Search Results for author:
Found 94 papers, 19 papers with code
Parameter-free Geometric Document Layout Analysis
Based on the proposed periodicity measure, multiscale analysis, and confirmation procedure, we could develop a robust method for geometric document layout analysis independent of character font sizes, text line spacing, and document layout structures.
The Role of Context for Object Detection and Semantic Segmentation in the Wild
In this paper we study the role of context in existing state-of-the-art detection and segmentation approaches.
Deep Reinforcement Learning in Continuous Action Spaces: a Case Study in the Game of Simulated Curling
Many real-world applications of reinforcement learning require an agent to select optimal actions from continuous spaces.
Relative Attributing Propagation: Interpreting the Comparative Contributions of Individual Units in Deep Neural Networks
As Deep Neural Networks (DNNs) have demonstrated superhuman performance in a variety of fields, there is an increasing interest in understanding the complex internal mechanisms of DNNs.
Interpreting Undesirable Pixels for Image Classification on Black-Box Models
To tackle this issue, in this paper, we propose an explanation method that visualizes undesirable regions to classify an image as a target class.
Network of Evolvable Neural Units: Evolving to Learn at a Synaptic Level
Here a model is proposed that bridges Neuroscience, Machine Learning and Evolutionary Algorithms to evolve individual soma and synaptic compartment models of neurons in a scalable manner.
Mel-spectrogram augmentation for sequence to sequence voice conversion
In addition, we proposed new policies (i. e., frequency warping, loudness and time length control) for more data variations.
Classification of High-Dimensional Motor Imagery Tasks based on An End-to-end role assigned convolutional neural network
A brain-computer interface (BCI) provides a direct communication pathway between user and external devices.
Towards Brain-Computer Interfaces for Drone Swarm Control
Hence, we could confirm the feasibility of the drone swarm control system based on EEG signals for performing high-level tasks.
A Two-Stream Symmetric Network with Bidirectional Ensemble for Aerial Image Matching
As a result, the training process of the deep network is regularized and the network becomes robust for the variance of aerial images.
Three-Stream Fusion Network for First-Person Interaction Recognition
First-person interaction recognition is a challenging task because of unstable video conditions resulting from the camera wearer's movement.
A Novel Online Action Detection Framework from Untrimmed Video Streams
Online temporal action localization from an untrimmed video stream is a challenging problem in computer vision.
Few-Shot Learning with Geometric Constraints
We assume a network trained for base categories with a large number of training examples, and we aim to add novel categories to it that have only a few, e. g., one or five, training examples.
Self-Augmentation: Generalizing Deep Networks to Unseen Classes for Few-Shot Learning
Few-shot learning aims to classify unseen classes with a few training examples.
Prediction of Memory Retrieval Performance Using Ear-EEG Signals
These results showed that it is possible to predict performance of a memory task using ear-EEG signals and it could be used for predicting memory retrieval in a practical brain-computer interface.
End-to-End Automatic Sleep Stage Classification Using Spectral-Temporal Sleep Features
For five sleep stage classification, the classification performance 85. 6% and 91. 1% using the raw input data and the proposed input, respectively.
Gradual Relation Network: Decoding Intuitive Upper Extremity Movement Imaginations Based on Few-Shot EEG Learning
In a real-time BCI environment, a calibration procedure is particularly necessary for each user and each session.
Assessment of Unconsciousness for Memory Consolidation Using EEG Signals
Seven participants performed two memory tasks (word-pairs and visuo-spatial) before and after the nap to assess the memory consolidation during unconsciousness.
Decoding of Intuitive Visual Motion Imagery Using Convolutional Neural Network under 3D-BCI Training Environment
As a result, the averaged classification performance of the proposed architecture for 4 classes from 16 channels was 67. 50 % across all subjects.
Reconstructing ERP Signals Using Generative Adversarial Networks for Mobile Brain-Machine Interface
As a result, the reconstructed signals had important components such as N200 and P300 similar to ERP during standing.
Counterfactual Explanation Based on Gradual Construction for Deep Networks
The masking step aims to select an important feature from the input data to be classified as a target class.
Audio Dequantization for High Fidelity Audio Generation in Flow-based Neural Vocoder
In recent works, a flow-based neural vocoder has shown significant improvement in real-time speech generation task.
Few-Shot Object Detection via Knowledge Transfer
If there are only a few training data and annotations, the object detectors easily overfit and fail to generalize.
Decoding Visual Recognition of Objects from EEG Signals based on Attention-Driven Convolutional Neural Network
Our findings showed that EEG signals are possible to differentiate when subjects are presented with visual stimulus of different semantic categories and at an exemplar-level with a high classification accuracy; this demonstrates its viability to be applied it in a real-world BMI.
Classification of Imagined Speech Using Siamese Neural Network
The proposed framework would help to increase the classification performance of imagined speech for a small amount of data and implement an intuitive communication system.
Online Multi-Object Tracking and Segmentation with GMPHD Filter and Mask-based Affinity Fusion
One affinity, for position and motion, is computed by using the GMPHD filter, and the other affinity, for appearance is computed by using the responses from a single object tracker such as a kernalized correlation filter.
Rotation Invariant Aerial Image Retrieval with Group Convolutional Metric Learning
In this work, we introduce a novel method for retrieving aerial images by merging group convolution with attention mechanism and metric learning, resulting in robustness to rotational variations.
Interpreting Deep Neural Networks with Relative Sectional Propagation by Analyzing Comparative Gradients and Hostile Activations
As a result, it is possible to assign the bi-polar relevance scores of the target (positive) and hostile (negative) attributions while maintaining each attribution aligned with the importance.
Uncertainty-Aware Human Mesh Recovery From Video by Learning Part-Based 3D Dynamics
Despite the recent success of 3D human reconstruction methods, recovering the accurate and smooth 3D human motion from video is still challenging.
Human Interaction Recognition Framework based on Interacting Body Part Attention
In this paper, we propose a novel framework that simultaneously considers both implicit and explicit representations of human interactions by fusing information of local image where the interaction actively occurred, primitive motion with the posture of individual subject's body parts, and the co-occurrence of overall appearance change.
Activity Recognition In Videos
Human Activity Recognition
+1
Visual Question Answering based on Local-Scene-Aware Referring Expression Generation
We quantitatively and qualitatively evaluated the proposed method on the VQA v2 dataset and compared it with state-of-the-art methods in terms of answer prediction.
Weakly Supervised Thoracic Disease Localization via Disease Masks
To enable a deep learning-based system to be used in the medical domain as a computer-aided diagnosis system, it is essential to not only classify diseases but also present the locations of the diseases.
Decoding Event-related Potential from Ear-EEG Signals based on Ensemble Convolutional Neural Networks in Ambulatory Environment
Recently, practical brain-computer interface is actively carried out, especially, in an ambulatory environment.
FBCNet: A Multi-view Convolutional Neural Network for Brain-Computer Interface
With this design, we compare FBCNet with state-of-the-art (SOTA) BCI algorithm on four MI datasets: The BCI competition IV dataset 2a (BCIC-IV-2a), the OpenBMI dataset, and two large datasets from chronic stroke patients.
Learning Free-Form Deformation for 3D Face Reconstruction from In-The-Wild Images
As FFD is based on mathematically defined basis functions, it has no limitation in representation power.
Ranked #3 on
3D Face Reconstruction
on AFLW2000-3D
ACNet: Mask-Aware Attention with Dynamic Context Enhancement for Robust Acne Detection
To address these problems, we propose an acne detection network which consists of three components, specifically: Composite Feature Refinement, Dynamic Context Enhancement, and Mask-Aware Multi-Attention.
Fre-GAN: Adversarial Frequency-consistent Audio Synthesis
Although recent works on neural vocoder have improved the quality of synthesized audio, there still exists a gap between generated and ground-truth audio in frequency space.
Reinforce-Aligner: Reinforcement Alignment Search for Robust End-to-End Text-to-Speech
Experimental results also show the superiority of our proposed model compared to other state-of-the-art TTS models with internal and external aligners.
Subject-Independent Brain-Computer Interface for Decoding High-Level Visual Imagery Tasks
Communication between humans and a drone using electroencephalogram (EEG) signals is one of the most challenging issues in the BCI domain.
Towards Natural Brain-Machine Interaction using Endogenous Potentials based on Deep Neural Networks
Moreover, our proposed TINN showed the highest accuracy of 0. 93 compared to the previous methods for classifying three different types of mental imagery tasks (MI, VI, and SI).
Detection of Abnormal Behavior with Self-Supervised Gaze Estimation
In this paper, we present a single video conferencing solution using gaze estimation in preparation for these problems.
Domain Generalization with Pseudo-Domain Label for Face Anti-Spoofing
Many recent studies in FAS have approached this problem with domain generalization technique.
One-Class Classification for Wafer Map using Adversarial Autoencoder with DSVDD Prior
Wafer map pattern classification is a typical way of quality assurance.
DAL: Feature Learning from Overt Speech to Decode Imagined Speech-based EEG Signals with Convolutional Autoencoder
In addition, when comparing the performance between w/o and w/ EEG features of overt speech, there was a performance improvement of 7. 42% when including EEG features of overt speech.
Motor Imagery Classification based on CNN-GRU Network with Spatio-Temporal Feature Representation
In the classification model, CNN is responsible for spatial feature extraction and GRU is responsible for temporal feature extraction.
Joint Dermatological Lesion Classification and Confidence Modeling with Uncertainty Estimation
Deep learning has played a major role in the interpretation of dermoscopic images for detecting skin defects and abnormalities.
Precise Aerial Image Matching based on Deep Homography Estimation
In this paper, we propose a deep homography alignment network to precisely match two aerial images by progressively estimating the various transformation parameters.
Improving Interpretability of Deep Neural Networks in Medical Diagnosis by Investigating the Individual Units
As an intuitive assessment metric for explanations, we report the performance of intersection of Union between visual explanation and bounding box of lesions.
GC-TTS: Few-shot Speaker Adaptation with Geometric Constraints
While numerous attempts have been made to the few-shot speaker adaptation system, there is still a gap in terms of speaker similarity to the target speaker depending on the amount of data.
VoiceMixer: Adversarial Voice Style Mixup
This insufficiency leads to the converted speech containing source speech style or losing source speech content.
Interpretable Convolutional Neural Networks for Subject-Independent Motor Imagery Classification
Furthermore, we classified EEG with the subject-independent manner to learn robust and generalized EEG features by avoiding subject dependency.
Complete Face Recovery GAN: Unsupervised Joint Face Rotation and De-Occlusion From a Single-View Image
In addition, the lack of high-quality paired data remains an obstacle for both methods.
Style-Guided Domain Adaptation for Face Presentation Attack Detection
Domain adaptation (DA) or domain generalization (DG) for face presentation attack detection (PAD) has attracted attention recently with its robustness against unseen attack scenarios.
Prototype-based Domain Generalization Framework for Subject-Independent Brain-Computer Interfaces
For this purpose, in this paper, we proposed a framework that employs the open-set recognition technique as an auxiliary task to learn subject-specific style features from the source dataset while helping the shared feature extractor with mapping the features of the unseen target dataset as a new unseen domain.
Decoding Neural Correlation of Language-Specific Imagined Speech using EEG Signals
In this paper, we investigated the neural signals for two groups of native speakers with two tasks with different languages, English and Chinese.
Few-Shot Object Detection with Proposal Balance Refinement
Few-shot object detection has gained significant attention in recent years as it has the potential to greatly reduce the reliance on large amounts of manually annotated bounding boxes.
Gradient Hedging for Intensively Exploring Salient Interpretation beyond Neuron Activation
Hedging is a strategy for reducing the potential risks in various types of investments by adopting an opposite position in a related asset.
Neural Architecture Adaptation for Object Detection by Searching Channel Dimensions and Mapping Pre-trained Parameters
Most object detection frameworks use backbone architectures originally designed for image classification, conventionally with pre-trained parameters on ImageNet.
Factorization Approach for Sparse Spatio-Temporal Brain-Computer Interface
From the results, we demonstrated that factorizing the EEG signal allows the model to extract rich and decisive features under sparse condition.
Multi-Contextual Predictions with Vision Transformer for Video Anomaly Detection
Video Anomaly Detection(VAD) has been traditionally tackled in two main methodologies: the reconstruction-based approach and the prediction-based one.
OTPose: Occlusion-Aware Transformer for Pose Estimation in Sparsely-Labeled Videos
We achieve state-of-the-art pose estimation results for PoseTrack2017 and PoseTrack2018 datasets and demonstrate the robustness of our approach to occlusion and motion blur in sparsely annotated video data.
HTNet: Anchor-free Temporal Action Localization with Hierarchical Transformers
Temporal action localization (TAL) is a task of identifying a set of actions in a video, which involves localizing the start and end frames and classifying each action instance.
Spatial Reasoning for Few-Shot Object Detection
Although modern object detectors rely heavily on a significant amount of training data, humans can easily detect novel objects using a few training examples.
Kinematic-aware Hierarchical Attention Network for Human Pose Estimation in Videos
Previous video-based human pose estimation methods have shown promising results by leveraging aggregated features of consecutive frames.
Ranked #1 on
Pose Estimation
on J-HMDB
Towards Voice Reconstruction from EEG during Imagined Speech
Translating imagined speech from human brain activity into voice is a challenging and absorbing research issue that can provide new means of human communication via brain signals.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
DDDM-VC: Decoupled Denoising Diffusion Models with Disentangled Representation and Prior Mixup for Verified Robust Voice Conversion
To address the above problem, this paper presents decoupled denoising diffusion models (DDDMs) with disentangled representations, which can control the style for each attribute in generative models.
HiddenSinger: High-Quality Singing Voice Synthesis via Neural Audio Codec and Latent Diffusion Models
To alleviate the challenges posed by model complexity in singing voice synthesis, we propose HiddenSinger, a high-quality singing voice synthesis system using a neural audio codec and latent diffusion models.
PauseSpeech: Natural Speech Synthesis via Pre-trained Language Model and Pause-based Prosody Modeling
Furthermore, we introduce a pause-based word encoder to model word-level prosody based on pause sequence.
HierVST: Hierarchical Adaptive Zero-shot Voice Style Transfer
With a hierarchical adaptive structure, the model can adapt to a novel voice style and convert speech progressively.
DiffProsody: Diffusion-based Latent Prosody Generation for Expressive Speech Synthesis with Prosody Conditional Adversarial Training
Expressive text-to-speech systems have undergone significant advancements owing to prosody modeling, but conventional methods can still be improved.
Local-Global Temporal Fusion Network with an Attention Mechanism for Multiple and Multiclass Arrhythmia Classification
To check the generalization ability of the proposed method, an AFDB-trained model was tested on the MITDB, and superior performance was attained compared with that of a state-of-the-art model.
DeepHealthNet: Adolescent Obesity Prediction System Based on a Deep Learning Framework
Childhood and adolescent obesity rates are a global concern because obesity is associated with chronic diseases and long-term health risks.
NeuroInspect: Interpretable Neuron-based Debugging Framework through Class-conditional Visualizations
We validate the effectiveness of our framework by addressing false correlations and improving inferences for classes with the worst performance in real-world settings.
Diff-HierVC: Diffusion-based Hierarchical Voice Conversion with Robust Pitch Generation and Masked Prior for Zero-shot Speaker Adaptation
Finally, by using the masked prior in diffusion models, our model can improve the speaker adaptation quality.
Sample Dominance Aware Framework via Non-Parametric Estimation for Spontaneous Brain-Computer Interface
In this study, we introduce the concept of sample dominance as a measure of EEG signal inconsistency and propose a method to modulate its effect on network training.
Relationship Between Mood, Sleepiness, and EEG Functional Connectivity by 40 Hz Monaural Beats
The monaural beat is known that it can modulate brain and personal states.
Multi-Signal Reconstruction Using Masked Autoencoder From EEG During Polysomnography
Polysomnography (PSG) is an indispensable diagnostic tool in sleep medicine, essential for identifying various sleep disorders.
Enhanced Generative Adversarial Networks for Unseen Word Generation from EEG Signals
Recent advances in brain-computer interface (BCI) technology, particularly based on generative adversarial networks (GAN), have shown great promise for improving decoding performance for BCI.
Neurophysiological Response Based on Auditory Sense for Brain Modulation Using Monaural Beat
For analysis, we calculated the power spectral density (PSD) of EEG for each session and compared them in frequency, time, and five brain regions.
Impact of Nap on Performance in Different Working Memory Tasks Using EEG
Electroencephalography (EEG) has been widely used to study the relationship between naps and working memory, yet the effects of naps on distinct working memory tasks remain unclear.
HierSpeech++: Bridging the Gap between Semantic and Acoustic Representation of Speech by Hierarchical Variational Inference for Zero-shot Speech Synthesis
Furthermore, we significantly improve the naturalness and speaker similarity of synthetic speech even in zero-shot speech synthesis scenarios.
Sparse Multitask Learning for Efficient Neural Representation of Motor Imagery and Execution
In the quest for efficient neural network models for neural data interpretation and user intent classification in brain-computer interfaces (BCIs), learning meaningful sparse representations of the underlying neural subspaces is crucial.
Neural Speech Embeddings for Speech Synthesis Based on Deep Generative Networks
Brain-to-speech technology represents a fusion of interdisciplinary applications encompassing fields of artificial intelligence, brain-computer interfaces, and speech synthesis.
Towards Better Visualizing the Decision Basis of Networks via Unfold and Conquer Attribution Guidance
Revealing the transparency of Deep Neural Networks (DNNs) has been widely studied to describe the decision mechanisms of network inner structures.
DurFlex-EVC: Duration-Flexible Emotional Voice Conversion with Parallel Generation
Emotional voice conversion (EVC) seeks to modify the emotional tone of a speaker's voice while preserving the original linguistic content and the speaker's unique vocal characteristics.
TranSentence: Speech-to-speech Translation via Language-agnostic Sentence-level Speech Encoding without Language-parallel Data
With this method, despite training exclusively on the target language's monolingual data, we can generate target language speech in the inference stage using language-agnostic speech embedding from the source language speech.
AM-SORT: Adaptable Motion Predictor with Historical Trajectory Embedding for Multi-Object Tracking
AM-SORT is a novel extension of the SORT-series trackers that supersedes the Kalman Filter with the transformer architecture as a motion predictor.
TIFu: Tri-directional Implicit Function for High-Fidelity 3D Character Reconstruction
Recent advances in implicit function-based approaches have shown promising results in 3D human reconstruction from a single RGB image.
Edge Conditional Node Update Graph Neural Network for Multi-variate Time Series Anomaly Detection
Moreover, the graph attention mechanism, commonly used to infer unknown graph structures, could constrain the diversity of source node representations.
Appearance Debiased Gaze Estimation via Stochastic Subject-Wise Adversarial Learning
In this paper, we address these challenges and propose a novel framework: Stochastic subject-wise Adversarial gaZE learning (SAZE), which trains a network to generalize the appearance of subjects.
Explaining generative diffusion models via visual analysis for interpretable decision-making process
To address this issue, we propose the three research questions to interpret the diffusion process from the perspective of the visual concepts generated by the model and the region where the model attends in each time step.
TE-TAD: Towards Full End-to-End Temporal Action Detection via Time-Aligned Coordinate Expression
In this paper, we investigate that the normalized coordinate expression is a key factor as reliance on hand-crafted components in query-based detectors for temporal action detection (TAD).
