no code implementations • 9 Jan 2025 • Jun-Hak Yun, Seung-bin Kim, Seong-Whan Lee
Audio super-resolution is challenging owing to its ill-posed nature.
no code implementations • 9 Jan 2025 • Hanna Zubkova, Ji-Hoon Park, Seong-Whan Lee
Bearing in mind the limited parametric knowledge of Large Language Models (LLMs), retrieval-augmented generation (RAG) which supplies them with the relevant external knowledge has served as an approach to mitigate the issue of hallucinations to a certain extent.
1 code implementation • 9 Jan 2025 • Sun-Hyuk Choi, Hayoung Jo, Seong-Whan Lee
The Aligner removes noise from queries and aligns them to achieve query consistency.
Ranked #5 on
Referring Video Object Segmentation
on MeViS
Referring Video Object Segmentation
Semantic Segmentation
+1
no code implementations • 9 Jan 2025 • Ji-Ha Park, Seo-Hyun Lee, Soowon Kim, Seong-Whan Lee
Decoding text, speech, or images from human neural signals holds promising potential both as neuroprosthesis for patients and as innovative communication tools for general users.
no code implementations • 9 Jan 2025 • Jun-Hyeok Cha, Seung-bin Kim, Hyung-Seok Oh, Seong-Whan Lee
To address this, we introduce JELLY, a novel CSS framework that integrates emotion recognition and context reasoning for generating appropriate speech in conversation by fine-tuning a large language model (LLM) with multiple partial LoRA modules.
no code implementations • 18 Nov 2024 • Heon-Gyu Kwak, Gi-Hwan Shin, Yeon-Woo Choi, Dong-Hoon Lee, Yoo-In Jeon, Jun-Su Kang, Seong-Whan Lee
In this paper, we propose a conceptual framework for personalized brain-computer interface (BCI) applications, which can offer an enhanced user experience by customizing services to individual preferences and needs, based on endogenous electroencephalography (EEG) paradigms including motor imagery (MI), speech imagery (SI), and visual imagery.
no code implementations • 14 Nov 2024 • Ji-Ha Park, Seo-Hyun Lee, Soowon Kim, Seong-Whan Lee
Interpreting human neural signals to decode static speech intentions such as text or images and dynamic speech intentions such as audio or video is showing great potential as an innovative communication tool.
1 code implementation • 13 Nov 2024 • Yeong-Joon Ju, Ho-Joong Kim, Seong-Whan Lee
Existing multimodal retrieval systems often rely on disjointed models for image comprehension, such as object detectors and caption generators, leading to cumbersome implementations and training processes.
1 code implementation • 4 Nov 2024 • Deok-Hyeon Cho, Hyung-Seok Oh, Seung-bin Kim, Seong-Whan Lee
Emotional text-to-speech (TTS) technology has achieved significant progress in recent years; however, challenges remain owing to the inherent complexity of emotions and limitations of the available emotional speech datasets and models.
no code implementations • 29 Oct 2024 • Kang Yin, Hye-Bin Shin, Dan Li, Seong-Whan Lee
Multimodal learning has been a popular area of research, yet integrating electroencephalogram (EEG) data poses unique challenges due to its inherent variability and limited availability.
1 code implementation • 15 Aug 2024 • Sang-Hoon Lee, Ha-Yeong Choi, Seong-Whan Lee
This paper introduces PeriodWave-Turbo, a high-fidelity and high-efficient waveform generation model via adversarial flow matching optimization.
Ranked #1 on
Speech Synthesis
on LibriTTS
1 code implementation • 14 Aug 2024 • Sang-Hoon Lee, Ha-Yeong Choi, Seong-Whan Lee
Additionally, we utilize a multi-period estimator that avoids overlaps to capture different periodic features of waveform signals.
Ranked #4 on
Speech Synthesis
on LibriTTS
1 code implementation • 12 Jun 2024 • Deok-Hyeon Cho, Hyung-Seok Oh, Seung-bin Kim, Sang-Hoon Lee, Seong-Whan Lee
Despite rapid advances in the field of emotional text-to-speech (TTS), recent studies primarily focus on mimicking the average style of a particular emotion.
1 code implementation • CVPR 2024 • Ho-Joong Kim, Jung-Ho Hong, Heejo Kong, Seong-Whan Lee
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).
1 code implementation • 16 Feb 2024 • Ji-Hoon Park, Yeong-Joon Ju, Seong-Whan Lee
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.
no code implementations • 25 Jan 2024 • Vitaliy Kim, Gunho Jung, Seong-Whan Lee
AM-SORT is a novel extension of the SORT-series trackers that supersedes the Kalman Filter with the transformer architecture as a motion predictor.
no code implementations • 25 Jan 2024 • Byoungsung Lim, Seong-Whan Lee
Recent advances in implicit function-based approaches have shown promising results in 3D human reconstruction from a single RGB image.
no code implementations • 25 Jan 2024 • Hayoung Jo, Seong-Whan Lee
Moreover, the graph attention mechanism, commonly used to infer unknown graph structures, could constrain the diversity of source node representations.
no code implementations • 25 Jan 2024 • Suneung Kim, Woo-Jeoung Nam, Seong-Whan Lee
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.
no code implementations • 17 Jan 2024 • Seung-bin Kim, Sang-Hoon Lee, Seong-Whan Lee
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.
1 code implementation • 16 Jan 2024 • Hyung-Seok Oh, Sang-Hoon Lee, Deok-Hyeon Cho, Seong-Whan Lee
Emotional voice conversion (EVC) involves modifying various acoustic characteristics, such as pitch and spectral envelope, to match a desired emotional state while preserving the speaker's identity.
1 code implementation • 21 Dec 2023 • Jung-Ho Hong, Woo-Jeoung Nam, Kyu-Sung Jeon, Seong-Whan Lee
Revealing the transparency of Deep Neural Networks (DNNs) has been widely studied to describe the decision mechanisms of network inner structures.
no code implementations • 10 Dec 2023 • Seo-Hyun Lee, Young-Eun Lee, Soowon Kim, Byung-Kwan Ko, Jun-Young Kim, Seong-Whan Lee
Brain-to-speech technology represents a fusion of interdisciplinary applications encompassing fields of artificial intelligence, brain-computer interfaces, and speech synthesis.
no code implementations • 10 Dec 2023 • Hye-Bin Shin, Kang Yin, Seong-Whan Lee
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.
2 code implementations • 21 Nov 2023 • Sang-Hoon Lee, Ha-Yeong Choi, Seung-bin Kim, Seong-Whan Lee
Furthermore, we significantly improve the naturalness and speaker similarity of synthetic speech even in zero-shot speech synthesis scenarios.
no code implementations • 15 Nov 2023 • Gi-Hwan Shin, Young-Seok Kweon, Heon-Gyu Kwak, Ha-Na Jo, Seong-Whan Lee
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.
no code implementations • 15 Nov 2023 • Ha-Na Jo, Young-Seok Kweon, Gi-Hwan Shin, Heon-Gyu Kwak, Seong-Whan Lee
For analysis, we calculated the power spectral density (PSD) of EEG for each session and compared them in frequency, time, and five brain regions.
no code implementations • 14 Nov 2023 • Soowon Kim, Seo-Hyun Lee, Young-Eun Lee, Ji-Won Lee, Ji-Ha Park, Seong-Whan Lee
Interpreting EEG signals linked to spoken language presents a complex challenge, given the data's intricate temporal and spatial attributes, as well as the various noise factors.
no code implementations • 14 Nov 2023 • Ha-Na Jo, Young-Seok Kweon, Gi-Hwan Shin, Heon-Gyu Kwak, Seong-Whan Lee
The monaural beat is known that it can modulate brain and personal states.
no code implementations • 14 Nov 2023 • Young-Eun Lee, Seo-Hyun Lee, Soowon Kim, Jung-Sun Lee, Deok-Seon Kim, Seong-Whan Lee
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.
no code implementations • 14 Nov 2023 • Young-Seok Kweon, Gi-Hwan Shin, Heon-Gyu Kwak, Ha-Na Jo, Seong-Whan Lee
Polysomnography (PSG) is an indispensable diagnostic tool in sleep medicine, essential for identifying various sleep disorders.
no code implementations • 13 Nov 2023 • Byeong-Hoo Lee, Byoung-Hee Kwon, Seong-Whan Lee
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.
1 code implementation • 8 Nov 2023 • Ha-Yeong Choi, Sang-Hoon Lee, Seong-Whan Lee
Finally, by using the masked prior in diffusion models, our model can improve the speaker adaptation quality.
1 code implementation • 11 Oct 2023 • Yeong-Joon Ju, Ji-Hoon Park, Seong-Whan Lee
We validate the effectiveness of our framework by addressing false correlations and improving inferences for classes with the worst performance in real-world settings.
no code implementations • 28 Aug 2023 • Ji-Hoon Jeong, In-Gyu Lee, Sung-Kyung Kim, Tae-Eui Kam, Seong-Whan Lee, Euijong Lee
Childhood and adolescent obesity rates are a global concern because obesity is associated with chronic diseases and long-term health risks.
no code implementations • 3 Aug 2023 • Yun Kwan Kim, Minji Lee, Kunwook Jo, Hee Seok Song, Seong-Whan Lee
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.
1 code implementation • 31 Jul 2023 • Hyung-Seok Oh, Sang-Hoon Lee, Seong-Whan Lee
Expressive text-to-speech systems have undergone significant advancements owing to prosody modeling, but conventional methods can still be improved.
no code implementations • 30 Jul 2023 • Sang-Hoon Lee, Ha-Yeong Choi, Hyung-Seok Oh, Seong-Whan Lee
With a hierarchical adaptive structure, the model can adapt to a novel voice style and convert speech progressively.
1 code implementation • 26 Jul 2023 • Soowon Kim, Young-Eun Lee, Seo-Hyun Lee, Seong-Whan Lee
Decoding EEG signals for imagined speech is a challenging task due to the high-dimensional nature of the data and low signal-to-noise ratio.
no code implementations • 13 Jun 2023 • Ji-Sang Hwang, Sang-Hoon Lee, Seong-Whan Lee
Furthermore, we introduce a pause-based word encoder to model word-level prosody based on pause sequence.
no code implementations • 12 Jun 2023 • Ji-Sang Hwang, Sang-Hoon Lee, Seong-Whan Lee
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.
1 code implementation • 25 May 2023 • Ha-Yeong Choi, Sang-Hoon Lee, Seong-Whan Lee
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.
1 code implementation • 2 Jan 2023 • Young-Eun Lee, Seo-Hyun Lee, Sang-Ho Kim, Seong-Whan Lee
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)
+4
1 code implementation • 29 Nov 2022 • Kyung-Min Jin, Byoung-Sung Lim, Gun-Hee Lee, Tae-Kyung Kang, Seong-Whan Lee
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
no code implementations • 2 Nov 2022 • Geonuk Kim, Hong-Gyu Jung, Seong-Whan Lee
Although modern object detectors rely heavily on a significant amount of training data, humans can easily detect novel objects using a few training examples.
1 code implementation • 20 Jul 2022 • Kyung-Min Jin, Gun-Hee Lee, Seong-Whan Lee
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.
no code implementations • 20 Jul 2022 • Tae-Kyung Kang, Gun-Hee Lee, Seong-Whan Lee
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.
no code implementations • 17 Jun 2022 • Joo-Yeon Lee, Woo-Jeoung Nam, Seong-Whan Lee
Video Anomaly Detection(VAD) has been traditionally tackled in two main methodologies: the reconstruction-based approach and the prediction-based one.
no code implementations • 17 Jun 2022 • Harim Jung, Myeong-Seok Oh, Cheoljong Yang, Seong-Whan Lee
Most object detection frameworks use backbone architectures originally designed for image classification, conventionally with pre-trained parameters on ImageNet.
no code implementations • 17 Jun 2022 • Byeong-Hoo Lee, Jeong-Hyun Cho, Byoung-Hee Kwon, Seong-Whan Lee
From the results, we demonstrated that factorizing the EEG signal allows the model to extract rich and decisive features under sparse condition.
no code implementations • 23 May 2022 • Woo-Jeoung Nam, Seong-Whan Lee
With the remarkable success of deep neural networks, there is a growing interest in research aimed at providing clear interpretations of their decision-making processes.
no code implementations • 22 Apr 2022 • Sueyeon Kim, Woo-Jeoung Nam, Seong-Whan Lee
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.
no code implementations • 15 Apr 2022 • Serkan Musellim, Dong-Kyun Han, Ji-Hoon Jeong, Seong-Whan Lee
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.
no code implementations • 15 Apr 2022 • Keon-Woo Lee, Dae-Hyeok Lee, Sung-Jin Kim, Seong-Whan Lee
In this paper, we investigated the neural signals for two groups of native speakers with two tasks with different languages, English and Chinese.
no code implementations • 28 Mar 2022 • Young-Eun Kim, Woo-Jeoung Nam, Kyungseo Min, Seong-Whan Lee
Domain adaptation (DA) or domain generalization (DG) for face presentation attack detection (PAD) has attracted attention recently with its robustness against unseen attack scenarios.
2 code implementations • Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2022 • Yeong-Joon Ju, Gun-Hee Lee, Jung-Ho Hong, Seong-Whan Lee
In addition, the lack of high-quality paired data remains an obstacle for both methods.
no code implementations • 14 Dec 2021 • Ji-Seon Bang, Seong-Whan Lee
Furthermore, we classified EEG with the subject-independent manner to learn robust and generalized EEG features by avoiding subject dependency.
no code implementations • NeurIPS 2021 • Sang-Hoon Lee, Ji-Hoon Kim, Hyunseung Chung, Seong-Whan Lee
This insufficiency leads to the converted speech containing source speech style or losing source speech content.
no code implementations • 16 Aug 2021 • Ji-Hoon Kim, Sang-Hoon Lee, Ji-Hyun Lee, Hong-Gyu Jung, Seong-Whan Lee
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.
no code implementations • 19 Jul 2021 • Woo-Jeoung Nam, Seong-Whan Lee
As an intuitive assessment metric for explanations, we report the performance of intersection of Union between visual explanation and bounding box of lesions.
no code implementations • 19 Jul 2021 • Gun-Hee Lee, Han-Bin Ko, Seong-Whan Lee
Deep learning has played a major role in the interpretation of dermoscopic images for detecting skin defects and abnormalities.
no code implementations • 19 Jul 2021 • Myeong-Seok Oh, Yong-Ju Lee, Seong-Whan Lee
In this paper, we propose a deep homography alignment network to precisely match two aerial images by progressively estimating the various transformation parameters.
no code implementations • 15 Jul 2021 • Ji-Seon Bang, Seong-Whan Lee
In the classification model, CNN is responsible for spatial feature extraction and GRU is responsible for temporal feature extraction.
no code implementations • 15 Jul 2021 • Ha Young Jo, Seong-Whan Lee
Wafer map pattern classification is a typical way of quality assurance.
no code implementations • 15 Jul 2021 • Dae-Hyeok Lee, Sung-Jin Kim, Seong-Whan Lee
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.
no code implementations • 14 Jul 2021 • Suneung-Kim, Seong-Whan Lee
In this paper, we present a single video conferencing solution using gaze estimation in preparation for these problems.
no code implementations • 14 Jul 2021 • Young Eun Kim, Seong-Whan Lee
Many recent studies in FAS have approached this problem with domain generalization technique.
no code implementations • 25 Jun 2021 • Hyung-Ju Ahn, Dae-Hyeok Lee, Ji-Hoon Jeong, Seong-Whan Lee
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).
no code implementations • 8 Jun 2021 • Dae-Hyeok Lee, Dong-Kyun Han, Sung-Jin Kim, Ji-Hoon Jeong, Seong-Whan Lee
Communication between humans and a drone using electroencephalogram (EEG) signals is one of the most challenging issues in the BCI domain.
no code implementations • 5 Jun 2021 • Hyunseung Chung, Sang-Hoon Lee, Seong-Whan Lee
Experimental results also show the superiority of our proposed model compared to other state-of-the-art TTS models with internal and external aligners.
2 code implementations • 4 Jun 2021 • Ji-Hoon Kim, Sang-Hoon Lee, Ji-Hyun Lee, Seong-Whan Lee
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.
no code implementations • 31 May 2021 • Kyungseo Min, Gun-Hee Lee, Seong-Whan Lee
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.
no code implementations • 31 May 2021 • Harim Jung, Myeong-Seok Oh, Seong-Whan Lee
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
1 code implementation • 17 Mar 2021 • Ravikiran Mane, Effie Chew, Karen Chua, Kai Keng Ang, Neethu Robinson, A. P. Vinod, Seong-Whan Lee, Cuntai Guan
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.
no code implementations • 3 Mar 2021 • Young-Eun Lee, Seong-Whan Lee
Recently, practical brain-computer interface is actively carried out, especially, in an ambulatory environment.
no code implementations • 25 Jan 2021 • Hyun-Woo Kim, Hong-Gyu Jung, Seong-Whan Lee
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.
no code implementations • 22 Jan 2021 • Jung-Jun Kim, Dong-Gyu Lee, Jialin Wu, Hong-Gyu Jung, Seong-Whan Lee
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.
no code implementations • 22 Jan 2021 • Dong-Gyu Lee, Seong-Whan Lee
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
no code implementations • ICCV 2021 • Gun-Hee Lee, Seong-Whan Lee
Despite the recent success of 3D human reconstruction methods, recovering the accurate and smooth 3D human motion from video is still challenging.
no code implementations • 7 Dec 2020 • Woo-Jeoung Nam, Jaesik Choi, Seong-Whan Lee
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.
no code implementations • 19 Oct 2020 • Hyunseung Chung, Woo-Jeoung Nam, Seong-Whan Lee
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.
1 code implementation • 31 Aug 2020 • Young-min Song, Young-chul Yoon, Kwangjin Yoon, Moongu Jeon, Seong-Whan Lee, Witold Pedrycz
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.
no code implementations • 28 Aug 2020 • Jenifer Kalafatovich, Minji Lee, Seong-Whan Lee
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.
no code implementations • 28 Aug 2020 • Dong-Yeon Lee, Minji Lee, Seong-Whan Lee
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.
no code implementations • 28 Aug 2020 • Geonuk Kim, Hong-Gyu Jung, Seong-Whan Lee
If there are only a few training data and annotations, the object detectors easily overfit and fail to generalize.
no code implementations • 16 Aug 2020 • Hyun-Wook Yoon, Sang-Hoon Lee, Hyeong-Rae Noh, Seong-Whan Lee
In recent works, a flow-based neural vocoder has shown significant improvement in real-time speech generation task.
no code implementations • 5 Aug 2020 • Hong-Gyu Jung, Sin-Han Kang, Hee-Dong Kim, Dong-Ok Won, Seong-Whan Lee
The masking step aims to select an important feature from the input data to be classified as a target class.
no code implementations • 18 May 2020 • Young-Eun Lee, Minji Lee, Seong-Whan Lee
As a result, the reconstructed signals had important components such as N200 and P300 similar to ERP during standing.
no code implementations • 15 May 2020 • Byoung-Hee Kwon, Ji-Hoon Jeong, Jeong-Hyun Cho, Seong-Whan Lee
As a result, the averaged classification performance of the proposed architecture for 4 classes from 16 channels was 67. 50 % across all subjects.
no code implementations • 15 May 2020 • Gi-Hwan Shin, Minji Lee, Seong-Whan Lee
Seven participants performed two memory tasks (word-pairs and visuo-spatial) before and after the nap to assess the memory consolidation during unconsciousness.
no code implementations • 6 May 2020 • Kyung-Hwan Shim, Ji-Hoon Jeong, Seong-Whan Lee
In a real-time BCI environment, a calibration procedure is particularly necessary for each user and each session.
no code implementations • 4 May 2020 • Hyeong-Jin Kim, Minji Lee, Seong-Whan Lee
For five sleep stage classification, the classification performance 85. 6% and 91. 1% using the raw input data and the proposed input, respectively.
no code implementations • 4 May 2020 • Jenifer Kalafatovich, Minji Lee, Seong-Whan Lee
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.
no code implementations • 1 Apr 2020 • Jin-Woo Seo, Hong-Gyu Jung, Seong-Whan Lee
Few-shot learning aims to classify unseen classes with a few training examples.
no code implementations • 20 Mar 2020 • Hong-Gyu Jung, Seong-Whan Lee
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.
no code implementations • 17 Mar 2020 • Da-Hye Yoon, Nam-Gyu Cho, Seong-Whan Lee
Online temporal action localization from an untrimmed video stream is a challenging problem in computer vision.
no code implementations • 19 Feb 2020 • Ye-Ji Kim, Dong-Gyu Lee, Seong-Whan Lee
First-person interaction recognition is a challenging task because of unstable video conditions resulting from the camera wearer's movement.
2 code implementations • 4 Feb 2020 • Jae-Hyun Park, Woo-Jeoung Nam, Seong-Whan Lee
As a result, the training process of the deep network is regularized and the network becomes robust for the variance of aerial images.
no code implementations • 3 Feb 2020 • Ji-Hoon Jeong, Dae-Hyeok Lee, Hyung-Ju Ahn, Seong-Whan Lee
Hence, we could confirm the feasibility of the drone swarm control system based on EEG signals for performing high-level tasks.
1 code implementation • 1 Feb 2020 • Byeong-Hoo Lee, Ji-Hoon Jeong, Kyung-Hwan Shim, Seong-Whan Lee
A brain-computer interface (BCI) provides a direct communication pathway between user and external devices.
2 code implementations • 6 Jan 2020 • Yeongtae Hwang, Hyemin Cho, Hongsun Yang, Dong-Ok Won, Insoo Oh, Seong-Whan Lee
In addition, we proposed new policies (i. e., frequency warping, loudness and time length control) for more data variations.
no code implementations • 16 Dec 2019 • Paul Bertens, Seong-Whan Lee
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.
no code implementations • 27 Sep 2019 • Sin-Han Kang, Hong-Gyu Jung, Seong-Whan Lee
To tackle this issue, in this paper, we propose an explanation method that visualizes undesirable regions to classify an image as a target class.
1 code implementation • 1 Apr 2019 • Woo-Jeoung Nam, Shir Gur, Jaesik Choi, Lior Wolf, Seong-Whan Lee
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.
1 code implementation • ICML 2018 • Kyowoon Lee, Sol-A Kim, Jaesik Choi, Seong-Whan Lee
Many real-world applications of reinforcement learning require an agent to select optimal actions from continuous spaces.
no code implementations • CVPR 2014 • Roozbeh Mottaghi, Xianjie Chen, Xiaobai Liu, Nam-Gyu Cho, Seong-Whan Lee, Sanja Fidler, Raquel Urtasun, Alan Yuille
In this paper we study the role of context in existing state-of-the-art detection and segmentation approaches.
no code implementations • IEEE Transactions on Pattern Analysis and Machine Intelligence 2001 • Seong-Whan Lee, Senior Member, IEEE, and Dae-Seok Ryu
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.