CVPRMay, 2024
DTLLM-VLT: 基于 LLM 的视觉语言跟踪多样化文本生成
DTLLM-VLT: Diverse Text Generation for Visual Language Tracking Based on LLM
Xuchen Li, Xiaokun Feng, Shiyu Hu, Meiqi Wu, Dailing Zhang...
TL;DRVisual Language Tracking (VLT) leverages multi-granularity text descriptions to enhance single object tracking (SOT) by providing fine-grained evaluation of multi-modal trackers.