Learning novel classes from a very few labeled samples has attracted
inc...
Conventional detection networks usually need abundant labeled training
s...
In this paper, we propose a multi-stage and high-resolution model for im...
In this paper, we investigate the problem of text-to-pedestrian synthesi...
Automatically learning features, especially robust features, has attract...
Zero-shot learning, which studies the problem of object classification f...
Zero-shot recognition aims to accurately recognize objects of unseen cla...
Visual question answering (VQA) has witnessed great progress since May, ...
This note presents some representative methods which are based on dictio...