Commonly used backbones for semantic segmentation, such as ResNet and
Sw...
Semantic segmentation has recently achieved notable advances by exploiti...
In this work, we study the black-box targeted attack problem from the mo...
In medical image segmentation, it is often necessary to collect opinions...
Motion transfer aims to transfer the motion of a driving video to a sour...
Image animation aims to animate a source image by using motion learned f...
On the medical images, many of the tissues/lesions may be ambiguous. Tha...
Detection transformers like DETR have recently shown promising performan...
Existing works typically treat cross-domain semantic segmentation (CDSS)...
Given a source image and a driving video depicting the same object type,...
The goal of video highlight detection is to select the most attractive
s...
Cold-start issues have been more and more challenging for providing accu...
Creative image animations are attractive in e-commerce applications, whe...
Video super-resolution has recently become one of the most important
mob...
Cold-start has being a critical issue in recommender systems with the
ex...
While deep learning has been successfully applied to many real-world com...
Multi-agent motion prediction is challenging because it aims to foresee ...
In this paper, we present a novel deep metric learning method to tackle ...
Cross-domain object detection has recently attracted more and more atten...
Zero-Shot Learning (ZSL) aims to learn recognition models for recognizin...
Cross domain object detection is challenging, because object detection m...
We study the problem of visual question answering (VQA) in images by
exp...
We propose a new approach, called self-motivated pyramid curriculum doma...
Visual question answering by using information from multiple modalities ...
Partial domain adaptation aims to transfer knowledge from a label-rich s...
Existing domain adaptation methods generally assume different domains ha...
How to effectively learn from unlabeled data from the target domain is
c...
Action recognition in videos has attracted a lot of attention in the pas...
Existing deep learning methods of video recognition usually require a la...
Along with the prosperity of recurrent neural network in modelling seque...