Filters








3,417 Hits in 9.2 sec

Fine-grained social relationship extraction from real activity data under coarse supervision

Kota Tsubouchi, Osamu Saisho, Junichi Sato, Seira Araki, Masamichi Shimosaka
2015 Proceedings of the 2015 ACM International Symposium on Wearable Computers - ISWC '15  
Our approach improve detection accuracy and achieve extraction of fine-grained relationships from coarse supervision data.  ...  We therefore focus on improving the accuracy of detection and propose a novel fine-grained social relationship extraction from coarse supervision data by supervised approach based on multiple instance  ...  Thus, we can extract fine-grained social relationships only from activity data and coarse questionnaire data.  ... 
doi:10.1145/2802083.2808402 dblp:conf/iswc/TsubouchiSSAS15 fatcat:nc2lhgdx3zfhvbtkhcneic6p34

Revisiting Local Descriptors via Frequent Pattern Mining for Fine-Grained Image Retrieval

Min Zheng, Yangliao Geng, Qingyong Li
2022 Entropy  
The main difficulty of this task derives from the small interclass distinction and the large intraclass variance of fine-grained images, posing severe challenges to the methods that only resort to global  ...  Fine-grained image retrieval aims at searching relevant images among fine-grained classes given a query.  ...  Data Availability Statement: Not applicable. Conflicts of Interest: The authors declare no conflict of interest. Entropy 2022, 24, 156  ... 
doi:10.3390/e24020156 pmid:35205452 pmcid:PMC8871172 fatcat:skhn7z2khff67gjb7x4a6wbxne

Cross-category Video Highlight Detection via Set-based Learning [article]

Minghao Xu, Hang Wang, Bingbing Ni, Riheng Zhu, Zhenbang Sun, Changhu Wang
2021 arXiv   pre-print
To attain this goal in a data-driven way, one may often face the situation where highlight annotations are not available on the target video category used in practice, while the supervision on another  ...  Autonomous highlight detection is crucial for enhancing the efficiency of video browsing on social media platforms.  ...  When the two learners are individually applied, the coarse-grained learner outperforms the fine-grained one, which, we think, is because the supervision for coarse-grained learner is more relevant to the  ... 
arXiv:2108.11770v1 fatcat:763ihi5cmvarhjgl6x3t5ac4je

Image Sentiment Analysis via Active Sample Refinement and Cluster Correlation Mining

Hongbin Zhang, Haowei Shi, Jingyi Hou, Qipeng Xiong, Donghong Ji, Yugen Yi
2022 Computational Intelligence and Neuroscience  
Meanwhile, the ASR strategy is a useful supplement to the current data augmentation method.  ...  To address this problem, we propose an active sample refinement (ASR) strategy to obtain sufficient high-quality images with definite sentiment semantics.  ...  available social media data.  ... 
doi:10.1155/2022/2477605 fatcat:grdujoicq5bzvgfmp7lvuxhly4

Fine-grained Prediction of Political Leaning on Social Media with Unsupervised Deep Learning

Tiziano Fagni, Stefano Cresci
2022 The Journal of Artificial Intelligence Research  
Here, we propose a novel unsupervised technique for learning fine-grained political leaning from the textual content of social media posts.  ...  Other than being interesting on their own, our results also pave the way for the development of new and better unsupervised approaches for the detection of fine-grained political leaning.  ...  ++: European Integrated Infrastructure for Social Mining and Big Data Analytics.  ... 
doi:10.1613/jair.1.13112 fatcat:x3jhn7kerbebbnuev24kmxsd7m

C2FHAR: Coarse-to-Fine Human Activity Recognition with Behavioral Context Modeling using Smart Inertial Sensors

Muhammad Ehatisham-ul-Haq, Muhammad Awais Azam, Yasar Amin, Usman Naeem
2020 IEEE Access  
or fine-grained, depending upon the real-time use-cases.  ...  living to learn and recognize the fine-grained human activities.  ...  In this way, the proposed scheme offers either coarse or fine-grained activity representation in-thewild based on real-time scenarios and use-cases.  ... 
doi:10.1109/access.2020.2964237 fatcat:zxmbpn3elrbelowwfldib3vhyi

Predictive Analysis on Twitter: Techniques and Applications [chapter]

Ugur Kursuncu, Manas Gaur, Usha Lokala, Krishnaprasad Thirunarayan, Amit Sheth, I. Budak Arpinar
2018 Lecture Notes in Social Networks  
Specifically, we present fine-grained analysis involving aspects such as sentiment, emotion, and the use of domain knowledge in the coarse-grained analysis of Twitter data for making decisions and taking  ...  Predictive analysis of social media data has attracted considerable attention from the research community as well as the business world because of the essential and actionable information it can provide  ...  This paradigm contains two levels of analysis: fine-grained and coarse-grained.  ... 
doi:10.1007/978-3-319-94105-9_4 fatcat:knquzcuqcjdjjguzq435nq5kni

Predictive Analysis on Twitter: Techniques and Applications [article]

Ugur Kursuncu, Manas Gaur, Usha Lokala, Krishnaprasad Thirunarayan, Amit Sheth, I. Budak Arpinar
2018 arXiv   pre-print
Specifically, we present fine-grained analysis involving aspects such as sentiment, emotion, and the use of domain knowledge in the coarse-grained analysis of Twitter data for making decisions and taking  ...  Predictive analysis of social media data has attracted considerable attention from the research community as well as the business world because of the essential and actionable information it can provide  ...  This paradigm contains two levels of analysis: fine-grained and coarse-grained.  ... 
arXiv:1806.02377v1 fatcat:gm5cqpmgvfggzgxgzocv4c3fqi

MIntRec: A New Dataset for Multimodal Intent Recognition [article]

Hanlei Zhang, Hua Xu, Xin Wang, Qianrui Zhou, Shaojie Zhao, Jiayan Teng
2022 arXiv   pre-print
It formulates coarse-grained and fine-grained intent taxonomies based on the data collected from the TV series Superstore.  ...  We extract features from each modality and model cross-modal interactions by adapting three powerful multimodal fusion methods to build baselines.  ...  Then, we design both coarse-grained and fine-grained intent taxonomies for the multimodal scene.  ... 
arXiv:2209.04355v1 fatcat:o4tubilyxrbvhf2vhhlnp5fs4e

Construction of a Mental Health Education Model for College Students Based on Fine-Grained Parallel Computing Programming

Jianjian Zhu, Yanlong Xue, Gengxin Sun
2022 Mathematical Problems in Engineering  
Because fine-grained category information can provide rich semantic clues, fine-grained parallel computing techniques are widely used in tasks such as sensitive feature filtering, medical image classification  ...  In this study, we adopt a fine-grained parallel computing programming approach and propose a multiobjective matrix regular optimization algorithm that can simultaneously perform the joint square root,  ...  Fine-grained identification mainly distinguishes subcategories under the same broad category, and the finegrained feature data collection is not simple due to the fine labeling of fine-grained features  ... 
doi:10.1155/2022/4206714 fatcat:idld6ykfqnbjzg6gvurldwi6dq

A Graph-Related High-Order Neural Network Architecture via Feature Aggregation Enhancement for Identification Application of Diseases and Pests

Jianlei Kong, Chengcai Yang, Yang Xiao, Sen Lin, Kai Ma, Qingzhen Zhu, Xin Ning
2022 Computational Intelligence and Neuroscience  
Disease and pest recognition is typically a fine-grained visual classification problem, which is easy to confuse the traditional coarse-grained methods due to the external similarity between different  ...  models and is more suitable for fine-grained identification applications in complex scenes.  ...  recognition networks, indicating that our network can extract more features than coarse-grained networks.  ... 
doi:10.1155/2022/4391491 pmid:35665281 pmcid:PMC9162821 fatcat:2344c2ov3jb6pjf6jcobwk5fli

Exploiting Fine-Grained Face Forgery Clues via Progressive Enhancement Learning

Qiqi Gu, Shen Chen, Taiping Yao, Yang Chen, Shouhong Ding, Ran Yi
2022 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
However, the exploitation of frequency information is coarse-grained, and more importantly, their vanilla learning process struggles to extract fine-grained forgery traces.  ...  Specifically, we perform a fine-grained decomposition of RGB images to completely decouple the real and fake traces in the frequency space.  ...  In this way, the original color input is decomposed and recombined to fine-grained frequency-aware data while maintaining the spatial relationship to match the shift-invariance of CNN.  ... 
doi:10.1609/aaai.v36i1.19954 fatcat:innevjhywjcmpmqr4jxvincrk4

Graph Representation Learning for Popularity Prediction Problem: A Survey [article]

Tiantian Chen, Jianxiong Guo, Weili Wu
2022 arXiv   pre-print
Due to the "word of mouth" effects, information usually can spread rapidly on these social media platforms.  ...  The online social platforms, like Twitter, Facebook, LinkedIn and WeChat, have grown really fast in last decade and have been one of the most effective platforms for people to communicate and share information  ...  For the micro-level prediction, the fine-grained version aims to predict who is the next activated node and is activated at what time, while the coarse-grained version ignores the exact activation time  ... 
arXiv:2203.07632v1 fatcat:jvgzbmih2fcvvfqdu44nax2qpa

A Spatial Feature-Enhanced Attention Neural Network with High-Order Pooling Representation for Application in Pest and Disease Recognition

Jianlei Kong, Hongxing Wang, Chengcai Yang, Xuebo Jin, Min Zuo, Xin Zhang
2022 Agriculture  
Therefore, in this paper, we propose a feature-enhanced attention neural network (Fe-Net) to handle the fine-grained image recognition of crop pests and diseases in innovative agronomy practices.  ...  However, pest and disease recognition in precision agriculture applications is essentially the fine-grained image classification task, which aims to learn effective discriminative features that can identify  ...  Fine-Grained Visual Recognition Modeling Unlike coarse-grained image classification tasks such as object recognition, the goal of fine-grained image recognition is to correctly identify objects in hundreds  ... 
doi:10.3390/agriculture12040500 fatcat:5lto2k2y45hkjahimlzgmy2pze

Activity Recognition: Approaches, Practices and Trends [chapter]

Liming Chen, Ismail Khalil
2011 Activity Recognition in Pervasive Intelligent Environments  
It then describes the practice and lifecycle of the ontology-based approach to activity recognition that has recently been under vigorous investigation.  ...  It is also driven by growing real-world application needs in such areas as ambient assisted living and security surveillance.  ...  The approach supports progressive activity recognition at both coarse-grained and fine-grained levels.  ... 
doi:10.2991/978-94-91216-05-3_1 fatcat:jvu3pv3mivdm5aw4incyrcoy3q
« Previous Showing results 1 — 15 out of 3,417 results