Video-based scene graph generation (VidSGG) is an approach that aims to
...
This work addresses the challenging domain adaptation setting in which
k...
In this paper, we focus on an under-explored issue of biased activation ...
Current video-based scene graph generation (VidSGG) methods have been fo...
Weakly-supervised object localization aims to indicate the category as w...
A thriving trend for domain adaptive segmentation endeavors to generate ...
We explore the task of language-guided video segmentation (LVS). Previou...
The expensive annotation cost is notoriously known as a main constraint ...
Unsupervised domain adaptive person re-identification has received
signi...
We focus on the problem of segmenting a certain object referred by a nat...
Few-shot segmentation (FSS) performance has been extensively promoted by...
In this paper, we investigate the task of hallucinating an authentic
hig...
The recent emerged weakly supervised object localization (WSOL) methods ...
Text-based video segmentation is a challenging task that segments out th...
With daily observation and prior knowledge, it is easy for us human to i...
We aim at the problem named One-Shot Unsupervised Domain Adaptation. Unl...
Existing face hallucination methods based on convolutional neural networ...
For unsupervised domain adaptation problems, the strategy of aligning th...
Graph convolutional network (GCN) provides a powerful means for graph-ba...
We consider the problem of unsupervised domain adaptation in semantic
se...
In human parsing, the pixel-wise classification loss has drawbacks in it...