Výsledky vyhledávání - "graph transduction"

Akademický článek

A novel sketch-based 3D model retrieval method by integrating skeleton graph and contour feature

Autor: Haopeng LEI, Yuhua LI, Helian CHEN, Shujin LIN, Guifeng ZHENG, Xiaonan LUO

Publikováno v: Journal of Advanced Mechanical Design, Systems, and Manufacturing, Vol 9, Iss 4, Pp JAMDSM0049-JAMDSM0049 (2015)

With the rapid growth of 3D models on the Web, effective methods to retrieve appropriate 3D models are becoming crucial. In this paper, we propose a novel sketch-based 3D model retrieval approach which integrates the skeleton graph and contour featur

Externí odkaz: https://doaj.org/article/849d89bee4234fd9a6bc4e9adda22547

Zobrazit plný text záznamu

Transductive Visual Verb Sense Disambiguation

Autor: Sinem Aslan, Marcello Pelillo, Gianluca Bigaglia, Sebastiano Vascon, Lorenzo Giudice

Publikováno v: WACV

IEEE Winter Conference on Applications of Computer Vision (WACV) -- JAN 05-09, 2021 -- ELECTR NETWORK
Verb Sense Disambiguation is a well-known task in NLP, the aim is to find the correct sense of a verb in a sentence. Recently, this problem has

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6507d72f4bf5afdaa70f3ebe4e0d3fa8
https://hdl.handle.net/11454/77492

Zobrazit plný text záznamu

Bottom-up unranked tree-to-graph transducers for translation into semantic graphs

Autor: Johanna Björklund, Shay B. Cohen, Frank Drewes, Giorgio Satta

Publikováno v: FSMNLP

We develop a finite-state transducer for translating unranked trees into general graphs. This work is motivated by recent progress in semantic parsing for natural language, where sentences are first mapped into tree-shaped syntactic representations,

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::83cc261bba0c6047498eb1c8d38dd8dd
http://hdl.handle.net/11577/3398880

Zobrazit plný text záznamu

Unsupervised Domain Adaptation using Graph Transduction Games

Autor: Sebastiano Vascon, Sinem Aslan, Elena Marchiori, Marcello Pelillo, Twan van Laarhoven, Alessandro Torcinovich

Publikováno v: IJCNN 2019: International Joint Conference on Neural Networks, Budapest, Hungary, July 14-19, 2019, pp. 1-8
IJCNN 2019: International Joint Conference on Neural Networks, Budapest, Hungary, July 14-19, 2019, 1-8. Piscataway : IEEE
STARTPAGE=1;ENDPAGE=8;TITLE=IJCNN 2019: International Joint Conference on Neural Networks, Budapest, Hungary, July 14-19, 2019
IJCNN

Unsupervised domain adaptation (UDA) amounts to assigning class labels to the unlabeled instances of a dataset from a target domain, using labeled instances of a dataset from a related source domain. In this paper, we propose to cast this problem in

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::93b3ca1b900d8139dafb26de75d71a65
https://hdl.handle.net/2066/209251

Zobrazit plný text záznamu

Akademický článek

Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.

Akademický článek

Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.

Ancient Coin Classification Using Graph Transduction Games

Autor: Marcello Pelillo, Sebastiano Vascon, Sinem Aslan

IEEE International Conference on Metrology for Archaeology and Cultural Heritage (MetroArchaeo) -- OCT 22-24, 2018 -- Cassino, ITALY
Aslan, Sinem/0000-0003-0068-6551
WOS:000588594200015
Recognizing the type of an ancient coin requires

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f02edbe8b062b850dd7be99434e6be4d
http://arxiv.org/abs/1810.01091

Zobrazit plný text záznamu

Transductive Label Augmentation for Improved Deep Network Learning

Autor: Alessandro Torcinovich, Ismail Elezi, Marcello Pelillo, Sebastiano Vascon

Publikováno v: ICPR

A major impediment to the application of deep learning to real-world problems is the scarcity of labeled data. Small training sets are in fact of no use to deep networks as, due to the large number of trainable parameters, they will very likely be su

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::44160b5fd323a915ab753bf5a1082f0e
http://hdl.handle.net/10278/3718951

Zobrazit plný text záznamu

Robust graph transduction

Autor: Gong, Chen

University of Technology Sydney. Faculty of Engineering and Information Technology. Given a weighted graph, graph transduction aims to assign unlabeled examples explicit class labels rather than build a general decision function based on the availabl

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=od_______363::c48372a42c60fdf47aa8d945ac88ed84
https://hdl.handle.net/10453/102708

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání