{"type":"ScholarlyArticle","title":"Subject-Agnostic Cross-View Referring Expression Comprehension via Reward-Driven Consistency Learning","authors":[{"name":"Liuwu Li","slug":"liuwu-li","given":"Liuwu","family":"Li","affiliation":""},{"name":"Ronger Ding","slug":"ronger-ding","given":"Ronger","family":"Ding","affiliation":""},{"name":"Zehang Lin","slug":"zehang-lin","given":"Zehang","family":"Lin","affiliation":""},{"name":"Qi Peng","slug":"qi-peng","given":"Qi","family":"Peng","affiliation":""},{"name":"Jiayuan Xie","slug":"jiayuan-xie","given":"Jiayuan","family":"Xie","affiliation":""}],"abstract":"Cross-view Referring Expression Comprehension (REC) requires a model to accurately localize objects in a spatial representation of one perspective based on descriptions generated from a different perspective. Essentially, it demands maintaining referential consistency under perspective shifts. This problem is prevalent in engineering application scenarios (e.g., Geographic Information Systems (GIS), urban planning, etc), where descriptions are typically generated from a top-down or planning view, while targets must be identified in a spatial representation distinct from the source. However, existing methods often assume shared perspectives or rely on an explicit observer to interpret observer-centric spatial relations (e.g., \"left/right\" of the observer). Consequently, they struggle to handle cross-view grounding cases commonly arising in engineering application scenarios, where descriptions are defined by the source-view representation itself and do not involve any observing subject. To this end, we propose a novel Subject-Agnostic Cross-View REC task and construct a controlled simulation environment to systematically study referential consistency under perspective changes. Methodologically, we propose a Reward-Driven Consistency Learning framework. By imposing mutually constraining reward signals on the grounding and localization results between the source and target views, we guide the model to maintain referential consistency across different view representations. Experimental results show that our method significantly outperforms baselines in multiple cross-view settings, exhibiting superior generalization and robustness under perspective shifts.","doi":"10.24963/ijcai.2026/148","url":"https://ijcai.org/proceedings/2026/148","pdf":"https://ijcai.org/proceedings/2026/0148.pdf","markdown":"https://ijcai.org/proceedings/2026/148.md","bibtex":"https://ijcai.org/proceedings/2026/bibtex/148","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":148,"pages":{"first":1324,"last":1332},"keywords":["Computer Vision: Multimodal learning","Computer Vision: Vision, language and reasoning","Machine Learning: Multi-view learning"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}