double125

MADTP

MADTP: Multimodal Alignment-Guided Dynamic Token Pruning for Accelerating Vision-Language Transformer

Graph-Matching-Attention

Bilateral Cross-Modality Graph Matching Attention for Feature Fusion in Visual Question Answering

datamining_work

double125

Config files for my GitHub profile.

models

Pre-trained and Reproduced Deep Learning Models （『飞桨』官方模型库，包含多种学术前沿和工业场景验证的深度学习模型）