2 code implementations • 4 Apr 2024 • Wencan Cheng, Hao Tang, Luc van Gool, Jong Hwan Ko
Extracting keypoint locations from input hand frames, known as 3D hand pose estimation, is a critical task in various human-computer interaction applications.
1 code implementation • 28 Feb 2024 • Joo Chan Lee, Taejune Kim, Eunbyung Park, Simon S. Woo, Jong Hwan Ko
To tackle all of the above challenges, we propose CRAD, a novel anomaly detection method for representing normal features within a "continuous" memory, enabled by transforming spatial features into coordinates and mapping them to continuous grids.
no code implementations • NeurIPS 2023 • Seungtae Nam, Daniel Rho, Jong Hwan Ko, Eunbyung Park
In this work, we present mip-Grid, a novel approach that integrates anti-aliasing techniques into grid-based representations for radiance fields, mitigating the aliasing artifacts while enjoying fast training time.
1 code implementation • 25 Nov 2023 • Joo Chan Lee, Daniel Rho, Seungtae Nam, Jong Hwan Ko, Eunbyung Park
Experimental results demonstrate that CAM enhances the performance of neural representation and improves learning stability across a range of signals.
1 code implementation • 22 Nov 2023 • Joo Chan Lee, Daniel Rho, Xiangyu Sun, Jong Hwan Ko, Eunbyung Park
On the other hand, 3D Gaussian splatting (3DGS) has recently emerged as an alternative representation that leverages a 3D Gaussisan-based representation and adopts the rasterization pipeline to render the images rather than volumetric rendering, achieving very fast rendering speed and promising image quality.
1 code implementation • ICCV 2023 • Wencan Cheng, Jong Hwan Ko
Scene flow estimation provides the fundamental motion perception of a dynamic scene, which is of practical importance in many computer vision applications.
1 code implementation • ICCV 2023 • Wencan Cheng, Jong Hwan Ko
3D hand pose estimation is a critical task in various human-computer interaction applications.
1 code implementation • 23 Dec 2022 • Joo Chan Lee, Daniel Rho, Jong Hwan Ko, Eunbyung Park
Neural fields, also known as coordinate-based or implicit neural representations, have shown a remarkable capability of representing, generating, and manipulating various forms of signals.
Ranked #2 on Video Reconstruction on UVG
1 code implementation • CVPR 2023 • Daniel Rho, Byeonghyeon Lee, Seungtae Nam, Joo Chan Lee, Jong Hwan Ko, Eunbyung Park
There have been recent studies on how to reduce these computational inefficiencies by using additional data structures, such as grids or trees.
1 code implementation • 20 Jul 2022 • Junwoo Cho, Seungtae Nam, Daniel Rho, Jong Hwan Ko, Eunbyung Park
Neural fields have emerged as a new data representation paradigm and have shown remarkable success in various signal representations.
1 code implementation • 15 Jul 2022 • Wencan Cheng, Jong Hwan Ko
Scene flow estimation, which extracts point-wise motion between scenes, is becoming a crucial task in many computer vision tasks.
no code implementations • ICASSP 2022 • Taesoo Kim, Jiho Chang, Jong Hwan Ko
In this paper, we propose adversarial domain adaptive VAD (ADA-VAD), which is a deep neural network (DNN) based VAD method highly robust to audio samples with various noise types and low SNRs.
Ranked #4 on Activity Detection on AVA-Speech (ROC-AUC metric)
1 code implementation • 22 Jan 2022 • Daniel Rho, Jinhyeok Park, Jong Hwan Ko
Various neural network-based approaches have been proposed for more robust and accurate voice activity detection (VAD).
1 code implementation • 12 Jan 2022 • Daniel Rho, Junwoo Cho, Jong Hwan Ko, Eunbyung Park
Inspired by standard video compression algorithms, we propose a neural field architecture for representing and compressing videos that deliberately removes data redundancy through the use of motion information across video frames.
1 code implementation • 21 Dec 2021 • Johnny Rhe, Sungmin Moon, Jong Hwan Ko
In this paper, we introduce a novel mapping algorithm called variable-window SDK (VW-SDK), which adaptively determines the shape of the parallel window that leads to the minimum computing cycles for a given convolutional layer and PIM array.
1 code implementation • ICCV 2021 • Wencan Cheng, Jae Hyun Park, Jong Hwan Ko
With increasing applications of 3D hand pose estimation in various human-computer interaction applications, convolution neural networks (CNNs) based estimation models have been actively explored.
Ranked #3 on Hand Pose Estimation on ICVL Hands
1 code implementation • 2 Sep 2020 • Jae Hyun Park, Ji Sub Choi, Jong Hwan Ko
On-line Precision scalability of the deep neural networks(DNNs) is a critical feature to support accuracy and complexity trade-off during the DNN inference.
no code implementations • ICLR 2019 • Taesik Na, Minah Lee, Burhan A. Mudassar, Priyabrata Saha, Jong Hwan Ko, Saibal Mukhopadhyay
We evaluate our proposed method for various machine learning tasks including object detection on MS-COCO 2014 dataset, multiple object tracking problem on MOT-Challenge dataset, and human activity classification on UCF 101 dataset.
no code implementations • 11 Feb 2018 • Jong Hwan Ko, Taesik Na, Mohammad Faisal Amir, Saibal Mukhopadhyay
The lossless or lossy encoding of the feature space is proposed to enhance the maximum input rate supported by the edge platform and/or reduce the energy of the edge platform.
1 code implementation • ICLR 2018 • Taesik Na, Jong Hwan Ko, Saibal Mukhopadhyay
Injecting adversarial examples during training, known as adversarial training, can improve robustness against one-step attacks, but not for unknown iterative attacks.