We propose TR0N, a highly general framework to turn pre-trained uncondit...
In text-video retrieval, the objective is to learn a cross-modal similar...
Localizing actions in video is a core task in computer vision. The weakl...
We present a novel Cross-Class Relevance Learning approach for the task ...
We present our solution to Landmark Image Retrieval Challenge 2019. This...
Text-to-Image translation has been an active area of research in the rec...