# Multi-scale Object-Aware Gaze Estimation via Geometric Reasoning

arXiv: https://arxiv.org/abs/2606.29334 · HTML: https://mlsanity.com/paper/2606.29334/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 31 of its 64 references that are in the map.
- First posted on arXiv 28 Jun 2026.

## Builds on (most cited first, 30 of 31)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [DINOv3](https://mlsanity.com/paper/2508.10104/) (2025)
- [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)
- [Understanding Human Gaze Communication by Spatio-Temporal Graph Reasoning](https://mlsanity.com/paper/1909.02144/) (2019)
- [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)
- [Multimodal Across Domains Gaze Target Detection](https://mlsanity.com/paper/2208.10822/) (2022)
- [Patch-level Gaze Distribution Prediction for Gaze Following](https://mlsanity.com/paper/2211.11062/) (2022)
- [GaTector: A Unified Framework for Gaze Object Prediction](https://mlsanity.com/paper/2112.03549/) (2021)
- [ViTGaze: Gaze Following with Interaction Features in Vision Transformers](https://mlsanity.com/paper/2403.12778/) (2024)
- [Modality Gap-Driven Subspace Alignment Training Paradigm For Multimodal Large Language Models](https://mlsanity.com/paper/2602.07026/) (2026)
- [GazeVLM: A Vision-Language Model for Multi-Task Gaze Understanding](https://mlsanity.com/paper/2511.06348/) (2025)
- [Co-Located Human-Human Interaction Analysis using Nonverbal Cues: A Survey](https://mlsanity.com/paper/2207.10574/) (2022)
- [TransGOP: Transformer-Based Gaze Object Prediction](https://mlsanity.com/paper/2402.13578/) (2024)
- [Predicting the Intention to Interact with a Service Robot:the Role of Gaze Cues](https://mlsanity.com/paper/2404.01986/) (2024)
- [Diffusion-Refined VQA Annotations for Semi-Supervised Gaze Following](https://mlsanity.com/paper/2406.02774/) (2024)
- [Multi-view Gaze Target Estimation](https://mlsanity.com/paper/2508.05857/) (2025)
- [Leveraging Multi-Modal Saliency and Fusion for Gaze Target Detection](https://mlsanity.com/paper/2504.19271/) (2025)
- [Anisotropic Modality Align](https://mlsanity.com/paper/2605.07825/) (2026)
- [GaTector+: A Unified Head-free Framework for Gaze Object and Gaze Following Prediction](https://mlsanity.com/paper/2510.25301/) (2025)

## Abstract (arXiv)

Gaze target estimation aims to predict the semantic object an observer fixates upon within an image, a task deeply rooted in the object-oriented nature of human gaze. Observers tend to select a specific semantic entity as the attentional target, rather than responding randomly across arbitrary regions of the image. However, existing methods typically model this task as a direct mapping from global features to gaze heatmaps, essentially treating it as a pixel-level regression problem. This approach fails to explicitly represent the gazed object as a distinct entity, making it difficult to produce stable and semantically consistent predictions in complex scenes. To address this, we propose a two-stage gaze estimation framework guided by object semantics, reformulating gaze target estimation as a hierarchical reasoning process. Our method incorporates object-level representations during feature encoding to align image features with discrete semantic entities, then introduces multi-scale feature fusion and geometric constraints from head pose and gaze direction for fine-grained localization and object-level discrimination. Extensive experiments on GazeFollow, VideoAttentionTarget, ChildPlay, and GOO-Real demonstrate that our method achieves AUC of 0.961, 0.948, 0.987, and 0.977 respectively, delivering strong performance across all benchmarks while maintaining a compact parameter size of 7.1M.