Search Results for author: Minjung Kim

Found 16 papers, 6 papers with code

FIMP: Future Interaction Modeling for Multi-Agent Motion Prediction

no code implementations29 Jan 2024 Sungmin Woo, Minjung Kim, Donghyeong Kim, Sungjun Jang, Sangyoun Lee

Multi-agent motion prediction is a crucial concern in autonomous driving, yet it remains a challenge owing to the ambiguous intentions of dynamic agents and their intricate interactions.

Motion Forecasting motion prediction

Regular Time-series Generation using SGM

no code implementations20 Jan 2023 Haksoo Lim, Minjung Kim, Sewon Park, Noseong Park

We propose a conditional score network for the time-series generation domain.

Denoising Time Series +2

Look Around for Anomalies: Weakly-Supervised Anomaly Detection via Context-Motion Relational Learning

no code implementations CVPR 2023 MyeongAh Cho, Minjung Kim, Sangwon Hwang, Chaewon Park, Kyungjae Lee, Sangyoun Lee

Furthermore, as the relationship between context and motion is important in order to identify the anomalies in complex and diverse scenes, we propose a Context--Motion Interrelation Module (CoMo), which models the relationship between the appearance of the surroundings and motion, rather than utilizing only temporal dependencies or motion information.

Relational Reasoning Supervised Anomaly Detection +2

Feature Disentanglement Learning with Switching and Aggregation for Video-based Person Re-Identification

no code implementations16 Dec 2022 Minjung Kim, MyeongAh Cho, Sangyoun Lee

In video person re-identification (Re-ID), the network must consistently extract features of the target person from successive frames.

Disentanglement Video-Based Person Re-Identification

Occluded Person Re-Identification via Relational Adaptive Feature Correction Learning

no code implementations9 Dec 2022 Minjung Kim, MyeongAh Cho, Heansung Lee, Suhwan Cho, Sangyoun Lee

Occluded person re-identification (Re-ID) in images captured by multiple cameras is challenging because the target person is occluded by pedestrians or objects, especially in crowded scenes.

Person Re-Identification

SOS: Score-based Oversampling for Tabular Data

1 code implementation17 Jun 2022 Jayoung Kim, Chaejeong Lee, Yehjin Shin, Sewon Park, Minjung Kim, Noseong Park, Jihoon Cho

To our knowledge, we are the first presenting a score-based tabular data oversampling method.

Style Transfer

Marvelous Agglutinative Language Effect on Cross Lingual Transfer Learning

no code implementations8 Apr 2022 Wooyoung Kim, Chaerin Jo, Minjung Kim, Wooju Kim

It is known that using languages with similar language structures is effective for cross lingual transfer learning (Pires et al., 2019).

Cross-Lingual Transfer Transfer Learning

3D-GIF: 3D-Controllable Object Generation via Implicit Factorized Representations

no code implementations12 Mar 2022 Minsoo Lee, Chaeyeon Chung, Hojun Cho, Minjung Kim, Sanghun Jung, Jaegul Choo, Minhyuk Sung

While NeRF-based 3D-aware image generation methods enable viewpoint control, limitations still remain to be adopted to various 3D applications.

Image Generation

Pixel-Level Bijective Matching for Video Object Segmentation

1 code implementation4 Oct 2021 Suhwan Cho, Heansung Lee, Minjung Kim, Sungjun Jang, Sangyoun Lee

Before finding the best matches for the query frame pixels, the optimal matches for the reference frame pixels are first considered to prevent each reference frame pixel from being overly referenced.

Object Semantic Segmentation +2

Drop-Bottleneck: Learning Discrete Compressed Representation for Noise-Robust Exploration

1 code implementation ICLR 2021 Jaekyeom Kim, Minjung Kim, Dongyeon Woo, Gunhee Kim

We propose a novel information bottleneck (IB) method named Drop-Bottleneck, which discretely drops features that are irrelevant to the target variable.

Adversarial Robustness Dimensionality Reduction

Memorization Precedes Generation: Learning Unsupervised GANs with Memory Networks

1 code implementation ICLR 2018 Youngjin Kim, Minjung Kim, Gunhee Kim

We propose an approach to address two issues that commonly occur during training of unsupervised GANs.

Memorization

Imaginary time, shredded propagator method for large-scale GW calculations

no code implementations21 Jul 2017 Minjung Kim, Glenn J. Martyna, Sohrab Ismail-Beigi

The GW method is a many-body approach capable of providing quasiparticle bands for realistic systems spanning physics, chemistry, and materials science.

Materials Science

Cannot find the paper you are looking for? You can Submit a new open access paper.