In Tags We Trust: Trust modeling in social tagging of multimedia content

Ivanov, Ivan; Vajda, Péter; Lee, Jong-Seok; Ebrahimi, Touradj

doi:10.1109/msp.2011.942345

Cited by 20 publications

(17 citation statements)

References 22 publications

(39 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To each video sequence in the dataset, a semi-automatic segmentation and tracking algorithm was applied in order to obtain a binary mask 4 , identifying a foreground object of interest, which not only plays a certain role in the understanding of the situation under White female, wears scarf around her face, walks toward the camera surveillance, but also may contain potentially privacy sensitive information. Different privacy protection filters were then applied to the extracted foreground objects.…”

Section: Use Cases and Underlying Databasementioning

confidence: 99%

“…Such measures insured significantly more reliable results of the subjective tests, compared to a classical crowdsourcing scenario. Otherwise, we could use statistical analysis for determining the behavioral outliers as presented in [4]. Also, we used Facebook, instead of such tools like Amazon Mechanical Turk 3 , to avoid paying people, which could lead to situation when people maximize their profits at the expense of honest evaluation results.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Crowdsourcing approach for evaluation of privacy filters in video surveillance

Korshunov

Cai

Ebrahimi

2012

Proceedings of the ACM Multimedia 2012 Workshop on Crowdsourcing for Multimedia

Self Cite

View full text Add to dashboard Cite

Extensive adoption of video surveillance, affecting many aspects of the daily life, alarms the concerned public about the increasing invasion into personal privacy. To address these concerns, many tools have been proposed for protection of personal privacy in image and video. However, little is understood regarding the effectiveness of such tools and especially their impact on the underlying surveillance tasks. In this paper, we propose conducting a subjective evaluation using crowdsourcing to analyze the tradeoff between the preservation of privacy offered by these tools and the intelligibility of activities under video surveillance. As an example, the proposed method is used to compare several commonly employed privacy protection techniques, such as blurring, pixelization, and masking applied to indoor surveillance video. Facebook based crowdsourcing application was specifically developed to gather the subjective evaluation data. Based on more than one hundred participants, the evaluation results demonstrate that the pixelization filter provides the best performance in terms of balance between privacy protection and intelligibility. The results obtained with crowdsourcing application were compared with results of previous work using more conventional subjective tests showing that they are highly correlated.

show abstract

Section: Use Cases and Underlying Databasementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Crowdsourcing approach for evaluation of privacy filters in video surveillance

Korshunov

Cai

Ebrahimi

2012

Proceedings of the ACM Multimedia 2012 Workshop on Crowdsourcing for Multimedia

Self Cite

View full text Add to dashboard Cite

show abstract

“…Ivanov et al [8] surveyed recent advances in techniques for combatting noise and spam in social tagging systems, classified the state-of-the-art approaches into a few categories and qualitatively compared and contrasted them.…”

Section: Spam Fighting In Social Tagging Systemsmentioning

confidence: 99%

Spam Fighting in Social Tagging Systems

Yazdani

Ivanov

Analoui

et al. 2012

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Abstract. Tagging in online social networks is very popular these days, as it facilitates search and retrieval of diverse resources available online. However, noisy and spam annotations often make it difficult to perform an efficient search. Users may make mistakes in tagging and irrelevant tags and resources may be maliciously added for advertisement or self-promotion. Since filtering spam annotations and spammers is time-consuming if it is done manually, machine learning approaches can be employed to facilitate this process. In this paper, we propose and analyze a set of distinct features based on user behavior in tagging and tags popularity to distinguish between legitimate users and spammers. The effectiveness of the proposed features is demonstrated through a set of experiments on a dataset of social bookmarks.

show abstract

“…Trust modeling can be performed at each level separately (e.g., [25]), or different levels can be considered jointly to produce trust models, for example, to assess a user's reliability, one can consider not only the user profile but also the content that the user uploaded to a social network (e.g., [20]). Trust modeling approaches can be categorized into two classes according to the target of trust, that is, content and user trust modeling [12].…”

Section: Trust Modeling In Social Mediamentioning

confidence: 99%

“…An interesting point is that, for the time being, Liu et al collected the largest dataset for trust modeling by crawling Delicious [12]. This dataset had around 82,000 users, 1:1 million tags, 9:3 million bookmarks, and 17:4 million tagbookmark associations.…”

Section: A Wisdom Of Crowds Modelmentioning

confidence: 99%

Geotag Propagation with User Trust Modeling

Ivanov

Vajda

Lee

et al. 2012

Computer Communications and Networks

Self Cite

View full text Add to dashboard Cite

The amount of information that people share on social networks is constantly increasing. People also comment, annotate, and tag their own content (videos, photos, notes, etc.), as well as the content of others. In many cases, the content is tagged manually. One way to make this time-consuming manual tagging process more efficient is to propagate tags from a small set of tagged images to the larger set of untagged images automatically. In such a scenario, however, a wrong or a spam tag can damage the integrity and reliability of the automated propagation system. Users may make mistakes in tagging, or irrelevant tags and content may be added maliciously for advertisement or self-promotion. Therefore, a certain mechanism insuring the trustworthiness of users or published content is needed. In this chapter, we discuss several image retrieval methods based on tags, various approaches to trust modeling and spam protection in social networks, and trust modeling in geotagging systems. We then consider a specific example of automated geotag propagation system that adopts a user trust model. The tag propagation in images relies on the similarity between image content (famous landmarks) and its context (associated geotags). For each tagged image, similar untagged images are found by the robust graph-based object duplicate detection, and the known tags are propagated accordingly. The user trust value is estimated based on a social feedback from the users of the photo-sharing system, and only tags from trusted users are propagated. This approach demonstrates that a practical tagging system significantly benefits from the intelligent combination of efficient propagation algorithm and a user-centered trust model.

show abstract

In Tags We Trust: Trust modeling in social tagging of multimedia content

Cited by 20 publications

References 22 publications

Crowdsourcing approach for evaluation of privacy filters in video surveillance

Crowdsourcing approach for evaluation of privacy filters in video surveillance

Spam Fighting in Social Tagging Systems

Geotag Propagation with User Trust Modeling

Contact Info

Product

Resources

About