← Search

Yi-Ting Shen

4 accepted papers

2025

AutoComPose: Automatic Generation of Pose Transition Descriptions for Composed Pose Retrieval Using Multimodal LLMs

ICCV 2025poster

Composed pose retrieval (CPR) enables users to search for human poses by specifying a reference pose and a transition description, but progress in this field is hindered by the scarcity and inconsistency of annotated pose transitions. Existing CPR datasets rely on costly human annotations or heurist…

Cited by 0SourcePDFScholar
2024

Real-Time Privacy-Preserving Fall Risk Assessment with a Single Body-Worn Tracking Camera

ICASSP 2024accepted

Falls are a major cause of injury among elderly adults. In addition, recent research indicates that elderly adults often fall because of the same individual biomechanical causes. Therefore, real-time individual fall risk assessment is crucial for designing a more effective and personalized fall redu…

Cited by 0SourceScholar
2023

Progressive Transformation Learning for Leveraging Virtual Images in Training

CVPR 2023highlight

To effectively interrogate UAV-based images for detecting objects of interest, such as humans, it is essential to acquire large-scale UAV-based datasets that include human instances with various poses captured from widely varying viewing angles. As a viable alternative to laborious and costly data c…

Cited by 12SourcePDFScholar
2019

What Synthesis Is Missing: Depth Adaptation Integrated With Weak Supervision for Indoor Scene Parsing

ICCV 2019poster

Scene Parsing is a crucial step to enable autonomous systems to understand and interact with their surroundings. Supervised deep learning methods have made great progress in solving scene parsing problems, however, come at the cost of laborious manual pixel-level annotation. Synthetic data as well a…

Cited by 5PDFScholar