Some Objects Are More Equal Than Others: Measuring and Predicting Importance

By Merrielle Spain, Pietro Perona. 2008

70 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

Recognition in Terra Incognita (2018, background): “Human photographers are biased towards well-lit, wellfocused images where the subjects are centered in the frame [30, 31].”
SUN Database: Exploring a Large Collection of Scene Categories (2014, methodology): “For comparison, we also show the distribution of objects in the SUN dataset (Spain and Perona 2008).”
Best of both worlds: Human-machine collaboration for object annotation (2015, background): “However, since some objects in the image may be more important than others [49, 25, 2], the requester may optionally specify a function mapping each image region and class label to a real value indicating importance.”
Measuring and Predicting Object Importance (2011, background): “A preliminary version of this work was published in the proceedings of ECCV 2008 (Spain and Perona 2008).”
Predicting Important Objects for Egocentric Video Summarization (2015, background): “Researchers have also explored ranking object importance in static images, learning what people mention first from human-annotated tags (Spain and Perona 2008; Hwang and Grauman 2010).”
Annotator rationales for visual recognition (2011, background): “However, more implicit measures are also possible, such as by learning what people mention first in a natural scene [11, 22], or what they deem a foreground object [16].”
A Survey on Truth Discovery (2015, background): “However, workers’ quality are quite diverse, which brings the core task of inferring true labels from the labeling eﬀorts of multiple workers [6,10,24,36,39,40, 43, 50, 51, 59].”
Understanding and predicting importance in images (2012, background): “Perhaps most similar to our goals, elegant work by Spain and Perona [22] [23] tackles the task of examining factors to predict the order in which objects will be mentioned given an image.”
Learning the Relative Importance of Objects from Tagged Images for Retrieval and Cross-Modal Search (2012, background): “Though difficult to state in the absolute, a number of previous studies lend support for both points (von Ahn and Dabbish 2004; Spain and Perona 2008; Einhauser et al. 2008; Elazary and Itti 2008; Tatler et al. 2005; Hwang and Grauman 2010b), as does our own experimental data.”
crowdsourcing : rating annotators and obtaining cost-effective labels (2010, unknown): “Smyth et al. [6] integrated the opinions of many experts to determine a gold standard, and Spain and Perona [9] developed a method for combining prioritized lists obtained from different annotators.”
Discovering important people and objects for egocentric video summarization (2012, background): “Researchers have also explored ranking object importance in static images, learning what peopl mention first from human-annotated tags [25, 11].”
Memorability of Image Regions (2012, background): “Recently, learning algorithms have been proposed to automatically interpret whether an image is aesthetically pleasant or not [20, 3], memorable or forgettable [7, 6], and the role that other high level photographic properties plays in image interpretation (photo quality [19], attractiveness [16], c”
The Multidimensional Wisdom of Crowds (2010, methodology): “Although approaches for modeling certain aspects of the annotation process have been proposed in the past [1, 5, 6, 9, 13, 4, 12], no attempt has been made to blend all characteristics of the process into a single unified model.”