How to enable learnability for new classes while keeping the capability ...
Visual Grounding (VG) aims at localizing target objects from an image ba...
Panoptic Scene Graph (PSG) is a challenging task in Scene Graph Generati...
With the rise of large-scale models trained on broad data, in-context
le...
Change detection is an essential and widely utilized task in remote sens...
Visual segmentation seeks to partition images, video frames, or point cl...
The goal of video segmentation is to accurately segment and track every ...
Few-shot class-incremental learning (FSCIL) has been a challenging probl...
Few Shot Instance Segmentation (FSIS) requires models to detect and segm...
Panoptic Part Segmentation (PPS) unifies panoptic segmentation and part
...
In this work, we focus on instance-level open vocabulary segmentation,
i...
Attention-based neural networks, such as Transformers, have become ubiqu...
Referring Image Segmentation (RIS) aims to connect image and language vi...
In this paper, we focus on exploring effective methods for faster, accur...
Motivated by biological evolution, this paper explains the rationality o...
This paper presents Video K-Net, a simple, strong, and unified framework...
Panoptic Part Segmentation (PPS) aims to unify panoptic segmentation and...
Human fashion understanding is one important computer vision task since ...
Modern deep neural networks for classification usually jointly learn a
b...
Detection Transformer (DETR) and Deformable DETR have been proposed to
e...
Video Instance Segmentation (VIS) is a new and inherently multi-task pro...
Modelling long-range contextual relationships is critical for pixel-wise...
We propose a novel method for fine-grained high-quality image segmentati...
Representation of semantic context and local details is the essential is...
In this paper, we propose an effective method for fast and accurate scen...
Recently, DETR and Deformable DETR have been proposed to eliminate the n...
Glass-like objects such as windows, bottles, and mirrors exist widely in...
Aerial Image Segmentation is a particular semantic segmentation problem ...
Graph-based convolutional model such as non-local block has shown to be
...
Existing semantic segmentation approaches either aim to improve the obje...
In this paper, we focus on effective methods for fast and accurate scene...
It has been widely proven that modelling long-range dependencies in full...
Exploiting long-range contextual information is key for pixel-wise predi...
Semantic segmentation generates comprehensive understanding of scenes at...