Yung-Hsu Yang

RoyYang0714

·

https://royyang0714.github.io/

AI & ML interests

Computer Vision & 3D Scene Understanding

Recent Activity

authored a paper about 15 hours ago

EgoTrack3D: A Modular Framework for Egocentric 3D Object Tracking

authored a paper 12 days ago

DVPSFormer: Efficient Online Depth-aware Video Panoptic Segmentation for Autonomous Driving

authored a paper 12 days ago

LIME: Learning Intent-aware Camera Motion from Egocentric Video

View all activity

Organizations

Papers 15

arxiv:2608.08016

arxiv:2607.26165

arxiv:2607.02417

arxiv:2512.05663

spaces 1

3D MOOD

Identify 3D objects in images using text prompts

models 4

RoyYang0714/dvpsformer_r50_cityscapes-dvps

Updated 12 days ago • 22

RoyYang0714/dvpsformer_r50_semkitti-dvps

Updated 12 days ago • 29

RoyYang0714/3D-MOOD

Image-to-3D • Updated Sep 8, 2025 • 2

RoyYang0714/cc-3dt

Updated Jul 21, 2025

datasets 1

RoyYang0714/3D-MOOD

Updated Sep 8, 2025 • 255 • 2