I may be slow to respond.
Block or Report
Block or report double125
Report abuse
Contact GitHub support about this user’s behavior. Learn more about reporting abuse.
Report abuse-
MADTP Public
MADTP: Multimodal Alignment-Guided Dynamic Token Pruning for Accelerating Vision-Language Transformer
-
Graph-Matching-Attention Public
Bilateral Cross-Modality Graph Matching Attention for Feature Fusion in Visual Question Answering
-
-
models Public
Forked from PaddlePaddle/modelsPre-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)
Python Apache License 2.0 UpdatedSep 3, 2019 -