We present CLUSTSEG, a general, transformer-based framework that tackles...
This paper proposes an anchor-based deformation model, namely AnchorDEF,...
The objective of this paper is self-supervised learning of video object
...
Federated learning is a distributed paradigm that allows multiple partie...
Partitioning an image into superpixels based on the similarity of pixels...
We devise deep nearest centroids (DNC), a conceptually elegant yet
surpr...
Prevalent semantic segmentation solutions, despite their different netwo...
Humans are able to recognize structured relations in observation, allowi...
Our target is to learn visual correspondence from unlabeled videos. We
d...
Abductive reasoning seeks the likeliest possible explanation for partial...
We explore the task of language-guided video segmentation (LVS). Previou...
Learning semantic segmentation from weakly-labeled (e.g., image tags onl...
Recently, numerous algorithms have been developed to tackle the problem ...
Magnetic resonance (MR) imaging is a commonly used scanning technique fo...
Video segmentation, i.e., partitioning video frames into multiple segmen...
Despite recent progress of automatic medical image segmentation techniqu...
Referring video object segmentation (RVOS) aims to segment video objects...
This paper addresses the task of unsupervised video multi-object
segment...
On existing public benchmarks, face forgery detection techniques have
ac...
To address the challenging task of instance-aware human part parsing, a ...
Chest X-rays are an important and accessible clinical imaging tool for t...
Current semantic segmentation methods focus only on mining "local" conte...
Acquiring sufficient ground-truth supervision to train deep visual model...
It is laborious to manually label point cloud data for training high-qua...
How to make a segmentation model to efficiently adapt to a specific vide...
Rapid progress has been witnessed for human-object interaction (HOI)
rec...
In this paper, we present a novel Motion-Attentive Transition Network
(M...
Multiple Instance Learning (MIL) recently provides an appealing way to
a...
Stochastic sampling based trackers have shown good performance for abrup...