24 citations · 93 across the 42 of their papers we have counts for
46 papers
OTT-Vid: Optimal Transport Temporal Token Compression for Video Large Language Models
Minseok Kang, Minhyeok Lee, Jungho Lee +6
As Video Large Language Models (Video-LLMs) scale to longer and more complex videos, their inference cost grows rapidly due to the large volume of visual tokens accumulated across…
Seen-to-Scene: Keep the Seen, Generate the Unseen for Video Outpainting
Inseok Jeon, Minhyeok Lee, Seunghoon Lee +3
Video outpainting aims to expand the visible content of a video beyond the original frame boundaries while preserving spatial fidelity and temporal coherence across frames. Existin…
CMTM: Cross-Modal Token Modulation for Unsupervised Video Object Segmentation
Inseok Jeon, Suhwan Cho, Minhyeok Lee +6
Recent advances in unsupervised video object segmentation have highlighted the potential of two-stream architectures that integrate appearance and motion cues. However, fully lever…
Revisiting Weakly-Supervised Video Scene Graph Generation via Pair Affinity Learning
Minseok Kang, Minhyeok Lee, Minjung Kim +5
Weakly-supervised video scene graph generation (WS-VSGG) aims to parse video content into structured relational triplets without bounding box annotations and with only sparse tempo…
SwiftVGGT: A Scalable Visual Geometry Grounded Transformer for Large-Scale Scenes
Jungho Lee, Minhyeok Lee, Sunghun Yang +2
3D reconstruction in large-scale scenes is a fundamental task in 3D perception, but the inherent trade-off between accuracy and computational efficiency remains a significant chall…
MonoCLUE : Object-Aware Clustering Enhances Monocular 3D Object Detection
Sunghun Yang, Minhyeok Lee, Jungho Lee +1
Monocular 3D object detection offers a cost-effective solution for autonomous driving but suffers from ill-posed depth and limited field of view. These constraints cause a lack of…
Empower Words: DualGround for Structured Phrase and Sentence-Level Temporal Grounding
Minseok Kang, Minhyeok Lee, Minjung Kim +2
Video Temporal Grounding (VTG) aims to localize temporal segments in long, untrimmed videos that align with a given natural language query. This task typically comprises two subtas…
DepthFlow: Exploiting Depth-Flow Structural Correlations for Unsupervised Video Object Segmentation
Suhwan Cho, Minhyeok Lee, Jungho Lee +2
Unsupervised video object segmentation (VOS) aims to detect the most prominent object in a video. Recently, two-stream approaches that leverage both RGB images and optical flow hav…
TransFlow: Motion Knowledge Transfer from Video Diffusion Models to Video Salient Object Detection
Suhwan Cho, Minhyeok Lee, Jungho Lee +2
Video salient object detection (SOD) relies on motion cues to distinguish salient objects from backgrounds, but training such models is limited by scarce video datasets compared to…
CoMoGaussian: Continuous Motion-Aware Gaussian Splatting from Motion-Blurred Images
Jungho Lee, Donghyeong Kim, Dogyoon Lee +6
3D Gaussian Splatting (3DGS) has gained significant attention due to its high-quality novel view rendering, motivating research to address real-world challenges. A critical issue i…
Find First, Track Next: Decoupling Identification and Propagation in Referring Video Object Segmentation
Suhwan Cho, Seunghoon Lee, Minhyeok Lee +2
Referring video object segmentation aims to segment and track a target object in a video using a natural language prompt. Existing methods typically fuse visual and textual feature…
CoCoGaussian: Leveraging Circle of Confusion for Gaussian Splatting from Defocused Images
Jungho Lee, Suhwan Cho, Taeoh Kim +6
3D Gaussian Splatting (3DGS) has attracted significant attention for its high-quality novel view rendering, inspiring research to address real-world challenges. While conventional…
STATIC : Surface Temporal Affine for TIme Consistency in Video Monocular Depth Estimation
Sunghun Yang, Minhyeok Lee, Suhwan Cho +2
Video monocular depth estimation is essential for applications such as autonomous driving, AR/VR, and robotics. Recent transformer-based single-image monocular depth estimation mod…
Transforming Static Images Using Generative Models for Video Salient Object Detection
Suhwan Cho, Minhyeok Lee, Jungho Lee +1
In many video processing tasks, leveraging large-scale image datasets is a common strategy, as image data is more abundant and facilitates comprehensive knowledge transfer. A typic…
Effective SAM Combination for Open-Vocabulary Semantic Segmentation
Minhyeok Lee, Suhwan Cho, Jungho Lee +4
Open-vocabulary semantic segmentation aims to assign pixel-level labels to images across an unlimited range of classes. Traditional methods address this by sequentially connecting…
Video Diffusion Models are Strong Video Inpainter
Minhyeok Lee, Suhwan Cho, Chajin Shin +3
Propagation-based video inpainting using optical flow at the pixel or feature level has recently garnered significant attention. However, it has limitations such as the inaccuracy…
Improving Unsupervised Video Object Segmentation via Fake Flow Generation
Suhwan Cho, Minhyeok Lee, Jungho Lee +4
Unsupervised video object segmentation (VOS), also known as video salient object detection, aims to detect the most prominent object in a video at the pixel level. Recently, two-st…
Sparse-DeRF: Deblurred Neural Radiance Fields from Sparse View
Dogyoon Lee, Donghyeong Kim, Jungho Lee +3
Recent studies construct deblurred neural radiance fields~(DeRF) using dozens of blurry images, which are not practical scenarios if only a limited number of blurry images are avai…
CRiM-GS: Continuous Rigid Motion-Aware Gaussian Splatting from Motion-Blurred Images
Jungho Lee, Donghyeong Kim, Dogyoon Lee +3
3D Gaussian Splatting (3DGS) has gained significant attention for their high-quality novel view rendering, motivating research to address real-world challenges. A critical issue is…
SMURF: Continuous Dynamics for Motion-Deblurring Radiance Fields
Jungho Lee, Dogyoon Lee, Minhyeok Lee +2
Neural radiance fields (NeRF) has attracted considerable attention for their exceptional ability in synthesizing novel views with high fidelity. However, the presence of motion blu…
Synchronizing Vision and Language: Bidirectional Token-Masking AutoEncoder for Referring Image Segmentation
Minhyeok Lee, Dogyoon Lee, Jungho Lee +4
Referring Image Segmentation (RIS) aims to segment target objects expressed in natural language within a scene at the pixel level. Various recent RIS models have achieved state-of-…
On the Amplification of Linguistic Bias through Unintentional Self-reinforcement Learning by Generative Language Models -- A Perspective
Minhyeok Lee
Generative Language Models (GLMs) have the potential to significantly shape our linguistic landscape due to their expansive use in various digital applications. However, this wides…
DuDGAN: Improving Class-Conditional GANs via Dual-Diffusion
Taesun Yeom, Minhyeok Lee
Class-conditional image generation using generative adversarial networks (GANs) has been investigated through various techniques; however, it continues to face challenges such as m…
ZIGNeRF: Zero-shot 3D Scene Representation with Invertible Generative Neural Radiance Fields
Kanghyeok Ko, Minhyeok Lee
Generative Neural Radiance Fields (NeRFs) have demonstrated remarkable proficiency in synthesizing multi-view images by learning the distribution of a set of unposed images. Despit…