Search Results for author:
Found 16 papers, 7 papers with code
I-vector Transformation Using Conditional Generative Adversarial Networks for Short Utterance Speaker Verification
I-vector based text-independent speaker verification (SV) systems often have poor performance with short utterances, as the biased phonetic distribution in a short utterance makes the extracted i-vector unreliable.
Generative Adversarial Network
Text-Independent Speaker Verification
A Fine-to-Coarse Convolutional Neural Network for 3D Human Action Recognition
This paper presents a new framework for human action recognition from a 3D skeleton sequence.
Ranked #99 on
Skeleton Based Action Recognition
on NTU RGB+D
Few-Shot Adaptation for Multimedia Semantic Indexing
Few-shot adaptation provides robust parameter estimation with few training examples, by optimizing the parameters of zero-shot learning and supervised many-shot learning simultaneously.
Sequence-Level Knowledge Distillation for Model Compression of Attention-based Sequence-to-Sequence Speech Recognition
We investigate the feasibility of sequence-level knowledge distillation of Sequence-to-Sequence (Seq2Seq) models for Large Vocabulary Continuous Speech Recognition (LVSCR).
Augmented Cyclic Consistency Regularization for Unpaired Image-to-Image Translation
Herein, we propose Augmented Cyclic Consistency Regularization (ACCR), a novel regularization method for unpaired I2I translation.
Speech Paralinguistic Approach for Detecting Dementia Using Gated Convolutional Neural Network
We propose a non-invasive and cost-effective method to automatically detect dementia by utilizing solely speech audio data.
Initialization Using Perlin Noise for Training Networks with a Limited Amount of Data
Our main idea is to initialize the network parameters by solving an artificial noise classification problem, where the aim is to classify Perlin noise samples into their noise categories.
Pre-training without Natural Images
Is it possible to use convolutional neural networks pre-trained without any natural images to assist natural image understanding?
Can Vision Transformers Learn without Natural Images?
Moreover, although the ViT pre-trained without natural images produces some different visualizations from ImageNet pre-trained ViT, it can interpret natural image datasets to a large extent.
Replacing Labeled Real-image Datasets with Auto-generated Contours
In the present work, we show that the performance of formula-driven supervised learning (FDSL) can match or even exceed that of ImageNet-21k without the use of real images, human-, and self-supervision during the pre-training of Vision Transformers (ViTs).
PoF: Post-Training of Feature Extractor for Improving Generalization
We developed a training algorithm called PoF: Post-Training of Feature Extractor that updates the feature extractor part of an already-trained deep model to search a flatter minimum.
Fixed-Weight Difference Target Propagation
Learning of the feedforward and feedback networks is sufficient to make TP methods capable of training, but is having these layer-wise autoencoders a necessary condition for TP to work?
Visual Atoms: Pre-training Vision Transformers with Sinusoidal Waves
Unlike JFT-300M which is a static dataset, the quality of synthetic datasets will continue to improve, and the current work is a testament to this possibility.
Pre-training Vision Transformers with Very Limited Synthesized Images
Prior work on FDSL has shown that pre-training vision transformers on such synthetic datasets can yield competitive accuracy on a wide range of downstream tasks.
SegRCDB: Semantic Segmentation via Formula-Driven Supervised Learning
SegRCDB has a high potential to contribute to semantic segmentation pre-training and investigation by enabling the creation of large datasets without manual annotation.
CityRefer: Geography-aware 3D Visual Grounding Dataset on City-scale Point Cloud Data
To tackle this problem, we introduce the CityRefer dataset for city-level visual grounding.
