相关论文: A Few Shot Multi-Representation Approach for N-gra…

Handwritten text recognition in low resource scenarios, such as manuscripts with rare alphabets, is a challenging problem. The main difficulty comes from the very few annotated data and the limited linguistic information (e.g. dictionaries…

Encoded (or ciphered) manuscripts are a special type of historical documents that contain encrypted text. The automatic recognition of this kind of documents is challenging because: 1) the cipher alphabet changes from one document to…

Existing approaches for learning word embeddings often assume there are sufficient occurrences for each word in the corpus, such that the representation of words can be accurately estimated from their contexts. However, in real-world…

Few-shot keyword spotting (KWS) aims to detect unknown keywords with limited training samples. A commonly used approach is the pre-training and fine-tuning framework. While effective in clean conditions, this approach struggles with mixed…

Keyword spotting (KWS) in historical documents is an important tool for the initial exploration of digitized collections. Nowadays, the most efficient KWS methods are relying on machine learning techniques that require a large amount of…

Few-shot keyword spotting (FS-KWS) models usually require large-scale annotated datasets to generalize to unseen target keywords. However, existing KWS datasets are limited in scale and gathering keyword-like labeled data is costly…

Query by String Keyword Spotting (KWS) is here considered as a key technology for indexing large collections of handwritten text images to allow fast textual access to the contents of these collections. Under this perspective, a…

In this paper, we investigate the feasibility of applying few-shot learning algorithms to a speech task. We formulate a user-defined scenario of spoken term classification as a few-shot learning problem. In most few-shot learning studies,…

Few-shot learning is a challenging problem since only a few examples are provided to recognize a new class. Several recent studies exploit additional semantic information, e.g. text embeddings of class names, to address the issue of rare…

Keyword Spotting plays a critical role in enabling hands-free interaction for battery-powered edge devices. Few-Shot Keyword Spotting (FS-KWS) addresses the scalability and adaptability challenges of traditional systems by enabling…

State-of-the-art methods for handwriting recognition are based on Long Short Term Memory (LSTM) recurrent neural networks (RNN), which now provides very impressive character recognition performance. The character recognition is generally…

For training a few-shot keyword spotting (FS-KWS) model, a large labeled dataset containing massive target keywords has known to be essential to generalize to arbitrary target keywords with only a few enrollment samples. To alleviate the…

Few-shot object detection aims to detect instances of specific categories in a query image with only a handful of support samples. Although this takes less effort than obtaining enough annotated images for supervised object detection, it…

Current state-of-the-art approaches in the field of Handwritten Text Recognition are predominately single task with unigram, character level target units. In our work, we utilize a Multi-task Learning scheme, training the model to perform…

In this paper, we explore meta-learning for few-shot text classification. Meta-learning has shown strong performance in computer vision, where low-level patterns are transferable across learning tasks. However, directly applying this…

Keyword spotting (KWS) is one of the speech recognition tasks most sensitive to the quality of the feature representation. However, the research on KWS has traditionally focused on new model topologies, putting little emphasis on other…

The advent of instruction-tuned language models that convincingly mimic human writing poses a significant risk of abuse. However, such abuse may be counteracted with the ability to detect whether a piece of text was composed by a language…

The bag-of-words (BOW) model is the common approach for classifying documents, where words are used as feature for training a classifier. This generally involves a huge number of features. Some techniques, such as Latent Semantic Analysis…

We propose a method that can perform one-class classification given only a small number of examples from the target class and none from the others. We formulate the learning of meaningful features for one-class classification as a…

Few-shot and zero-shot text classification aim to recognize samples from novel classes with limited labeled samples or no labeled samples at all. While prevailing methods have shown promising performance via transferring knowledge from seen…