Announcements
- 30th July: List of confirmed speakers is here. More to follow!
- 14th June: The submission site is open.
- 12th April: MULL Workshop will be held in conjunction with ACM Multimedia 2021. More details to follow.
Workshop Overview
The past several years have witnessed an explosion of interest in and a dizzyingly fast development of machine learning, a subfield of artificial intelligence. Foremost among these approaches are Deep Neural Networks (DNNs) that can learn powerful feature representations with multiple levels of abstraction directly from data when large amounts of labeled data is available. Undoubtedly, DNNs have shown remarkable success in many Multimedia tasks, such as understanding text, recognizing images, analyzing videos and so on. Despite a wide range of impressive results, current DNN based methods typically depend on massive amounts of accurately annotated training data to achieve high accuracy, and are brittle in that their performance can degrade severely with less labeling data.
DNNs lack the ability of learning from limited exemplars and fast generalizing to new tasks. However, real-word Multimedia applications often require models that are able to (a) learn with few annotated samples, and (b) continually adapt to new data without forgetting prior knowledge. By contrast, humans can learn from just one or a handful of examples, can do very long-term learning, and can form abstract models of a situation and manipulate these models to achieve extreme generalization. As a result, one of the next big challenges in Multimedia is to develop learning approaches that are capable of addressing the important shortcomings of existing methods in this regard. Therefore, in order to address the current inefficiency of deep learning based Multimedia methods, there is pressing need to research methods, (1) to drastically reduce requirements for labeled training data, (2) to significantly reduce the amount of data necessary to adapt models to new environments, and (3) to even use as little labeled training data as people need.
Therefore, we would like to focus on Multimedia Understanding with Less Labeling (MULL) to host such a workshop which consists of a paper submission session and an invited talk session. Specifically, in the paper submission session, we will peer-review paper submissions involving the Multimedia Understanding with Less Labeling related topics. Moreover, we will invite several domain-specific experts in Multimedia for sharing their insights and research progress on the topic of our workshop.
