DC Field | Value | Language |
---|---|---|
dc.contributor.author | Park, Jongchan | ko |
dc.contributor.author | Kim, Min-Hyun | ko |
dc.contributor.author | Choi, Seibum | ko |
dc.contributor.author | Kweon, In So | ko |
dc.contributor.author | Choi, Dong-Geol | ko |
dc.date.accessioned | 2020-06-25T03:20:25Z | - |
dc.date.available | 2020-06-25T03:20:25Z | - |
dc.date.created | 2020-06-11 | - |
dc.date.created | 2020-06-11 | - |
dc.date.issued | 2019-01 | - |
dc.identifier.citation | 18th Annual International Conference on Electronics, Information, and Communication (ICEIC), pp.278 - 284 | - |
dc.identifier.issn | 2377-8431 | - |
dc.identifier.uri | http://hdl.handle.net/10203/274881 | - |
dc.description.abstract | Deep learning based recognition systems have shown high performances in various tasks. Most of them are single-modality based, using camera inputs only, thus are vulnerable to look-alike fraud inputs. Fraud inputs may frequently be abused when rewards are given to the users, such as in reverse vending machines. Joint use of multi-modal inputs can be a solution to fraud inputs since modalities contain different information about the target task. In this work, we propose a deep neural network that utilizes multi-modal inputs with an attention mechanism and a correspondence learning scheme. With an attention mechanism, the network can learn better feature representation for multiple modalities; with the correspondence learning scheme, the network learns intermodal relationships and thus can detect fraud inputs where modalities do not correspond to each other. We investigate the proposed approach in a reverse vending machine system, where the task is to perform classification among 3 given classes (can, PET bottles, glass bottles), and reject any suspicious input. Three different modalities (image, ultrasound, and weight) are used. As a result, we show that our proposed model can effectively learn to detect fraud inputs while maintaining a high accuracy for the given classification task. | - |
dc.language | English | - |
dc.publisher | IEEE | - |
dc.title | Fraud Detection with Multi-Modal Attention and Correspondence Learning | - |
dc.type | Conference | - |
dc.identifier.wosid | 000470015800067 | - |
dc.identifier.scopusid | 2-s2.0-85065887138 | - |
dc.type.rims | CONF | - |
dc.citation.beginningpage | 278 | - |
dc.citation.endingpage | 284 | - |
dc.citation.publicationname | 18th Annual International Conference on Electronics, Information, and Communication (ICEIC) | - |
dc.identifier.conferencecountry | US | - |
dc.identifier.conferencelocation | Inst Elect & Informat Engineers, Auckland, NEW ZEALAND | - |
dc.identifier.doi | 10.23919/ELINFOCOM.2019.8706354 | - |
dc.contributor.localauthor | Choi, Seibum | - |
dc.contributor.localauthor | Kweon, In So | - |
dc.contributor.nonIdAuthor | Park, Jongchan | - |
dc.contributor.nonIdAuthor | Kim, Min-Hyun | - |
dc.contributor.nonIdAuthor | Choi, Dong-Geol | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.