6 papers · 1 filter
V-LynX: Token Interface Alignment for Video+X LLMs
Jungin Park, Jiyoung Lee, Kwanghoon Sohn
This study introduces an intriguing phenomenon in Video LLMs: rather than merely translating frames into textual embeddings, Video LLMs establish a continuous manifold, token inter…
Language-guided Recursive Spatiotemporal Graph Modeling for Video Summarization
Jungin Park, Jiyoung Lee, Kwanghoon Sohn
Video summarization aims to select keyframes that are visually diverse and can represent the whole story of a given video. Previous approaches have focused on global interlinkabili…
PointFix: Learning to Fix Domain Bias for Robust Online Stereo Adaptation
Kwonyoung Kim, Jungin Park, Jiyoung Lee +2
Online stereo adaptation tackles the domain shift problem, caused by different environments between synthetic (training) and real (test) datasets, to promptly adapt stereo models i…
Bootstrap Your Own Views: Masked Ego-Exo Modeling for Fine-grained View-invariant Video Representations
Jungin Park, Jiyoung Lee, Kwanghoon Sohn
View-invariant representation learning from egocentric (first-person, ego) and exocentric (third-person, exo) videos is a promising approach toward generalizing video understanding…
Bridging Vision and Language Spaces with Assignment Prediction
Jungin Park, Jiyoung Lee, Kwanghoon Sohn
This paper introduces VLAP, a novel approach that bridges pretrained vision models and large language models (LLMs) to make frozen LLMs understand the visual world. VLAP transforms…
Let 2D Diffusion Model Know 3D-Consistency for Robust Text-to-3D Generation
Junyoung Seo, Wooseok Jang, Min-Seop Kwak +6
Text-to-3D generation has shown rapid progress in recent days with the advent of score distillation, a methodology of using pretrained text-to-2D diffusion models to optimize neura…