Monthly Archive for August, 2008

A. Graham, H. Garcia-Molina, A. Paepcke, and T. Winograd. Time as essence for photo browsing through personal digital libraries. In JCDL ’02: Proceedings of the 2nd ACM/IEEE-CS joint conference on Digital libraries, pages 326–335, New York, NY, USA, 2002. ACM. [PDF]

———-

This paper decribes PhotoBrowser, a prototype system for personal digital pictures that organize the content using the timestamps of each photo. The authors’ main assumption is that text annotations are great because are accessible to a variety of search and processing algorithms. Many systems exploits this possibility requiring time-intensive manual annotations (e.g., FotoFile [Kang and Shneiderman, 2000] and PhotoFinder Kuchinsky et al., 1999]).

The authors’ proposal is that of exploiting the timestamps at which the pictures have been taken. They propose an organizational, and visual, clustering of the pictures which divide the photos using longer periods of inactivities between one picture and the next.

To verify their assumption, the authors tested the PhotoBrowser against other two applications. The first was a Hierarchical Browser, which organized the pictures at different levels corresponding to time at different granularity. The Scrollable Browser, organized the pictures into a single time-ordered list that could be scrolled.

The author asked 12 subjects to perform 6 retrieval tasks following different criteria. Their main result was that the browser that organized the pictures into temporal clusters enabled significantly faster completion times at an average of about 50 seconds.

T. Tan, J. Chen, P. Mulhem, and M. Kankanhalli. Smartalbum: a multi-modal photo annotation system. In MULTIMEDIA ’02: Proceedings of the tenth ACM international conference on Multimedia, pages 87–88, New York, NY, USA, 2002. ACM. [PDF]

——-

Applications supporting annotation of pictures with voice: SmartAlbum (Tan et al., 2002) that unifies two indexing approaches, namely content-based and speech, Chen et al. (2001) proposed the use of a structural speech syntax to annotate photographs in four different fields, namely event, location, people, and date/time. Show&Tell (Srihari et al., 1999), which uses speech annotations to index and retrieve both personal and medical images, and FotoFile (Kuchinsky et al., 1999), which extends annotation to a more general multimedia object.

This demonstration presents a novel application (called SmartAlbum) for photo indexing and retrieval that unifies two different image indexing approaches. The system uses two modalities to extract information about a digital photograph; i.e. content-based and speech annotation for image description. The result is a powerful image retrieval tool that has capabilities beyond what current single-mode retrieval systems can offer. We show on a corpus of 1200 images the interest of our approach.

R. Wasinger and A. Krüger. Modality preference – learning from users. In Proceedings of the User Experience Design for Pervasive Computing workshop, Munich, Germany, 11 May 2005. [PDF]

——-

This paper describes a qualitative comparison of input modalities for mobile applications. The author conducted a user study with about 50 users that were asked to fill questionnaires on a PDA. The questions targeted products that the users could find in a shop and therefore had to be answered while on the place. The users were divided in different groups and each group was exposed to different input modality: speech, handwriting, intra- and extra-gestures.

Interestingly, speech was reported as being the most comfortable modality to use in comparison with handwriting but also the modality that could mostly expose privacy. Users reported being uncomfortable speaking sensible information to their devices. Handwriting was see as conflicting with other manual activities that needed to be carried out while shopping.

B. Schneiderman and H. Kang. Direct annotation: A drag-and-drop strategy for labeling photos. In IV ’00: Proceedings of the International Conference on Information Visualisation, pages 88–96, Washington, DC, USA, 2000. IEEE Computer Society. [PDF]

———–

The basic argument of the authors of this paper is that large pictures collections need annotation in order to support efficient retrieval. However, annotation is a tedious and time-consuming task. The authors present in this paper a basic HCI technique which allows the user to annotate without much typing. Keywords can be inputed once-for-all through a list and becomes available to be dragged and dropped over pictures.

The system has the advantage of supporting labeling of regions of the pictures (see figure below) but has the disadvantage of reduced scalability.

Annotating photos is such a time-consuming, tedious and error-prone data entry task that it discourages most owners of personal photo libraries. By allowing users to drag labels such as personal names from a scrolling list and drop them on a photo, we believe we can make the task faster, easier and more appealing. Since the names are entered in a database, searching for all photos of a friend or family member is dramatically simplified. We describe the user interface design and the database schema to support direct annotation, as implemented in our PhotoFinder prototype.

A. Wilhelm, Y. Takhteyev, R. Sarvas, N. V. House, and M. Davis. Photo annotation on a camera phone. In CHI ’04: CHI ’04 extended abstracts on Human factors in computing systems, pages 1403–1406, New York, NY, USA, 2004. ACM. [PDF]

——

This paper argues for the use of the multimedia capabilities of phones for helping indexing and retrieval of pictures. They built a system capable of incorporating metadata, like the user’s position, and keywords defined by the user to the picture. This information was stored to a remote server and then used during retrieval.

To evaluate their design they conducted a user study where they deployed the system to a group of 55 participants. They found that one fo the major problem was the unpredictability of the network connection that made interaction with the remote server lenghty. From the study they also learned that participants used the camera of their phone extensively but the value that they attributed to many pictures was very little. Instead, they users took advantage of the networking capabilities of the phone to share events of their life with their friends. The capture of these moments would have not been possible without the continuous availability of the mobile phone.

Interviewed participants expressed more interest for sharing and browsing the captured images than retrieving specific pictures. They were generally not interested in fully annotating pictures using keywords.

C. Marlow, M. Naaman, D. Boyd, and M. Davis. Ht06, tagging paper, taxonomy, flickr, academic article, to read. In HYPERTEXT ’06: Proceedings of the seventeenth conference on Hypertext and hypermedia, pages 31–40, New York, NY, USA, 2006. ACM. [PDF]

———

This seminal paper presents a taxonomy of tagging systems based on incentives and contribution models to inform potential evaluative frameworks. First, the authors explain why tagging systems are used and the different strands of research around this area, namely the social bookmarking, the social tagging systems, and folksonomies. They explain how these systems are affected by the vocabulary problem, where different users use different terms to describe the same thing.

The authors model a prototypical tagging system as having three components, a number of resourcer, tags associated to these resources and users who generated the tags. Some systems can have links among the resources and/or links among the users.

The taxonomy they define contains seven categories: tagging rights, or the system’s restriction on group tagging; tagging support, or the mechanism of tag entry being either blind (the user cannot view the tags assigned by others to the same resource), viewable or suggestive; the form of aggregation of tags around a given resource, namely collecting repeated tags generated by different users, or bag-model, or aggregating the most frequent tags, or set-model; another difference is the type of object being tagged; related to this last point is the source of the material, the resources can be supplied by the participants, by the system, or being pubicly available; additionally, the resources can be linked, grouped or separated; finally, the users can be linked, grouped or kept separated.

Concerning the user incentives, tagging is performed for different reasons: for future retrieval; for contribution and sharing; to attract attention; to play or compete; for self presentation; and finally for expressing opinions.

Finally the paper presents an interesting analysis of a Flickr dataset. The authors studied the growth of distinct tags for 10 randomly selected users over the course of uploaded photo. They found a number of different behaviors. In some cases new tags are added consistently as photo are uploaded. Sometimes, only few tags are used at the beginning and more later on. For many users distinct tag growth declines over time. Finaly, they found vocabulary inside a community of users to be more overlapping than the vocabulary of a random sample of unconnected users.

M. Ames and M. Naaman. Why we tag: motivations for annotation in mobile and online media. In CHI ’07: Proceedings of the SIGCHI conference on Human factors in computing systems, pages 971–980, New York, NY, USA, 2007. ACM. [PDF]

——-

This paper present a throughout study of people using a mobile application for tagging pictures. The author conducted photo elicitation interviews of Flickr users that were active in uploading pictures from their mobile using ZoneTag, an ad-hoc application for mobile picture tagging and photo sharing.

The authors defined eight intertwined reasons of why people use tags. These could be described by the different function, being either organization or communication, or sociality, directed to self or to others.

Interestingly, the author found that while adding context is the traditional motivation for annotating printed photographs, this was not the primary concern of interviewed participants: ”while it is likely that tags will provide this function as a currently-unanticipated benefit in the future, adding context to facilitate remembering details about photographs was not the primary motivation for tagging in the present.”

As the picture taken by ZoneTag were automatically uploaded to Flickr, a community portal for photo sharing, other interesting behavior emerge. For instance, some participant reported coordinating tags with other to form a distributed photo ”pool”.

The authors conclude the article by suggesting a number of implications for design. In particular they suggested that the annotation functionality should be pervasive and multi-functional covering the different aspect of their suggested taxonomy. Also, they suggested to have flexibility in the annotation mecanism, leaving the tagging feature as an option and not mandatory. Finally, they suggested to have both mobile and desktop components to leverage the fast entry and the processing power of the desktop application.