Junsik Kim

Dr. Junsik Kim

orcid

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

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

Representative Publications

View All Publications
8 November 2019 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
ASArda Senocak
Arda Senocak
TOTae-Hyun Oh
Tae-Hyun Oh
JKJunsik Kim
Junsik Kim
MYMing Yang
Ming Yang
In So KweonIn So Kweon
In So Kweon
Visual events are usually accompanied by sounds in our daily lives. However, can the machines learn to correlate the visual scene and sound, as well as localize the sound source only by observing them like humans? To investigate its empirical learnability, in this work we first present a novel unsupervised algorithm to address the problem of localizing sound sources in visual scenes. In order to achieve this goal, a two-stream network structure which handles each modality, with attention mechanism is developed for sound source localization. The network naturally reveals the localized response in the scene without human annotation. In addition, a new sound source dataset is developed for performance evaluation. Nevertheless, our empirical evaluation shows that the unsupervised method generates false conclusions in some cases. Thereby, we show that this false conclusion cannot be fixed without human prior knowledge due to the well-known correlation and causality mismatch misconception. We show that the false conclusion can be effectively corrected even with a small amount of supervision, i.e., semi-supervised setup. We present the versatility of the learned audio and visual embeddings on the cross-modal content alignment and we incorporate this proposed algorithm into sound saliency based automatic camera view panning in 360 degree videos.

30 January 2018 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
KJKyungdon Joo
Kyungdon Joo
TOTae-Hyun Oh
Tae-Hyun Oh
JKJunsik Kim
Junsik Kim
In So KweonIn So Kweon
In So Kweon
Most man-made environments, such as urban and indoor scenes, consist of a set of parallel and orthogonal planar structures. These structures are approximated by the Manhattan world assumption, of which notion can be represented as a Manhattan Frame (MF). Given a set of inputs such as surface normals or vanishing points, we pose an MF estimation problem as a consensus set maximization that maximizes the number of inliers over the rotation search space. Conventionally this problem can be solved by a branch-and-bound framework which mathematically guarantees global optimality. However, the computational time of the conventional branch-and-bound algorithms is rather far from real-time. In this paper, we propose a novel bound computation method on an efficient measurement domain for MF estimation, i.e., the extended Gaussian image (EGI). By relaxing the original problem, we can compute the bound with a constant complexity, while preserving global optimality. Furthermore, we quantitatively and qualitatively demonstrate the performance of the proposed method for various synthetic and real-world data. We also show the versatility of our approach through three different applications: extension to multiple MF estimation, 3D rotation based video stabilization and vanishing point estimation (line clustering).


9 May 2023 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
MKMinkyung Kim
Minkyung Kim
JYJongmin Yu
Jongmin Yu
JKJunsik Kim
Junsik Kim
TOTae-Hyun Oh
Tae-Hyun Oh
JCJun Kyun Choi
Jun Kyun Choi
Most deep anomaly detection models are based on learning normality from datasets due to the difficulty of defining abnormality by its diverse and inconsistent nature. Therefore, it has been a common practice to learn normality under the assumption that anomalous data are absent in a training dataset, which we call normality assumption. However, in practice, the normality assumption is often violated due to the nature of real data distributions that includes anomalous tails, i.e., a contaminated dataset. Thereby, the gap between the assumption and actual training data affects detrimentally in learning of an anomaly detection model. In this work, we propose a learning framework to reduce this gap and achieve better normality representation. Our key idea is to identify sample-wise normality and utilize it as an importance weight, which is updated iteratively during the training. Our framework is designed to be model-agnostic and hyperparameter insensitive so that it applies to a wide range of existing methods without careful parameter tuning. We apply our framework to three different representative approaches of deep anomaly detection that are classified into one-class classification-, probabilistic model-, and reconstruction-based approaches. In addition, we address the importance of a termination condition for iterative methods and propose a termination criterion inspired by the anomaly detection objective. We validate that our framework improves the robustness of the anomaly detection models under different levels of contamination ratios on five anomaly detection benchmark datasets and two image datasets. On various contaminated datasets, our framework improves the performance of three representative anomaly detection methods, measured by area under the ROC curve.

20 December 2022 in Pattern Recognition Letters
Verified
Journal Article
Closed access
MKMinkyung Kim
Minkyung Kim
JKJunsik Kim
Junsik Kim
JYJongmin Yu
Jongmin Yu
JCJun Kyun Choi
Jun Kyun Choi

4 July 2023 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
JYJongmin Yu
Jongmin Yu
HOHyeontaek Oh
Hyeontaek Oh
MKMinkyung Kim
Minkyung Kim
JKJunsik Kim
Junsik Kim
Reidentification (Re-id) of vehicles in a multicamera system is an essential process for traffic control automation. Previously, there have been efforts to reidentify vehicles based on shots of images with identity (id) labels, where the model training relies on the quality and quantity of the labels. However, labeling vehicle ids is a labor-intensive procedure. Instead of relying on expensive labels, we propose to exploit camera and tracklet ids that are automatically obtainable during a Re-id dataset construction. In this article, we present weakly supervised contrastive learning (WSCL) and domain adaptation (DA) techniques using camera and tracklet ids for unsupervised vehicle Re-id. We define each camera id as a subdomain and tracklet id as a label of a vehicle within each subdomain, i.e., weak label in the Re-id scenario. Within each subdomain, contrastive learning using tracklet ids is applied to learn a representation of vehicles. Then, DA is performed to match vehicle ids across the subdomains. We demonstrate the effectiveness of our method for unsupervised vehicle Re-id using various benchmarks. Experimental results show that the proposed method outperforms the recent state-of-the-art unsupervised Re-id methods. The source code is publicly available on https://github.com/andreYoo/WSCL_VeReid .