We propose a novel method, Modality-based Redundancy Reduction Fusion (MRRF), for understanding and modulating the relative contribution of each modality in multimodal inference tasks. This is achieved by obtaining an (M+1)-way tensor to consider the high-order relationships between M modalities and the output layer of a neural network model. Applying a modality-based tensor factorization method, which adopts different factors for different modalities, results in removing information present in a modality that can be compensated by other modalities, with respect to model outputs. This helps to understand the relative utility of information in each modality. In addition it leads to a less complicated model with less parameters and therefore could be applied as a regularizer avoiding overfitting. We have applied this method to three different multimodal datasets in sentiment analysis, personality trait recognition, and emotion recognition. We are able to recognize relationships and relative importance of different modalities in these tasks and achieves a 1% to 4% improvement on several evaluation measures compared to the state-of-the-art for all three tasks.

Extreme classification is a classification task on an extremely large number of labels (tags). User generated labels for any type of online data can be sparing per individual user but intractably large among all users. It would be useful to automatically select a smaller, standard set of labels to represent the whole label set. We can then solve efficiently the problem of multi-label learning with an intractably large number of interdependent labels, such as automatic tagging of Wikipedia pages. We propose a submodular maximization framework with linear cost to find informative labels which are most relevant to other labels yet least redundant with each other. A simple prediction model can then be trained on this label subset. Our framework includes both label-label and label-feature dependencies, which aims to find the labels with the most representation and prediction ability. In addition, to avoid information loss, we extract and predict outlier labels with weak dependency on other labels. We apply our model to four standard natural language data sets including Bibsonomy entries with users assigned tags, web pages with user assigned tags, legal texts with EUROVOC descriptors(A topic hierarchy with almost 4000 categories regarding different aspects of European law) and Wikipedia pages with tags from social bookmarking as well as news videos for automated label detection from a lexicon of semantic concepts. Experimental results show that our proposed approach improves label prediction quality, in terms of precision and nDCG, by 3% to 5% in three of the 5 tasks and is competitive in the others, even with a simple linear prediction model. An ablation study shows how different data sets benefit from different aspects of our model, with all aspects contributing substantially to at least one data set.

We propose a tri-modal architecture to predict Big Five personality trait scores from video clips with different channels for audio, text, and video data. For each channel, stacked Convolutional Neural Networks are employed. The channels are fused both on decision-level and by concatenating their respective fully connected layers. It is shown that a multimodal fusion approach outperforms each single modality channel, with an improvement of 9.4% over the best individual modality (video). Full backpropagation is also shown to be better than a linear combination of modalities, meaning complex interactions between modalities can be leveraged to build better models. Furthermore, we can see the prediction relevance of each modality for each trait. The described model can be used to increase the emotional intelligence of virtual agents.