3 papers
cs.CV2026
Auditing Training-Free 3D Shape Retrieval with Diffused Geodesic Moments
Zhicheng Du, Changyue Liu, Wenji Xi +5
Reported retrieval scores for training-free shape descriptors conflate local signal design, normalization, aggregation, codebook fitting, and metric choices, making isolated compon…
cs.CV2024
Cognitive resilience: Unraveling the proficiency of image-captioning models to interpret masked visual content
Zhicheng Du, Zhaotian Xie, Huazhang Ying +2
This study explores the ability of Image Captioning (IC) models to decode masked visual content sourced from diverse datasets. Our findings reveal the IC model's capability to gene…
cs.AI2024
LAMPER: LanguAge Model and Prompt EngineeRing for zero-shot time series classification
Zhicheng Du, Zhaotian Xie, Yan Tong +1
This study constructs the LanguAge Model with Prompt EngineeRing (LAMPER) framework, designed to systematically evaluate the adaptability of pre-trained language models (PLMs) in a…