Jae Hyeon Park

Two-stage anthropometric landmark detection framework on human point cloud: Dynamic-invariant and static-specific strategy

Ji Sun Byun, Joo Won Park, Jae Hyeon Park, Min Hee Cha et autres

kr (code pays fourni par la source)

Online Hand Gesture Recognition Using Semantically Interpretable Attention Mechanism

Moon Ju Chae, Jae Hyeon Park, Min Hee Cha, Sung In Cho

Hand gesture recognition (HGR) is a field of action recognition widely used in various domains such as robotics, virtual reality (VR), and augmented reality (AR). In this paper, we propose a semantically interpretable attention technique based on the compression and exchange of …

kr (code pays fourni par la source)

DCID: A divide and conquer approach to solving the trade-off problem between artifacts caused by enhancement procedure in image downscaling

Eun Su Kang, Yeon Jeong Chae, Jae Hyeon Park, Sung In Cho

kr (code pays fourni par la source)

Human visual system-based perceptual Mura index for quantitative Mura evaluation

Jae Hyeon Park, Ju Hyun Kim, Ba Hung Ngo, Jung Eun Kwon et autres

kr (code pays fourni par la source)

Anthropometric Landmark Detection Network via Geodesic Heatmap on 3D Human Scan

Min Hee Cha, Jae Hyeon Park, Ji Sun Byun, Gyoomin Lee et autres

In recent years, with the commercialization of three-dimensional (3D) scanners, there is an increasing demand for automated techniques that can extract anthropometric data accurately and swiftly from 3D human body scans. With advancement in computer vision and machine learning, researchers have increasingly …

kr (code pays fourni par la source)

Improved Knowledge Transfer for Semi-supervised Domain Adaptation via Trico Training Strategy

Ba Hung Ngo, Yeon Jeong Chae, Jung Eun Kwon, Jae Hyeon Park et autres

The motivation of the semi-supervised domain adaptation (SSDA) is to train a model by leveraging knowledge acquired from the plentiful labeled source combined with extremely scarce labeled target data to achieve the lowest error on the unlabeled target data at the testing …

kr (code pays fourni par la source)

Adversarial representation teaching with perturbation-agnostic student-teacher structure for semi-supervised learning

Jae Hyeon Park, Ju Hyun Kim, Ba Hung Ngo, Jung Eun Kwon et autres

kr (code pays fourni par la source)

Context and scale-aware YOLO for welding defect detection

Jung Eun Kwon, Jae Hyeon Park, Ju Hyun Kim, Yun Hak Lee et autres

kr (code pays fourni par la source)

Easy-to-Hard Structure for Remote Sensing Scene Classification in Multitarget Domain Adaptation

Ba Hung Ngo, Yeon Jeong Chae, Jae Hyeon Park, Ju Hyun Kim et autres

Multitarget domain adaptation (MTDA) is a transfer learning task that uses knowledge extracted from a labeled source domain to adapt across multiple unlabeled target domains. The MTDA setting is more complicated than the single-source-single-target domain adaptation (S3TDA) setting because domain shift not …

kr (code pays fourni par la source)

Dcid: A Divide and Conquer Approach to Solving the Trade-Off Problem between Enhancement and Artifacts in Image Downscaling

Eun Su Kang, Yeon Jeong Chae, Jae Hyeon Park, Sung In Cho

kr (code pays fourni par la source)

Dcid: A Divide and Conquer Approach to Solving the Trade-Off Enhancement and Artifacts in Image Downscaling

Eun Su Kang, Yeon Jeong Chae, Jae Hyeon Park, Sung In Cho

kr (code pays fourni par la source)

Adversarial Representation Teaching with Perturbation-Agnostic Student-Teacher Structure for Semi-Supervised Learning

Jae Hyeon Park, Ju Hyun Kim, Ba Hung Ngo, Sung In Cho

kr (code pays fourni par la source)