工智能在理解我们周围的世界方面取得进展，它需要能够一起解释这种多模式信号。多模式机器学习旨在构建可以处理和关联多种方式信息的模型。这是一个充满活力的多学科领域，具有越来越重要的重要性和非凡的潜力。本文没有专注于特定的多模式应用，而是调查了多模式机器学习本身的最新进展，并将其呈现为共同的分类法。我们超越了典型的早期和晚期融合分类，并确定了多模式机器学习面临的更广泛的挑战，即：代表，翻译，对齐，融合和共同学习。这种新的分类法将使研究人员能够更好地了解该领域的状态并确定未来研究的方向。
Our experience of the world is multimodal - we see objects, hear sounds, feel texture, smell odors, and taste flavors. Modality refers to the way in which something happens or is experienced and a research problem is characterized as multimodal when it includes multiple such modalities. In order for Artificial Intelligence to make progress in understanding the world around us, it needs to be able to interpret such multimodal signals together. Multimodal machine learning aims to build models that can process and relate information from multiple modalities. It is a vibrant multi-disciplinary field of increasing importance and with extraordinary potential. Instead of focusing on specific multimodal applications, this paper surveys the recent advances in multimodal machine learning itself and presents them in a common taxonomy. We go beyond the typical early and late fusion categorization and identify broader challenges that are faced by multimodal machine learning, namely: representation, translation, alignment, fusion, and co-learning. This new taxonomy will enable researchers to better understand the state of the field and identify directions for future research.