Computing iconic summaries of general visual concepts

Raguram, Rahul; Lazebnik, Svetlana

doi:10.1109/cvprw.2008.4562959

Cited by 45 publications

(38 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some other research works use clusteringbased approaches to discover canonical images. Raguram and Lazebnik [26] proposed to compute iconic views for a collection of images of any concept with joint clustering based on visual and textual features to extract subsets of images. Iconic views were chosen from images with the highest visual quality from each subset.…”

Section: Related Workmentioning

confidence: 99%

Latent visual context learning for web image applications

Zhou¹,

Tian²,

Lu³

et al. 2011

Pattern Recognition

View full text Add to dashboard Cite

Section: Related Workmentioning

confidence: 99%

Latent visual context learning for web image applications

Zhou¹,

Tian²,

Lu³

et al. 2011

Pattern Recognition

View full text Add to dashboard Cite

“…Iconic images: Our work is indirectly related to iconic images, explored by Raguram et al [20] and Berg and Berg [3]. Iconic images are representative images of a specified object category.…”

Section: Scene Understandingmentioning

confidence: 99%

Learning to Select and Order Vacation Photographs

Sadeghi

Tena²,

Farhadi

et al. 2015

2015 IEEE Winter Conference on Applications of Computer Vision

View full text Add to dashboard Cite

We propose the problem of automated photo album creation from an unordered image collection. The problem is difficult as it involves a number of complex perceptual tasks that facilitate selection and ordering of photos to create a compelling visual narrative. To help solve this problem, we collect (and will make available) a new benchmark dataset based on Flickr images. Flickr Album Dataset and provides a variety of annotations useful for the task, including manually created albums of various lengths. We analyze the problem and provide experimental evidence, through user studies, that both selection and ordering of photos within an album is important for human observers. To capture and learn rules of album composition, we propose a discriminative structured model capable of encoding simple preferences for contextual layout of the scene (e.g., spatial layout of faces, global scene context, and presence/absence of attributes) and ordering between photos (e.g., exclusion principles or correlations). The parameters of the model are learned using a structured SVM framework. Once learned, the model allows automatic composition of photo albums from unordered and untagged collections of images. We quantitatively evaluate the results obtained using our model against manually created albums and baselines on a dataset of 63 personal photo collections from 5 different topics.

show abstract

“…Recently, a number of papers have proposed a very general notion of canonical or iconic images as good representative images for arbitrary visual categories [Berg and Berg, 2009, Jing and Baluja, 2008, Raguram and Lazebnik, 2008. These approaches try to find iconic images essentially by 2D image clustering, with some possible help from additional features such as text.…”

Section: Previous Workmentioning

confidence: 99%

Modeling and Recognition of Landmark Image Collections Using Iconic Scene Graphs

Raguram

Frahm

et al. 2011

Int J Comput Vis

Self Cite

View full text Add to dashboard Cite

This article presents an approach for modeling landmarks based on large-scale, heavily contaminated image collections gathered from the Internet. Our system efficiently combines 2D appearance and 3D geometric constraints to extract scene summaries and construct 3D models. In the first stage of processing, images are clustered based on low-dimensional global appearance descriptors, and the clusters are refined using 3D geometric constraints. Each valid cluster is represented by a single iconic view, and the geometric relationships between iconic views are captured by an iconic scene graph. Using structure from motion techniques, the system then registers the iconic images to efficiently produce 3D models of the different aspects of the landmark. To improve coverage of the scene, these 3D models are subsequently extended using additional, non-iconic views. We also demonstrate the use of iconic images for recognition and browsing. Our experimental results demonstrate the ability to process datasets containing up to 46,000 images in less than 20 hours, using a single commodity PC equipped with a graphics card. This is a significant advance towards Internet-scale operation.

show abstract

Computing iconic summaries of general visual concepts

Cited by 45 publications

References 17 publications

Latent visual context learning for web image applications

Latent visual context learning for web image applications

Learning to Select and Order Vacation Photographs

Modeling and Recognition of Landmark Image Collections Using Iconic Scene Graphs

Contact Info

Product

Resources

About