Junsu Cho
YOU?
Author Swipe
View article: Auxiliary Task Graph Convolution Network: A Skeleton-Based Action Recognition for Practical Use
Auxiliary Task Graph Convolution Network: A Skeleton-Based Action Recognition for Practical Use Open
Graph convolution networks (GCNs) have been extensively researched for action recognition by estimating human skeletons from video clips. However, their image sampling methods are not practical because they require video-length information…
Dynamic Multi-Behavior Sequence Modeling for Next Item Recommendation Open
Sequential Recommender Systems (SRSs) aim to predict the next item that users will consume, by modeling the user interests within their item sequences. While most existing SRSs focus on a single type of user behavior, only a few pay attent…
Dynamic Multi-Behavior Sequence Modeling for Next Item Recommendation Open
Sequential Recommender Systems (SRSs) aim to predict the next item that users will consume, by modeling the user interests within their item sequences. While most existing SRSs focus on a single type of user behavior, only a few pay attent…
Beyond Learning from Next Item Open
Sequential recommender systems have shown effective suggestions by capturing users' interest drift. There have been two groups of existing sequential models: user- and item-centric models. The user-centric models capture personalized inter…
View article: Sparse Network Inversion for Key Instance Detection in Multiple Instance Learning
Sparse Network Inversion for Key Instance Detection in Multiple Instance Learning Open
Multiple Instance Learning (MIL) involves predicting a single label for a bag of instances, given positive or negative labels at bag-level, without accessing to label for each instance in the training phase. Since a positive bag contains b…
Effects of Tilting Mechanism of Narrow Vehicle on Psychophysiological States of Driver Open
Narrow tilting vehicles have been proposed to address transportation issues such as traffic congestion, lack of parking space. The investigation of the effects of narrow tilting vehicles on user is insufficient though many methods for impr…
Building Large-Scale English and Korean Datasets for Aspect-Level Sentiment Analysis in Automotive Domain Open
We release large-scale datasets of users’ comments in two languages, English and Korean, for aspect-level sentiment analysis in automotive domain. The datasets consist of 58,000+ commentaspect pairs, which are the largest compared to exist…
A study on usability of narrow track vehicle utilizing physiological indices Open
In this paper, we reviewed the usability of the narrow track vehicle with a leaning mechanism by using physiological indices. There are many factors in usability, but among them, we focused on the user's satisfaction with the vehicle. An e…