This report describes our solution to the VALUE Challenge 2021 in the
ca...
Video advertisement content structuring aims to segment a given video
ad...
The defect detection task can be regarded as a realistic scenario of obj...
We study joint learning of Convolutional Neural Network (CNN) and Transf...
Contrastive learning has delivered impressive results in many audio-visu...
Deep networks achieve excellent results on large-scale clean data but de...
We propose Pixel-BERT to align image pixels with text by deep multi-moda...
We propose to boost VQA by leveraging more powerful feature extractors b...
"SMP Challenge" aims to discover novel prediction tasks for numerous dat...
We study on weakly-supervised object detection (WSOD) which plays a vita...
Contextual reasoning is essential to understand events in long untrimmed...