From Gaze to Meaning: A Training-Free AI Agent for Unified Grounding and Explanation

• URL: http://arxiv.org/abs/2609.06208v1
• Date: Sat, 05 Sep 2026 17:54:58 GMT
• Title: From Gaze to Meaning: A Training-Free AI Agent for Unified Grounding and Explanation
• Abstract summary: This work introduces the first training-free Gaze Target Agent (GTA) for gaze-guided reasoning across tasks such as gaze target prediction, attention localization, and object identification.<n>This is achieved by leveraging pretrained vision-language models, augmenting them with visually guided prompts, and employing a memory-based retrieval strategy for high-uncertainty samples.
• Score: 6.812620443565403
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Understanding human attention is fundamental for scene interpretation, yet existing approaches often rely on heavily trained models that lack interpretability. Prior methods struggle to jointly reason about gaze targets, attended objects, and visual grounding without extensive supervision. To the best of our knowledge, this work introduces the first training-free Gaze Target Agent (GTA) for gaze-guided reasoning across tasks such as gaze target prediction, attention localization, and object identification. This is achieved by leveraging pretrained vision-language models, augmenting them with visually guided prompts, and employing a memory-based retrieval strategy for high-uncertainty samples to improve performance without additional training. We evaluate our approach using both quantitative metrics and qualitative results. Quantitatively, our method achieves state of the art performance on the GazeFollow and GazeHOI benchmarks. Qualitatively, our agent provides detailed semantic predictions, predicts the correct targets even when ground truth labels are wrong, and remains flexible without vocabulary constraints.

Related papers

• Towards Robustness against Typographic Attack with Training-free Concept Localization [42.575178574443946]
  Contrastive Language-Image Pretraining models (CLIP) serve as the foundational vision encoders for most modern Large Vision Language Models (LVLMs)<n>CLIP models exhibit a critical yet underexplored failure mode: irrelevant text appearing within images confounds visual representations, biasing them toward lexical meaning rather than true visual semantics.<n>This issue, commonly described as a Typographic Attack (TA), exposes a vulnerability that poses a significant risk to safety-critical applications such as autonomous driving.<n>We propose a novel, training-free mechanistic interpretability method to achieve interpretable and effective robustness against TA.
  arXiv  Detail & Related papers  (2026-07-02T17:55:24Z)
• Enhancing Gaze Reasoning in Vision Foundation Models for Gaze Following [67.84259349601501]
  We propose a novel training mechanism to enhance gaze reasoning in vision foundation models for gaze following.<n>Our method achieves state-of-the-art performance, with particularly strong improvements when gaze targets are not semantically salient.
  arXiv  Detail & Related papers  (2026-05-21T15:21:14Z)
• Gaze-Regularized VLMs for Ego-Centric Behavior Understanding [7.281396624646809]
  Eye gaze, encompassing fixations and saccades, provides critical insights into human intentions and future actions.<n>This study introduces a gaze-regularized framework that enhances Vision Language Models (VLMs) for egocentric behavior understanding.
  arXiv  Detail & Related papers  (2026-03-24T13:37:28Z)
• SpotAgent: Grounding Visual Geo-localization in Large Vision-Language Models through Agentic Reasoning [31.665287327579026]
  SpotAgent is a framework that formalizes geo-localization into an agentic reasoning process.<n>It actively explores and verifies visual cues by leveraging external tools (e.g., web search, maps) through a ReAct diagram.<n>It achieves state-of-the-art performance, effectively mitigating hallucinations while delivering precise and verifiable geo-localization.
  arXiv  Detail & Related papers  (2026-02-10T06:57:12Z)
• Exploring Conditions for Diffusion models in Robotic Control [70.27711404291573]
  We explore leveraging pre-trained text-to-image diffusion models to obtain task-adaptive visual representations for robotic control.<n>We find that naively applying textual conditions yields minimal or even negative gains in control tasks.<n>We propose ORCA, which introduces learnable task prompts that adapt to the control environment and visual prompts that capture fine-grained, frame-specific details.
  arXiv  Detail & Related papers  (2025-10-17T10:24:14Z)
• Preserving Clusters in Prompt Learning for Unsupervised Domain Adaptation [29.809079908218607]
  This work introduces a fresh solution to reinforce base pseudo-labels and facilitate target-prompt learning.<n>We first propose to leverage the reference predictions based on the relationship between source and target visual embeddings.<n>We later show that there is a strong clustering behavior observed between visual and text embeddings in pre-trained multi-modal models.
  arXiv  Detail & Related papers  (2025-06-13T06:33:27Z)
• POUF: Prompt-oriented unsupervised fine-tuning for large pre-trained models [62.23255433487586]
  We propose an unsupervised fine-tuning framework to fine-tune the model or prompt on the unlabeled target data. We demonstrate how to apply our method to both language-augmented vision and masked-language models by aligning the discrete distributions extracted from the prompts and target data.
  arXiv  Detail & Related papers  (2023-04-29T22:05:22Z)
• Weakly-supervised HOI Detection via Prior-guided Bi-level Representation Learning [66.00600682711995]
  Human object interaction (HOI) detection plays a crucial role in human-centric scene understanding and serves as a fundamental building-block for many vision tasks. One generalizable and scalable strategy for HOI detection is to use weak supervision, learning from image-level annotations only. This is inherently challenging due to ambiguous human-object associations, large search space of detecting HOIs and highly noisy training signal. We develop a CLIP-guided HOI representation capable of incorporating the prior knowledge at both image level and HOI instance level, and adopt a self-taught mechanism to prune incorrect human-object associations.
  arXiv  Detail & Related papers  (2023-03-02T14:41:31Z)
• Sentence Representation Learning with Generative Objective rather than Contrastive Objective [86.01683892956144]
  We propose a novel generative self-supervised learning objective based on phrase reconstruction. Our generative learning achieves powerful enough performance improvement and outperforms the current state-of-the-art contrastive methods.
  arXiv  Detail & Related papers  (2022-10-16T07:47:46Z)
• Improving Visual Grounding by Encouraging Consistent Gradient-based Explanations [58.442103936918805]
  We show that Attention Mask Consistency produces superior visual grounding results than previous methods. AMC is effective, easy to implement, and is general as it can be adopted by any vision-language model.
  arXiv  Detail & Related papers  (2022-06-30T17:55:12Z)
• Heterogeneous Contrastive Learning: Encoding Spatial Information for Compact Visual Representations [183.03278932562438]
  This paper presents an effective approach that adds spatial information to the encoding stage to alleviate the learning inconsistency between the contrastive objective and strong data augmentation operations. We show that our approach achieves higher efficiency in visual representations and thus delivers a key message to inspire the future research of self-supervised visual representation learning.
  arXiv  Detail & Related papers  (2020-11-19T16:26:25Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.