14 Hits in 10.2 sec

Multi-Graph Transformer for Free-Hand Sketch Recognition [article]

Peng Xu, Chaitanya K. Joshi, Xavier Bresson
2021 arXiv   pre-print
We design a novel Graph Neural Network (GNN), the Multi-Graph Transformer (MGT), for learning representations of sketches from multiple graphs which simultaneously capture global and local geometric stroke  ...  Learning meaningful representations of free-hand sketches remains a challenging task given the signal sparsity and the high-level abstraction of sketches.  ...  This multi-graph modeling idea works well for both sketch and other modalities.  ... 
arXiv:1912.11258v3 fatcat:pxurw2kxbffzdn4esi2ydkejtm

Learning Neural Textual Representations for Citation Recommendation

Binh Thanh Kieu, Inigo Jauregi Unanue, Son Bao Pham, Hieu Xuan Phan, Massimo Piccardi
2021 2020 25th International Conference on Pattern Recognition (ICPR)  
of Abundance and Distribution of SaltMarsh Plants from Images Using Deep Learning Emerging Relation Network and Task Embedding for Multi-Task Regression Problems.pdf Learning from Learners: Adapting Reinforcement  ...  1025 Multi-Modal Contextual Graph Neural Network for Text Visual Question Answering DAY 3 -Jan 14, 2021 Zhou, Junwei; Gao, Hongchao; Dai, Jiao; Liu, Dongqin; Han, Jizhong 1119 A Multi-Head  ... 
doi:10.1109/icpr48806.2021.9412725 fatcat:3vge2tpd2zf7jcv5btcixnaikm

2021 Index IEEE Transactions on Intelligent Transportation Systems Vol. 22

2021 IEEE transactions on intelligent transportation systems (Print)  
-that appeared in this periodical during 2021, and items from previous years that were commented upon or corrected in 2021.  ...  The primary entry includes the coauthors' names, the title of the paper or other item, and its location, specified by the publication abbreviation, year, month, and inclusive pagination.  ...  Logo Recognition From Frontal and Rear Images of Vehicles.  ... 
doi:10.1109/tits.2021.3139738 fatcat:p2mkawtrsbaepj4zk24xhyl2oa

Health State Estimation [article]

Nitish Nag
2020 arXiv   pre-print
This dissertation presents an approach to build a personal model and dynamically estimate the health state of an individual by fusing multi-modal data and domain knowledge.  ...  Edges and nodes in this graph structure are then regularly updated with learning techniques as data is continuously digested.  ...  We can use multi-modal data to learn if a user is executing an action from intrinsic motivation or external factors.  ... 
arXiv:2003.09312v1 fatcat:sm7vadoyerbf5gmeujvobcqop4

GIS Mashups [chapter]

Ilya Zaslavsky
2017 Encyclopedia of GIS  
Originally developed for geo-spatial contexts, they are also applicable in general contexts that involve computing and modeling with multi-level spatial aggregates, e.g., modeling a configuration space  ...  It took more than a decade from this point for the larger computer science community to investigate GPs for pattern analysis purposes.  ...  A prototypical view of a city might be defined as a dense collection of municipal and industrial buildings, and multi modal transportation infrastructures.  ... 
doi:10.1007/978-3-319-17885-1_530 fatcat:rrr5buo3zrevpigdtjwhewipvm

Graph Embedding for Retrieval

Chi Thang Duong
My parents and my sister who have always got my back and kept reminding me that I can always go home when things get difficult.  ...  Last but not least, my wife -thank you for choosing me and being here with me. Without you, I would be "sad to death".  ...  Acknowledgements First and foremost, I would like to thank my advisor Prof. Karl Aberer. He gave me the chance to do my bachelor thesis at LSIR 10 years ago and the rest is history.  ... 
doi:10.5075/epfl-thesis-8046 fatcat:tbaipy4blza7tkzxgfk52ivdoy

Network Structure Inference: Methodology and Applications

Ivan C Brugere
I introduce a task-focused network structure inference and model selection methodology, and a principled measurement of model utility over arbitrary representations and tasks.  ...  Networks represent relationships between entities in many complex systems, spanning from online social interactions to biological cell development and brain connectivity.  ...  Modeling the predictive aspects of the data allows researchers to learn regular relationships between modalities (e.g., call, text, and location in mobile phone data) or over time (e.g., periodicities)  ... 
doi:10.25417/uic.13475814.v1 fatcat:qlsx55aopvacdewkaagkwrfgdm

Knowledge-enhance Neural Text Generation

Ye Liu
To make machines express like a human, we have considered incorporating various forms of internal and external knowledge beyond the input text into the generation models to solve this issue.  ...  Therefore, text generation performance is still far from satisfactory in many real-world scenarios.  ...  The goal of text generation is to generate the human language from various input formats such as textual data, image data, and knowledge graph.  ... 
doi:10.25417/uic.19187354 fatcat:5dird7xgcvgnvm2lita24wqe6e

Graph Summarization Meets Representation Learning for Scalable Feature Summarization: Methods and Applications [article]

Di Jin, University, My
Recently, graph representation learning has gained significant popularity in both academia and industry thanks to its state-of-the-art performance in a variety of downstream machine learning (ML) tasks  ...  On the other hand, graph summarization aims to find a concise and interpretable representation of the original graph that describes its key information, but it is often lossy and trades off space and performance  ...  Danai Koutra, who has enlightened my career and taught me step by step to be a researcher. Danai inspired my interests in research when I was a newbie conducting projects under her advisory at CMU,  ... 
doi:10.7302/3881 fatcat:dujglexds5gs3jmcb3shhicdb4

Video visual analytics [article]

Markus Johannes Höferlin, Universität Stuttgart, Universität Stuttgart
It originates from a wide range of application areas, such as surveillance, sports analysis, scientific video analysis, surgery documentation, and entertainment, and its analysis represents one of the  ...  However, automatic evaluation of video material is not reliable enough, especially when it comes to semantic abstraction from the video signal.  ...  Static Graph Representation Each adjacency edge in a multi-graph consists of a start and a target node, and additionally of a list of weights attached to it.  ... 
doi:10.18419/opus-6431 fatcat:7sq47blfarcw7cdluxeyqx5rgm

LIPIcs-Leibniz International Proceedings in Informatics

Eliseo Clementini, Maureen Donnelly, May Yuan, Christian Kray, Paolo Fogliaroni, Andrea Ballatore, Eliseo Clementini, Maureen Donnelly, May Yuan, Christian Kray, Paolo Fogliaroni, Andrea Ballatore (+4 others)
Physical Sciences and Engineering] Earth and Atmospheric Sciences   unpublished
A specific form of topological closure between graphs is expressible in this logic, both as a combination of the negation ¬ and its dual ¬ , and as modality, using the stable relation Q, which describes  ...  the incidence structure of the graph.  ...  We would like to thank Michele Volpi for the fruitful discussions and his and the reviewers helpful comments.  ... 

ICCGI 2011 The Sixth International Multi-Conference on Computing in the Global Information Technology Luxembourg City, Luxembourg ICCGI 2011 Editors ICCGI 2011 Committee ICCGI Advisory Chairs ICCGI 2011 Technical Program Committee

Constantin Paleologu, Hermann Kaindl, Tu-Wien Austria, Yasushi Kambayashi, Mary Luz, Mouronte López, S Ericsson, Krishna Spain, Hcl Murthy, America, Amir Razavi, José Rouillard (+43 others)
Foreword The Sixth International Multi-Conference on Computing in the Global Information Technology   unpublished
, multi-agent computing, autonomic computing, evolutionary computation) and communication and networking and telecommunications technologies (mobility, networking, biotechnologies , autonomous systems,  ...  image processing, Internet and web technologies), towards secure, self-defendable, autonomous, privacy-safe, and context-aware scalable systems.  ...  We hope that ICCGI 2011 was a successful international forum for the exchange of ideas and results between academia and industry and for the promotion of progress in the area of computing in the global  ... 

Learning to Find Bugs in Programs and their Documentation

Andrew Habib
to also allow statistical learning from it.  ...  This dissertation argues that learning from programs and their documentation provides an effective means to prevent and detect software bugs.  ...  Work on this problem includes graph-based representations [ABK17; Bro+18] , embeddings learned from sequences of API calls [DTR18] , embeddings learned from paths through ASTs [Alo+18a; Alo+18b], and  ... 
doi:10.26083/tuprints-00017377 fatcat:o47olqxg5rhrzoqg4j5tazo3ni

Committee SEMAPRO Advisory Chairs

Fabio Grandi, David Ostrowski, Michael Mohler, Bernd Stadlhofer, Wladyslaw Homenda, Fabio Grandi, David Ostrowski, Michael Mohler, Bernd Stadlhofer, Mario Neri, Bruno Bachimont, Ebrahim Bagheri (+97 others)
and services Similar to previous editions, this event attracted excellent contributions and active participation from all over the world.  ...  Searching for video, voice and speech [VVS] raises additional problems to specialized engines with respect to text search.  ...  platform and first prototype of our software system development.  ...