Seokju Cho
YOU?
Author Swipe
View article: Flip-flopping and valence in two-candidate competition
Flip-flopping and valence in two-candidate competition Open
We develop a game-theoretic model of two-candidate elections in which voters are concerned with the consistency of candidates’ political positions as well as their valence characteristics unrelated to policy positions. We examine two versi…
View article: Pose-dIVE: Pose-Diversified Augmentation with Diffusion Model for Person Re-Identification
Pose-dIVE: Pose-Diversified Augmentation with Diffusion Model for Person Re-Identification Open
Person re-identification (Re-ID) often faces challenges due to variations in human poses and camera viewpoints, which significantly affect the appearance of individuals across images. Existing datasets frequently lack diversity and scalabi…
View article: Distribution and Risk Assessment of Perfluoroalkyl and Polyfluoroalkyl Substances (PFAS) in the South Han River
Distribution and Risk Assessment of Perfluoroalkyl and Polyfluoroalkyl Substances (PFAS) in the South Han River Open
The aim of this study was to determine the concentrations of 24 perfluoroalkyl and polyfluoroalkyl substances (PFAS) in the South Han River and to assess human health risks of exposure to PFAS through ingestion of water in the same river. …
View article: MIDMs: Matching Interleaved Diffusion Models for Exemplar-Based Image Translation
MIDMs: Matching Interleaved Diffusion Models for Exemplar-Based Image Translation Open
We present a novel method for exemplar-based image translation, called matching interleaved diffusion models (MIDMs). Most existing methods for this task were formulated as GAN-based matching-then-generation framework. However, in this fra…
View article: DaRF: Boosting Radiance Fields from Sparse Inputs with Monocular Depth Adaptation
DaRF: Boosting Radiance Fields from Sparse Inputs with Monocular Depth Adaptation Open
Neural radiance fields (NeRF) shows powerful performance in novel view synthesis and 3D geometry reconstruction, but it suffers from critical performance degradation when the number of known viewpoints is drastically reduced. Existing work…
View article: Neural Matching Fields: Implicit Representation of Matching Fields for Visual Correspondence
Neural Matching Fields: Implicit Representation of Matching Fields for Visual Correspondence Open
Existing pipelines of semantic correspondence commonly include extracting high-level semantic features for the invariance against intra-class variations and background clutters. This architecture, however, inevitably results in a low-resol…
View article: Integrative Feature and Cost Aggregation with Transformers for Dense Correspondence
Integrative Feature and Cost Aggregation with Transformers for Dense Correspondence Open
We present a novel architecture for dense correspondence. The current state-of-the-art are Transformer-based approaches that focus on either feature descriptors or cost volume aggregation. However, they generally aggregate one or the other…
View article: LANIT: Language-Driven Image-to-Image Translation for Unlabeled Data
LANIT: Language-Driven Image-to-Image Translation for Unlabeled Data Open
Existing techniques for image-to-image translation commonly have suffered from two critical problems: heavy reliance on per-sample domain annotation and/or inability of handling multiple attributes per image. Recent truly-unsupervised meth…
View article: Cost Aggregation with 4D Convolutional Swin Transformer for Few-Shot Segmentation
Cost Aggregation with 4D Convolutional Swin Transformer for Few-Shot Segmentation Open
This paper presents a novel cost aggregation network, called Volumetric Aggregation with Transformers (VAT), for few-shot segmentation. The use of transformers can benefit correlation map aggregation through self-attention over a global re…
View article: CATs++: Boosting Cost Aggregation with Convolutions and Transformers
CATs++: Boosting Cost Aggregation with Convolutions and Transformers Open
Cost aggregation is a highly important process in image matching tasks, which aims to disambiguate the noisy matching scores. Existing methods generally tackle this by hand-crafted or CNN-based methods, which either lack robustness to seve…
View article: AggMatch: Aggregating Pseudo Labels for Semi-Supervised Learning
AggMatch: Aggregating Pseudo Labels for Semi-Supervised Learning Open
Semi-supervised learning (SSL) has recently proven to be an effective paradigm for leveraging a huge amount of unlabeled data while mitigating the reliance on large labeled data. Conventional methods focused on extracting a pseudo label fr…
View article: Conflict of Interest in the Legislature
Conflict of Interest in the Legislature Open
이 논문은 공공선택론의 관점에서 입법부 의원들에 대한 이해충돌 방지를 논한다. 공직자의 이해충돌은 공익과 사익의 충돌로 개념화되는데, 의회 구성원인 시민의 대표들은 각기 서로 다른 부분 이익을 대변하는 기능을 한다는 점에서 이해충돌 규제에서 특수한 지위를 갖는다. 이 논문에서는 방법론적 개인주의의 입장에서 의회의 대표자들이 추구해야 할 공익이 국민 전체의 이익이나 지역구민의 이익이라는 가정이 부적합함을 주장한다. 대의민주주의…
View article: Cost Aggregation Is All You Need for Few-Shot Segmentation
Cost Aggregation Is All You Need for Few-Shot Segmentation Open
We introduce a novel cost aggregation network, dubbed Volumetric Aggregation with Transformers (VAT), to tackle the few-shot segmentation task by using both convolutions and transformers to efficiently handle high dimensional correlation m…
View article: Semantic Correspondence with Transformers.
Semantic Correspondence with Transformers. Open
We propose a novel cost aggregation network, called Cost Aggregation with Transformers (CATs), to find dense correspondences between semantically similar images with additional challenges posed by large intra-class appearance and geometric…