Enhancing Eye Feature Estimation from Event Data Streams through Adaptive Inference State Space Modeling

2026-03-14

AI Summary

This work addresses the challenge that existing eye movement feature extraction methods suffer performance degradation when confronted with abrupt changes in event density caused by variations in fixation behavior within event streams. To overcome this limitation, the authors propose the Adaptive Inference State Space Model (AISSM), which integrates a dynamic confidence network to jointly estimate the signal-to-noise ratio and event density in real time, thereby adaptively modulating the fusion weights between historical and current information. The method also incorporates an efficient learning strategy that substantially improves training efficiency. Experimental results demonstrate that AISSM achieves superior accuracy and robustness over state-of-the-art approaches in eye movement feature extraction from event camera data.

Technology Category

• Computer Vision: Motion & Tracking
• Intelligent Robots: State Estimation
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Eye feature extraction from event-based data streams can be performed efficiently and with low energy consumption, offering great utility to real-world eye tracking pipelines. However, few eye feature extractors are designed to handle sudden changes in event density caused by the changes between gaze behaviors that vary in their kinematics, leading to degraded prediction performance. In this work, we address this problem by introducing the \emph{adaptive inference state space model} (AISSM), a novel architecture for feature extraction that is capable of dynamically adjusting the relative weight placed on current versus recent information. This relative weighting is determined via estimates of the signal-to-noise ratio and event density produced by a complementary \emph{dynamic confidence network}. Lastly, we craft and evaluate a novel learning technique that improves training efficiency. Experimental results demonstrate that the AISSM system outperforms state-of-the-art models for event-based eye feature extraction.

Problem

• eye feature extraction
• event-based data
• event density
• gaze behavior
• prediction performance

Innovation

• adaptive inference
• state space model
• event-based vision
• dynamic confidence network
• eye feature extraction