Fashion vision-language pre-training models have shown efficacy for a wi...
Fine-grained supervision based on object annotations has been widely use...
Cross-model retrieval has emerged as one of the most important upgrades ...
Graph convolutional network (GCN) has become popular in various natural
...
Few-shot learning is a challenging task, which aims to learn a classifie...
Neural image inpainting has achieved promising performance in generating...
Integrating visual features has been proved useful in language represent...