3 papers
cs.CV2023
A Multi-In-Single-Out Network for Video Frame Interpolation without Optical Flow
Jaemin Lee, Minseok Seo, Sangwoo Lee +2
In general, deep learning-based video frame interpolation (VFI) methods have predominantly focused on estimating motion vectors between two input frames and warping them to the tar…
cs.CV2021
Exploiting Features with Split-and-Share Module
Jaemin Lee, Minseok Seo, Jongchan Park +1
Deep convolutional neural networks (CNNs) have shown state-of-the-art performances in various computer vision tasks. Advances on CNN architectures have focused mainly on designing…
cs.CV2020
Sequential Feature Filtering Classifier
Minseok Seo, Jaemin Lee, Jongchan Park +1
We propose Sequential Feature Filtering Classifier (FFC), a simple but effective classifier for convolutional neural networks (CNNs). With sequential LayerNorm and ReLU, FFC zeroes…