TextGaze: Prompting Gaze Target Estimation with Textual Scene Cues

• URL: http://arxiv.org/abs/2607.10130v1
• Date: Sat, 11 Jul 2026 05:40:45 GMT
• Title: TextGaze: Prompting Gaze Target Estimation with Textual Scene Cues
• Abstract summary: Multi-branch methods require extra supervision and annotations.<n> streamlined designs prioritize low-level visual saliency over true gaze intent.<n>We propose TextGaze, a unified cross-modal architecture that leverages a Large Vision-Language Model.
• Score: 15.615000069929605
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Gaze target estimation aims to infer the position of a person's gaze within a scene. Within mainstream design logic, multi-branch methods require extra supervision and annotations, while streamlined designs prioritize low-level visual saliency over true gaze intent. The former leads to a high annotation burden and hinders domain transfer, whereas the latter causes misalignment between predicted attention and actual gaze targets. To address this issue, we propose TextGaze, a unified cross-modal architecture that leverages a Large Vision-Language Model (LVLM) as scalable semantic guidance to balance the two design paradigms. The model extracts visual features from a frozen encoder and utilizes an LVLM to obtain gaze-aligned textual cues. We design a transformer-based fusion module with hierarchical text supervision to preserve task semantics. Lightweight decoding heads enable the joint prediction of gaze heatmaps and in-/out-of-frame status. We evaluate our method on four mainstream datasets, and the results show competitive performance across key metrics with robust cross-dataset generalisation without extra fine-tuning. Overall, we provide a streamlined alternative to traditional designs and highlight the potential of LVLMs as accessible auxiliary guidance for gaze estimation.

Related papers

• Gaze Target Estimation Anywhere with Concepts [28.49132281076088]
  We introduce the Promptable Gaze Target Estimation (PGE) task for gaze analysis.<n>PGE conditions gaze prediction on flexible user text or visual prompts to identify a specific subject.<n>We develop a scalable data engine to generate Gaze-Co, a dataset and benchmark of 120K high-quality, prompt-annotated image pairs.<n>We also propose GazeAnywhere, the first model designed for PGE.
  arXiv  Detail & Related papers  (2026-08-11T19:23:48Z)
• OmniGF: A Dual-Branch Vision-Language Framework for Unified Gaze Following [59.53720386342017]
  We propose a unified vision-language framework that adapts foundational Vision-Language Models for scalable multi-person gaze reasoning.<n>By modeling all individuals, OmniGF seamlessly integrates precise spatial gaze target estimation, semantic gaze prediction, and complex social gaze reasoning.
  arXiv  Detail & Related papers  (2026-05-26T00:08:06Z)
• LaCoVL-FER: Landmark-Guided Contrastive Learning Network with Vision-Language Enhancement for Facial Expression Recognition [51.70817823155725]
  We propose a novel landmark-guided contrastive learning network with vision-language enhancement for Facial Expression Recognition (FER)<n>LaCoVL-FER integrates geometric priors from facial landmarks and semantic priors from a vision-language model.<n>Experiments demonstrate that LaCoVL-FER outperforms state-of-the-art methods on three representative real-world FER datasets.
  arXiv  Detail & Related papers  (2026-05-19T13:15:41Z)
• GazeCLIP: Gaze-Guided CLIP with Adaptive-Enhanced Fine-Grained Language Prompt for Deepfake Attribution and Detection [80.12497948980378]
  Current deepfake attribution or deepfake detection works tend to exhibit poor generalization to novel generative methods.<n>We propose a novel gaze-guided CLIP with adaptive-enhanced fine-grained language prompts for fine-grained deepfake attribution and detection (DFAD)<n>We conduct a novel and fine-grained benchmark to evaluate the DFAD performance of networks on novel generators like diffusion and flow models.<n>We introduce a gaze-aware model based on CLIP, which is devised to enhance the generalization to unseen face forgery attacks.
  arXiv  Detail & Related papers  (2026-03-31T05:59:59Z)
• SGHA-Attack: Semantic-Guided Hierarchical Alignment for Transferable Targeted Attacks on Vision-Language Models [73.19044613922911]
  Large vision-language models (VLMs) are vulnerable to transfer-based adversarial perturbations.<n>We propose SGHA-Attack, a framework that adopts multiple target references and enforces intermediate-layer consistency.<n>Experiments on open-source and commercial black-box VLMs show that SGHA-Attack achieves stronger targeted transferability than prior methods.
  arXiv  Detail & Related papers  (2026-02-02T03:10:41Z)
• From Data to Modeling: Fully Open-vocabulary Scene Graph Generation [29.42202665594218]
  OvSGTR is a transformer-based framework for fully open-vocabulary scene graph generation.<n>Our approach jointly predicts objects (nodes) and their inter-relationships (edges) beyond predefined categories.
  arXiv  Detail & Related papers  (2025-05-26T15:11:23Z)
• Top-Down Compression: Revisit Efficient Vision Token Projection for Visual Instruction Tuning [70.57180215148125]
  Visual instruction tuning aims to enable large language models to comprehend the visual world.<n>Existing methods often grapple with the intractable trade-off between accuracy and efficiency.<n>We present LLaVA-Meteor, a novel approach that strategically compresses visual tokens without compromising core information.
  arXiv  Detail & Related papers  (2025-05-17T10:22:29Z)
• Gaze-LLE: Gaze Target Estimation via Large-Scale Learned Encoders [33.26237143983192]
  We address the problem of gaze target estimation, which aims to predict where a person is looking in a scene.<n>We propose Gaze-LLE, a novel transformer framework that streamlines gaze target estimation by leveraging features from a frozen DINOv2 encoder.
  arXiv  Detail & Related papers  (2024-12-12T18:55:30Z)
• Towards Pixel-Level Prediction for Gaze Following: Benchmark and Approach [27.84672974344777]
  We propose a novel gaze target prediction solution named GazeSeg.<n>It can fully utilize the spatial visual field of the person as guiding information and lead to a progressively coarse-to-fine gaze target segmentation and recognition process.<n>Our approach achieves the Dice of 0.325 in gaze target segmentation and 71.7% top-5 recognition.
  arXiv  Detail & Related papers  (2024-11-30T01:27:48Z)
• GazeCLIP: Enhancing Gaze Estimation Through Text-Guided Multimodal Learning [12.706496295933343]
  We propose GazeCLIP, a novel gaze estimation framework that deeply explores text-face collaboration.<n>Specifically, we introduce a meticulously designed linguistic description generator to produce text signals enriched with coarse directional cues.<n>Our findings underscore the potential of using visual-language collaboration to advance gaze estimation and open new avenues for future research in multimodal learning for visual tasks.
  arXiv  Detail & Related papers  (2023-12-30T15:24:50Z)
• Enhanced Modality Transition for Image Captioning [51.72997126838352]
  We build a Modality Transition Module (MTM) to transfer visual features into semantic representations before forwarding them to the language model. During the training phase, the modality transition network is optimised by the proposed modality loss. Experiments have been conducted on the MS-COCO dataset demonstrating the effectiveness of the proposed framework.
  arXiv  Detail & Related papers  (2021-02-23T07:20:12Z)

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.