no code implementations • 21 Mar 2024 • Sumin Lee, Yooseung Wang, Sangmin Woo, Changick Kim
Panoramic Activity Recognition (PAR) seeks to identify diverse human activities across different scales, from individual actions to social group and global activities in crowded panoramic scenes.
1 code implementation • 22 Feb 2024 • Sumin Lee, Jihoon Kim, Namwoo Kang
The proposed model is based on a conditional generative adversarial network (cGAN) with modifications for mechanism synthesis, which is trained to learn the relationship between the requirements of a mechanism with respect to linkage lengths.
no code implementations • 21 Nov 2023 • Sumin Lee, Sangmin Woo, Muhammad Adi Nugroho, Changick Kim
CFEM incorporates sepearte learnable query embeddings for each modality, which guide CFEM to extract complementary information and global action content from the other modalities.
no code implementations • 10 Oct 2023 • Sung Moon Ko, Sumin Lee, Dae-Woong Jeong, Woohyung Lim, Sehui Han
Transfer learning is a crucial technique for handling a small amount of data that is potentially related to other abundant data.
1 code implementation • 11 Sep 2023 • Amr S. Mohamed, Sumin Lee, Deepa Kundur
The ongoing modernization of the power system, involving new equipment installations and upgrades, exposes the power system to the introduction of malware into its operation through supply chain attacks.
no code implementations • ICCV 2023 • Muhammad Adi Nugroho, Sangmin Woo, Sumin Lee, Changick Kim
To address this issue, we propose Audio-Visual Glance Network (AVGN), which leverages the commonly available audio and visual modalities to efficiently process the spatio-temporally important parts of a video.
1 code implementation • 2 Apr 2023 • Sangmin Woo, So-Yeong Jeon, Jinyoung Park, Minji Son, Sumin Lee, Changick Kim
We introduce Sketch-based Video Object Localization (SVOL), a new task aimed at localizing spatio-temporal object boxes in video queried by the input sketch.
1 code implementation • 25 Nov 2022 • Sangmin Woo, Sumin Lee, Yeonju Park, Muhammad Adi Nugroho, Changick Kim
We ask: how can we train a model that is robust to missing modalities?
no code implementations • 29 Sep 2022 • Seongok Ryu, Sumin Lee
In drug discovery, aqueous solubility is an important pharmacokinetic property which affects absorption and assay availability of drug.
no code implementations • 24 Aug 2022 • Sumin Lee, Sangmin Woo, Yeonju Park, Muhammad Adi Nugroho, Changick Kim
In multi-modal action recognition, it is important to consider not only the complementary nature of different modalities but also global action content.
1 code implementation • ACS Omega 2022 • Sumin Lee, Myeonghun Lee, Ki-Won Gyak, Sung Dug Kim, Mi-Jeong Kim, Kyoungmin Min
Predicting both accurate and reliable solubility values has long been a crucial but challenging task.
1 code implementation • 25 Jan 2022 • Sangmin Woo, Jinyoung Park, Inyong Koo, Sumin Lee, Minki Jeong, Changick Kim
To our surprise, we found that training schedule shows divide-and-conquer-like pattern: time segments are first diversified regardless of the target, then coupled with each target, and fine-tuned to the target again.
no code implementations • 8 Sep 2021 • Sumin Lee, Hyunjun Eun, Jinyoung Moon, Seokeon Choi, Yoonhyung Kim, Chanho Jung, Changick Kim
To overcome this problem, we propose a novel recurrent unit, named Information Discrimination Unit (IDU), which explicitly discriminates the information relevancy between an ongoing action and others to decide whether to accumulate the input information.
1 code implementation • CVPR 2020 • Seokeon Choi, Sumin Lee, Youngeun Kim, Taekyung Kim, Changick Kim
To implement our approach, we introduce an ID-preserving person image generation network and a hierarchical feature learning module.
no code implementations • 26 Nov 2019 • Hyunjun Eun, Sumin Lee, Jinyoung Moon, Jongyoul Park, Chanho Jung, Changick Kim
Recent temporal action proposal generation approaches have suggested integrating segment- and snippet score-based methodologies to produce proposals with high recall and accurate boundaries.
no code implementations • 29 Sep 2019 • Youngeun Kim, Seokeon Choi, Taekyung Kim, Sumin Lee, Changick Kim
Since the cost of labeling increases dramatically as the number of cameras increases, it is difficult to apply the re-identification algorithm to a large camera network.
1 code implementation • 28 Aug 2019 • Sumin Lee, Sungchan Oh, Chanho Jung, Changick Kim
To that end, in this paper, we propose a fashion landmark detection network with a global-local embedding module.