Related papers: Cascade Neural Ensemble for Identifying Scientific…

Speech, Music and Noise classification/segmentation is an important preprocessing step for audio processing/indexing. To this end, we propose a novel 1D Convolutional Neural Network (CNN) - SwishNet. It is a fast and lightweight…

This work presents CascadeCNN, an automated toolflow that pushes the quantisation limits of any given CNN model, to perform high-throughput inference by exploiting the computation time-accuracy trade-off. Without the need for retraining, a…

This paper presents a context-aware framework for feature selection and classification procedures to realize a fast and accurate audio event annotation and classification. The context-aware design starts with exploring feature extraction…

AI agents have seen widespread adoption in information retrieval for scientific research, giving rise to tools such as Deep Research. However, existing retrieval agents mainly rely on keyword- or embedding-based methods. While effective at…

Convolutional neural networks (CNN) have shown promising results for end-to-end speech recognition, albeit still behind other state-of-the-art methods in performance. In this paper, we study how to bridge this gap and go beyond with a novel…

Predicting the number of citations of scholarly documents is an upcoming task in scholarly document processing. Besides the intrinsic merit of this information, it also has a wider use as an imperfect proxy for quality which has the…

While various end-to-end models for spoken language understanding tasks have been explored recently, this paper is probably the first known attempt to challenge the very difficult task of end-to-end spoken question answering (SQA). Learning…

We introduce CASED, a novel curriculum sampling algorithm that facilitates the optimization of deep learning segmentation or detection models on data sets with extreme class imbalance. We evaluate the CASED learning framework on the task of…

Stereo matching is essential for robot navigation. However, the accuracy of current widely used traditional methods is low, while methods based on CNN need expensive computational cost and running time. This is because different cost…

Recently, the pre-trained language model, BERT (and its robustly optimized version RoBERTa), has attracted a lot of attention in natural language understanding (NLU), and achieved state-of-the-art accuracy in various NLU tasks, such as…

Automated analysis of electron microscopy datasets poses multiple challenges, such as limitation in the size of the training dataset, variation in data distribution induced by variation in sample quality and experiment conditions, etc. It…

Despite the widely reported success of embedding-based machine learning methods on natural language processing tasks, the use of more easily interpreted engineered features remains common in fields such as cognitive impairment (CI)…

Systematic literature reviews (SLRs) play an essential role in summarising, synthesising and validating scientific evidence. In recent years, there has been a growing interest in using machine learning techniques to automate the…

The summarization literature focuses on the summarization of news articles. The news articles in the CNN-DailyMail are relatively short documents with about 30 sentences per document on average. We introduce SciBERTSUM, our summarization…

Recently, deep neural networks have become to be used in a variety of applications. While the accuracy of deep neural networks is increasing, the confidence score, which indicates the reliability of the prediction results, is becoming more…

Scientific document understanding is challenging as the data is highly domain specific and diverse. However, datasets for tasks with scientific text require expensive manual annotation and tend to be small and limited to only one or a few…

The theory of compressed sensing (CS) has been successfully applied to image compression in the past few years, whose traditional iterative reconstruction algorithm is time-consuming. However, it has been reported deep learning-based CS…

Traditional machine learning approaches may fail to perform satisfactorily when dealing with complex data. In this context, the importance of data mining evolves w.r.t. building an efficient knowledge discovery and mining framework.…

With the tremendous growth in the number of scientific papers being published, searching for references while writing a scientific paper is a time-consuming process. A technique that could add a reference citation at the appropriate place…

Image captioning, a challenging task where the machine automatically describes an image by sentences, has drawn significant attention in recent years. Despite the remarkable improvements of recent approaches, however, these methods are…