Traditional approaches for Visual Question Answering (VQA) require large amount of labeled data for training. Unfortunately, such large scale data is usually not available for medical domain. In this paper, we propose a novel medical VQA framework that overcomes the labeled data limitation. The proposed framework explores the use of the unsupervised Denoising Auto-Encoder (DAE) and the supervised Meta-Learning. The advantage of DAE is to leverage the large amount of unlabeled images while the advantage of Meta-Learning is to learn meta-weights that quickly adapt to VQA problem with limited labeled data. By leveraging the advantages of these techniques, it allows the proposed framework to be efficiently trained using a small labeled training set. The experimental results show that the proposed method significantly outperforms the state-of-the-art medical VQA. The source code is available at https://github.com/aioz-ai/MICCAI19-MedVQA.
In recent years, studies on automatic speech recognition (ASR) have shown outstanding results that reach human parity on short speech segments. However, there are still difficulties in standardizing the output of ASR such as capitalization and punctuation restoration for long-speech transcription. The problems obstruct readers to understand the ASR output semantically and also cause difficulties for natural language processing models such as NER, POS and semantic parsing. In this paper, we propose a method to restore the punctuation and capitalization for long-speech ASR transcription. The method is based on Transformer models and chunk merging that allows us to (1), build a single model that performs punctuation and capitalization in one go, and (2), perform decoding in parallel while improving the prediction accuracy. Experiments on British National Corpus showed that the proposed approach outperforms existing methods in both accuracy and decoding speed.
Abstract-This paper discusses the design and current capabilities of a new software tool, dVC, capable of simulating planar systems of bodies experiencing unilateral contacts with friction. Since different problems require different levels of accuracy, dVC provides user-selectable body types (rigid or locally-compliant), motion models (first-order, quasi-static, dynamic), and several state-of-the-art time-stepping methods. One can also choose to include friction between each body and the plane of motion. To support optimal and robust part design, dVC also allows on-the-fly changes to parameters of the geometric and physical models. The results obtained for three representative planar problems are presented: the design of a passive part-orienting device, the planning of a meso-scale assembly operation, and the design of a grasp strategy.
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.