{"type":"ScholarlyArticle","title":"TextGaze: Prompting Gaze Target Estimation with Textual Scene Cues","authors":[{"name":"Junhui She","slug":"junhui-she","given":"Junhui","family":"She","affiliation":""},{"name":"Fei Wang","slug":"fei-wang","given":"Fei","family":"Wang","affiliation":""},{"name":"Kun Li","slug":"kun-li","given":"Kun","family":"Li","affiliation":""},{"name":"Yiqi Nie","slug":"yiqi-nie","given":"Yiqi","family":"Nie","affiliation":""},{"name":"Yuxin Liu","slug":"yuxin-liu","given":"Yuxin","family":"Liu","affiliation":""},{"name":"Zhangling Duan","slug":"zhangling-duan","given":"Zhangling","family":"Duan","affiliation":""},{"name":"Xun Yang","slug":"xun-yang","given":"Xun","family":"Yang","affiliation":""}],"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. All contents are available at: https://github.com/idremo/TextGaze-IJCAI2026.","doi":"10.24963/ijcai.2026/177","url":"https://ijcai.org/proceedings/2026/177","pdf":"https://ijcai.org/proceedings/2026/0177.pdf","markdown":"https://ijcai.org/proceedings/2026/177.md","bibtex":"https://ijcai.org/proceedings/2026/bibtex/177","volume":{"slug":"2026","title":"Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2026","url":"https://ijcai.org/proceedings/2026/","year":2026,"location":"Bremen, Germany","dates":"15-21 August 2026","editors":"Diego Calvanese","isbn":"978-1-956792-09-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2026"},"section":"Computer Vision","track":"Main Track","number":177,"pages":{"first":1586,"last":1594},"keywords":["Humans and AI: Human-computer interaction","Computer Vision: Scene analysis and understanding","Machine Learning: Multi-modal learning"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}