v226: Proceedings of the NeurIPS 2023 Gaze Meets ML Workshop

2026-06-10 · Source: Proceedings of Machine Learning Research · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Computer Vision · Depth: Expert, quick

Summary

The "2nd Gaze Meets ML workshop," held on December 16, 2023, presented diverse research integrating gaze data with machine learning across various applications. Key advancements included dynamic 3D gaze estimation, appearance-based gaze estimation with self-supervision, and the detection of drowsiness and microsleep from eye movements. Several papers explored novel applications such as leveraging passive eye tracking with the "Segment Anything Model" (SAM) for instance segmentation and improving weakly-supervised localization through foveation and saccade analysis. Further contributions detailed temporal understanding of gaze communication using "GazeTransformer," multi-modal saliency for gaze target detection, and crafting expert-level visual attention for medical image contrastive learning. The workshop underscored the broad utility of combining gaze and ML for tasks ranging from recognition to human-like object tracking and active sensing.

Key takeaway

The "Gaze Meets ML" workshop highlights significant advances in integrating eye gaze data with machine learning for enhanced computer vision and human behavior analysis. Key contributions include novel methods for interactive image segmentation (e.g., GazeSAM), improved 3D gaze estimation, human-like object tracking, and real-time drowsiness detection from eye movements. These innovations offer critical tools for AI/ML developers, HCI specialists, and medical professionals seeking more intuitive systems and precise human-centric data.

Topics

• Gaze Estimation
• Eye Tracking
• Machine Learning
• Attention Mechanisms
• Instance Segmentation

Best for: Research Scientist, AI Scientist, Machine Learning Engineer, Computer Vision Engineer

Related on AIssential

• v210: Proceedings of the NeurIPS 2022 Gaze Meets ML Workshop — The "1st Gaze Meets ML workshop," held on December 3, 2022, in New Orleans, USA, showcased diverse research at the intersection of eye-gaze and machine learning.
• Lazy or Efficient? Towards Accessible Eye-Tracking Event Detection Using LLMs — An LLM-driven pipeline automates eye-tracking event detection, making complex analysis accessible without specialized programming.
• Eye Tracking in Recommender Systems — Eye tracking data offers richer insights into user behavior than clicks, enabling more effective recommender systems.
• Seeing Without Eyes: 4D Human-Scene Understanding from Wearable IMUs — 4D human-scene understanding is achievable using only wearable IMUs, bypassing visual perception limitations.
• Enhancing Gaze Reasoning in Vision Foundation Models for Gaze Following — A novel training mechanism significantly improves Vision Foundation Models' gaze reasoning for gaze following, particularly with non-salient targets.
• GAZE: Grounded Agentic Zero-shot Evaluation with Viewer-Level Tools and Literature Retrieval on Rare Brain MRI — Agentic VLMs with iterative tool use and retrieval enhance medical image interpretation, especially for rare conditions.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Proceedings of Machine Learning Research.