Filters








15,800 Hits in 5.2 sec

Tripartie Graph Models for Multi Modal Retrieval

Chandrika Pulla, C. V. Jawahar
2010 Procedings of the British Machine Vision Conference 2010  
In this paper, we propose a tri-partite graph based representation of the multi model data for image retrieval tasks.  ...  Most of the traditional image retrieval methods use either low level visual features or embedded text for representation and indexing.  ...  [22] proposed a multi model web image retrieval techniques based on multi-graph enabled active learning.  ... 
doi:10.5244/c.24.86 dblp:conf/bmvc/PullaJ10 fatcat:5jnmwjkwuvcgjjctzk5k4mjtey

General Knowledge Embedded Image Representation Learning

Peng Cui, Shaowei Liu, Wenwu Zhu
2018 IEEE transactions on multimedia  
In this paper, we propose a General Knowledge Base Embedded Image Representation Learning approach, which uses general knowledge graph, which is a multi-type relational knowledge graph consisting of human  ...  Image representation learning is a fundamental problem in understanding semantics of images.  ...  (General Knowledge Graph) A general knowledge graph is a multi-type relational graph whose vertices are concepts (one or several words), and edges are the types of relations between two tags.  ... 
doi:10.1109/tmm.2017.2724843 fatcat:cpg3cozjprdfperib7n677vq5q

Thoughts on a Recursive Classifier Graph: a Multiclass Network for Deep Object Recognition [article]

Marius Leordeanu, Rahul Sukthankar
2014 arXiv   pre-print
We propose a general multi-class visual recognition model, termed the Classifier Graph, which aims to generalize and integrate ideas from many of today's successful hierarchical recognition approaches.  ...  The proposed multi-class system is efficiently learned using step by step updates.  ...  The authors also thank Shumeet Baluja and Jay Yagnik for interesting discussions and valuable feedback on these ideas. M. Leordeanu was supported by CNCS-UEFISCDI, under PNII PCE-2012-4-0581.  ... 
arXiv:1404.2903v1 fatcat:ldcvocpyindznb4o3is3hj7jqm

Cyberlearners and learning resources

Leyla Zhuhadar, Rong Yang
2012 Proceedings of the 2nd International Conference on Learning Analytics and Knowledge - LAK '12  
The method used is heuristic and is based on visual clustering and a modularity measure.  ...  We propose a visual method to extract communities of cyberlearners 1 in a large interconnected network consisting of cyberlearners and learning resources.  ...  , 079 Edges (# of edges between users and learning resources).  ... 
doi:10.1145/2330601.2330621 dblp:conf/lak/ZhuhadarY12 fatcat:e2gymv2cn5clflto4n6thsdxue

First Steps to Netviz Nirvana: Evaluating Social Network Analysis with NodeXL

Elizabeth M. Bonsignore, Cody Dunne, Dana Rotman, Marc Smith, Tony Capone, Derek L. Hansen, Ben Shneiderman
2009 2009 International Conference on Computational Science and Engineering  
framework for teaching and learning SNA.  ...  Six of the participants had more technical backgrounds and were chosen specifically for their experience with graph drawing and information visualization.  ...  Exploratory learning can be described, fundamentally, as a cycle of exploration, insight (learned concept), and deeper exploration.  ... 
doi:10.1109/cse.2009.120 dblp:conf/cse/BonsignoreDRSCHS09 fatcat:7x4uh6uwc5hndcmgrurnm2azwm

A Metamodel and Framework for Artificial General Intelligence From Theory to Practice [article]

Hugo Latapie, Ozkan Kilic, Gaowen Liu, Yan Yan, Ramana Kompella, Pei Wang, Kristinn R. Thorisson, Adam Lawrence, Yuhong Sun, Jayanth Srinivasa
2021 arXiv   pre-print
ranging from machine learning, to graph network analysis and learning by reasoning engines to interoperate in a highly synergistic way.  ...  This paper introduces a new metamodel-based knowledge representation that significantly improves autonomous learning and adaptation.  ...  Embeddings Graph embedding Hamilton et al., 2017] is a technique used to represent graph nodes, edges, and sub-graphs in vector space that other machine learning algorithms can use.  ... 
arXiv:2102.06112v1 fatcat:fjphh32flzawbaeropr3svyjsy

Graphonomy: Universal Human Parsing via Graph Transfer Learning

Ke Gong, Yiming Gao, Xiaodan Liang, Xiaohui Shen, Meng Wang, Liang Lin
2019 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
In particular, Graphonomy first learns and propagates compact high-level graph representation among the labels within one dataset via Intra-Graph Reasoning, and then transfers semantic information across  ...  This poses many fundamental learning challenges, e.g. discovering underlying semantic structures among different label granularity, performing proper transfer learning across different image domains, and  ...  Based on the high-level graph feature Z, we leverage semantic constraints from the human body structured knowledge to evolve global representations by graph reasoning.  ... 
doi:10.1109/cvpr.2019.00763 dblp:conf/cvpr/Gong0LS0L19 fatcat:rv5xgqag4jcghmzffi3s67fp2u

Graphonomy: Universal Human Parsing via Graph Transfer Learning [article]

Ke Gong, Yiming Gao, Xiaodan Liang, Xiaohui Shen, Meng Wang, Liang Lin
2019 arXiv   pre-print
In particular, Graphonomy first learns and propagates compact high-level graph representation among the labels within one dataset via Intra-Graph Reasoning, and then transfers semantic information across  ...  This poses many fundamental learning challenges, e.g. discovering underlying semantic structures among different label granularity, performing proper transfer learning across different image domains, and  ...  Based on the high-level graph feature Z, we leverage semantic constraints from the human body structured knowledge to evolve global representations by graph reasoning.  ... 
arXiv:1904.04536v1 fatcat:di2yce3ytbhadml5lljt7yn66m

Towards Unsupervised Knowledge Extraction

Dorothea Tsatsou, Konstantinos Karageorgos, Anastasios Dimou, Javier Carbo, Jose M. Molina, Petros Daras
2021 Zenodo  
This paper presents a proof-of-concept approach towards an unsupervised learning method, based on Restricted Boltzmann Machines (RBMs), for extracting semantic associations among prominent entities within  ...  Validation of the approach is performed in two datasets that connect language and vision, namely Visual Genome and GQA.  ...  found in multi-labelled images of the Visual Genome and GQA datasets.  ... 
doi:10.5281/zenodo.4686854 fatcat:3ndbi23wx5cmddegj6otqekqqy

One of a Kind

Xue Geng, Hanwang Zhang, Zheng Song, Yang Yang, Huanbo Luan, Tat-Seng Chua
2014 Proceedings of the ACM International Conference on Multimedia - MM '14  
In particular, we propose a new deep learning strategy called multi-task convolutional neural network (mtCNN) to learn profile models and profile-related visual features simultaneously.  ...  Extensive experiments on 1,293 users and 1.5 million images collected from Pinterest in fashion domain demonstrate that recommendation methods based on the proposed user profiles are considerably more  ...  The visual link is based on the visual similarities while the semantic link is based on the hierarchical semantic similarities between two images.  ... 
doi:10.1145/2647868.2654950 dblp:conf/mm/GengZSYLC14 fatcat:drvzd5jsojdp7jqzbrmcfdqxgu

Visualizing Knowledge Networks in Online Courses

Marni Baker-Stein, Sean York, Brian Dashew
2014 Internet Learning  
of concept connectedness.  ...  It overviews the graph database schema and technologies employed, and describes examples of how the data is used to describe, differentiate among, and visualize individuals, conversations, and patterns  ...  We hope this report will contribute to a responsible evolution of online and blended teaching and learning, through an increased awareness and understanding of the social spaces in which these increasingly  ... 
doi:10.18278/il.3.2.7 fatcat:dhyk2pijx5ajxenasyuaeb2sf4

Graph-based Text Representation and Matching: A Review of the State of the Art and Future Challenges

Ahmed Hamza Osman, Omar Mohammed Barukub
2020 IEEE Access  
We provide a formal description of the problem of graph-based text representation and introduce some basic concepts.  ...  In this review, we conduct an inclusive survey of the state of the art in graph-based text representation and learning.  ...  In addition, a graph with the directed edges is called a directed graph, or digraph. In addition, the concept of a multi-graph refers to a multi-graph that requires multiple edges between nodes.  ... 
doi:10.1109/access.2020.2993191 fatcat:wkss6xzzcneujfe6ynnmbydhsa

Graph Models for Knowledge Representation and Reasoning for Contemporary and Emerging Needs – A Survey

Engels Rajangam, Chitra Annamalai
2016 International Journal of Information Technology and Computer Science  
This paper surveys graph based knowledge representation and reasoning, various graph models such as Conceptual Graphs, Concept Graphs, Semantic Networks, Inference Graphs and Causal Bayesian Networks used  ...  Reasoning is the fundamental capability which requires knowledge. Various graph models have proven to be very valuable in knowledge representation and reasoning.  ...  Knowledge representation based on graphs provides the advantages of graphical models in terms of readability, visual clarity and computational viability.  ... 
doi:10.5815/ijitcs.2016.02.02 fatcat:hzq62w7slnbjzh7clg4vxvqfi4

Visualization of Aligned Biological Networks: A Survey

Steffen Brasch, Lars Linsen, Georg Fuellen
2007 2007 International Conference on Cyberworlds (CW'07)  
This is no standard network visualization problem, as we have to deal with more than one network and inter-network relationships. Several approaches to visualize aligned networks exist.  ...  In this survey we present and discuss these different approaches and report on their advantages and drawbacks. We draw conclusions on the applicability of the various approaches.  ...  Yet another network alignment approach called "Local Graph Aligner" was developed based on a spin model [19] .  ... 
doi:10.1109/cw.2007.51 dblp:conf/cw/BraschLF07 fatcat:tx3td5o5drhsrfk4a2k5herway

Graph signal processing for machine learning: A review and new perspectives [article]

Xiaowen Dong, Dorina Thanou, Laura Toni, Michael Bronstein, Pascal Frossard
2020 arXiv   pre-print
In this article, we review a few important contributions made by GSP concepts and tools, such as graph filters and transforms, to the development of novel machine learning algorithms.  ...  The effective representation, processing, analysis, and visualization of large-scale structured data, especially those related to complex domains such as networks and graphs, are one of the key questions  ...  on graphs; 3) learning models inspired or interpretable by GSP concepts and tools.  ... 
arXiv:2007.16061v1 fatcat:76jhe3mhlnfkrkyjcyibmkth24
« Previous Showing results 1 — 15 out of 15,800 results