The idea of lifelogging [1] has recently been gaining public interest and it's noted that there has been over a decade of research activity in the area [2]. In this talk, I will describe LIAM (Lifestyle-Integrated Automation Machine) which represents a first attempt at a holistic lifelogging solution that supports gathering lifelog data, accessing this data and (uniquely) using this data to report and automate aspects of my life. LIAM represents lifelogging journey that has recorded 7100 days. LIAM may be described as a "Life Management System" or a pervasive technology system to record, report, assess, and control aspects of my life. Logically, LIAM may be viewed across three dimensions: LifeChronicle: LifeChronicle represents a record of the past (my lifelog). It contains over a dozen categories from physical activities to completed tasks to life events. Over time, this data has become more and more extensive. LifeState: LifeState is a description of my life's current state compartmentalized into nine essential "elements" which I propose create a "whole person". LIAM summarizes and computes these states with data from LifeChronicle near real-time. It also compares LifeState constituents against targets and using a weighted scorecard creates a LifeScore. This abstracts my life as a single number. LifeConsole: LifeConsole is the collection of tools and processes I use to drive LifeChronicle and LifeState -- or to be driven by them. This goes beyond desktop and mobile tools but includes extensive home automation as well.
{"title":"LIAM: A Two Decade Exploration of Lifelogging","authors":"Tahl Milburn","doi":"10.1145/3133202.3133209","DOIUrl":"https://doi.org/10.1145/3133202.3133209","url":null,"abstract":"The idea of lifelogging [1] has recently been gaining public interest and it's noted that there has been over a decade of research activity in the area [2]. In this talk, I will describe LIAM (Lifestyle-Integrated Automation Machine) which represents a first attempt at a holistic lifelogging solution that supports gathering lifelog data, accessing this data and (uniquely) using this data to report and automate aspects of my life. LIAM represents lifelogging journey that has recorded 7100 days. LIAM may be described as a \"Life Management System\" or a pervasive technology system to record, report, assess, and control aspects of my life. Logically, LIAM may be viewed across three dimensions: LifeChronicle: LifeChronicle represents a record of the past (my lifelog). It contains over a dozen categories from physical activities to completed tasks to life events. Over time, this data has become more and more extensive. LifeState: LifeState is a description of my life's current state compartmentalized into nine essential \"elements\" which I propose create a \"whole person\". LIAM summarizes and computes these states with data from LifeChronicle near real-time. It also compares LifeState constituents against targets and using a weighted scorecard creates a LifeScore. This abstracts my life as a single number. LifeConsole: LifeConsole is the collection of tools and processes I use to drive LifeChronicle and LifeState -- or to be driven by them. This goes beyond desktop and mobile tools but includes extensive home automation as well.","PeriodicalId":265670,"journal":{"name":"Proceedings of the 2nd Workshop on Lifelogging Tools and Applications","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124852935","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The prevalence of modern technology has enabled people to record a digital trove of life experiences and these datasets continue to grow exponentially day by day. Exploring these huge datasets effectively has been the subject of much research in the lifelogging community. In this paper we describe a pilot study performed to investigate the feasibility of using virtual reality as a platform for exploring visual lifelog data. The dataset used in this experiment consisted of image data captured by wearable cameras and keywords describing the visual content of each image. The results of this experiment suggested there was no notable impact on user performance using the virtual reality platform. This research was performed as part of a larger study to investigate the overall potential of virtual reality as a platform for visual lifelog exploration.
{"title":"Pilot Study to Investigate Feasibility of Visual Lifelog Exploration in Virtual Reality","authors":"Aaron Duane, C. Gurrin","doi":"10.1145/3133202.3133208","DOIUrl":"https://doi.org/10.1145/3133202.3133208","url":null,"abstract":"The prevalence of modern technology has enabled people to record a digital trove of life experiences and these datasets continue to grow exponentially day by day. Exploring these huge datasets effectively has been the subject of much research in the lifelogging community. In this paper we describe a pilot study performed to investigate the feasibility of using virtual reality as a platform for exploring visual lifelog data. The dataset used in this experiment consisted of image data captured by wearable cameras and keywords describing the visual content of each image. The results of this experiment suggested there was no notable impact on user performance using the virtual reality platform. This research was performed as part of a larger study to investigate the overall potential of virtual reality as a platform for visual lifelog exploration.","PeriodicalId":265670,"journal":{"name":"Proceedings of the 2nd Workshop on Lifelogging Tools and Applications","volume":"81 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126225056","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
C. Gurrin, Xavier Giró-i-Nieto, P. Radeva, Duc-Tien Dang-Nguyen, Mariella Dimiccoli, Hideo Joho
We are pleased to welcome you to the 2017 ACM Multimedia Workshop on Lifelogging Tools and Applications - LTA'17. This workshop aims at bringing together interdisciplinary researchers and practitioners to discuss approaches to lifelog data analytics and the applications of same. This second edition of LTA offers a forum to debate the opportunities and challenges for researchers in this new and challenging area. The call for papers attracted submissions from Italy, China, Spain, Switzerland and Ireland. Accepted long papers will be presented in an oral session, and short poster introduced with a brief talk during a spotlight session. All accepted papers will also be presented during the poster session. We also encourage attendees to attend the keynote. This valuable and insightful talk can and will guide us to a better understanding of the future: LIAM - A Two Decade Exploration of Lifelogging, Tahl Milburn (CEO of lifestate.io)
{"title":"Proceedings of the 2nd Workshop on Lifelogging Tools and Applications","authors":"C. Gurrin, Xavier Giró-i-Nieto, P. Radeva, Duc-Tien Dang-Nguyen, Mariella Dimiccoli, Hideo Joho","doi":"10.1145/3133202","DOIUrl":"https://doi.org/10.1145/3133202","url":null,"abstract":"We are pleased to welcome you to the 2017 ACM Multimedia Workshop on Lifelogging Tools and Applications - LTA'17. This workshop aims at bringing together interdisciplinary researchers and practitioners to discuss approaches to lifelog data analytics and the applications of same. This second edition of LTA offers a forum to debate the opportunities and challenges for researchers in this new and challenging area. \u0000 \u0000The call for papers attracted submissions from Italy, China, Spain, Switzerland and Ireland. \u0000 \u0000Accepted long papers will be presented in an oral session, and short poster introduced with a brief talk during a spotlight session. All accepted papers will also be presented during the poster session. \u0000 \u0000We also encourage attendees to attend the keynote. This valuable and insightful talk can and will guide us to a better understanding of the future: \u0000LIAM - A Two Decade Exploration of Lifelogging, Tahl Milburn (CEO of lifestate.io)","PeriodicalId":265670,"journal":{"name":"Proceedings of the 2nd Workshop on Lifelogging Tools and Applications","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127776975","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In lifelogging, as the volume of personal life archive data is ever increasing, we have to consider how to take advantage of a tool to extract or exploit valuable information from these personal life archives. In this work we motivate the need for, and present, a baseline search engine for personal life archives, which aims to make the personal life archive searchable, organizable and easy to be updated. We also present some preliminary results, which illustrate the feasibility of the baseline search engine as a tool for getting insights from personal life archives.
{"title":"A Baseline Search Engine for Personal Life Archives","authors":"Liting Zhou, Duc-Tien Dang-Nguyen, C. Gurrin","doi":"10.1145/3133202.3133206","DOIUrl":"https://doi.org/10.1145/3133202.3133206","url":null,"abstract":"In lifelogging, as the volume of personal life archive data is ever increasing, we have to consider how to take advantage of a tool to extract or exploit valuable information from these personal life archives. In this work we motivate the need for, and present, a baseline search engine for personal life archives, which aims to make the personal life archive searchable, organizable and easy to be updated. We also present some preliminary results, which illustrate the feasibility of the baseline search engine as a tool for getting insights from personal life archives.","PeriodicalId":265670,"journal":{"name":"Proceedings of the 2nd Workshop on Lifelogging Tools and Applications","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132152667","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Yewen Wang, Min Zhang, Pouneh Soleimaninejadian, Haoyue Tong, Zehui Feng
When evaluating personality traits, both researchers and participants always find themselves annoyed by the questionnaires and surveys, and the answers may vary according to different degrees of the participant's carefulness. In this paper, we propose a novel and operable solution to make personality evaluations based on the lifelog data using a logistic regression model. It is the first time, to the best of our knowledge, that a new way is discovered of Big Five personality evaluation by using proactive and objective lifelog data, which is available for the large-scale user analyses. Impressive results have been achieved which shows the effectiveness of the proposed novel and easy-applicable idea with simple model.
{"title":"Big Five Personality Measurement Based on Lifelog","authors":"Yewen Wang, Min Zhang, Pouneh Soleimaninejadian, Haoyue Tong, Zehui Feng","doi":"10.1145/3133202.3133207","DOIUrl":"https://doi.org/10.1145/3133202.3133207","url":null,"abstract":"When evaluating personality traits, both researchers and participants always find themselves annoyed by the questionnaires and surveys, and the answers may vary according to different degrees of the participant's carefulness. In this paper, we propose a novel and operable solution to make personality evaluations based on the lifelog data using a logistic regression model. It is the first time, to the best of our knowledge, that a new way is discovered of Big Five personality evaluation by using proactive and objective lifelog data, which is available for the large-scale user analyses. Impressive results have been achieved which shows the effectiveness of the proposed novel and easy-applicable idea with simple model.","PeriodicalId":265670,"journal":{"name":"Proceedings of the 2nd Workshop on Lifelogging Tools and Applications","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114847420","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In recent years with the emergence of wearable devices for lifelogging, every day huge archives of data consisting of images, audio, etc are generated from a person's life. As a result researchers in this field have focused on building applications that utilize lifelog archives for various human-aid applications. Several studies have shown the effectiveness of replaying recordings of one's life in aiding human memory to recall past events. Specifically, lifelog images captured automatically by wearable cameras have been very popular in these studies. In this paper, we examine the effectiveness of lifelog conversations in a workplace environment as useful sources of information for extracting memory cues to recall past events. We present a method for generating memory cues for augmenting one's memory. Furthermore, we conduct a user study with five groups of people, where each group consists of two individuals, in order to examine the effectiveness of our approach. Our results on real-world data demonstrate the effectiveness of our method in aiding people recalling the contents of past conversations. Such results were achieved by showing summary memory cues of past conversations to each participant for a maximum duration of only five minutes to aid recall of past events.
{"title":"Are Conversation Logs Useful Sources for Generating Memory Cues for Recalling Past Memories?","authors":"Seyed Ali Bahrainian, F. Crestani","doi":"10.1145/3133202.3133205","DOIUrl":"https://doi.org/10.1145/3133202.3133205","url":null,"abstract":"In recent years with the emergence of wearable devices for lifelogging, every day huge archives of data consisting of images, audio, etc are generated from a person's life. As a result researchers in this field have focused on building applications that utilize lifelog archives for various human-aid applications. Several studies have shown the effectiveness of replaying recordings of one's life in aiding human memory to recall past events. Specifically, lifelog images captured automatically by wearable cameras have been very popular in these studies. In this paper, we examine the effectiveness of lifelog conversations in a workplace environment as useful sources of information for extracting memory cues to recall past events. We present a method for generating memory cues for augmenting one's memory. Furthermore, we conduct a user study with five groups of people, where each group consists of two individuals, in order to examine the effectiveness of our approach. Our results on real-world data demonstrate the effectiveness of our method in aiding people recalling the contents of past conversations. Such results were achieved by showing summary memory cues of past conversations to each participant for a maximum duration of only five minutes to aid recall of past events.","PeriodicalId":265670,"journal":{"name":"Proceedings of the 2nd Workshop on Lifelogging Tools and Applications","volume":"57 9-10","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131496668","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
A. Lidon, Marc Bolaños, Mariella Dimiccoli, P. Radeva, M. Garolera, Xavier Giró-i-Nieto
With the rapid increase of users of wearable cameras in recent years and of the amount of data they produce, there is a strong need for automatic retrieval and summarization techniques. This work addresses the problem of automatically summarizing egocentric photo streams captured through a wearable camera by taking an image retrieval perspective. After removing non-informative images by a new CNN-based filter, images are ranked by relevance to ensure semantic diversity and finally re-ranked by a novelty criterion to reduce redundancy. To assess the results, a new evaluation metric is proposed which takes into account the non-uniqueness of the solution. Experimental results applied on a database of 7,110 images from 6 different subjects and evaluated by experts gave 95.74% of experts satisfaction and a Mean Opinion Score of 4.57 out of 5.0.
{"title":"Semantic Summarization of Egocentric Photo Stream Events","authors":"A. Lidon, Marc Bolaños, Mariella Dimiccoli, P. Radeva, M. Garolera, Xavier Giró-i-Nieto","doi":"10.1145/3133202.3133204","DOIUrl":"https://doi.org/10.1145/3133202.3133204","url":null,"abstract":"With the rapid increase of users of wearable cameras in recent years and of the amount of data they produce, there is a strong need for automatic retrieval and summarization techniques. This work addresses the problem of automatically summarizing egocentric photo streams captured through a wearable camera by taking an image retrieval perspective. After removing non-informative images by a new CNN-based filter, images are ranked by relevance to ensure semantic diversity and finally re-ranked by a novelty criterion to reduce redundancy. To assess the results, a new evaluation metric is proposed which takes into account the non-uniqueness of the solution. Experimental results applied on a database of 7,110 images from 6 different subjects and evaluated by experts gave 95.74% of experts satisfaction and a Mean Opinion Score of 4.57 out of 5.0.","PeriodicalId":265670,"journal":{"name":"Proceedings of the 2nd Workshop on Lifelogging Tools and Applications","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128196172","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：