Minki Jeong

Minki Jeong

Auto-generated profile, based on publicly available information

Minki Jeong

School of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), Daejeon, South Korea

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
23 November 2022 in IEEE Sensors Journal
Verified
Journal Article
Closed access
IKInyong Koo
Inyong Koo
YPYeonju Park
Yeonju Park
MJMinki Jeong
Minki Jeong
CKChangick Kim
Changick Kim
Recently, the widespread use of smart devices has invoked more interest in sensor-based applications. Human activity recognition (HAR) with body-worn sensors is an underlying task that aims to recognize a person’s physical activity from on-body sensor readings. In this paper, we address the HAR problem that utilizes accelerometers and gyroscopes. While deep learning-based feature extraction methods are advancing, recent HAR systems with multimodal sensors mostly use data-level fusion, aggregating different sensor signals into one multi-channel input. However, they neglect the fact that different sensors capture different physical properties and produce distinct patterns. In this paper, we propose a two-stream convolutional neural network model that processes the accelerometer and gyroscope signals separately. The modality-specific features are fused in feature-level and jointly used for the recognition task. Furthermore, we introduce a self-supervised learning task that pairs the accelerometer and the gyroscope embeddings acquired from the same activity instance. This auxiliary objective allows the feature extractors of our model to communicate during training and exploit complementary information, achieving better representations for HAR. We name our end-to-end multimodal HAR system the Contrastive Accelerometer-Gyroscope Embedding model (CAGE). CAGE outperforms preceding HAR models in four publicly available benchmarks. Code is available at github.com/quotation2520/CAGE4HAR.

1 October 2020
Verified
Conference Paper
Closed access
HPHyoungseob Park
Hyoungseob Park
MJMinki Jeong
Minki Jeong
YKYoungeun Kim
Youngeun Kim
CKChangick Kim
Changick Kim
Filtering noisy labels is crucial for robust training of deep neural networks. To train networks with noisy labels, sampling methods have been introduced, which sample the reliable instances to update networks using only sampled data. Since they rarely employ the non-sampled data for training, these methods have a fundamental limitation that they reduce the amount of the training data. To alleviate this problem, our approach aims to fully utilize the whole dataset by leveraging the information of the sampled data. To this end, we propose a novel graph-based learning framework that enables networks to propagate the label information of the sampled data to adjacent data, whether they are sampled or not. Also, we propose a novel self-training strategy to utilize the non-sampled data without labels and to regularize the network update using the information of the sampled data. Our method outperforms state-of-the-art sampling methods.