Consensus Clustering of Free-Viewing Gaze Data: New Insights into Human-Information Interaction
2026-06-29 • Computer Vision and Pattern Recognition
Computer Vision and Pattern RecognitionHuman-Computer InteractionMachine Learning
AI summaryⓘ
The authors studied how people look at images when they are free to explore without a specific task. They created a new system called EnsembleGaze that uses multiple clustering methods to find patterns in where and how people fixate their gaze, considering both user behavior and image features. Their approach helps group similar viewing patterns and distinct image types, revealing consistent ways people view images (like focusing or scanning). The method works well across different datasets and offers new insights into how attention varies by both images and users.
free-viewing gaze datafixationsconsensus clusteringensemble learningfeature engineeringspectral biclusteringsubspace clusteringhuman visual attentionimage stimuliunsupervised analysis
Authors
Beryl Gnanaraj, Jaya Sreevalsan-Nair, Saqib Alam Ansari, Maanasa Rajaraman
Abstract
Free-viewing gaze data provides a rich, task-free window into human visual attention. Conventional exploratory data analysis of the data provides user attention patterns through fixations and areas of interest. However, despite the richness of this gaze data, its human-information interaction (HII) patterns are understudied. We address this gap using consensus clustering of gaze data with respect to users and stimulus characteristics. We present a novel end-to-end unsupervised ensemble learning system for consensus clustering of free-viewing gaze datasets, EnsembleGaze. With a goal of characterizing the user behavior and stimulus type, we propose a feature engineering step based on statistical descriptors of fixation-based distributions. EnsembleGaze involves consensus voting of selected clustering methods implemented on the feature vector to compute the co-association matrix. Using the separate consensus clustering of users and stimuli as a baseline, we further propose two high-dimensional clustering strategies for determining gaze clusters based on joint user and image characterization. They are consensus subspace clustering and spectral biclustering. Clustering performance is evaluated using selected standard metrics and is further interpreted through image-level properties. Our system provides a replicable method for the unsupervised analysis of fixation behavior in scene perception research. Our results show that image stimuli groupings are highly consistent across methods, reflecting a robust ambient-versus-focal viewing mode distinction, whereas user groupings are image-context-dependent, a structure that only biclustering and the two-step conditional approaches are architecturally capable of recovering. Testing on the publicly available datasets revealed dataset-specific patterns, with each offering complementary insights through distinct clustering strategies.