# PAGE: Towards Practical Human-level Gaze Target Estimation

arXiv: https://arxiv.org/abs/2607.04860 · HTML: https://mlsanity.com/paper/2607.04860/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Multimodal distillation, one of 12 directions in Knowledge distillation.
- Builds on 23 of its 35 references that are in the map.
- First posted on arXiv 6 Jul 2026.

## Placed in

- Knowledge distillation / [Multimodal distillation](https://mlsanity.com/distill/multimodal-distillation/)

## Builds on (most cited first, 23 of 23)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [DINOv3](https://mlsanity.com/paper/2508.10104/) (2025)
- [Vision Transformer Adapter for Dense Predictions](https://mlsanity.com/paper/2205.08534/) (2022)
- [Rotary Position Embedding for Vision Transformer](https://mlsanity.com/paper/2403.13298/) (2024)
- [Detecting Attended Visual Targets in Video](https://mlsanity.com/paper/2003.02501/) (2020)
- [Connecting Gaze, Scene, and Attention: Generalized Attention Estimation via Joint Modeling of Gaze and Scene Saliency](https://mlsanity.com/paper/1807.10437/) (2018)
- [End-to-End Human-Gaze-Target Detection with Transformers](https://mlsanity.com/paper/2203.10433/) (2022)
- [Believe It or Not, We Know What You Are Looking at!](https://mlsanity.com/paper/1907.02364/) (2019)
- [Gaze-LLE: Gaze Target Estimation via Large-Scale Learned Encoders](https://mlsanity.com/paper/2412.09586/) (2024)
- [ChildPlay: A New Benchmark for Understanding Children's Gaze Behaviour](https://mlsanity.com/paper/2307.01630/) (2023)
- [A Modular Multimodal Architecture for Gaze Target Prediction: Application to Privacy-Sensitive Settings](https://mlsanity.com/paper/2307.05158/) (2023)
- [Object-aware Gaze Target Detection](https://mlsanity.com/paper/2307.09662/) (2023)
- [GOO: A Dataset for Gaze Object Prediction in Retail Environments](https://mlsanity.com/paper/2105.10793/) (2021)
- [Patch-level Gaze Distribution Prediction for Gaze Following](https://mlsanity.com/paper/2211.11062/) (2022)
- [ViTGaze: Gaze Following with Interaction Features in Vision Transformers](https://mlsanity.com/paper/2403.12778/) (2024)
- [TIPSv2: Advancing Vision-Language Pretraining with Enhanced Patch-Text Alignment](https://mlsanity.com/paper/2604.12012/) (2026)
- [What Makes a Good Dataset for Knowledge Distillation?](https://mlsanity.com/paper/2411.12817/) (2024)
- [Vision-Language Models Mistake Head Orientation for Gaze Direction: Nonverbal Conversation Cues](https://mlsanity.com/paper/2506.05412/) (2025)
- [HiSync: Spatio-Temporally Aligning Hand Motion from Wearable IMU and On-Robot Camera for Command Source Identification in Long-Range HRI](https://mlsanity.com/paper/2603.11809/) (2026)
- [Gaze Estimation for Human-Robot Interaction: Analysis Using the NICO Platform](https://mlsanity.com/paper/2509.24001/) (2025)
- [Fusing Complementary Multi-view Features for Screen-Based Eye Tracking](https://mlsanity.com/paper/2606.31211/) (2026)

## Abstract (arXiv)

Gaze target estimation, the task of predicting where a person is looking in a scene, is crucial to understanding human attention and intent. It is a challenging task that combines high-level understanding of global scene semantics and precise spatial reasoning using human appearance (e.g. pose, eye orientation). As a result, human-level performance remains elusive for existing models, limiting their practical application. To this end, we propose PaGE (Practical Gaze Estimator), a gaze estimation model that explicitly models the complex interaction between scene and head features. Using a PaGE model with a large ViT-H+ backbone as the teacher, we further distill student models with lighter backbones on a much larger and more diverse unlabeled dataset. The architectural improvements and novel training recipe allow PaGE to achieve state-of-the-art performance on several gaze estimation tasks, outperforming humans in 7 out of 9 metrics while reducing the human-AI gap by at least 60% in the remaining 2. The distilled student models retain most of the teacher's performance while being lightweight enough for practical deployment on robots and consumer devices. The code and model checkpoints are available at our project page.