Despite recent advances in semantic segmentation, an inevitable challeng...
3D point cloud visual grounding plays a critical role in 3D scene
compre...
Convolution-based and Transformer-based vision backbone networks process...
Image-to-text generation aims to describe images using natural language....
Glass-like objects are widespread in daily life but remain intractable t...
Change detection is a widely adopted technique in remote sense imagery (...
Image harmonization aims to solve the visual inconsistency problem in
co...
Recently, emotional talking face generation has received considerable
at...
Weak feature representation problem has influenced the performance of
fe...
We propose a novel visual re-localization method based on direct matchin...
Most of the existing blind image Super-Resolution (SR) methods assume th...
Auto-Regressive (AR) models have achieved impressive results in 2D image...
2D-based Industrial Anomaly Detection has been widely discussed, however...
Image anomaly detection (IAD) is an emerging and vital computer vision t...
The recent rapid development of deep learning has laid a milestone in
in...
Few Shot Instance Segmentation (FSIS) requires models to detect and segm...
The task of Few-shot learning (FSL) aims to transfer the knowledge learn...
Incremental semantic segmentation(ISS) is an emerging task where old mod...
Few-shot learning problem focuses on recognizing unseen classes given a ...
Few-Shot Learning (FSL) alleviates the data shortage challenge via embed...
Bird's eye view (BEV) is widely adopted by most of the current point clo...
Accurate and reliable sensor calibration is critical for fusing LiDAR an...
To achieve promising results on blind image super-resolution (SR), some
...
In this paper, we present the Multi-Forgery Detection Challenge held
con...
Point cloud completion has become increasingly popular among generation ...
Local image feature matching, aiming to identify and correspond similar
...
Unsupervised Domain Adaptation (UDA) aims to adapt the model trained on ...
Motivated by biological evolution, this paper explains the rationality o...
Change detection (CD) aims to identify changes that occur in an image pa...
Prevailing video frame interpolation algorithms, that generate the
inter...
Accurate sensor calibration is a prerequisite for multi-sensor perceptio...
Most prior work represents the shapes of point clouds by coordinates.
Ho...
Spotting camouflaged objects that are visually assimilated into the
back...
Generating artistic portraits is a challenging problem in computer visio...
Despite plenty of efforts focusing on improving the domain adaptation ab...
Pseudo-label-based semi-supervised learning (SSL) has achieved great suc...
Visual sensory anomaly detection (AD) is an essential problem in compute...
Recently, there is growing attention on one-stage panoptic segmentation
...
Weakly supervised object localization (WSOL) aims to learn object locali...
Recent progress in few-shot learning promotes a more realistic cross-dom...
Few-shot semantic segmentation aims to segment novel-class objects in a ...
In this paper, we place the atomic action detection problem into a Long-...
Localizing individuals in crowds is more in accordance with the practica...
Recently, the problem of inaccurate learning targets in crowd counting d...
In this work, we propose a high fidelity face swapping method, called
Hi...
Non-parametric face modeling aims to reconstruct 3D face only from image...
Recent advances in image inpainting have shown impressive results for
ge...
Inspired by biological evolution, we explain the rationality of Vision
T...
Recently, most siamese network based trackers locate targets via object
...
Few-shot semantic segmentation aims to segment novel-class objects in a ...