15 Result(s)
-
Article
MadFormer: multi-attention-driven image super-resolution method based on Transformer
While the Transformer-based method has demonstrated exceptional performance in low-level visual processing tasks, it has a strong modeling ability only locally, thereby neglecting the importance of spatial fea...
-
Article
A cross-view geo-localization method guided by relation-aware global attention
Cross-view geo-localization mainly exploits query images to match images from the same geographical location from different platforms. Most existing methods fail to adequately consider the effect of image stru...
-
Article
Style transfer network for complex multi-stroke text
Neural style transfer has achieved success in many tasks. It is also introduced to text style transfer, which uses a style image to generate transferred images with textures and shapes consistent with the sema...
-
Article
Deblurring transformer tracking with conditional cross-attention
In object tracking, motion blur is a common challenge induced by rapid movement of target object or long time exposure of the camera, which leads to poor tracking performance. Traditional solutions usually per...
-
Article
Context and saliency aware correlation filter for visual tracking
Visual tracking in complex scenarios is a big challenge in the computer vision community. Due to correlation filter (CF) recently have achieved excellent results both on accuracy and robustness in visual track...
-
Article
AMTSet: a benchmark for abrupt motion tracking
Since the OTB100 benchmark dataset is released, it has been widely used in a large number of researches on object tracking for performance evaluation. However, the existing datasets are insufficient to evaluat...
-
Chapter and Conference Paper
Towards Stereo Matching Algorithm Based on Multi-matching Primitive Fusion
Classical adaptive support weight (ASW) algorithm has poor robustness and high computational complexity for stereo matching in the case of relatively low texture and complex texture regions. To solve this issu...
-
Chapter and Conference Paper
Parameter Selection for Denoising Algorithms Using NR-IQA with CNN
In order to yield satisfied image after denosing processing, the process of error tracing is nearly necessary for parameter selection. In practice, usually the choice of such parameters is time consuming and e...
-
Chapter and Conference Paper
Incremental Nonnegative Matrix Factorization with Sparseness Constraint for Image Representation
Nonnegative matrix factorization (NMF) is a powerful method of data dimension reduction and has been widely used in face recognition. However, existing NMF algorithms have two main drawbacks. One is that the s...
-
Article
Social video annotation by combining features with a tri-adaptation approach
Online social video websites such as YouTube allow users to manually annotate their video documents with textual labels. These labels can be used as indexing keywords to facilitate search and organization of v...
-
Article
Active learning SVM with regularization path for image classification
In classification problems, many different active learning techniques are often adopted to find the most informative samples for labeling in order to save human labors. Among them, active learning support vect...
-
Chapter and Conference Paper
Robust Multi-label Image Classification with Semi-Supervised Learning and Active Learning
Most existing work on multi-label learning focused on supervised learning which requires manual annotation samples that is labor-intensive, time-consuming and costly. To address such a problem, we present a no...
-
Chapter and Conference Paper
High-Level Video Semantic Concept Detection Based on Multi-level Feature Representations
Semantic concept detection is a fundamental problem with many practical applications such as concept-based video retrieval. The major challenge of concept detection lies in the existence of the well-known sema...
-
Chapter and Conference Paper
Compact and Robust Image Fingerprints Based on CCA of Local Features
Image fingerprints are perceptual features or short summaries of a given image. They can be used for identifying image contents just as human fingerprints are used for identification. In this paper, we propose...
-
Chapter and Conference Paper
Robust Detection and Localization of Human Action in Video
We propose a robust and efficient method for accurate detecting and localizing complex human action in video in space and time dimensions using spatio-temporal templates. A simple but effective motion descript...
