scholarly journals Segmenting Handwritten Math Symbols Using AdaBoost and Multi-scale Shape Context Features

2013 ◽  
Author(s):  
Lei Hu ◽  
Richard Zanibbi
Keyword(s):  
Shape Context ◽  
Multi Scale ◽  
Context Features

Action Recognition

2010 ◽  
pp. 228-243
Author(s):  
Qingdi Wei ◽  
Xiaoqin Zhang ◽  
Weiming Hu
Keyword(s):  
Action Recognition ◽  
Mean Shift ◽  
Human Action ◽  
Shape Context ◽  
Research Fields ◽  
Dominant Set ◽  
Novel Method ◽  
Active Research ◽  
Context Features ◽  
Human Silhouette

Action recognition is one of the most active research fields in computer vision. This chapter first reviews the action recognition methods in literature from two aspects: action representation and recognition strategy. Then, a novel method for classifying human actions from image sequences is investigated. In this method, each human action is represented by a sequence of shape context features of human silhouette during the action, and a dominant set-based approach is employed to classify the action to the predefined classes. The dominant set-based approach to classification is compared with K-means, mean shift, and Fuzzy-Cmean approaches.

scholarly journals Attention-Based Multi-Context Guiding for Few-Shot Semantic Segmentation

2019 ◽  
Vol 33 ◽  
pp. 8441-8448 ◽  
Author(s):  
Tao Hu ◽  
Pengwan Yang ◽  
Chiliang Zhang ◽  
Gang Yu ◽  
Yadong Mu ◽  
...  
Keyword(s):  
Deep Learning ◽  
Feature Fusion ◽  
State Of The Art ◽  
Semantic Segmentation ◽  
Research Topic ◽  
Context Information ◽  
Multi Scale ◽  
Support Set ◽  
Segmentation Task ◽  
Context Features

Few-shot learning is a nascent research topic, motivated by the fact that traditional deep learning methods require tremendous amounts of data. The scarcity of annotated data becomes even more challenging in semantic segmentation since pixellevel annotation in segmentation task is more labor-intensive to acquire. To tackle this issue, we propose an Attentionbased Multi-Context Guiding (A-MCG) network, which consists of three branches: the support branch, the query branch, the feature fusion branch. A key differentiator of A-MCG is the integration of multi-scale context features between support and query branches, enforcing a better guidance from the support set. In addition, we also adopt a spatial attention along the fusion branch to highlight context information from several scales, enhancing self-supervision in one-shot learning. To address the fusion problem in multi-shot learning, Conv-LSTM is adopted to collaboratively integrate the sequential support features to elevate the final accuracy. Our architecture obtains state-of-the-art on unseen classes in a variant of PASCAL VOC12 dataset and performs favorably against previous work with large gains of 1.1%, 1.4% measured in mIoU in the 1-shot and 5-shot setting.

scholarly journals Building Change Detection Using a Shape Context Similarity Model for LiDAR Data

2020 ◽  
Vol 9 (11) ◽  
pp. 678
Author(s):  
Xuzhe Lyu ◽  
Ming Hao ◽  
Wenzhong Shi
Keyword(s):  
Change Detection ◽  
Detection Methods ◽  
Lidar Data ◽  
Shape Context ◽  
Multi Scale ◽  
Detection Approach ◽  
Context Similarity ◽  
Surface Models ◽  
Similarity Model ◽  
The Difference

In this paper, a novel building change detection approach is proposed using statistical region merging (SRM) and a shape context similarity model for Light Detection and Ranging (LiDAR) data. First, digital surface models (DSMs) are generated from LiDAR acquired at two different epochs, and the difference data D-DSM is created by difference processing. Second, to reduce the noise and registration error of the pixel-based method, the SRM algorithm is applied to segment the D-DSM, and multi-scale segmentation results are obtained under different scale values. Then, the shape context similarity model is used to calculate the shape similarity between the segmented objects and the buildings. Finally, the refined building change map is produced by the k-means clustering method based on shape context similarity and area-to-length ratio. The experimental results indicated that the proposed method could effectively improve the accuracy of building change detection compared with some popular change detection methods.

scholarly journals Multi-Level Context Pyramid Network for Visual Sentiment Analysis

Sensors ◽  
2021 ◽  
Vol 21 (6) ◽  
pp. 2136
Author(s):  
Haochun Ou ◽  
Chunmei Qing ◽  
Xiangmin Xu ◽  
Jianxiu Jin
Keyword(s):  
Sentiment Analysis ◽  
Classification Performance ◽  
Global Perspective ◽  
Visual Content ◽  
Multi Scale ◽  
Emotional Representation ◽  
Correlation Degree ◽  
Multi Level ◽  
Context Features ◽  
Emotional Representations

Sharing our feelings through content with images and short videos is one main way of expression on social networks. Visual content can affect people’s emotions, which makes the task of analyzing the sentimental information of visual content more and more concerned. Most of the current methods focus on how to improve the local emotional representations to get better performance of sentiment analysis and ignore the problem of how to perceive objects of different scales and different emotional intensity in complex scenes. In this paper, based on the alterable scale and multi-level local regional emotional affinity analysis under the global perspective, we propose a multi-level context pyramid network (MCPNet) for visual sentiment analysis by combining local and global representations to improve the classification performance. Firstly, Resnet101 is employed as backbone to obtain multi-level emotional representation representing different degrees of semantic information and detailed information. Next, the multi-scale adaptive context modules (MACM) are proposed to learn the sentiment correlation degree of different regions for different scale in the image, and to extract the multi-scale context features for each level deep representation. Finally, different levels of context features are combined to obtain the multi-cue sentimental feature for image sentiment classification. Extensive experimental results on seven commonly used visual sentiment datasets illustrate that our method outperforms the state-of-the-art methods, especially the accuracy on the FI dataset exceeds 90%.

Sign in / Sign up

Export Citation Format

Share Document