3 code implementations • CVPR 2021 • Hyeonseob Nam, Hyunjae Lee, Jongchan Park, Wonjun Yoon, Donggeun Yoo
Convolutional Neural Networks (CNNs) often fail to maintain their performance when they confront new test domains, which is known as the problem of domain shift.
Ranked #62 on Domain Generalization on PACS
1 code implementation • 26 Mar 2019 • HyunJae Lee, Hyo-Eun Kim, Hyeonseob Nam
Following the advance of style transfer with Convolutional Neural Networks (CNNs), the role of styles in CNNs has drawn growing attention from a broader perspective.
Ranked #129 on Image Classification on CIFAR-10
3 code implementations • NeurIPS 2018 • Hyeonseob Nam, Hyo-Eun Kim
Real-world image recognition is often challenged by the variability of visual styles including object textures, lighting conditions, filter effects, etc.
2 code implementations • CVPR 2017 • Hyeonseob Nam, Jung-Woo Ha, Jeonghee Kim
We propose Dual Attention Networks (DANs) which jointly leverage visual and textual attention mechanisms to capture fine-grained interplay between vision and language.
Ranked #2 on Visual Question Answering (VQA) on VQA v1 test-dev
no code implementations • 25 Aug 2016 • Hyeonseob Nam, Mooyeol Baek, Bohyung Han
We present an online visual tracking algorithm by managing multiple target appearance models in a tree structure.
2 code implementations • CVPR 2016 • Hyeonseob Nam, Bohyung Han
Our algorithm pretrains a CNN using a large set of videos with tracking ground-truths to obtain a generic target representation.