41 citations · 64 across the 22 of their papers we have counts for
23 papers
Inference-Time Scaling for Joint Audio-Video Generation
Jaemin Jung, Kyeongha Rho, Inkyu Shin +1
Joint audio-video generation aims to synthesize realistic audio-video pairs that are both semantically aligned with text prompts and precisely synchronized. While existing joint au…
GeoNVS: Geometry Grounded Video Diffusion for Novel View Synthesis
Minjun Kang, Inkyu Shin, Taeyeop Lee +3
Novel view synthesis requires strong 3D geometric consistency and the ability to generate visually coherent images across diverse viewpoints. While recent camera-controlled video d…
Drag4D: Align Your Motion with Text-Driven 3D Scene Generation
Minjun Kang, Inkyu Shin, Taeyeop Lee +2
We introduce Drag4D, an interactive framework that integrates object motion control within text-driven 3D scene generation. This framework enables users to define 3D trajectories f…
SCORE: Scaling audio generation using Standardized COmposite REwards
Jaemin Jung, Jaehun Kim, Inkyu Shin +1
The goal of this paper is to enhance Text-to-Audio generation at inference, focusing on generating realistic audio that precisely aligns with text prompts. Despite the rapid advanc…
Deeply Supervised Flow-Based Generative Models
Inkyu Shin, Chenglin Yang, Liang-Chieh Chen
Flow based generative models have charted an impressive path across multiple visual generation tasks by adhering to a simple principle: learning velocity representations of a linea…
Enhancing Temporal Consistency in Video Editing by Reconstructing Videos with 3D Gaussian Splatting
Inkyu Shin, Qihang Yu, Xiaohui Shen +3
Recent advancements in zero-shot video diffusion models have shown promise for text-driven video editing, but challenges remain in achieving high temporal consistency. To address t…
MTMMC: A Large-Scale Real-World Multi-Modal Camera Tracking Benchmark
Sanghyun Woo, Kwanyong Park, Inkyu Shin +2
Multi-target multi-camera tracking is a crucial task that involves identifying and tracking individuals over time using video streams from multiple cameras. This task has practical…
A Simple Video Segmenter by Tracking Objects Along Axial Trajectories
Ju He, Qihang Yu, Inkyu Shin +4
Video segmentation requires consistently segmenting and tracking objects over time. Due to the quadratic dependency on input size, directly applying self-attention to video segment…
Video-kMaX: A Simple Unified Approach for Online and Near-Online Video Panoptic Segmentation
Inkyu Shin, Dahun Kim, Qihang Yu +6
Video Panoptic Segmentation (VPS) aims to achieve comprehensive pixel-level scene understanding by segmenting all pixels and associating objects in a video. Current solutions can b…
TTA-COPE: Test-Time Adaptation for Category-Level Object Pose Estimation
Taeyeop Lee, Jonathan Tremblay, Valts Blukis +6
Test-time adaptation methods have been gaining attention recently as a practical solution for addressing source-to-target domain gaps by gradually updating the model without requir…
Bidirectional Domain Mixup for Domain Adaptive Semantic Segmentation
Daehan Kim, Minseok Seo, Kwanyong Park +4
Mixup provides interpolated training samples and allows the model to obtain smoother decision boundaries for better generalization. The idea can be naturally applied to the domain…
Learning Classifiers of Prototypes and Reciprocal Points for Universal Domain Adaptation
Sungsu Hur, Inkyu Shin, Kwanyong Park +2
Universal Domain Adaptation aims to transfer the knowledge between the datasets by handling two shifts: domain-shift and category-shift. The main challenge is correctly distinguish…
Test-time Adaptation in the Dynamic World with Compound Domain Knowledge Management
Junha Song, Kwanyong Park, InKyu Shin +3
Prior to the deployment of robotic systems, pre-training the deep-recognition models on all potential visual cases is infeasible in practice. Hence, test-time adaptation (TTA) allo…
MATE: Masked Autoencoders are Online 3D Test-Time Learners
M. Jehanzeb Mirza, Inkyu Shin, Wei Lin +8
Our MATE is the first Test-Time-Training (TTT) method designed for 3D data, which makes deep networks trained for point cloud classification robust to distribution shifts occurring…
Moving from 2D to 3D: volumetric medical image classification for rectal cancer staging
Joohyung Lee, Jieun Oh, Inkyu Shin +4
Volumetric images from Magnetic Resonance Imaging (MRI) provide invaluable information in preoperative staging of rectal cancer. Above all, accurate preoperative discrimination bet…
MM-TTA: Multi-Modal Test-Time Adaptation for 3D Semantic Segmentation
Inkyu Shin, Yi-Hsuan Tsai, Bingbing Zhuang +5
Test-time adaptation approaches have recently emerged as a practical solution for handling domain shift without access to the source domain data. In this paper, we propose and expl…
UDA-COPE: Unsupervised Domain Adaptation for Category-level Object Pose Estimation
Taeyeop Lee, Byeong-Uk Lee, Inkyu Shin +4
Learning to estimate object pose often requires ground-truth (GT) labels, such as CAD model and absolute-scale object pose, which is expensive and laborious to obtain in the real w…
Discover, Hallucinate, and Adapt: Open Compound Domain Adaptation for Semantic Segmentation
KwanYong Park, Sanghyun Woo, Inkyu Shin +1
Unsupervised domain adaptation (UDA) for semantic segmentation has been attracting attention recently, as it could be beneficial for various label-scarce real-world scenarios (e.g.…
LabOR: Labeling Only if Required for Domain Adaptive Semantic Segmentation
Inkyu Shin, Dong-jin Kim, Jae Won Cho +3
Unsupervised Domain Adaptation (UDA) for semantic segmentation has been actively studied to mitigate the domain gap between label-rich source data and unlabeled target data. Despit…
Unsupervised Domain Adaptation for Video Semantic Segmentation
Inkyu Shin, Kwanyong Park, Sanghyun Woo +1
Unsupervised Domain Adaptation for semantic segmentation has gained immense popularity since it can transfer knowledge from simulation to real (Sim2Real) by largely cutting out the…
Two-phase Pseudo Label Densification for Self-training based Domain Adaptation
Inkyu Shin, Sanghyun Woo, Fei Pan +1
Recently, deep self-training approaches emerged as a powerful solution to the unsupervised domain adaptation. The self-training scheme involves iterative processing of target data;…
Unsupervised Intra-domain Adaptation for Semantic Segmentation through Self-Supervision
Fei Pan, Inkyu Shin, Francois Rameau +2
Convolutional neural network-based approaches have achieved remarkable progress in semantic segmentation. However, these approaches heavily rely on annotated data which are labor i…
Image-to-Image Translation via Group-wise Deep Whitening-and-Coloring Transformation
Wonwoong Cho, Sungha Choi, David Keetae Park +2
Recently, unsupervised exemplar-based image-to-image translation, conditioned on a given exemplar without the paired data, has accomplished substantial advancements. In order to tr…