1 code implementation • 10 Mar 2024 • Boeun Kim, Jungho Kim, Hyung Jin Chang, Jin Young Choi
While existing motion style transfer methods are effective between two motions with identical content, their performance significantly diminishes when transferring style between motions with different contents.
no code implementations • 8 Jan 2024 • Hyunjun Choi, Hawook Jeong, Jin Young Choi
The evaluation includes a new approach to measure the performance on our goal, i. e. both localization and OOD detection of UFOs.
1 code implementation • 27 Dec 2023 • Sunoh Kim, Jungchan Cho, Joonsang Yu, Youngjoon Yoo, Jin Young Choi
In the weakly supervised temporal video grounding study, previous methods use predetermined single Gaussian proposals which lack the ability to express diverse events described by the sentence query.
no code implementations • 2 Aug 2023 • Hyunjun Choi, JaeHo Chung, Hawook Jeong, Jin Young Choi
In the problem of out-of-distribution (OOD) detection, the usage of auxiliary data as outlier data for fine-tuning has demonstrated encouraging performance.
1 code implementation • CVPR 2023 • Hyunjun Choi, Hawook Jeong, Jin Young Choi
Our balanced energy regularization loss utilizes class-wise different prior probabilities for auxiliary data to address the class imbalance in OOD data.
1 code implementation • 26 May 2023 • Daeho Um, Jiwoong Park, Seulki Park, Jin Young Choi
To overcome this limitation, we introduce a novel concept of channel-wise confidence in a node feature, which is assigned to each imputed channel feature of a node for reflecting certainty of the imputation.
1 code implementation • 21 Apr 2023 • Seulki Park, Daeho Um, Hajung Yoon, Sanghyuk Chun, Sangdoo Yun, Jin Young Choi
In this paper, we propose a robustness benchmark for image-text matching models to assess their vulnerabilities.
no code implementations • 11 Apr 2023 • Tushar Sandhan, Sukanya Sonowal, Jin Young Choi
Automatic audio event recognition plays a pivotal role in making human robot interaction more closer and has a wide applicability in industrial automation, control and surveillance systems.
no code implementations • CVPR 2023 • Hoseok Do, EunKyung Yoo, Taehyeong Kim, Chul Lee, Jin Young Choi
While 3D-based GAN techniques have been successfully applied to render photo-realistic 3D images with a variety of attributes while preserving view consistency, there has been little research on how to fine-control 3D images without limiting to a specific category of objects of their properties.
1 code implementation • 20 Nov 2022 • Junho Cho, Kyuewang Lee, Jin Young Choi
For the discriminative representation of a font from others, we propose a paired-glyph matching-based font representation learning model that attracts the representations of glyphs in the same font to one another, but pushes away those of other fonts.
no code implementations • 26 Oct 2022 • Jiwoong Park, Jisu Jeong, KyungMin Kim, Jin Young Choi
To tackle this challenge, we propose a novel concept of meta-node for message passing that can learn enriched relational knowledge from complex heterogeneous graphs without any meta-paths and meta-graphs by explicitly modeling the relations among the same type of nodes.
1 code implementation • 13 Jul 2022 • Boeun Kim, Hyung Jin Chang, Jungho Kim, Jin Young Choi
To tackle the learning of whole-body motion, long-range temporal dynamics, and person-to-person interactions, we design a global and local attention mechanism, where, global body motions and local joint motions pay attention to each other.
no code implementations • 12 Apr 2022 • Sunoh Kim, Kimin Yun, Jin Young Choi
The key to successful grounding for video surveillance is to understand a semantic phrase corresponding to important actors and objects.
no code implementations • 15 Mar 2022 • Jongmok Kim, Hwijun Lee, Jaeseung Lim, Jongkeun Na, Nojun Kwak, Jin Young Choi
A well-designed strong-weak augmentation strategy and the stable teacher to generate reliable pseudo labels are essential in the teacher-student framework of semi-supervised learning (SSL).
1 code implementation • CVPR 2022 • Jongin Lim, Sangdoo Yun, Seulki Park, Jin Young Choi
In this paper, we propose Hypergraph-Induced Semantic Tuplet (HIST) loss for deep metric learning that leverages the multilateral semantic relations of multiple samples to multiple classes via hypergraph modeling.
1 code implementation • CVPR 2022 • Seulki Park, Youngkyu Hong, Byeongho Heo, Sangdoo Yun, Jin Young Choi
The problem of class imbalanced data is that the generalization performance of the classifier deteriorates due to the lack of data from minority classes.
Ranked #20 on Long-tail Learning on ImageNet-LT
1 code implementation • ICCV 2021 • Seulki Park, Jongin Lim, Younghan Jeon, Jin Young Choi
In this paper, we propose a balancing training method to address problems in imbalanced data learning.
Ranked #46 on Long-tail Learning on CIFAR-10-LT (ρ=10)
no code implementations • 14 Jun 2021 • Seulki Park, Hwanjun Song, Daeho Um, Dae Ung Jo, Sangdoo Yun, Jin Young Choi
Deep neural network can easily overfit to even noisy labels due to its high capacity, which degrades the generalization performance of a model.
1 code implementation • CVPR 2021 • Jiwoong Park, Junho Cho, Hyung Jin Chang, Jin Young Choi
Most of the existing literature regarding hyperbolic embedding concentrate upon supervised learning, whereas the use of unsupervised hyperbolic embedding is less well explored.
no code implementations • 2 Oct 2020 • Do Gyun Kim, Jin Young Choi
However, existing H-RTGL based OCC classifiers have limitations that (i) most of them cannot reflect density of target class and (ii) that considering density has primitive interval generation method, and (iii) there exists no systematic procedure for hyperparameter of H-RTGL based OCC classifier, which influences classification performance of classifier.
1 code implementation • 18 Jun 2020 • Jongin Lim, Daeho Um, Hyung Jin Chang, Dae Ung Jo, Jin Young Choi
In contrast to the existing diffusion methods with a transition matrix determined solely by the graph structure, CAD considers both the node features and the graph structure with the design of our class-attentive transition matrix that utilizes a classifier.
1 code implementation • 14 Feb 2020 • Youngmin Ro, Jin Young Choi
Existing fine-tuning methods use a single learning rate over all layers.
no code implementations • 7 Feb 2020 • Younghan Jeon, Minsik Lee, Jin Young Choi
FPI\_NN is intuitive, simple, and fast to train, while FPI_GD can be used for efficient training of energy networks that have been recently studied.
no code implementations • CVPR 2017 • YoungJoon Yoo, Sangdoo Yun, Hyung Jin Chang, Yiannis Demiris, Jin Young Choi
(iii) The proposed regression is embedded into a generative model, and the whole procedure is developed by the variational autoencoder framework.
1 code implementation • ICCV 2019 • Jiwoong Park, Minsik Lee, Hyung Jin Chang, Kyuewang Lee, Jin Young Choi
For the reconstruction of node features, the decoder is designed based on Laplacian sharpening as the counterpart of Laplacian smoothing of the encoder, which allows utilizing the graph structure in the whole processes of the proposed autoencoder architecture.
no code implementations • 30 May 2019 • Dae Ung Jo, ByeongJu Lee, Jongwon Choi, Haanju Yoo, Jin Young Choi
We formulate the cross-modal association in Bayesian inference framework realized by a deep neural network with multiple variational auto-encoders and variational associators.
no code implementations • 24 May 2019 • Younghan Jeon, Minsik Lee, Jin Young Choi
With a carefully-designed objective function, mathematical optimization can be quite helpful in solving many problems.
2 code implementations • ICCV 2019 • Byeongho Heo, Jeesoo Kim, Sangdoo Yun, Hyojin Park, Nojun Kwak, Jin Young Choi
We investigate the design aspects of feature distillation methods achieving network compression and propose a novel feature distillation method in which the distillation loss is designed to make a synergy among various aspects: teacher transform, student transform, distillation feature position and distance function.
Ranked #38 on Knowledge Distillation on ImageNet
no code implementations • 21 Jan 2019 • Sunoh Kim, Kimin Yun, Jongyoul Park, Jin Young Choi
In this paper, to address this problem, we propose a new framework for recognizing object-related human actions by graph convolutional networks using human and object poses.
Ranked #1 on Action Recognition on IRD
1 code implementation • 18 Jan 2019 • Youngmin Ro, Jongwon Choi, Dae Ung Jo, Byeongho Heo, Jongin Lim, Jin Young Choi
Our strategy alleviates the problem of gradient vanishing in low-level layers and robustly trains the low-level layers to fit the ReID dataset, thereby increasing the performance of ReID tasks.
2 code implementations • 8 Nov 2018 • Byeongho Heo, Minsik Lee, Sangdoo Yun, Jin Young Choi
In this paper, we propose a knowledge transfer method via distillation of activation boundaries formed by hidden neurons.
1 code implementation • 15 May 2018 • Byeongho Heo, Minsik Lee, Sangdoo Yun, Jin Young Choi
In this paper, we provide a new perspective based on a decision boundary, which is one of the most important component of a classifier.
1 code implementation • CVPR 2018 • Jongwon Choi, Hyung Jin Chang, Tobias Fischer, Sangdoo Yun, Kyuewang Lee, Jiyeoup Jeong, Yiannis Demiris, Jin Young Choi
We propose a new context-aware correlation filter based tracking framework to achieve both high computational speed and state-of-the-art performance among real-time trackers.
Ranked #15 on Visual Object Tracking on VOT2017/18
no code implementations • ICCV 2017 • Tushar Sandhan, Jin Young Choi
Interestingly, shape of the high-altitude clouds serves as a beacon for weather forecasting, so its detection is of vital importance.
1 code implementation • The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops 2017 • Junho Cho, Sangdoo Yun, Kyoung Mu Lee, Jin Young Choi
PaletteNet is then designed to change the color concept of a source image so that the palette of the output image is close to the target palette.
1 code implementation • IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017 • Jongwon Choi, Hyung Jin Chang, Sangdoo Yun, Tobias Fischer, Yiannis Demiris, Jin Young Choi
We propose a new tracking framework with an attentional mechanism that chooses a subset of the associated correlation filters for increased robustness and computational efficiency.
no code implementations • CVPR 2017 • Tushar Sandhan, Jin Young Choi
Absence of a clear eye visibility not only degrades the aesthetic value of an entire face image but also creates difficulties in many computer vision tasks.
1 code implementation • CVPR 2017 • Sangdoo Yun, Jongwon Choi, Youngjoon Yoo, Kimin Yun, Jin Young Choi
In contrast to the existing trackers using deep networks, the proposed tracker is designed to achieve a light computation as well as satisfactory tracking accuracy in both location and scale.
no code implementations • CVPR 2016 • YoungJoon Yoo, Kimin Yun, Sangdoo Yun, JongHee Hong, Hawook Jeong, Jin Young Choi
In this paper, we consider moving dynamics of co-occurring objects for path prediction in a scene that includes crowded moving objects.
no code implementations • CVPR 2016 • Jongwon Choi, Hyung Jin Chang, Jiyeoup Jeong, Yiannis Demiris, Jin Young Choi
In this paper, we present a novel attention-modulated visual tracking algorithm that decomposes an object into multiple cognitive units, and trains multiple elementary trackers in order to modulate the distribution of attention according to various feature and kernel types.