# Gaze-Regularized VLMs for Ego-Centric Behavior Understanding

arXiv: https://arxiv.org/abs/2603.23190 · HTML: https://mlsanity.com/paper/2603.23190/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 50 references that are in the map.
- First posted on arXiv 24 Mar 2026.

## Builds on (most cited first, 26 of 26)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks](https://mlsanity.com/paper/2312.14238/) (2023)
- [ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks](https://mlsanity.com/paper/1908.02265/) (2019)
- [LXMERT: Learning Cross-Modality Encoder Representations from Transformers](https://mlsanity.com/paper/1908.07490/) (2019)
- [LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention](https://mlsanity.com/paper/2303.16199/) (2023)
- [Rescaling Egocentric Vision](https://mlsanity.com/paper/2006.13256/) (2020)
- [ShareGPT4Video: Improving Video Understanding and Generation with Better Captions](https://mlsanity.com/paper/2406.04325/) (2024)
- [Annotating and Modeling Fine-grained Factuality in Summarization](https://mlsanity.com/paper/2104.04302/) (2021)
- [What Would You Expect? Anticipating Egocentric Actions with Rolling-Unrolling LSTMs and Modality Attention](https://mlsanity.com/paper/1905.09035/) (2019)
- [Binding Touch to Everything: Learning Unified Multimodal Tactile Representations](https://mlsanity.com/paper/2401.18084/) (2024)
- [AntGPT: Can Large Language Models Help Long-term Action Anticipation from Videos?](https://mlsanity.com/paper/2307.16368/) (2023)
- [RED: Reinforced Encoder-Decoder Networks for Action Anticipation](https://mlsanity.com/paper/1707.04818/) (2017)
- [Mutual Context Network for Jointly Estimating Egocentric Gaze and Actions](https://mlsanity.com/paper/1901.01874/) (2019)
- [Integrating Human Gaze into Attention for Egocentric Activity Recognition](https://mlsanity.com/paper/2011.03920/) (2020)
- [Interaction Region Visual Transformer for Egocentric Action Anticipation](https://mlsanity.com/paper/2211.14154/) (2022)
- [Attention is All We Need: Nailing Down Object-centric Attention for Egocentric Activity Recognition](https://mlsanity.com/paper/1807.11794/) (2018)
- [LEGO: Learning EGOcentric Action Frame Generation via Visual Instruction Tuning](https://mlsanity.com/paper/2312.03849/) (2023)
- [VIALM: A Survey and Benchmark of Visually Impaired Assistance with Large Models](https://mlsanity.com/paper/2402.01735/) (2024)
- [MirrorFlow: Exploiting Symmetries in Joint Optical Flow and Occlusion Estimation](https://mlsanity.com/paper/1708.05355/) (2017)
- [Gaze-based, Context-aware Robotic System for Assisted Reaching and Grasping](https://mlsanity.com/paper/1809.08095/) (2018)
- [Enhancing Next Active Object-based Egocentric Action Anticipation with Guided Attention](https://mlsanity.com/paper/2305.12953/) (2023)
- [The Visual Experience Dataset: Over 200 Recorded Hours of Integrated Eye Movement, Odometry, and Egocentric Video](https://mlsanity.com/paper/2404.18934/) (2024)
- [Short-term Object Interaction Anticipation with Disentangled Object Detection @ Ego4D Short Term Object Interaction Anticipation Challenge](https://mlsanity.com/paper/2407.05713/) (2024)

## Abstract (arXiv)

Eye gaze, encompassing fixations and saccades, provides critical insights into human intentions and future actions. This study introduces a gaze-regularized framework that enhances Vision Language Models (VLMs) for egocentric behavior understanding. Unlike existing methods that rely solely on visual data and overlook gaze information, our approach directly incorporates gaze information into the VLM architecture during training. By generating gaze-based queries, the model dynamically focuses on gaze-highlighted regions, while a gaze-regularization mechanism ensures the alignment of model attention with human attention patterns. To better understand how gaze can be effectively integrated into VLMs, we conducted extensive experiments exploring various strategies for incorporating gaze data. These innovations enable the prediction of future events with detailed action descriptions. Experimental results demonstrate a nearly 13 % improvement in semantic scores compared to baseline models not leveraging gaze data, highlighting the effectiveness of our approach. This work establishes a foundation for leveraging the human gaze in VLMs, significantly boosting their predictive capabilities in applications requiring accurate and robust future event prediction.