Measuring and Predicting Importance of Objects in Our Visual World

22 citations recorded by the source corpus.

How researchers see this paper

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

LVIS: A Dataset for Large Vocabulary Instance Segmentation (2019, neutral): “9 and [29, 25, 24, 27]) .”
Learning to share visual appearance for multiclass object detection (2011, methodology): “A distribution similar to Zipf’s law also has been found in several large object databases (e.g., what and where [ 26 ], labelme [23]).”
Exploring Balanced Feature Spaces for Representation Learning (2021, background): “In practice, the visual data usually follow a long-tailed distribution (Zipf, 1999; Spain & Perona, 2007), challenging supervised learning methods.”
Learning to Segment the Tail (2020, background): “The long-tail distribution inherently exists in our visual world, where a few head classes occupy most of the instances [48, 1, 37, 44].”
80 Million Tiny Images: A Large Data Set for Nonparametric Object and Scene Recognition (2008, unknown): “Similar distributio ns are also obtained from datasets collected by other groups [38].”
LabelMe: Online Image Annotation and Applications (2010, background): “This observation was made in [63] and seems to indicate that the number of visual object categories is large.”