Human computation: Image metadata acquisition based on a single-player annotation game

Šimko, Jakub; Tvaroek, Michal; Bieliková, Mária

doi:10.1016/j.ijhcs.2013.05.002

Cited by 12 publications

(5 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Automatic approaches aim to identify semantics relevant to the content of static images via the identification of visual features. Various approaches that use machine learning for image or image region categorization can perform well, but are limited to a small number of categories and the lack of training sets to be used effectively for the acquisition of more specific metadata [13]. Generally, automated approaches introduce certain inaccuracy, which makes them difficult to apply to heterogeneous resources.…”

Section: Gamifying Image Labellingmentioning

confidence: 99%

“…Generally, automated approaches introduce certain inaccuracy, which makes them difficult to apply to heterogeneous resources. More or less, they also need large training sets of already annotated images, which stress the initial requirement of human labour needed to create them [13]. The traditional approach to achieve high metadata quality is carried out by using dedicated experts, who are aware of the purpose of their activity and who annotate resources as their primary job.…”

Section: Gamifying Image Labellingmentioning

confidence: 99%

See 1 more Smart Citation

Crowdsourcing image descriptions using gamification: a comparison between game-generated labels and professional descriptors

Ivanjko

2019

2019 42nd International Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO)

View full text Add to dashboard Cite

The traditional approach to achieve high metadata quality in image description is to use subject experts. However, cultural heritage institutions often lack the human resources to handle the amount of material that is in need of description. One of the possible solutions to this problem is applying the gamification approach in the process of description. Many studies have shown that applying game design features outside traditional game environments can increase the motivation and productivity, and that those games can be particularly effective in invoking intrinsic motivations and overall enjoyment. However, there is a need to explore the quality of such game-generated tags in comparison with using controlled vocabularies and traditional approaches. In this paper, we compare game-generated image labels and professional descriptors. First, a subject expert using controlled vocabulary added descriptors for each image. Then, by using a gamified platform for collecting semantic annotations of digitized images, game-generated tags were collected. In the final stage, game-generated labels were evaluated by the subject expert in the context of appropriateness of using them as descriptors within a standardized system. Results have shown that gamegenerated labels can serve as a basis for high quality labels suitable for including a standardized description in order to enhance description and retrieval.

show abstract

Section: Gamifying Image Labellingmentioning

confidence: 99%

Section: Gamifying Image Labellingmentioning

confidence: 99%

Crowdsourcing image descriptions using gamification: a comparison between game-generated labels and professional descriptors

Ivanjko

2019

2019 42nd International Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO)

View full text Add to dashboard Cite

show abstract

“…The authors in [7] solve the problem that the GWAPs need to be multiplayer game by developing a game called PexAce. PexAce was developed to be a single player game to solve a problem called cold start.…”

Section: Related Workmentioning

confidence: 99%

“…To solve the problem that ESP need two or more players to label images. Jakub developed a new concentration game called PexAce [7]. The game solves the artifact validation problem using -helper artifacts‖.…”

Section: Introductionmentioning

confidence: 99%

Human Computation: Object Recognition for Mobile Games Based on Single Player

Sakr¹,

Mahgoub²,

Keshk³

2014

IJMECS

View full text Add to dashboard Cite

Smart phones and its applications gain a lot of popularity nowadays. Many people depend on them to finish their tasks banking, social networking, fun and a lot other things. Games with a purpose (GWAP) and microtask crowdsourcing are considered two techniques of the human-computation. GWAPs depend on humans to accomplish their tasks. Porting GWAPs to smart phones will be great in increasing the number of humans in it. One of the systems of human-computation is ESP Game. ESP Game is a type of games with a purpose. ESP game will be good candidate to be ported to smart phones. This paper presents a new mobile game called MemoryLabel. It is a single player mobile game. It helps in labeling images and gives description for them. In addition, the game gives description for objects in the image not the whole image. We deploy our algorithm at the University of Menoufia for evaluation. In addition, the game is published on Google play market for android applications. In this trial, we first focused on measuring the total number of labels generated by our game and also the number of objects that have been labeled. The results reveal that the proposed game has promising results in describing images and objects.

show abstract

“…Metadata has been demonstrated to help individuals understand the conceptual similarity between images retrieved by search systems and hence to facilitate an effective search process [15,16] by increasing information visibility [17]. However, metadata sometimes leads users astray, as their interpretation of the metadata can differ from that of the creators of the metadata [18,19]. As the nature of various types of metadata is different, individuals can have different preferences or search strategies when using it [20].…”

mentioning

confidence: 99%

Using eye movement sequences and hidden Markov model to explore strategy blending in metadata-supported image search

Lin

Chan

2023

Preprint

View full text Add to dashboard Cite

This study explores users’ search strategies associated with different information aids in an image search context. We investigate "strategy blending", i.e., the mixture of different strategies (tag-based and header-based) in a display with both possibilities. Using eye-movement-recordings, supported by Hidden Markov Model (HMM) modeling, we attempt to reveal strategies and tactics as well as the blending of different strategies. The findings make theoretical contributions to the literature on strategy blending and information seeking behavior and provide practitioners with guidelines on metadata support for website design to enhance the user experience and meet user needs. In our understanding of this domain, we are the first to bridge strategies in decision making to search strategies with actual users instead of using mere simulation. Strategy blending can be explained by investigating user search behavior in an image search context. HMMs can be used to discover latent search tactics, and user eye movement sequences reveal different types of strategy blending. For practical design in the context of image search, metadata is indeed useful to assist image search as a navigation support, and represents a better chance to fulfill the information needs of users. Responding to the emerging digital environment and the new paradigm of people’s search behavior with various devices, these results can be generalized to other research fields, such as mobile system design or user modeling, to satisfy various users with different needs.

show abstract

Human computation: Image metadata acquisition based on a single-player annotation game

Cited by 12 publications

References 26 publications

Crowdsourcing image descriptions using gamification: a comparison between game-generated labels and professional descriptors

Crowdsourcing image descriptions using gamification: a comparison between game-generated labels and professional descriptors

Human Computation: Object Recognition for Mobile Games Based on Single Player

Using eye movement sequences and hidden Markov model to explore strategy blending in metadata-supported image search

Contact Info

Product

Resources

About