activity
20152022
most citedUnsupervised Visual Attribute Transfer with Reconfigurable Generative Adversarial Networks

30 citations · 43 across the 8 of their papers we have counts for

collaborators
Showing cs.LGShow all

7 papers · 1 filter

cs.LG20224 cited

Trajectory Flow Map: Graph-based Approach to Analysing Temporal Evolution of Aggregated Traffic Flows in Large-scale Urban Networks

Jiwon Kim, Kai Zheng, Jonathan Corcoran +2

This paper proposes a graph-based approach to representing spatio-temporal trajectory data that allows an effective visualization and characterization of city-wide traffic dynamics…

cs.LG2022

AggMatch: Aggregating Pseudo Labels for Semi-Supervised Learning

Jiwon Kim, Kwangrok Ryoo, Gyuseong Lee +5

Semi-supervised learning (SSL) has recently proven to be an effective paradigm for leveraging a huge amount of unlabeled data while mitigating the reliance on large labeled data. C…

cs.LG2018

Attention-based Recurrent Neural Network for Urban Vehicle Trajectory Prediction

Seongjin Choi, Jiwon Kim, Hwasoo Yeo

With the increasing deployment of diverse positioning devices and location-based services, a huge amount of spatial and temporal information has been collected and accumulated as t…

cs.LG2018

Doubly Nested Network for Resource-Efficient Inference

Jaehong Kim, Sungeun Hong, Yongseok Choi +1

We propose doubly nested network(DNNet) where all neurons represent their own sub-models that solve the same task. Every sub-model is nested both layer-wise and channel-wise. While…

cs.LG2018

Meta Continual Learning

Risto Vuorio, Dong-Yeon Cho, Daejoong Kim +1

Using neural networks in practical settings would benefit from the ability of the networks to learn new tasks throughout their lifetimes without forgetting the previous tasks. This…

cs.LG2018

Auto-Meta: Automated Gradient Based Meta Learner Search

Jaehong Kim, Sangyeul Lee, Sungwan Kim +6

Fully automating machine learning pipelines is one of the key challenges of current artificial intelligence research, since practical machine learning often requires costly and tim…