no code implementations • 23 May 2022 • Ilchae Jung, Minji Kim, Eunhyeok Park, Bohyung Han
This paper presents a novel hybrid representation learning framework for streaming data, where an image frame in a video is modeled by an ensemble of two distinct deep neural networks; one is a low-bit quantized network and the other is a lightweight full-precision network.
no code implementations • 25 Nov 2019 • Ilchae Jung, Kihyun You, Hyeonwoo Noh, Minsu Cho, Bohyung Han
We propose a novel meta-learning framework for real-time object tracking with efficient model adaptation and channel pruning.
3 code implementations • ECCV 2018 • Ilchae Jung, Jeany Son, Mooyeol Baek, Bohyung Han
We present a fast and accurate visual tracking algorithm based on the multi-domain convolutional neural network (MDNet).
no code implementations • ICCV 2017 • Jonghwan Mun, Paul Hongsuck Seo, Ilchae Jung, Bohyung Han
To address this objective, we automatically generate a customized synthetic VideoQA dataset using {\em Super Mario Bros.} gameplay videos so that it contains events with different levels of reasoning complexity.
no code implementations • ICCV 2015 • Jeany Son, Ilchae Jung, Kayoung Park, Bohyung Han
We evaluate the performance of our tracking algorithm based on the measures for segmentation masks, where our algorithm illustrates superior accuracy compared to the state-of-the-art segmentation-based tracking methods.