Jaehun Kim

Jaehun Kim

Auto-generated profile, based on publicly available information

Jaehun Kim

Department of Intelligent Systems Faculty of Electrical Engineering Mathematics and Computer Science Multimedia Computing Group Delft University of Technology

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

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

Representative Publications

View All Publications
2 March 2020 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
HAHyemin Ahn
Hyemin Ahn
JKJaehun Kim
Jaehun Kim
KKKihyun Kim
Kihyun Kim
SOSonghwai Oh
Songhwai Oh

4 March 2019 in Neural Computing and Applications
Verified
Journal Article
Open access
PDF file
JKJaehun Kim
Jaehun Kim
JUJulián Urbano
Julián Urbano
CLCynthia C. S. Liem
Cynthia C. S. Liem
AHAlan Hanjalic
Alan Hanjalic
Inspired by the success of deploying deep learning in the fields of Computer Vision and Natural Language Processing, this learning paradigm has also found its way into the field of Music Information Retrieval. In order to benefit from deep learning in an effective, but also efficient manner, deep transfer learning has become a common approach. In this approach, it is possible to reuse the output of a pre-trained neural network as the basis for a new learning task. The underlying hypothesis is that if the initial and new learning tasks show commonalities and are applied to the same type of input data (e.g., music audio), the generated deep representation of the data is also informative for the new task. Since, however, most of the networks used to generate deep representations are trained using a single initial learning source, their representation is unlikely to be informative for all possible future tasks. In this paper, we present the results of our investigation of what are the most important factors to generate deep representations for the data and learning tasks in the music domain. We conducted this investigation via an extensive empirical study that involves multiple learning sources, as well as multiple deep learning architectures with varying levels of information sharing between sources, in order to learn music representations. We then validate these representations considering multiple target datasets for evaluation. The results of our experiments yield several insights into how to approach the design of methods for learning widely deployable deep data representations in the music domain.

8 November 2019 in Frontiers in Applied Mathematics and Statistics
Verified
Journal Article
Open access
JKJaehun Kim
Jaehun Kim
JUJulián Urbano
Julián Urbano
CLCynthia C. S. Liem
Cynthia C. S. Liem
AHAlan Hanjalic
Alan Hanjalic
Deep neural networks have frequently been used to directly learn representations useful for a given task from raw input data. In terms of overall performance metrics, machine learning solutions employing deep representations frequently have been reported to greatly outperform those using hand-crafted feature representations. At the same time, they may pick up on aspects that are predominant in the data, yet not actually meaningful or interpretable. In this paper, we therefore propose a systematic way to test the trustworthiness of deep music representations, considering musical semantics. The underlying assumption is that in case a deep representation is to be trusted, distance consistency between known related points should be maintained both in the input audio space and corresponding latent deep space. We generate known related points through semantically meaningful transformations, both considering imperceptible and graver transformations. Then, we examine within- and between-space distance consistencies, both considering audio space and latent embedded space, the latter either being a result of a conventional feature extractor or a deep encoder. We illustrate how our method, as a complement to task-specific performance, provides interpretable insight into what a network may have captured from training data signals.

11 November 2019 in arXiv
Verified
Preprint
Open access
PDF file
HAHyemin Ahn
Hyemin Ahn
JKJaehun Kim
Jaehun Kim
KKKihyun Kim
Kihyun Kim
SOSonghwai Oh
Songhwai Oh
This paper proposes a framework which is able to generate a sequence of three-dimensional human dance poses for a given music. The proposed framework consists of three components: a music feature encoder, a pose generator, and a music genre classifier. We focus on integrating these components for generating a realistic 3D human dancing move from music, which can be applied to artificial agents and humanoid robots. The trained dance pose generator, which is a generative autoregressive model, is able to synthesize a dance sequence longer than 5,000 pose frames. Experimental results of generated dance sequences from various songs show how the proposed method generates human-like dancing move to a given music. In addition, a generated 3D dance sequence is applied to a humanoid robot, showing that the proposed framework can make a robot to dance just by listening to music.

12 February 2019 in arXiv
Verified
Preprint
Open access
PDF file
JKJaehun Kim
Jaehun Kim
JUJulián Urbano
Julián Urbano
CLCynthia C. S. Liem
Cynthia C. S. Liem
AHAlan Hanjalic
Alan Hanjalic
Inspired by the success of deploying deep learning in the fields of Computer Vision and Natural Language Processing, this learning paradigm has also found its way into the field of Music Information Retrieval. In order to benefit from deep learning in an effective, but also efficient manner, deep transfer learning has become a common approach. In this approach, it is possible to reuse the output of a pre-trained neural network as the basis for a new learning task. The underlying hypothesis is that if the initial and new learning tasks show commonalities and are applied to the same type of input data (e.g. music audio), the generated deep representation of the data is also informative for the new task. Since, however, most of the networks used to generate deep representations are trained using a single initial learning source, their representation is unlikely to be informative for all possible future tasks. In this paper, we present the results of our investigation of what are the most important factors to generate deep representations for the data and learning tasks in the music domain. We conducted this investigation via an extensive empirical study that involves multiple learning sources, as well as multiple deep learning architectures with varying levels of information sharing between sources, in order to learn music representations. We then validate these representations considering multiple target datasets for evaluation. The results of our experiments yield several insights on how to approach the design of methods for learning widely deployable deep data representations in the music domain.

23 October 2023 in OSF Preprints
Verified
Preprint
Open access
ADAndrew M. Demetriou
Andrew M. Demetriou
JKJaehun Kim
Jaehun Kim
SMSandy Manolios
Sandy Manolios
CLCynthia C. S. Liem
Cynthia C. S. Liem
This work describes a validated procedure for collecting reference data to estimate personal values from song lyrics. The undertaken work describes our method for sampling songs for lyric annotation, the specific wording and response format of the annotation tool, and estimation of necessary number of annotations per song. We describe two waves of data collection with over 500 respondents each, the first as a method to estimate the necessary number of ratings using 20 songs, and the second to examine the structure of annotations on 360 songs. We show promising similarity in the structure of annotations when compared with the theoretical structure of personal values.