Related papers: Training LDCRF model on unsegmented sequences usin…
The segmentation-free research efforts for addressing handwritten text recognition can be divided into three categories: connectionist temporal classification (CTC), hidden Markov model and encoder-decoder methods. In this paper, inspired…
Attribute recognition has become crucial because of its wide applications in many computer vision tasks, such as person re-identification. Like many object recognition problems, variations in viewpoints, illumination, and recognition at far…
This paper presents an empirical study of two widely-used sequence prediction models, Conditional Random Fields (CRFs) and Long Short-Term Memory Networks (LSTMs), on two fundamental tasks for Vietnamese text processing, including…
Semi-supervised learning has demonstrated promising results in automatic speech recognition (ASR) by self-training using a seed ASR model with pseudo-labels generated for unlabeled data. The effectiveness of this approach largely relies on…
Online and offline handwritten Chinese text recognition (HTCR) has been studied for decades. Early methods adopted oversegmentation-based strategies but suffered from low speed, insufficient accuracy, and high cost of character segmentation…
The present study introduces a method for improving the classification performance of imbalanced multiclass data streams from wireless body worn sensors. Data imbalance is an inherent problem in activity recognition caused by the irregular…
Recent works on deep conditional random fields (CRF) have set new records on many vision tasks involving structured predictions. Here we propose a fully-connected deep continuous CRF model for both discrete and continuous labelling…
Many of the state-of-the-art algorithms for gesture recognition are based on Conditional Random Fields (CRFs). Successful approaches, such as the Latent-Dynamic CRFs, extend the CRF by incorporating latent variables, whose values are mapped…
Pixel-level labelling tasks, such as semantic segmentation, play a central role in image understanding. Recent approaches have attempted to harness the capabilities of deep learning techniques for image recognition to tackle pixel-level…
Recently, end-to-end automatic speech recognition models based on connectionist temporal classification (CTC) have achieved impressive results, especially when fine-tuned from wav2vec2.0 models. Due to the conditional independence…
Connectionist temporal classification (CTC) provides an end-to-end acoustic model (AM) training strategy. CTC learns accurate AMs without time-aligned phonetic transcription, but sometimes fails to converge, especially in…
Connectionist Temporal Classification (CTC) is a widely used method for automatic speech recognition (ASR), renowned for its simplicity and computational efficiency. However, it often falls short in recognition performance. In this work, we…
Temporal action localization is an important yet challenging problem. Given a long, untrimmed video consisting of multiple action instances and complex background contents, we need not only to recognize their action categories, but also to…
There have been several recent efforts towards developing representations for multivariate time-series in an unsupervised learning framework. Such representations can prove beneficial in tasks such as activity recognition, health…
In this work, we tackle the challenging problem of long-tailed image recognition. Previous long-tailed recognition approaches mainly focus on data augmentation or re-balancing strategies for the tail classes to give them more attention…
In end-to-end automatic speech recognition (ASR), a model is expected to implicitly learn representations suitable for recognizing a word-level sequence. However, the huge abstraction gap between input acoustic signals and output linguistic…
Code-Switching (CS) remains a challenge for Automatic Speech Recognition (ASR), especially character-based models. With the combined choice of characters from multiple languages, the outcome from character-based models suffers from phoneme…
In this paper, a novel video classification method is presented that aims to recognize different categories of third-person videos efficiently. Our motivation is to achieve a light model that could be trained with insufficient training…
Connectionist Temporal Classification (CTC) is a widely used approach for automatic speech recognition (ASR) that performs conditionally independent monotonic alignment. However for translation, CTC exhibits clear limitations due to the…
Sleep signals from a polysomnographic database are sequences in nature. Commonly employed analysis and classification methods, however, ignored this fact and treated the sleep signals as non-sequence data. Treating the sleep signals as…