2 papers
cs.LG2026
Task-Specific Prompt with Global Context for Multi-Task Graph Pre-Training
Zhiyang Qiu, Yangtao Wang, Xiaocui Li +3
Graph prompt learning is an effective paradigm to adapt pre-trained graph models to downstream tasks in low-resource scenarios. However, existing multi-task graph pre-training fram…
cs.CV2025
Leveraging Vision-Language Large Models for Interpretable Video Action Recognition with Semantic Tokenization
Jingwei Peng, Zhixuan Qiu, Boyu Jin +1
Human action recognition often struggles with deep semantic understanding, complex contextual information, and fine-grained distinction, limitations that traditional methods freque…