Computing iconic summaries of general visual concepts

By Rahul Raguram, Svetlana Lazebnik. 2008

63 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Webly Supervised Learning of Convolutional Networks (2015, methodology): “After seventh layer, another fully connected layer is used to predict class labels.”
A Multi-View Embedding Space for Modeling Internet Images, Tags, and Their Semantics (2012, methodology): “The visual and semantic clusters discovered by tag clustering and subsequent CCA projection can be used to summarize and browse the content of Internet photo collections (Berg and Berg, 2009; Raguram and Lazebnik, 2008).”
Why do deep convolutional networks generalize so poorly to small image transformations? (2018, neutral): “Consistent with previous results on "dataset bias" [37, 33, 2, 44, 45, 32] we find that the ImageNet dataset is not invariant to translations and rescalings.”
Learning about Canonical Views from Internet Image Collections (2012, methodology): “Next we find the two first modes in the GIST space using Parzen window.”
Finding iconic images (2009, methodology): “In addition the data in our work (and [20, 18 , 15]) comes from flickr.com (Flickr) and has not been filtered by the multitude of hyper-link and anchor text features Google implements to rank it’s own image and web page search results as used in [10, 9, 3, 19, 7]. In addition the Flickr images are ”
NEIL: Extracting Visual Knowledge from Web Data (2013, background): “Affinity propagation also allows us to extract a representative window (prototype) for each cluster which acts as an iconic image for the object [32] (Figure 3).”
PRISM: concept-preserving social image search results summarization (2014, methodology): “Raguram and Lazebnik [12] propose a method that constructs a joint clustering on image descriptors and tag topic vectors independently before obtaining their intersection.”
Multi-Modal Knowledge Graph Construction and Application: A Survey (2022, background): “For example, in [112] the images of Beauty are associated with following word clusters: woman/girl, water/beach/ocean, flower/rose, sky/cloud/sunset.”
Sense discovery via co-clustering on images and text (2015, background): “There have been early efforts on automatically training visual classifiers using web data to build large datasets automatically [26, 39, 42, 27, 20], find iconic images [5, 35] and improve image retrieval results [19, 28, 45, 34].”