VIP: Finding important people in images

By Clint Solomon Mathialagan, Andrew C. Gallagher, Dhruv Batra. 2015

32 citations recorded by the source corpus.

People preserve memories of events such as birthdays, weddings, or vacations by capturing photos, often depicting groups of people. Invariably, some individuals in the image are more important than others given the context of the event. This paper analyzes the concept of the importance of individuals in group photographs. We address two specific questions - Given an image, who are the most important individuals in it? Given multiple images of a person, which image depicts the person in the most important role? We introduce a measure of importance of people in images and investigate the correlation between importance and visual saliency. We find that not only can we automatically predict the importance of people from purely visual cues, incorporating this predicted importance results in significant improvement in applications such as im2text (generating sentences that describe images of groups of people).

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

Faceless Person Recognition: Privacy Implications in Social Media (2016, background): “Other related tasks are, for example, face clustering [33, 26], finding important people [34], or associating names in text to faces in images [35, 36].”
Person Recognition in Personal Photo Collections (2015, background): “Other related tasks are, for instance, face clustering [9, 33], finding important people [30], or associating names in text to faces in images [13, 14].”
Person Recognition in Personal Photo Collections (2017, background): “Closed world identification: given a single test image (probe), who is this person among the identities that are among the training identities (gallery set)? Open world recognition [21] (Section 7) : given a singe test image (probe), is this person among the training identities (gallery set)? If so,”
It ’ s in the bag : Stronger supervision for automated face labelling (2015, background): “In still images, [14] shows approaches to find important people using image cues.”