The gap between low-level visual signals and high-level semantics has be...
Knowledge distillation has been widely adopted in a variety of tasks and...
Image inpainting has achieved remarkable progress and inspired abundant
...
Domain adaptation (DA) tries to tackle the scenarios when the test data ...
Multi-label classification aims to recognize multiple objects or attribu...
In this paper, we present HoloBoard, an interactive large-format
pseudo-...
Distance metric learning is successful in discovering intrinsic relation...
Food is essential for human life and it is fundamental to the human
expe...
Deep learning has achieved substantial success in a series of tasks in
c...
We present in this paper a systematic study on how to morph a well-train...
Automatically describing video content with natural language is a fundam...
Convolutional Neural Networks (CNNs) have achieved comparable error rate...
Visual reranking is effective to improve the performance of the text-bas...