2025
DLM-VMTL: A Double LayerMapper For Heterogeneous Data Video Multi-Task Prompt Learning
ICASSP 2025accepted
In recent years, the parameters of backbones of Video Understanding tasks continue to increase and even reach billion-level. Whether fine-tuning a specific task on the Video Foundation Models(VFMs) or pre-training the model designed for the specific task, incurs significant overhead. How to enable t…