Cite
Notes
Only stored in your browser.
Attribution
VPTracker: Global Vision-Language Tracking via Visual Prompt and MLLM
arXiv 2025
Unlocking the Potential of MLLMs in Referring Expression Segmentation via a Light-weight Mask Decoder
from 2 papers
Dingjiang Huang
Jingchao Wang
Yefeng Zheng
Hong Wang
Kaiwen Zhou
Kunhua Ji