Search Results for author: Ig-Jae Kim

Found 13 papers, 3 papers with code

Probabilistic Representations for Video Contrastive Learning

no code implementations8 Apr 2022 Jungin Park, Jiyoung Lee, Ig-Jae Kim, Kwanghoon Sohn

This paper presents Probabilistic Video Contrastive Learning, a self-supervised representation learning method that bridges contrastive learning with probabilistic representation.

Action Recognition Contrastive Learning +2

Learning Canonical 3D Object Representation for Fine-Grained Recognition

no code implementations ICCV 2021 Sunghun Joung, Seungryong Kim, Minsu Kim, Ig-Jae Kim, Kwanghoon Sohn

By incorporating 3D shape and appearance jointly in a deep representation, our method learns the discriminative representation of the object and achieves competitive performance on fine-grained image recognition and vehicle re-identification.

3D Shape Reconstruction Fine-Grained Image Recognition +2

Prototype-Guided Saliency Feature Learning for Person Search

no code implementations CVPR 2021 Hanjae Kim, Sunghun Joung, Ig-Jae Kim, Kwanghoon Sohn

Existing person search methods integrate person detection and re-identification (re-ID) module into a unified system.

Human Detection Person Search

K-FACE: A Large-Scale KIST Face Database in Consideration with Unconstrained Environments

1 code implementation3 Mar 2021 Yeji Choi, Hyunjung Park, Gi Pyo Nam, Haksub Kim, Heeseung Choi, Junghyun Cho, Ig-Jae Kim

In this paper, we introduce a new large-scale face database from KIST, denoted as K-FACE, and describe a novel capturing device specifically designed to obtain the data.

Age Estimation Face Model +1

A 3D model-based approach for fitting masks to faces in the wild

1 code implementation1 Mar 2021 Je Hyeong Hong, Hanjo Kim, Minsoo Kim, Gi Pyo Nam, Junghyun Cho, Hyeong-Seok Ko, Ig-Jae Kim

Our method proceeds by first fitting a 3D morphable model on the input image, second overlaying the mask surface onto the face model and warping the respective mask texture, and last projecting the 3D mask back to 2D.

Face Model Face Recognition

Cross-Domain Grouping and Alignment for Domain Adaptive Semantic Segmentation

1 code implementation15 Dec 2020 Minsu Kim, Sunghun Joung, Seungryong Kim, Jungin Park, Ig-Jae Kim, Kwanghoon Sohn

Existing techniques to adapt semantic segmentation networks across the source and target domains within deep convolutional neural networks (CNNs) deal with all the samples from the two domains in a global or category-aware manner.

Domain Adaptation Semantic Segmentation

ElderSim: A Synthetic Data Generation Platform for Human Action Recognition in Eldercare Applications

no code implementations28 Oct 2020 Hochul Hwang, Cheongjae Jang, Geonwoo Park, Junghyun Cho, Ig-Jae Kim

We then generate KIST SynADL, a large-scale synthetic dataset of elders' activities of daily living, from ElderSim and use the data in addition to real datasets to train three state-of the-art human action recognition models.

Action Recognition Synthetic Data Generation

Unsupervised Video Anomaly Detection via Normalizing Flows with Implicit Latent Features

no code implementations15 Oct 2020 MyeongAh Cho, Taeoh Kim, Ig-Jae Kim, Sangyoun Lee

In contrast, we propose an implicit two-path AE (ITAE), a structure in which two encoders implicitly model appearance and motion features, and a single decoder that combines them to learn normal video patterns.

Anomaly Detection Density Estimation +2

SumGraph: Video Summarization via Recursive Graph Modeling

no code implementations ECCV 2020 Jungin Park, Jiyoung Lee, Ig-Jae Kim, Kwanghoon Sohn

The goal of video summarization is to select keyframes that are visually diverse and can represent a whole story of an input video.

Frame Video Summarization

Cylindrical Convolutional Networks for Joint Object Detection and Viewpoint Estimation

no code implementations CVPR 2020 Sunghun Joung, Seungryong Kim, Hanjae Kim, Minsu Kim, Ig-Jae Kim, Junghyun Cho, Kwanghoon Sohn

To overcome this limitation, we introduce a learnable module, cylindrical convolutional networks (CCNs), that exploit cylindrical representation of a convolutional kernel defined in the 3D space.

Object Detection Viewpoint Estimation

Relational Deep Feature Learning for Heterogeneous Face Recognition

no code implementations2 Mar 2020 MyeongAh Cho, Taeoh Kim, Ig-Jae Kim, Kyungjae Lee, Sangyoun Lee

Due to the lack of databases, HFR methods usually exploit the pre-trained features on a large-scale visual database that contain general facial information.

Face Recognition Heterogeneous Face Recognition

The Unconstrained Ear Recognition Challenge 2019 - ArXiv Version With Appendix

no code implementations11 Mar 2019 Žiga Emeršič, Aruna Kumar S. V., B. S. Harish, Weronika Gutfeter, Jalil Nourmohammadi Khiarak, Andrzej Pacut, Earnest Hansley, Mauricio Pamplona Segundo, Sudeep Sarkar, Hyeonjung Park, Gi Pyo Nam, Ig-Jae Kim, Sagar G. Sangodkar, Ümit Kaçar, Murvet Kirci, Li Yuan, Jishou Yuan, Haonan Zhao, Fei Lu, Junying Mao, Xiaoshuang Zhang, Dogucan Yaman, Fevziye Irem Eyiokur, Kadir Bulut Özler, Hazim Kemal Ekenel, Debbrota Paul Chowdhury, Sambit Bakshi, Pankaj K. Sa, Banshidhar Majhi, Peter Peer, Vitomir Štruc

The goal of the challenge is to assess the performance of existing ear recognition techniques on a challenging large-scale ear dataset and to analyze performance of the technology from various viewpoints, such as generalization abilities to unseen data characteristics, sensitivity to rotations, occlusions and image resolution and performance bias on sub-groups of subjects, selected based on demographic criteria, i. e. gender and ethnicity.

Person Recognition

Person Re-identification in Videos by Analyzing Spatio-Temporal Tubes

no code implementations13 Feb 2019 Sk. Arif Ahmed, Debi Prosad Dogra, Heeseung Choi, Seungho Chae, Ig-Jae Kim

In this paper, we extract spatio-temporal sequences of frames (referred to as tubes) of moving persons and apply a multi-stage processing to match a given query tube with a gallery of stored tubes recorded through other cameras.

Person Re-Identification

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