Search Results for author: Hun-Seok Kim

Found 14 papers, 11 papers with code

Differentiable Learning of Generalized Structured Matrices for Efficient Deep Neural Networks

1 code implementation29 Oct 2023 Changwoo Lee, Hun-Seok Kim

To address this issue, we propose a generalized and differentiable framework to learn efficient structures of weight matrices by gradient descent.

Siamese Learning-based Monarch Butterfly Localization

no code implementations4 Jul 2023 Sara Shoouri, Mingyu Yang, Gordy Carichner, Yuyang Li, Ehab A. Hamed, Angela Deng, Delbert A. Green II, Inhee Lee, David Blaauw, Hun-Seok Kim

A new GPS-less, daily localization method is proposed with deep learning sensor fusion that uses daylight intensity and temperature sensor data for Monarch butterfly tracking.

Sensor Fusion

MMVC: Learned Multi-Mode Video Compression with Block-based Prediction Mode Selection and Density-Adaptive Entropy Coding

1 code implementation CVPR 2023 Bowen Liu, Yu Chen, Rakesh Chowdary Machineni, Shiyu Liu, Hun-Seok Kim

In this paper, we propose multi-mode video compression (MMVC), a block wise mode ensemble deep video compression framework that selects the optimal mode for feature domain prediction adapting to different motion patterns.

Benchmarking MS-SSIM +4

Efficient Computation Sharing for Multi-Task Visual Scene Understanding

1 code implementation ICCV 2023 Sara Shoouri, Mingyu Yang, Zichen Fan, Hun-Seok Kim

Solving multiple visual tasks using individual models can be resource-intensive, while multi-task learning can conserve resources by sharing knowledge across different tasks.

Multi-Task Learning Scene Understanding

Deep Joint Source-Channel Coding with Iterative Source Error Correction

1 code implementation17 Feb 2023 Changwoo Lee, Xiao Hu, Hun-Seok Kim

In this paper, we propose an iterative source error correction (ISEC) decoding scheme for deep-learning-based joint source-channel coding (Deep JSCC).

Efficient Deep Visual and Inertial Odometry with Adaptive Visual Modality Selection

1 code implementation12 May 2022 Mingyu Yang, Yu Chen, Hun-Seok Kim

In recent years, deep learning-based approaches for visual-inertial odometry (VIO) have shown remarkable performance outperforming traditional geometric methods.

Pose Estimation

Millimeter-Scale Ultra-Low-Power Imaging System for Intelligent Edge Monitoring

no code implementations9 Mar 2022 Andrea Bejarano-Carbo, Hyochan An, Kyojin Choo, Shiyu Liu, Qirui Zhang, Dennis Sylvester, David Blaauw, Hun-Seok Kim

Millimeter-scale embedded sensing systems have unique advantages over larger devices as they are able to capture, analyze, store, and transmit data at the source while being unobtrusive and covert.

Data Compression Event Detection +1

Deep Joint Source-Channel Coding for Wireless Image Transmission with Adaptive Rate Control

1 code implementation9 Oct 2021 Mingyu Yang, Hun-Seok Kim

To the best of our knowledge, this is the first deep JSCC scheme that can automatically adjust its rate using a single network model.

Unified Signal Compression Using a GAN with Iterative Latent Representation Optimization

1 code implementation23 Sep 2021 Bowen Liu, Changwoo Lee, Ang Cao, Hun-Seok Kim

We propose a unified signal compression framework that uses a generative adversarial network (GAN) to compress heterogeneous signals.

Generative Adversarial Network Image Compression +2

OFDM-guided Deep Joint Source Channel Coding for Wireless Multipath Fading Channels

1 code implementation11 Sep 2021 Mingyu Yang, Chenghong Bian, Hun-Seok Kim

We investigate joint source channel coding (JSCC) for wireless image transmission over multipath fading channels.

Deep Learning in Latent Space for Video Prediction and Compression

1 code implementation CVPR 2021 Bowen Liu, Yu Chen, Shiyu Liu, Hun-Seok Kim

The proposed method first learns the efficient lower-dimensional latent space representation of each video frame and then performs inter-frame prediction in that latent domain.

Anomaly Detection Event Detection +3

Deep Joint Source Channel Coding for WirelessImage Transmission with OFDM

2 code implementations5 Jan 2021 Mingyu Yang, Chenghong Bian, Hun-Seok Kim

We present a deep learning based joint source channel coding (JSCC) scheme for wireless image transmission over multipath fading channels with non-linear signal clipping.

BIG-bench Machine Learning

Migrating Monarch Butterfly Localization Using Multi-Sensor Fusion Neural Networks

no code implementations14 Dec 2019 Mingyu Yang, Roger Hsiao, Gordy Carichner, Katherine Ernst, Jaechan Lim, Delbert A. Green II, Inhee Lee, David Blaauw, Hun-Seok Kim

Details of Monarch butterfly migration from the U. S. to Mexico remain a mystery due to lack of a proper localization technology to accurately localize and track butterfly migration.

Sensor Fusion

Unified Signal Compression Using Generative Adversarial Networks

2 code implementations8 Dec 2019 Bowen Liu, Ang Cao, Hun-Seok Kim

We propose a unified compression framework that uses generative adversarial networks (GAN) to compress image and speech signals.

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