AutoGain: Gain Function Adaptation with Submovement Efficiency Optimization
Honorable MentionAuthors
A well-designed control-to-display gain function can improve pointing performance with indirect pointing devices like trackpads. However, the design of gain functions is challenging and mostly based on trial and error. AutoGain is a novel method to individualize a gain function for indirect pointing devices in contexts where cursor trajectories can be tracked. It gradually improves pointing efficiency by using a novel submovement-level tracking+optimization technique that minimizes aiming error (undershooting/overshooting) for each submovement. We first show that AutoGain can produce, from scratch, gain functions with performance comparable to commercial designs, in less than a half-hour of active use. Second, we demonstrate AutoGain's applicability to emerging input devices (here, a Leap Motion controller) with no reference gain functions. Third, a one-month longitudinal study of normal computer use with AutoGain showed performance improvements from participants' default functions.
Research Questions / Practical Problems
Question signals indexed for this paper.
- 75%
Control Theoretic Models of Pointing
CHI '18· Hand Gesture Recognition +1
- 75%
Gesture Elicitation as a Computational Optimization Problem
CHI '22· Hand Gesture Recognition +1
- 67%
AutoChainer: Automatic Data Augmentation for Stroke-based Input
CHI '26· Hand Gesture Recognition +2
- 60%
Designing Ground Truth and the Social Life of Labels
CHI '21· Computational Methods in HCI +1
- 60%
Model Sketching: Centering Concepts in Early-Stage Machine Learning Model Design
CHI '23· AI-Assisted Decision-Making & Automation +1
- 60%
DeepSeer: Interactive RNN Explanation and Debugging via State Abstraction
CHI '23· Explainable AI (XAI) +1
- 60%
"The Conduit by which Change Happens": Processes, Barriers, and Support for Interpersonal Learning about Responsible AI
CHI '25· AI Ethics, Fairness & Accountability +1
- 60%
HINT: Integration Testing for AI-based features with Humans in the Loop
IUI '22· AI-Assisted Decision-Making & Automation +1
- 60%
A Dynamic Bayesian Network Based Framework for Multimodal Context-Aware Interactions
IUI '25· Context-Aware Computing +1
- 60%
Abacus Gestures: A Large Set of Math-Based Usable Finger-Counting Gestures for Mid-Air Interactions
UbiComp '23· Hand Gesture Recognition +1
Based on Jaccard similarity of research subtopics & professions (≥60%)