meChat: In-Device Personal Assistant for Conversational Photo Sharing

Kang Min Kim, Woo Jong Ryu, Jun Hyung Park, Sang-Geun Lee

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

It is still challenging to search in-device photos without the sacrifice of privacy or the poor latency, while photos have been an essential medium of the communication in messaging applications. In this article, we propose a novel in-device personal assistant for conversational photo sharing, called meChat. By understanding user's conversations and in-device photos, meChat intelligently searches in-device photos that are semantically relevant to the conversation context. Notably, meChat works in a stand-alone, privacy-protecting manner without sending out any in-device personal content. The scenario-based user studies show that meChat efficiently searches highly relevant in-device photos with low perceived latency and energy consumption.

Original languageEnglish
JournalIEEE Internet Computing
DOIs
Publication statusAccepted/In press - 2018 Jan 1

Fingerprint

Energy utilization
Communication

Keywords

  • Computational modeling
  • Global Positioning System
  • In-device photo search
  • Intelligent chatbots
  • Internet
  • On-device intelligence
  • Personal assistant
  • Privacy
  • Semantics
  • Servers
  • Smart phones

ASJC Scopus subject areas

  • Computer Networks and Communications

Cite this

meChat : In-Device Personal Assistant for Conversational Photo Sharing. / Kim, Kang Min; Ryu, Woo Jong; Park, Jun Hyung; Lee, Sang-Geun.

In: IEEE Internet Computing, 01.01.2018.

Research output: Contribution to journalArticle

@article{9ced89167ace4d0a8b18d80919060e5e,
title = "meChat: In-Device Personal Assistant for Conversational Photo Sharing",
abstract = "It is still challenging to search in-device photos without the sacrifice of privacy or the poor latency, while photos have been an essential medium of the communication in messaging applications. In this article, we propose a novel in-device personal assistant for conversational photo sharing, called meChat. By understanding user's conversations and in-device photos, meChat intelligently searches in-device photos that are semantically relevant to the conversation context. Notably, meChat works in a stand-alone, privacy-protecting manner without sending out any in-device personal content. The scenario-based user studies show that meChat efficiently searches highly relevant in-device photos with low perceived latency and energy consumption.",
keywords = "Computational modeling, Global Positioning System, In-device photo search, Intelligent chatbots, Internet, On-device intelligence, Personal assistant, Privacy, Semantics, Servers, Smart phones",
author = "Kim, {Kang Min} and Ryu, {Woo Jong} and Park, {Jun Hyung} and Sang-Geun Lee",
year = "2018",
month = "1",
day = "1",
doi = "10.1109/MIC.2018.2883059",
language = "English",
journal = "IEEE Internet Computing",
issn = "1089-7801",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - meChat

T2 - In-Device Personal Assistant for Conversational Photo Sharing

AU - Kim, Kang Min

AU - Ryu, Woo Jong

AU - Park, Jun Hyung

AU - Lee, Sang-Geun

PY - 2018/1/1

Y1 - 2018/1/1

N2 - It is still challenging to search in-device photos without the sacrifice of privacy or the poor latency, while photos have been an essential medium of the communication in messaging applications. In this article, we propose a novel in-device personal assistant for conversational photo sharing, called meChat. By understanding user's conversations and in-device photos, meChat intelligently searches in-device photos that are semantically relevant to the conversation context. Notably, meChat works in a stand-alone, privacy-protecting manner without sending out any in-device personal content. The scenario-based user studies show that meChat efficiently searches highly relevant in-device photos with low perceived latency and energy consumption.

AB - It is still challenging to search in-device photos without the sacrifice of privacy or the poor latency, while photos have been an essential medium of the communication in messaging applications. In this article, we propose a novel in-device personal assistant for conversational photo sharing, called meChat. By understanding user's conversations and in-device photos, meChat intelligently searches in-device photos that are semantically relevant to the conversation context. Notably, meChat works in a stand-alone, privacy-protecting manner without sending out any in-device personal content. The scenario-based user studies show that meChat efficiently searches highly relevant in-device photos with low perceived latency and energy consumption.

KW - Computational modeling

KW - Global Positioning System

KW - In-device photo search

KW - Intelligent chatbots

KW - Internet

KW - On-device intelligence

KW - Personal assistant

KW - Privacy

KW - Semantics

KW - Servers

KW - Smart phones

UR - http://www.scopus.com/inward/record.url?scp=85057873312&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85057873312&partnerID=8YFLogxK

U2 - 10.1109/MIC.2018.2883059

DO - 10.1109/MIC.2018.2883059

M3 - Article

AN - SCOPUS:85057873312

JO - IEEE Internet Computing

JF - IEEE Internet Computing

SN - 1089-7801

ER -