default author photo

Haoyu Zhang

affiliation not provided to SSRN

SCHOLARLY PAPERS

1

DOWNLOADS

8

TOTAL CITATIONS

0

Scholarly Papers (1)

1.

Refsam: Efficiently Adapting Segmenting Anything Model for Referring Video Object Segmentation

Number of pages: 35 Posted: 07 May 2025
National University of Defense Technology, The University of Sydney, National University of Defense Technology, affiliation not provided to SSRN, National University of Defense Technology and National University of Defense Technology
Downloads 8 (1,555,090)

Abstract:

Loading...

Object Segmentation, Vision Transformer, Multimodal learning, Segment Anything