Finding iconic images

By Tamara L. Berg, Alexander C. Berg. 2009

82 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

Microsoft COCO: Common Objects in Context (2014, background): “ 3.2 Non-iconic Image Collection Given the list of object categories, our next goal was to collect a set of candidate images. We may roughly group images into three types, Fig.2: iconic-object images [41], iconic-scene images [3] and non-iconic images. Typical iconic-object images have a single larg”
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.”
Furniture-geek: Understanding fine-grained furniture attributes from freely associated text and tags (2014, background): “Another application that has found ground recently in the vision literature is that of iconicity or finding prototypi cal images for a given visual concept [1, 25].”
ConceptMap: Mining Noisy Web Data for Concept Learning (2014, background): “Berg and Berg [1] find iconic images that are the representatives of the collection given a query concept.”
Learning about Canonical Views from Internet Image Collections (2012, methodology): “In the automatic phase we download images for the category (e.g using Google), remove duplicate images and create GIST descriptors for each image.”
Measuring the Objectness of Image Windows (2011, background): “Berg and Berg [6] find iconic images representative for an object class.”
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].”
Web-Based Classifiers for Human Action Recognition (2012, background): “Berg and Berg [20] present the problem as finding the iconic images of an image category.”
Concept Generalization in Visual Representation Learning (2020, unknown): “We need these datasets to have diverse object-level images [2] and to be as less biased as possible, e.”
Salient Object Subitizing (2015, background): “However, many existing salient object detection methods assume the existence of salient objects, and they are mainly tested and optimized for images that contain a single dominant object (Li et al., 2014; Borji et al., 2012).”