1 code implementation • 30 Nov 2023 • Pilhyeon Lee, Hyeran Byun
However, they suffer from the issue of center misalignment raised by the inherent ambiguity of moment centers, leading to inaccurate predictions.
Ranked #1 on Natural Language Moment Retrieval on TACoS
no code implementations • 25 Sep 2023 • Cheolhyun Mun, Sanghuk Lee, Youngjung Uh, Junsuk Choe, Hyeran Byun
Weakly-supervised semantic segmentation (WSSS) performs pixel-wise classification given only image-level labels for training.
Weakly supervised Semantic Segmentation Weakly-Supervised Semantic Segmentation
no code implementations • ICCV 2023 • Seogkyu Jeon, Bei Liu, Pilhyeon Lee, Kibeom Hong, Jianlong Fu, Hyeran Byun
Due to the data absence, the textual description of the target domain and the vision-language models, e. g., CLIP, are utilized to effectively guide the generator.
1 code implementation • ICCV 2023 • Kibeom Hong, Seogkyu Jeon, Junsoo Lee, Namhyuk Ahn, Kunhee Kim, Pilhyeon Lee, Daesik Kim, Youngjung Uh, Hyeran Byun
To deliver the artistic expression of the target style, recent studies exploit the attention mechanism owing to its ability to map the local patches of the style image to the corresponding patches of the content image.
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 • ICCV 2023 • Minjung Shin, Yunji Seo, Jeongmin Bae, Young Sun Choi, Hyunsu Kim, Hyeran Byun, Youngjung Uh
To solve this problem, we propose to approximate the background as a spherical surface and represent a scene as a union of the foreground placed in the sphere and the thin spherical background.
1 code implementation • 20 Jan 2023 • Pilhyeon Lee, Seogkyu Jeon, Sunhee Hwang, Minjung Shin, Hyeran Byun
In this paper, we introduce a novel and practical problem setup, namely source-free subject adaptation, where the source subject data are unavailable and only the pre-trained model parameters are provided for subject adaptation.
no code implementations • 8 Aug 2022 • Sungpil Kho, Pilhyeon Lee, Wonyoung Lee, Minsong Ki, Hyeran Byun
To this end, previous methods adopt the common pipeline: they generate pseudo masks from class activation maps (CAMs) and use such masks to supervise segmentation networks.
no code implementations • 20 Jul 2022 • Mirae Do, Seogkyu Jeon, Pilhyeon Lee, Kibeom Hong, Yu-seung Ma, Hyeran Byun
Domain adaptation for object detection (DAOD) has recently drawn much attention owing to its capability of detecting target objects without any annotations.
1 code implementation • CVPR 2022 • Sungho Park, Jewook Lee, Pilhyeon Lee, Sunhee Hwang, Dohyung Kim, Hyeran Byun
Through extensive experiments on CelebA and UTK Face, we validate that the proposed method significantly outperforms SupCon and existing state-of-the-art methods in terms of the trade-off between top-1 accuracy and fairness.
1 code implementation • 7 Feb 2022 • Pilhyeon Lee, Sunhee Hwang, Jewook Lee, Minjung Shin, Seogkyu Jeon, Hyeran Byun
This paper tackles the problem of subject adaptive EEG-based visual recognition.
1 code implementation • 26 Oct 2021 • Pilhyeon Lee, Sunhee Hwang, Seogkyu Jeon, Hyeran Byun
It limits recognition systems to work only for the subjects involved in model training, which is undesirable for real-world scenarios where new subjects are frequently added.
1 code implementation • 19 Aug 2021 • Seogkyu Jeon, Kibeom Hong, Pilhyeon Lee, Jewook Lee, Hyeran Byun
To these ends, we propose a novel domain generalization framework where feature statistics are utilized for stylizing original features to ones with novel domain properties.
Ranked #34 on Domain Generalization on Office-Home
1 code implementation • ICCV 2021 • Pilhyeon Lee, Hyeran Byun
To learn completeness from the obtained sequence, we introduce two novel losses that contrast action instances with background ones in terms of action score and feature similarity, respectively.
Ranked #1 on Weakly Supervised Action Localization on THUMOS’14
Weakly Supervised Action Localization Weakly-supervised Temporal Action Localization +1
1 code implementation • ICCV 2021 • Kibeom Hong, Seogkyu Jeon, Huan Yang, Jianlong Fu, Hyeran Byun
To this end, we design a novel domainness indicator that captures the domainness value from the texture and structural features of reference images.
no code implementations • 26 Feb 2021 • Seogkyu Jeon, Pilhyeon Lee, Kibeom Hong, Hyeran Byun
Face aging is the task aiming to translate the faces in input images to designated ages.
no code implementations • 11 Jan 2021 • Kibeom Hong, Youngjung Uh, Hyeran Byun
Training GANs on videos is even more sophisticated than on images because videos have a distinguished dimension: time.
no code implementations • ICCV 2021 • Minsong Ki, Youngjung Uh, Junsuk Choe, Hyeran Byun
The goal of unsupervised co-localization is to locate the object in a scene under the assumptions that 1) the dataset consists of only one superclass, e. g., birds, and 2) there are no human-annotated labels in the dataset.
no code implementations • 1 Dec 2020 • Sunhee Hwang, Sungho Park, Dohyung Kim, Mirae Do, Hyeran Byun
Further, we also evaluate image translation performances, where FairFaceGAN shows competitive results, compared to those of existing methods.
1 code implementation • 25 Sep 2020 • Minsong Ki, Youngjung Uh, Wonyoung Lee, Hyeran Byun
Furthermore, we propose foreground consistency loss that penalizes earlier layers producing noisy attention regarding the later layer as a reference to provide them with a sense of backgroundness.
no code implementations • 7 Jul 2020 • Sungho Park, Dohyung Kim, Sunhee Hwang, Hyeran Byun
After the representation learning, this disentangled representation is leveraged for fairer downstream classification by excluding the subspace with the protected attribute information.
2 code implementations • 12 Jun 2020 • Pilhyeon Lee, Jinglu Wang, Yan Lu, Hyeran Byun
Experimental results show that our uncertainty modeling is effective at alleviating the interference of background frames and brings a large performance gain without bells and whistles.
1 code implementation • CVPR 2020 • Myeongjin Kim, Hyeran Byun
However, due to the domain gap between synthetic domain and real domain, it is challenging for a model trained with synthetic data to generalize to real data.
2 code implementations • 22 Nov 2019 • Pilhyeon Lee, Youngjung Uh, Hyeran Byun
This formulation does not fully model the problem in that background frames are forced to be misclassified as action classes to predict video-level labels accurately.
Ranked #9 on Weakly Supervised Action Localization on ActivityNet-1.2 (mAP@0.5 metric)
Weakly Supervised Action Localization Weakly-supervised Temporal Action Localization +1
no code implementations • Sensors 2019, 19(6), 1382 2019 • Jongkwang Hong, Bora Cho, Yong Won Hong, Hyeran Byun
However, depending on the action characteristics, contextual information, such as the existence of specific objects or globally-shared information in the image, becomes vital information to define the action.
Ranked #17 on Action Recognition on HMDB-51