This paper addresses observation duplication and lack of whole picture problems for ensemble learning with the attention model integrated convolutional recurrent neural network (ACRNN) in imbalanced speech emotion recognition. Firstly, we introduce Bagging with ACRNN and the observation duplication problem. Then Redagging is devised and proved to address the observation duplication problem by generating bootstrap samples from permutations of observations. Moreover, Augagging is proposed to get oversampling learner to participate in majority voting for addressing the lack of whole picture problem. Finally, Extensive experiments on IEMOCAP and Emo-DB samples demonstrate the superiority of our proposed methods (i.e., Redagging and Augagging).
In order to deal with variant-length long videos, prior works extract multimodal features and fuse them to predict students' engagement intensity. In this paper, we present a new end-to-end method Class Attention in Video Transformer (CavT), which involves a single vector to process class embedding and to uniformly perform end-to-end learning on variant-length long videos and fixedlength short videos. Furthermore, to address the lack of sufficient samples, we propose a binary-order representatives sampling method (BorS) to add multiple video sequences of each video to augment the training set. BorS+CavT not only achieves the state-of-the-art MSE (0.0495) on the EmotiW-EP dataset, but also obtains the state-of-the-art MSE (0.0377) on the DAiSEE dataset. The code and models will be made publicly available at https://github.com/mountainai/cavt.
Most of the existing knowledge graph embedding models are supervised methods and largely relying on the quality and quantity of obtainable labelled training data. The cost of obtaining high quality triples is high and the data sources are facing a serious problem of data sparsity, which may result in insufficient training of long-tail entities. However, unstructured text encoding entities and relational knowledge can be obtained anywhere in large quantities. Word vectors of entity names estimated from the unlabelled raw text using natural language model encode syntax and semantic properties of entities. Yet since these feature vectors are estimated through minimizing prediction error on unsupervised entity names, they may not be the best for knowledge graphs. We propose a two-phase approach to adapt unsupervised entity name embeddings to a knowledge graph subspace and jointly learn the adaptive matrix and knowledge representation. Experiments on Freebase show that our method can rely less on the labelled data and outperforms the baselines when the labelled data is relatively less. Especially, it is applicable to zero-shot scenario.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.