Convolution-based and Transformer-based vision backbone networks process...
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...
In this paper, we focus on a recently proposed novel task called Audio-V...
Most of the existing blind image Super-Resolution (SR) methods assume th...
2D-based Industrial Anomaly Detection has been widely discussed, however...
The task of Few-shot Learning (FSL) aims to do the inference on novel
ca...
Few Shot Instance Segmentation (FSIS) requires models to detect and segm...
Positive-Unlabeled (PU) learning aims to learn a model with rare positiv...
The task of Few-shot learning (FSL) aims to transfer the knowledge learn...
Training deep neural network (DNN) with noisy labels is practically
chal...
Unsupervised Domain Adaptation (UDA) aims to adapt the model trained on ...
Motivated by biological evolution, this paper explains the rationality o...
Despite plenty of efforts focusing on improving the domain adaptation ab...
In the practical application of restoring low-resolution gray-scale imag...
Weakly supervised object localization (WSOL) aims to learn object locali...
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...
Non-Maximum Suppression (NMS) is essential for object detection and affe...
Inspired by biological evolution, we explain the rationality of Vision
T...
Recently, most siamese network based trackers locate targets via object
...
Temporal action localization is an important yet challenging task in vid...
For action recognition learning, 2D CNN-based methods are efficient but ...
Most recent semantic segmentation methods adopt a fully-convolutional ne...
Multiple Object Tracking (MOT) is an important task in computer vision. ...
Existing Multiple-Object Tracking (MOT) methods either follow the
tracki...
Motivated by the previous success of Two-Dimensional Convolutional Neura...
Cartoon face detection is a more challenging task than human face detect...
Unsupervised learning of optical flow, which leverages the supervision f...
In this paper, we propose a novel Automatic and Scalable Face Detector
(...
Efficiency is an important issue in designing video architectures for ac...
Generating temporal action proposals remains a very challenging problem,...
Recently, Convolutional Neural Network (CNN) has achieved great success ...