Automatic image semantic interpretation using social action and tagging data

Sawant, Neela; Li, Jia; Wang, James

doi:10.1007/s11042-010-0650-8

Cited by 41 publications

(36 citation statements)

References 161 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…and have posted queries as the following with max weight (5) with weight (4) these annotations are to be more convenient to be used as indexing due to its weight factor and by socializing it to other clients like the highest effective annotations will be , This is for the same URL. will be indexed using key {race, fancy, celebrity and sport .…”

Section: Resultsmentioning

confidence: 99%

“…The AIM project can be integrated with what we are presenting to provide consistent ontological environment for image retrieval and annotations. The same annotation context is presented by [7] and [4] but both depend on the retrieval and extraction of knowledge from the resources available on the global net.…”

Section: Related Workmentioning

confidence: 99%

“…Other sources of image annotations are collaborative games and social media sharing which undoubtedly represent the fastest growing labeled image collections in the world [3] [4].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Automatic Image Annotation using Image clustering in Multi – Agent Society

Khorsheed¹,

Chible²,

Giacinto³

2014

IJCATR

View full text Add to dashboard Cite

Image annotation is the natural language description for essential blobs within an Image. Many methodologies have recruited to reveal image semantics and represent it as annotation. Due to the exclusionary growth of number of images distributed over massive repositories, the task of manual annotation is tedious and over killing in term of times and efforts. This paper is presenting automatic annotation system based on the interaction between intelligent agents. Agent interaction is synonym to socialization behavior dominating Agent society. The presented system is exploiting knowledge evolution revenue due to the socialization to charge up the annotation process

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Automatic Image Annotation using Image clustering in Multi – Agent Society

Khorsheed¹,

Chible²,

Giacinto³

2014

IJCATR

View full text Add to dashboard Cite

show abstract

“…Content analysis was then introduced to complement metadata in clustering photos: colour analysis and time to detect a scene and mark an event (Platt et al 2003, Cooper et al 2005; content analysis and GPS information to automatically identify relevant buildings (O'Hare et al 2005); and face recognition to organize personal photos into albums (Zhang et al 2005). This trend of enriching metadata has expanded to include other contextual information such as weather conditions (Naaman 2004), movement detection (to detect walking or standing via accelerometer data in a SenseCam (Qui et al 2011)), tags and social use (Sawant et al 2011). All these techniques performed well in lab evaluations, but studies in the home show that people do not use photo systems to organize their collections and often fail when retrieving .…”

Section: Systems For Capturing Organising and Retrieving Photosmentioning

confidence: 99%

Photo mementos: Designing digital media to represent ourselves at home

Petrelli

Bowen

Whittaker

2014

International Journal of Human-Computer Studies

View full text Add to dashboard Cite

We examine photos in the family home as examples of mementos, cherished objects kept in memory of a person or event. In a 'memory tour', we asked participants to walk us through their family home selecting and discussing significant mnemonic objects. With each personal narrative we recorded memento location, i.e. the room, place within the room and any nearby objects. Although photos were not the most popular mementos, when chosen they were highly significant, and often unique. These photo mementos were usually not representational but symbolic, where only the owner knows their many layers of meaning. Photos from different times in the person's life were strategically placed in different rooms. Their location afforded different functions, e.g. photo mementos in family spaces reinforced family bonds, photo mementos in personal spaces were for immersive reminiscing, whereas those in public rooms had an aesthetic value and to spark conversations with visitors. Finally photo mementos were rarely isolated: they were clustered in displayed albums or stored with other memorabilia in boxes or drawers to represent a stage in life. We explore the implications of these findings by designing potential new home photo technologies, looking at how new designs might support the types of behaviours observed. Through four conceptual designs we examine how photo technology might integrate into the practices and aesthetic of the family home. The concepts led to a set of concluding considerations that need to be taken into account when designing new forms of display technology that are part of a larger domestic photo system.

show abstract

“…The images are provided with the Flickr community's annotations, which sets this database apart from the previously mentioned. The annotations are of lower quality because they come from a large uncontrolled group of people (social tagging [22]), but they are abundant. Both the high quality of the photographs and the social tagging made us choose this database.…”

Section: Related Workmentioning

confidence: 99%

Joint statistical analysis of images and keywords with applications in semantic image enhancement

Lindner

Shaji

Bonnier³

et al. 2012

Proceedings of the 20th ACM International Conference on Multimedia

View full text Add to dashboard Cite

With the advent of social image-sharing communities, millions of images with associated semantic tags are now available online for free and allow us to exploit this abundant data in new ways. We present a fast non-parametric statistical framework designed to analyze a large data corpus of images and semantic tag pairs and find correspondences between image characteristics and semantic concepts. We learn the relevance of different image characteristics for thousands of keywords from one million annotated images. We demonstrate the framework's effectiveness with three different examples of semantic image enhancement: we adapt the gray-level tone-mapping, emphasize semantically relevant colors, and perform a defocus magnification for an image based on its semantic context. The performance of our algorithms is validated with psychophysical experiments.

show abstract

Automatic image semantic interpretation using social action and tagging data

Cited by 41 publications

References 161 publications

Automatic Image Annotation using Image clustering in Multi – Agent Society

Automatic Image Annotation using Image clustering in Multi – Agent Society

Photo mementos: Designing digital media to represent ourselves at home

Joint statistical analysis of images and keywords with applications in semantic image enhancement

Contact Info

Product

Resources

About