no code implementations • 2 Jun 2023 • Minho Shim, Taeoh Kim, Jinhyung Kim, Dongyoon Wee
Summarizing a video requires a diverse understanding of the video, ranging from recognizing scenes to evaluating how much each frame is essential enough to be selected as a summary.
no code implementations • CVPR 2023 • Pilhyeon Lee, Taeoh Kim, Minho Shim, Dongyoon Wee, Hyeran Byun
Temporal action detection aims to predict the time intervals and the classes of action instances in the video.
no code implementations • 30 Jun 2022 • Taeoh Kim, Jinhyung Kim, Minho Shim, Sangdoo Yun, Myunggu Kang, Dongyoon Wee, Sangyoun Lee
The magnitude of augmentation operations on each frame is changed by an effective mechanism, Fourier Sampling that parameterizes diverse, smooth, and realistic temporal variations.
no code implementations • 8 Apr 2022 • Jinhyung Kim, Taeoh Kim, Minho Shim, Dongyoon Han, Dongyoon Wee, Junmo Kim
FreqAug stochastically removes specific frequency components from the video so that learned representation captures essential features more from the remaining information for various downstream tasks.
no code implementations • 2 Feb 2021 • Chajin Shin, Taeoh Kim, Sangjin Lee, Sangyoun Lee
From this test-time adaptation, our network can exploit externally learned image priors from the pre-trained features as well as the internal prior of the test image explicitly.
no code implementations • 15 Oct 2020 • MyeongAh Cho, Taeoh Kim, Woo Jin Kim, Suhwan Cho, Sangyoun Lee
For the complex distribution of normal scenes, we suggest normal density estimation of ITAE features through normalizing flow (NF)-based generative models to learn the tractable likelihoods and identify anomalies using out of distribution detection.
no code implementations • 5 Oct 2020 • Hyeongmin Lee, Taeoh Kim, Hanbin Son, Sangwook Baek, Minsu Cheon, Sangyoun Lee
Extensive results for various image processing tasks indicate that the performance of FTN is comparable in multiple continuous levels, and is significantly smoother and lighter than that of other frameworks.
no code implementations • 30 Sep 2020 • Hanbin Son, Taeoh Kim, Hyeongmin Lee, Sangyoun Lee
The postprocessing network increases the quality of decoded images using an example-based learning.
1 code implementation • 13 Aug 2020 • Taeoh Kim, Hyeongmin Lee, MyeongAh Cho, Ho Seong Lee, Dong Heon Cho, Sangyoun Lee
Based on our novel temporal data augmentation algorithms, video recognition performances are improved using only a limited amount of training data compared to the spatial-only data augmentation algorithms, including the 1st Visual Inductive Priors (VIPriors) for data-efficient action recognition challenge.
no code implementations • 27 May 2020 • Sangjin Lee, Hyeongmin Lee, Taeoh Kim, Sangyoun Lee
Unlike previous studies that usually have been focused on the design of modules or construction of networks, we propose a novel Extrapolative-Interpolative Cycle (EIC) loss using pre-trained frame interpolation module to improve extrapolation performance.
no code implementations • 11 Mar 2020 • Hyeongmin Lee, Taeoh Kim, Hanbin Son, Sangwook Baek, Minsu Cheon, Sangyoun Lee
In this paper, we propose a novel continuous-level learning framework using a Filter Transition Network (FTN) which is a non-linear module that easily adapt to new levels, and is regularized to prevent undesirable side-effects.
no code implementations • 2 Mar 2020 • MyeongAh Cho, Taeoh Kim, Ig-Jae Kim, Kyungjae Lee, Sangyoun Lee
Due to the lack of databases, HFR methods usually exploit the pre-trained features on a large-scale visual database that contain general facial information.
1 code implementation • CVPR 2020 • Hyeongmin Lee, Taeoh Kim, Tae-young Chung, Daehyun Pak, Yuseok Ban, Sangyoun Lee
Video frame interpolation is one of the most challenging tasks in video processing research.
Ranked #14 on Video Frame Interpolation on X4K1000FPS