Modeling tagged photos for automatic image annotation

Sawant, Neela

doi:10.1145/2072298.2072496

Cited by 4 publications

(3 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Among other interesting findings, scholars have determined that images are often used for self and social disclosure. In particular, tags associated with images are used to convey contextual or social information to those viewing the photo [35,30,14,4], motivating our hypothesis of using metadata as one among other features for privacy extraction.…”

Section: Related Workmentioning

confidence: 99%

“…A loosely related body of work is on recommendation of tags for social discovery [35,30,47,14] and for image classification [34,48,14] in photo sharing websites like Flickr. In these works, the typical approach is for authors to firstly collect adequate images and then classify images according to visual and context-related features.…”

Section: Related Workmentioning

confidence: 99%

“…Each of these feature vectors is invariant to any scaling, rotation or translation of the image. We extract a image profile based on the state-of-the-art model called Bag-of-visual-words (BoW) [37,44], which can effectively evaluate the image similarity, and is widely used in image similarity search, image retrieval and even content-based social discovery [35]. The image BoW vector is first obtained by extracting the features of preferred images, then clustering them into the visual word vocabulary , where each element is the distinct word occurrence.…”

Section: Visual Featuresmentioning

confidence: 99%

See 2 more Smart Citations

Analyzing images' privacy for the modern web

Squicciarini

Caragea

Balakavi

2014

Proceedings of the 25th ACM Conference on Hypertext and Social Media

View full text Add to dashboard Cite

Images are now one of the most common form of content shared in online user-contributed sites and social Web 2.0 applications. In this paper, we present an extensive study exploring privacy and sharing needs of users' uploaded images. We develop learning models to estimate adequate privacy settings for newly uploaded images, based on carefully selected image-specific features. We focus on a set of visualcontent features and on tags. We identify the smallest set of features, that by themselves or combined together with others, can perform well in properly predicting the degree of sensitivity of users' images. We consider both the case of binary privacy settings (i.e. public, private), as well as the case of more complex privacy options, characterized by multiple sharing options. Our results show that with few carefully selected features, one may achieve extremely high accuracy, especially when high-quality tags are available.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Visual Featuresmentioning

confidence: 99%

See 1 more Smart Citation

Analyzing images' privacy for the modern web

Squicciarini

Caragea

Balakavi

2014

Proceedings of the 25th ACM Conference on Hypertext and Social Media

View full text Add to dashboard Cite

show abstract

From Tag to Protect: A Tag-Driven Policy Recommender System for Image Sharing

Squicciarini¹,

Novelli

Lin

et al. 2017

2017 15th Annual Conference on Privacy, Security and Trust (PST)

View full text Add to dashboard Cite

Toward Automated Online Photo Privacy

2017

View full text Add to dashboard Cite

Online photo sharing is an increasingly popular activity for Internet users. More and more users are now constantly sharing their images in various social media, from social networking sites to online communities, blogs, and content sharing sites. In this article, we present an extensive study exploring privacy and sharing needs of users’ uploaded images. We develop learning models to estimate adequate privacy settings for newly uploaded images, based on carefully selected image-specific features. Our study investigates both visual and textual features of images for privacy classification. We consider both basic image-specific features, commonly used for image processing, as well as more sophisticated and abstract visual features. Additionally, we include a visual representation of the sentiment evoked by images. To our knowledge, sentiment has never been used in the context of image classification for privacy purposes. We identify the smallest set of features, that by themselves or combined together with others, can perform well in properly predicting the degree of sensitivity of users’ images. We consider both the case of binary privacy settings (i.e., public, private), as well as the case of more complex privacy options, characterized by multiple sharing options. Our results show that with few carefully selected features, one may achieve high accuracy, especially when high-quality tags are available.

show abstract

Modeling tagged photos for automatic image annotation

Cited by 4 publications

References 2 publications

Analyzing images' privacy for the modern web

Analyzing images' privacy for the modern web

From Tag to Protect: A Tag-Driven Policy Recommender System for Image Sharing

Toward Automated Online Photo Privacy

Contact Info

Product

Resources

About