Representation Learning for Multimodal Content Understanding
Millions of content posts are posted each day on social media platforms, which have rich information present in more than one of these modalities: image, text, video, and audio. To holistically understand such content, AI models are required to learn a unified representation of multimodal data that effectively captures information from all of the present modalities. There are two important aspects of Multi-modal Representation Learning: firstly designing deep learning architectures to effectively integrate information from each modality, and secondly designing the training objectives that require good understanding from all the modalities to solve the task. In the talk, we will discuss some of these approaches for multi-modal representation learning.
Our mission
Our mission is to help develop the next generation of machine intelligence specifically focusing on accelerating AI at the edge. For new and groundbreaking start-ups, we want to inspire and inform your journey, and for those giants in the space, we want to provide the tools you need to innovate and continue to propel your growth.
What we do
Since our inception, we’ve achieved a great deal. But we don’t rest on our laurels. We’re constantly looking for ways in which we can evolve and further engage, educate, and inspire our community. Got an idea? Great. We’d love to hear from you.