![Loading...](https://link.springer.com/static/c4a417b97a76cc2980e3c25e2271af3129e08bbe/images/pdf-preview/spacer.gif)
-
Chapter and Conference Paper
Dense Cross-Query-and-Support Attention Weighted Mask Aggregation for Few-Shot Segmentation
Research into Few-shot Semantic Segmentation (FSS) has attracted great attention, with the goal to segment target objects in a query image given only a few annotated support images of the target class. A key t...
-
Chapter and Conference Paper
Deep Image Clustering with Category-Style Representation
Deep clustering which adopts deep neural networks to obtain optimal representations for clustering has been widely studied recently. In this paper, we propose a novel deep image clustering framework to learn a...
-
Chapter and Conference Paper
Help Me! Sharing of Instructions Between Remote and Heterogeneous Robots
Service robots frequently face similar tasks. However, they are still not able to share their knowledge efficiently on how to accomplish those tasks. We introduce a new framework, which allows remote and heter...
-
Chapter and Conference Paper
Finding Frequent Items in Time Decayed Data Streams
Identifying frequently occurring items is a basic building block in many data stream applications. A great deal of work for efficiently identifying frequent items has been studied on the landmark and sliding w...
-
Chapter and Conference Paper
Improving Semi-supervised Text Classification by Using Wikipedia Knowledge
Semi-supervised text classification uses both labeled and unlabeled data to construct classifiers. The key issue is how to utilize the unlabeled data. Clustering based classification method outperforms other s...
-
Chapter and Conference Paper
OptRegion: Finding Optimal Region for Bichromatic Reverse Nearest Neighbors
The MaxBRNN problem is to find an optimal region such that setting up a new service site within this region might attract the maximal number of customers by proximity. It has many practical applications such a...
-
Chapter and Conference Paper
A Technique for Improving the Performance of Naive Bayes Text Classification
Naive Bayes classifier is widely used in text classification tasks, and it can perform surprisingly well, it is often regarded as a baseline. But previous researches show that the skewed distribution of traini...
-
Chapter and Conference Paper
Exploiting Semantic Hierarchies for Flickr Group
The development of Web 2.0 provides a convenient platform for on-line members to exchange information, keep contact with others and express oneselves. Flickr group, as a representative one, is a user-organized...
-
Chapter and Conference Paper
Composition Based Semantic Scene Retrieval for Ancient Murals
Retrieval of similar scenes in ancient murals research is an important but time-consuming job for researchers. However, content-based image retrieval (CBIR) systems cannot fully deal with such issues since the...
-
Chapter
Large Area Interactive Browsing for High Resolution Digitized Dunhuang Murals
The Dunhuang Motao Grottoes consist of about 45000 square meters murals, which are the most important part of the Dunhuang Art. As Dunhuang murals are rich in contents, large in sizes and amounts, high resolut...
-
Chapter and Conference Paper
Multi-projector Calibration and Alignment Using Flatness Analysis for Irregular-Shape Surfaces
A multi-projector calibration and alignment method, which has no assumptions on projection surfaces’ shape, is presented. Based on surface flatness analysis, the method will automatically partition the project...
-
Chapter and Conference Paper
Knowledge Based Lacunas Detection and Segmentation for Ancient Paintings
Lacunas are a common form of the damage that can occur to paintings and more often to murals. Taking Dunhuang murals as research background, a new algorithm to detect and segment the lacuna area from mural ima...
-
Chapter and Conference Paper
Interactive High Resolution Texture Map** for the 3D Models of Cultural Heritages
Virtual reconstruction of cultural heritage is not only the basis but also one of important contents of its digitized research. The techniques of interactive texture reconstruction researched in this article a...
-
Chapter and Conference Paper
An Ultra Large Area Scanner for Ancient Painting and Calligraphy
It is of great significance to digitize ancient paintings and calligraphy, especially for a country with five thousand years of history and rich cultural heritages. Millions of paintings and calligraphy are ha...
-
Chapter and Conference Paper
Color Changing and Fading Simulation for Frescoes Based on Empirical Knowledge from Artists
Visualizing the color changing and fading process of ancient Chinese wall paintings to tourists and researchers is of great value in both education and preservation. But previously, because empirical knowledge...
-
Chapter and Conference Paper
Style Strokes Extraction Based on Color and Shape Information
Taking Dunhuang MoGao Frescoes as research background, a new algorithm to extract style strokes from fresco images is proposed. All the pixels in a fresco image are classified into either the stroke objects or...
-
Chapter and Conference Paper
Worm Traffic Modeling for Network Performance Analysis
Worm research depends on simulation to a large degree due to worm propagation characters. In worm simulation, worm traffic generation is the base to analyze influences of worm traffic on network. The popular R...
-
Chapter and Conference Paper
An Integrated Color Changing Simulation System Based on Colorimetric and Chemical Modeling
Employing computer techniques to visualize the color changing of Dunhuang Frescoes is of great significance since the audience can re-experience this process and the protectors can discuss the protection measu...
-
Chapter and Conference Paper
A Novel Mechanism to Defend Against Low-Rate Denial-of-Service Attacks
Low-rate TCP-targeted Denial-of-Service (DoS) attack (shrew) is a new kind of DoS attack which is based on TCP’s Retransmission Timeout (RTO) mechanism and can severely reduce the throughput of TCP traffic on ...
-
Chapter and Conference Paper
Interactive Sketch Generation for Dunhuang Frescoes
Taking Dunhuang MoGao Frescoes as research background, a new method to generate the sketch for Dunhuang frescoes is proposed. Learning from the traditional manual imitation procedure, we first get the contour ...