Related papers: End-to-End Signal Classification in Signed Cumulat…

In this paper, we design a new class of high-efficiency deep joint source-channel coding methods to achieve end-to-end video transmission over wireless channels. The proposed methods exploit nonlinear transform and conditional coding…

Real-world datasets usually are class-imbalanced and corrupted by label noise. To solve the joint issue of long-tailed distribution and label noise, most previous works usually aim to design a noise detector to distinguish the noisy and…

Stochastic gradient descent in continuous time (SGDCT) provides a computationally efficient method for the statistical learning of continuous-time models, which are widely used in science, engineering, and finance. The SGDCT algorithm…

The past few years have witnessed a remarkable advance in deep learning for EEG-based sleep stage classification (SSC). However, the success of these models is attributed to possessing a massive amount of labeled data for training, limiting…

We propose a distributed algorithm for controlling traffic signals. Our algorithm is adapted from backpressure routing, which has been mainly applied to communication and power networks. We formally prove that our algorithm ensures global…

Channel estimation is a critical task in digital communications that greatly impacts end-to-end system performance. In this work, we introduce a novel approach for multiple-input multiple-output (MIMO) channel estimation using score-based…

In this paper, we develop a deep learning based semantic communication system for speech transmission, named DeepSC-ST. We take the speech recognition and speech synthesis as the transmission tasks of the communication system, respectively.…

Given a small set of labeled data and a large set of unlabeled data, semi-supervised learning (SSL) attempts to leverage the location of the unlabeled datapoints in order to create a better classifier than could be obtained from supervised…

This paper presents a novel training method for end-to-end scene text recognition. End-to-end scene text recognition offers high recognition accuracy, especially when using the encoder-decoder model based on Transformer. To train a highly…

Data-driven models achieve successful results in Speech Emotion Recognition (SER). However, these models, which are often based on general acoustic features or end-to-end approaches, show poor performance when the testing set has a…

Sign language recognition (SLR) has recently achieved a breakthrough in performance thanks to deep neural networks trained on large annotated sign datasets. Of the many different sign languages, these annotated datasets are only available…

Sign Language Translation (SLT) is a promising technology to bridge the communication gap between the deaf and the hearing people. Recently, researchers have adopted Neural Machine Translation (NMT) methods, which usually require…

Long Short Term Memory Connectionist Temporal Classification (LSTM-CTC) based end-to-end models are widely used in speech recognition due to its simplicity in training and efficiency in decoding. In conventional LSTM-CTC based models, a…

Recent research in the design of end to end communication system using deep learning has produced models which can outperform traditional communication schemes. Most of these architectures leveraged autoencoders to design the encoder at the…

Node tokenized graph Transformers (GTs) have shown promising performance in node classification. The generation of token sequences is the key module in existing tokenized GTs which transforms the input graph into token sequences,…

MetaDL Challenge 2020 focused on image classification tasks in few-shot settings. This paper describes second best submission in the competition. Our meta learning approach modifies the distribution of classes in a latent space produced by…

Currently, under supervised learning, a model pretrained by a large-scale nature scene dataset and then fine-tuned on a few specific task labeling data is the paradigm that has dominated the knowledge transfer learning. It has reached the…

Gradient boosting methods based on Structured Categorical Decision Trees (SCDT) have been demonstrated to outperform numerical and one-hot-encodings on problems where the categorical variable has a known underlying structure. However, the…

The detection of change-points in a spatially or time ordered data sequence is an important problem in many fields such as genetics and finance. We derive the asymptotic distribution of a statistic recently suggested for detecting…

Panoptic segmentation, which needs to assign a category label to each pixel and segment each object instance simultaneously, is a challenging topic. Traditionally, the existing approaches utilize two independent models without sharing…