2 papers
cs.CV2024
MambaVLT: Time-Evolving Multimodal State Space Model for Vision-Language Tracking
Xinqi Liu, Li Zhou, Zikun Zhou +2
The vision-language tracking task aims to perform object tracking based on various modality references. Existing Transformer-based vision-language tracking methods have made remark…
cs.CV2024
Instruction-guided Multi-Granularity Segmentation and Captioning with Large Multimodal Model
Li Zhou, Xu Yuan, Zenghui Sun +2
Large Multimodal Models (LMMs) have achieved significant progress by extending large language models. Building on this progress, the latest developments in LMMs demonstrate the abi…