mlsanityData to 7 Oct 2026

Structuring Quantitative Image Analysis with Object Prominence

arXiv 2409.00216 ↗First posted 30 Aug 2024cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

When photographers or media professionals compose an image, they make deliberate choices about what to foreground and what to background, shaping how viewers interpret visual content. Yet most quantitative approaches to image analysis overlook this structure and treat detected objects as equally important. We introduce a framework for measuring object prominence-- the relative salience of objects in an image-- as a means to make computational image analysis attentive to the compositional emphasis a curator has built into an image. Drawing on research in cognitive psychology and computer vision, we outline three approaches for estimating object prominence: size and centeredness, inferred depth, and saliency maps. Validating that curator-composed prominence measurably shifts human visual attention in a pre-registered eye-tracking study, we illustrate this framework's benefits in two further applications. First, we demonstrate how weighting features in line with their prominence can enhance the unsupervised ideological scaling of U.S. newspaper images. Second, we examine gendered visual prominence in U.S. presidential campaign ads from 2016 and 2020, showing that Republican candidates depict women less prominently than their Democratic counterparts. Our framework lets researchers analyze image data at scale while remaining attentive to its communicative structure and intent.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 21 of its 106 references that are in the map. First posted on arXiv 30 Aug 2024.

Builds on

21 of 106 references.

References · 21

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  2. 2024Depth Anything: Unleashing the Power of Large-Scale Unlabeled Datacited by 1,346
  3. 2023ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depthcited by 646
  4. 2019DeepPruner: Learning Efficient Stereo Matching via Differentiable PatchMatchcited by 114
  5. 2014Salient Object Detection: A Surveycited by 98
  6. 2020A Survey on Deep Learning Techniques for Stereo-based Depth Estimationcited by 90
  7. 2014Salient Object Detection: A Discriminative Regional Feature Integration Approachcited by 89
  8. 2020Model Interpretability through the Lens of Computational Complexitycited by 75
  9. 2020RGB-D Salient Object Detection: A Surveycited by 73
  10. 2018How to Make Causal Inferences Using Textscited by 59
  11. 2021DeepGaze IIE: Calibrated prediction in and out-of-domain for state-of-the-art saliency modelingcited by 55
  12. 2021TranSalNet: Towards perceptually relevant visual saliency predictioncited by 44
9 more
  1. 2023Recurrent Multi-scale Transformer for High-Resolution Salient Object Detectioncited by 15
  2. 2022Promoting Saliency From Depth: Deep Unsupervised RGB-D Saliency Detectioncited by 12
  3. 2019Predicting the Politics of an Image Using Webly Supervised Datacited by 10
  4. 2019Understanding the Political Ideology of Legislators from Social Media Imagescited by 9
  5. 2021Boosting Salient Object Detection with Transformer-based Asymmetric Bilateral U-Netcited by 9
  6. 2023Model-agnostic explainable artificial intelligence for object detection in image datacited by 6
  7. 2018Size-to-depth: A New Perspective for Single Image Depth Estimationcited by 5
  8. 2017How Polarized Have We Become? A Multimodal Classification of Trump Followers and Clinton Followerscited by 4
  9. 2024Improving Computer Vision Interpretability: Transparent Two-level Classification for Complex Scenescited by 2

Built on by

Not cited yet.