Rahul Nair - Academia.edu (original) (raw)

Papers by Rahul Nair

The advent of media-sharing sites like Flickr and YouTube has drastically increased the volume of... more The advent of media-sharing sites like Flickr and YouTube has drastically increased the volume of community-contributed multimedia resources available on the web. These collections have a previously unimagined depth and breadth, and have generated new opportunities -and new challenges -to multimedia research. How do we analyze, understand and extract patterns from these new collections? How can we use these unstructured, unrestricted community contributions of media (and annotation) to generate "knowledge"?

The number of digital photographs is growing beyond the abilities of individuals to easily manage... more The number of digital photographs is growing beyond the abilities of individuals to easily manage and understand their own photo collections. Photo LOI (Level of Interest) is a technique that filters, aggregates, and visualizes photographs taken by multiple users who shared temporal, spatial, and/or social context at the point of photo capture. Photo LOI enables groups of photographers to see and manipulate visualizations of their photographic activities over time and social space in order to help cluster and select photos, and enables researchers to study contextual patterns in the phototaking habits of different users and groups of users. In this paper we give a brief overview of Photo LOI's features and describe some of its applications.

The availability of map interfaces and location-aware devices makes a growing amount of unstructu... more The availability of map interfaces and location-aware devices makes a growing amount of unstructured, geo-referenced information available on the Web. This type of information can be valuable not only for browsing, finding and making sense of individual items, but also in aggregate form to help understand data trends and features. In particular, over twenty million geo-referenced photos are now available on Flickr, a photo-sharing website -the first major collection of its kind. These photos are often associated with userentered unstructured text labels (i.e., tags). We show how we analyze the tags associated with the geo-referenced Flickr images to generate aggregate knowledge in the form of "representative tags" for arbitrary areas in the world. We use these tags to create a visualization tool, World Explorer, that can help expose the content of the data, using a map interface to display the derived tags and the original photo items. We perform a qualitative evaluation of World Explorer that outlines the visualization's benefits in browsing this type of content. We provide insights regarding the aggregate versus individual-item requirements in browsing digital geo-referenced material.

IEEE Multimedia, 2008

We describe ZoneTag, a camera phone application that allows users to capture, annotate, and share... more We describe ZoneTag, a camera phone application that allows users to capture, annotate, and share photos directly from their phone. We describe the simple mechanism for deriving tag suggestions and the ensuing interaction design for presenting these suggestions to the user. We also discuss quantitative and qualitative results from an 18-months deployment of ZoneTag, emphasizing the way people use and understand tag suggestions. In addition, we highlight several emerging issues that could play an important role in the collaborative tagging for multimedia as well as other resources. While the quantitative study on the use of the suggested tags feature implies clear benefits for tag suggestions, a set of qualitative studies imply that while tag suggestions are helpful, there are multiple issues that arise and require careful consideration.

Bluetooth has become a widely used source of co-presence information to determine a user's social... more Bluetooth has become a widely used source of co-presence information to determine a user's social context. However using Bluetooth in this way has several technological limitations including sensing time and effective range. This paper describes the technique of "Bluetooth pooling" which aggregates Bluetooth metadata collected from multiple users and propagates it among proximal users to create a more accurate record of co-presence. We also present the results of applying the Bluetooth pooling technique to a real world dataset of cameraphone photos annotated with Bluetooth co-presence metadata collected from over 65 users over 7 months.

Cameraphones are rapidly becoming a global platform for everyday digital imaging especially for n... more Cameraphones are rapidly becoming a global platform for everyday digital imaging especially for networked sharing of media from mobile devices. However, their constrained user interfaces and the current network and application infrastructure encumber the basic tasks of transferring, finding, and sharing captured media. We have deployed a prototype context-aware cameraphone application for mobile media sharing (MMM2) that aims to overcome these difficulties. MMM2 leverages the point of capture and of sharing to gather metadata, and uses metadata to support sharing. Based on the early results of the first 6 weeks of a sixmonth trial involving 60 users, indications are that with MMM2 users are actively capturing and sharing photos. The ability to automatically upload photos from a cameraphone to a web-based photo management application and to automatically suggest sharing recipients at the time of capture based on Bluetooth-sensed co-presence and sharing frequency promise to reduce the current difficulty of mobile media sharing.

Data regarding the physical location of GSM cell towers is important for many practical applicati... more Data regarding the physical location of GSM cell towers is important for many practical applications. Unfortunately, such data is not freely available in many countries. We present a system where users who tag and organize their camera-phone photos on Flickr implicitly contribute information about the physical location of cell towers. The system has been deployed on a test basis for 3 months, and currently has about 100 active users. In this period, users mapped a total of 1799 cell towers to a city level or zip (postal) code level. At this rate, assuming uniform distribution of users and cell towers, 10,000 users could map every GSM cell tower in the United States in less than 10 weeks.

What happens when you can access all the world's media, but the access is constrained by screen s... more What happens when you can access all the world's media, but the access is constrained by screen size, bandwidth, attention, and battery life? We present a novel mobile contextaware software prototype that enables access to images on the go. Our prototype utilizes the channel metaphor to give users contextual access to media of interest according to key dimensions: spatial, social, and topical.

ZoneTag is a rich mobile client that enables context-aware upload of photographs from cameraphone... more ZoneTag is a rich mobile client that enables context-aware upload of photographs from cameraphones. In addition to automatically supplying location metadata for each photograph, ZoneTag supports media annotation via context-based tag suggestions. Sources for tag suggestions include past tags from the user, the user's social network, and the public, as well as names of real world entities such as restaurants, events, and venues near the user's location. A seamless interface makes it easy to assign tags to a photo, forming the basis for a richer personal media retrieval and organization system. We believe that lowering the barriers to tagging has great potential for effective retrieval.

Abstract We designed and iterated on a photo browsing application for high-end mobile phones. The... more Abstract We designed and iterated on a photo browsing application for high-end mobile phones. The application, Zurfer, supports viewing of photos from the user, their contacts, and the general user population. Photos are organized using a channel metaphor, driven by multiple dimensions: social, spatial and topical. Zurfer was deployed to over 500 users; extensive user research was conducted with nine participants. The data from the deployment and the study exposes general themes of mobile application use, as well as ...

As sharing personal media online becomes easier and widely spread, new privacy concerns emerge -e... more As sharing personal media online becomes easier and widely spread, new privacy concerns emerge -especially when the persistent nature of the media and associated context reveals details about the physical and social context in which the media items were created. In a first-of-its-kind study, we use context-aware camerephone devices to examine privacy decisions in mobile and online photo sharing. Through data analysis on a corpus of privacy decisions and associated context data from a real-world system, we identify relationships between location of photo capture and photo privacy settings. Our data analysis leads to further questions which we investigate through a set of interviews with 15 users. The interviews reveal common themes in privacy considerations: security, social disclosure, identity and convenience. Finally, we highlight several implications and opportunities for design of media sharing applications, including using past privacy patterns to prevent oversights and errors.

The advent of media-sharing sites like Flickr and YouTube has drastically increased the volume of... more The advent of media-sharing sites like Flickr and YouTube has drastically increased the volume of community-contributed multimedia resources available on the web. These collections have a previously unimagined depth and breadth, and have generated new opportunities -and new challenges -to multimedia research. How do we analyze, understand and extract patterns from these new collections? How can we use these unstructured, unrestricted community contributions of media (and annotation) to generate "knowledge"?

The number of digital photographs is growing beyond the abilities of individuals to easily manage... more The number of digital photographs is growing beyond the abilities of individuals to easily manage and understand their own photo collections. Photo LOI (Level of Interest) is a technique that filters, aggregates, and visualizes photographs taken by multiple users who shared temporal, spatial, and/or social context at the point of photo capture. Photo LOI enables groups of photographers to see and manipulate visualizations of their photographic activities over time and social space in order to help cluster and select photos, and enables researchers to study contextual patterns in the phototaking habits of different users and groups of users. In this paper we give a brief overview of Photo LOI's features and describe some of its applications.

The availability of map interfaces and location-aware devices makes a growing amount of unstructu... more The availability of map interfaces and location-aware devices makes a growing amount of unstructured, geo-referenced information available on the Web. This type of information can be valuable not only for browsing, finding and making sense of individual items, but also in aggregate form to help understand data trends and features. In particular, over twenty million geo-referenced photos are now available on Flickr, a photo-sharing website -the first major collection of its kind. These photos are often associated with userentered unstructured text labels (i.e., tags). We show how we analyze the tags associated with the geo-referenced Flickr images to generate aggregate knowledge in the form of "representative tags" for arbitrary areas in the world. We use these tags to create a visualization tool, World Explorer, that can help expose the content of the data, using a map interface to display the derived tags and the original photo items. We perform a qualitative evaluation of World Explorer that outlines the visualization's benefits in browsing this type of content. We provide insights regarding the aggregate versus individual-item requirements in browsing digital geo-referenced material.

IEEE Multimedia, 2008

We describe ZoneTag, a camera phone application that allows users to capture, annotate, and share... more We describe ZoneTag, a camera phone application that allows users to capture, annotate, and share photos directly from their phone. We describe the simple mechanism for deriving tag suggestions and the ensuing interaction design for presenting these suggestions to the user. We also discuss quantitative and qualitative results from an 18-months deployment of ZoneTag, emphasizing the way people use and understand tag suggestions. In addition, we highlight several emerging issues that could play an important role in the collaborative tagging for multimedia as well as other resources. While the quantitative study on the use of the suggested tags feature implies clear benefits for tag suggestions, a set of qualitative studies imply that while tag suggestions are helpful, there are multiple issues that arise and require careful consideration.

Bluetooth has become a widely used source of co-presence information to determine a user's social... more Bluetooth has become a widely used source of co-presence information to determine a user's social context. However using Bluetooth in this way has several technological limitations including sensing time and effective range. This paper describes the technique of "Bluetooth pooling" which aggregates Bluetooth metadata collected from multiple users and propagates it among proximal users to create a more accurate record of co-presence. We also present the results of applying the Bluetooth pooling technique to a real world dataset of cameraphone photos annotated with Bluetooth co-presence metadata collected from over 65 users over 7 months.

Cameraphones are rapidly becoming a global platform for everyday digital imaging especially for n... more Cameraphones are rapidly becoming a global platform for everyday digital imaging especially for networked sharing of media from mobile devices. However, their constrained user interfaces and the current network and application infrastructure encumber the basic tasks of transferring, finding, and sharing captured media. We have deployed a prototype context-aware cameraphone application for mobile media sharing (MMM2) that aims to overcome these difficulties. MMM2 leverages the point of capture and of sharing to gather metadata, and uses metadata to support sharing. Based on the early results of the first 6 weeks of a sixmonth trial involving 60 users, indications are that with MMM2 users are actively capturing and sharing photos. The ability to automatically upload photos from a cameraphone to a web-based photo management application and to automatically suggest sharing recipients at the time of capture based on Bluetooth-sensed co-presence and sharing frequency promise to reduce the current difficulty of mobile media sharing.

Data regarding the physical location of GSM cell towers is important for many practical applicati... more Data regarding the physical location of GSM cell towers is important for many practical applications. Unfortunately, such data is not freely available in many countries. We present a system where users who tag and organize their camera-phone photos on Flickr implicitly contribute information about the physical location of cell towers. The system has been deployed on a test basis for 3 months, and currently has about 100 active users. In this period, users mapped a total of 1799 cell towers to a city level or zip (postal) code level. At this rate, assuming uniform distribution of users and cell towers, 10,000 users could map every GSM cell tower in the United States in less than 10 weeks.

What happens when you can access all the world's media, but the access is constrained by screen s... more What happens when you can access all the world's media, but the access is constrained by screen size, bandwidth, attention, and battery life? We present a novel mobile contextaware software prototype that enables access to images on the go. Our prototype utilizes the channel metaphor to give users contextual access to media of interest according to key dimensions: spatial, social, and topical.

ZoneTag is a rich mobile client that enables context-aware upload of photographs from cameraphone... more ZoneTag is a rich mobile client that enables context-aware upload of photographs from cameraphones. In addition to automatically supplying location metadata for each photograph, ZoneTag supports media annotation via context-based tag suggestions. Sources for tag suggestions include past tags from the user, the user's social network, and the public, as well as names of real world entities such as restaurants, events, and venues near the user's location. A seamless interface makes it easy to assign tags to a photo, forming the basis for a richer personal media retrieval and organization system. We believe that lowering the barriers to tagging has great potential for effective retrieval.

Abstract We designed and iterated on a photo browsing application for high-end mobile phones. The... more Abstract We designed and iterated on a photo browsing application for high-end mobile phones. The application, Zurfer, supports viewing of photos from the user, their contacts, and the general user population. Photos are organized using a channel metaphor, driven by multiple dimensions: social, spatial and topical. Zurfer was deployed to over 500 users; extensive user research was conducted with nine participants. The data from the deployment and the study exposes general themes of mobile application use, as well as ...

As sharing personal media online becomes easier and widely spread, new privacy concerns emerge -e... more As sharing personal media online becomes easier and widely spread, new privacy concerns emerge -especially when the persistent nature of the media and associated context reveals details about the physical and social context in which the media items were created. In a first-of-its-kind study, we use context-aware camerephone devices to examine privacy decisions in mobile and online photo sharing. Through data analysis on a corpus of privacy decisions and associated context data from a real-world system, we identify relationships between location of photo capture and photo privacy settings. Our data analysis leads to further questions which we investigate through a set of interviews with 15 users. The interviews reveal common themes in privacy considerations: security, social disclosure, identity and convenience. Finally, we highlight several implications and opportunities for design of media sharing applications, including using past privacy patterns to prevent oversights and errors.