Related papers: Introducing SKYSET - a Quintuple Approach for Impr…

Recent scene text detection methods are almost based on deep learning and data-driven. Synthetic data is commonly adopted for pre-training due to expensive annotation cost. However, there are obvious domain discrepancies between synthetic…

Knowledge distillation transfers knowledge from the teacher network to the student one, with the goal of greatly improving the performance of the student network. Previous methods mostly focus on proposing feature transformation and loss…

Ensemble Machine Learning (EML) techniques, especially stacking, have been shown to improve predictive performance by combining multiple base models. However, they are often criticized for their lack of interpretability. In this paper, we…

Sketch semantic segmentation is a well-explored and pivotal problem in computer vision involving the assignment of pre-defined part labels to individual strokes. This paper presents ContextSeg - a simple yet highly effective approach to…

Self-supervised learning (SSL) has achieved remarkable success across various speech-processing tasks. To enhance its efficiency, previous works often leverage the use of compression techniques. A notable recent attempt is DPHuBERT, which…

Scarcity of parallel sentence-pairs poses a significant hurdle for training high-quality Neural Machine Translation (NMT) models in bilingually low-resource scenarios. A standard approach is transfer learning, which involves taking a model…

We introduce TechTrack, a new dataset for tracking entities in technical procedures. The dataset, prepared by annotating open domain articles from WikiHow, consists of 1351 procedures, e.g., "How to connect a printer", identifies more than…

Few-shot class-incremental learning (FSCIL) aims to continually learn new classes using a few samples while not forgetting the old classes. The key of this task is effective knowledge transfer from the base session to the incremental…

State-of-the-art sign language translation (SLT) systems facilitate the learning process through gloss annotations, either in an end2end manner or by involving an intermediate step. Unfortunately, gloss labelled sign language data is…

Question Answering (QA) is a growing area of research, often used to facilitate the extraction of information from within documents. State-of-the-art QA models are usually pre-trained on domain-general corpora like Wikipedia and thus tend…

To be informative, an evaluation must measure how well systems generalize to realistic unseen data. We identify limitations of and propose improvements to current evaluations of text-to-SQL systems. First, we compare human-generated and…

In this paper, we present CogNet, a knowledge base (KB) dedicated to integrating three types of knowledge: (1) linguistic knowledge from FrameNet, which schematically describes situations, objects and events. (2) world knowledge from YAGO,…

In the past few years, convolutional neural networks (CNNs) have achieved impressive results in computer vision tasks, which however mainly focus on photos with natural scene content. Besides, non-sensor derived images such as…

Abstractive summarization systems aim to produce more coherent and concise summaries than their extractive counterparts. Popular neural models have achieved impressive results for single-document summarization, yet their outputs are often…

Representation learning is a critical ingredient for natural language processing systems. Recent Transformer language models like BERT learn powerful textual representations, but these models are targeted towards token- and sentence-level…

KNET is a general-purpose shell for constructing expert systems based on belief networks and decision networks. Such networks serve as graphical representations for decision models, in which the knowledge engineer must define clearly the…

This study aims to investigate the challenge of insufficient three-dimensional context in synthetic datasets for scene text rendering. Although recent advances in diffusion models and related techniques have improved certain aspects of…

The pursuit of diverse, complex, and large-scale instruction data is crucial for automatically aligning large language models (LLMs). While there are methods capable of generating synthetic instructions at scale, they either suffer from…

Enabling machines to understand structured visuals like slides and user interfaces is essential for making them accessible to people with disabilities. However, achieving such understanding computationally has required manual data…

A growing number of approaches exist to generate explanations for image classification. However, few of these approaches are subjected to human-subject evaluations, partly because it is challenging to design controlled experiments with…