Search Results for author:
Found 32 papers, 9 papers with code
Gated Low-rank Adaptation for personalized Code-Switching Automatic Speech Recognition on the low-spec devices
To tackle this problem, we propose code-switching speech recognition models that incorporate fine-tuned monolingual and multilingual speech recognition models.
Automatic Speech Recognition
parameter-efficient fine-tuning
+2
Towards Multi-domain Face Landmark Detection with Synthetic Data from Diffusion model
Finally, we fine-tuned a pre-trained face landmark detection model on the synthetic dataset to achieve multi-domain face landmark detection.
ViVid-1-to-3: Novel View Synthesis with Video Diffusion Models
Thus, to perform novel-view synthesis, we create a smooth camera trajectory to the target view that we wish to render, and denoise using both a view-conditioned diffusion model and a video diffusion model.
MPE4G: Multimodal Pretrained Encoder for Co-Speech Gesture Generation
Through the series of experiments and human evaluation, the proposed method renders realistic co-speech gestures not only when all input modalities are given but also when the input modalities are missing or noisy.
Spatial-temporal Transformer-guided Diffusion based Data Augmentation for Efficient Skeleton-based Action Recognition
In this paper, we introduce a novel data augmentation method for skeleton-based action recognition tasks, which can effectively generate high-quality and diverse sequential actions.
DIFAI: Diverse Facial Inpainting using StyleGAN Inversion
Image inpainting is an old problem in computer vision that restores occluded regions and completes damaged images.
Reference Guided Image Inpainting using Facial Attributes
Image inpainting is a technique of completing missing pixels such as occluded region restoration, distracting objects removal, and facial completion.
Single Cell Training on Architecture Search for Image Denoising
With these modules, then we employ reinforcement learning in search of an optimal image denoising network at a module level.
3d human motion generation from the text via gesture action classification and the autoregressive model
To achieve the goal, the proposed method predicts expression from the sentences using a text classification model based on a pretrained language model and generates gestures using the gate recurrent unit-based autoregressive model.
Discriminatory and orthogonal feature learning for noise robust keyword spotting
In order to train the network for more robust performance in noisy environments, we introduce the LOw Variant Orthogonal (LOVO) loss.
Pose-Guided Graph Convolutional Networks for Skeleton-Based Action Recognition
Graph convolutional networks (GCNs), which can model the human body skeletons as spatial and temporal graphs, have shown remarkable potential in skeleton-based action recognition.
Controllable Face Manipulation and UV Map Generation by Self-supervised Learning
Our model relies on pretrained StyleGAN, and the proposed model is trained in a self-supervised manner without any manual annotations or datasets.
Injecting 3D Perception of Controllable NeRF-GAN into StyleGAN for Editable Portrait Image Synthesis
To alleviate the issue, many 3D-aware GANs have been proposed and shown notable results, but 3D GANs struggle with editing semantic attributes.
Generate and Edit Your Own Character in a Canonical View
Although the progress of generative models enables the stylization of a portrait, obtaining the stylized image in canonical view is still a challenging task.
Efficient dynamic filter for robust and low computational feature extraction
However, the performance of the dynamic filter might be degraded since simple feature pooling is used to reduce the computational resource in the IDF part.
Adverse Weather Image Translation with Asymmetric and Uncertainty-aware GAN
To address this issue, we propose a novel GAN model, i. e., AU-GAN, which has an asymmetric architecture for adverse domain translation.
Action Recognition with Domain Invariant Features of Skeleton Image
Due to the fast processing-speed and robustness it can achieve, skeleton-based action recognition has recently received the attention of the computer vision community.
A Teacher-Student Framework with Fourier Augmentation for COVID-19 Infection Segmentation in CT Images
Automatic segmentation of infected regions in computed tomography (CT) images is necessary for the initial diagnosis of COVID-19.
A Lightweight dynamic filter for keyword spotting
Keyword Spotting (KWS) from speech signals is widely applied to perform fully hands-free speech recognition.
CaraNet: Context Axial Reverse Attention Network for Segmentation of Small Medical Objects
Segmenting medical images accurately and reliably is important for disease diagnosis and treatment.
Ranked #14 on
Medical Image Segmentation
on ETIS-LARIBPOLYPDB
Memory-based Semantic Segmentation for Off-road Unstructured Natural Environments
In this paper, a built-in memory module for semantic segmentation is proposed to overcome these problems.
CPNet: Cross-Parallel Network for Efficient Anomaly Detection
Anomaly detection in video streams is a challenging problem because of the scarcity of abnormal events and the difficulty of accurately annotating them.
Few-shot Learning for CT Scan based COVID-19 Diagnosis
To compensate for the sparseness of labeled data, the proposed method utilizes a large amount of synthetic COVID-19 CT images and adjusts the networks from the source domain (synthetic data) to the target domain (real data) with a cross-domain training mechanism.
CAFE-GAN: Arbitrary Face Attribute Editing with Complementary Attention Feature
The goal of face attribute editing is altering a facial image according to given target attributes such as hair color, mustache, gender, etc.
Unsupervised domain adaptation based COVID-19 CT infection segmentation network
In this paper, we propose an unsupervised domain adaptation based segmentation network to improve the segmentation performance of the infection areas in COVID-19 CT images.
COVID-19 CT Image Synthesis with a Conditional Generative Adversarial Network
However, training a deep-learning model requires large volumes of data, and medical staff faces a high risk when collecting COVID-19 CT data due to the high infectivity of the disease.
Data Separability for Neural Network Classifiers and the Development of a Separability Index
In machine learning, the performance of a classifier depends on both the classifier model and the dataset.
NTIRE 2020 Challenge on Real-World Image Super-Resolution: Methods and Results
This paper reviews the NTIRE 2020 challenge on real world super-resolution.
Correlation Distance Skip Connection Denoising Autoencoder (CDSK-DAE) for Speech Feature Enhancement
Performance of learning based Automatic Speech Recognition (ASR) is susceptible to noise, especially when it is introduced in the testing data while not presented in the training data.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Sinusoidal wave generating network based on adversarial learning and its application: synthesizing frog sounds for data augmentation
Audio waveform generation can then be performed using the proposed network.
KU-ISPL Speaker Recognition Systems under Language mismatch condition for NIST 2016 Speaker Recognition Evaluation
As development dataset which is spoken in Cebuano and Mandarin, we could prepare the evaluation trials through preliminary experiments to compensate the language mismatched condition.
KU-ISPL Language Recognition System for NIST 2015 i-Vector Machine Learning Challenge
The experimental results show that the use of duration and score fusion improves language recognition performance by 5% relative in LRiMLC15 cost.
