---
title: "SARA: Semantic-Anchored Referential Alignment for Ego–Exo Instance Correspondence"
authors:
  - "Yueyang Ge"
  - "Ye Lin"
  - "Bojun Yang"
  - "Yilin Huang"
  - "Yi Guo"
doi: "10.24963/ijcai.2026/126"
url: "https://ijcai.org/proceedings/2026/126"
pdf: "https://ijcai.org/proceedings/2026/0126.pdf"
venue: "Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence"
year: 2026
pages: "1124-1132"
track: "Main Track"
keywords:
  - "Computer Vision: Image and video retrieval"
  - "Computer Vision: Multimodal learning"
  - "Computer Vision: Vision, language and reasoning"
---

# SARA: Semantic-Anchored Referential Alignment for Ego–Exo Instance Correspondence

Yueyang Ge, Ye Lin, Bojun Yang, Yilin Huang, Yi Guo

*Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence*, pages 1124-1132. DOI: [10.24963/ijcai.2026/126](https://doi.org/10.24963/ijcai.2026/126)

## Abstract

Achieving visual coordination between egocentric (ego) and exocentric (exo) perspectives is a cornerstone of augmented reality and human-machine collaboration.  However, extreme viewpoint shifts and occlusions often cause semantic drift in existing methods,  making robust cross-view correspondence a formidable challenge.  In this paper, we propose SARA (Semantic-Anchored Referential Alignment),  a framework designed to bridge the ego-exo gap by leveraging viewpoint-invariant, high-level semantic information as region-level semantic anchors for robust feature mapping. Specifically, our approach incorporates:  (1) the Semantic  Anchoring  Module  extracts  cross-view  category priors and invariant features to provide stable region-level references across perspectives, and (2) the Multimodal Semantic Vector Fusion mechanism achieves language-guided manifold fusion of semantic vectors to synthesize unified embeddings, effectively establishing representational correspondence across disparate perspectives.  Extensive experiments across diverse, complex scenarios demonstrate SARA’s superior performance in establishing stable mappings,validating the effectiveness of semantic-invariant features and multimodal fusion in addressing the core hurdles of cross-view understanding.