# Cross-View Multi-Modal Segmentation @ Ego-Exo4D Challenges 2025

arXiv: https://arxiv.org/abs/2506.05856 · HTML: https://mlsanity.com/paper/2506.05856/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 20 references that are in the map.
- First posted on arXiv 6 Jun 2025.

## Builds on (most cited first, 19 of 19)

- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [LISA: Reasoning Segmentation via Large Language Model](https://mlsanity.com/paper/2308.00692/) (2023)
- [Segment Everything Everywhere All at Once](https://mlsanity.com/paper/2304.06718/) (2023)
- [Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives](https://mlsanity.com/paper/2311.18259/) (2023)
- [GLaMM: Pixel Grounding Large Multimodal Model](https://mlsanity.com/paper/2311.03356/) (2023)
- [PixelLM: Pixel Reasoning with Large Multimodal Model](https://mlsanity.com/paper/2312.02228/) (2023)
- [Universal Instance Perception as Object Discovery and Retrieval](https://mlsanity.com/paper/2303.06674/) (2023)
- [PSALM: Pixelwise SegmentAtion with Large Multi-Modal Model](https://mlsanity.com/paper/2403.14598/) (2024)
- [OMG-Seg: Is One Model Good Enough For All Segmentation?](https://mlsanity.com/paper/2401.10229/) (2024)
- [CAFuser: Condition-Aware Multimodal Fusion for Robust Semantic Perception of Driving Scenes](https://mlsanity.com/paper/2410.10791/) (2024)
- [Learning Modality-agnostic Representation for Semantic Segmentation from Any Modalities](https://mlsanity.com/paper/2407.11351/) (2024)
- [ObjectRelator: Enabling Cross-View Object Relation Understanding Across Ego-Centric and Exo-Centric Perspectives](https://mlsanity.com/paper/2411.19083/) (2024)
- [Distilling Efficient Vision Transformers from CNNs for Semantic Segmentation](https://mlsanity.com/paper/2310.07265/) (2023)
- [Object Segmentation by Mining Cross-Modal Semantics](https://mlsanity.com/paper/2305.10469/) (2023)
- [Temporal-aware Hierarchical Mask Classification for Video Semantic Segmentation](https://mlsanity.com/paper/2309.08020/) (2023)
- [X-Prompt: Multi-modal Visual Prompt for Video Object Segmentation](https://mlsanity.com/paper/2409.19342/) (2024)
- [CamSAM2: Segment Anything Accurately in Camouflaged Videos](https://mlsanity.com/paper/2503.19730/) (2025)

## Built on by (most cited first, 5 of 5)

- [EgoCross: Benchmarking Multimodal Large Language Models for Cross-Domain Egocentric Video Question Answering](https://mlsanity.com/paper/2508.10729/) (2025)
- [Exo2EgoSyn: Unlocking Foundation Video Generation Models for Exocentric-to-Egocentric Video Synthesis](https://mlsanity.com/paper/2511.20186/) (2025)
- [V2-SAM: Marrying SAM2 with Multi-Prompt Experts for Cross-View Object Correspondence](https://mlsanity.com/paper/2511.20886/) (2025)
- [EgoSound: Benchmarking Sound Understanding in Egocentric Videos](https://mlsanity.com/paper/2602.14122/) (2026)
- [From Synchrony to Sequence: Exo-to-Ego Generation via Interpolation](https://mlsanity.com/paper/2604.13793/) (2026)

## Abstract (arXiv)

In this report, we present a cross-view multi-modal object segmentation approach for the object correspondence task in the Ego-Exo4D Correspondence Challenges 2025. Given object queries from one perspective (e.g., ego view), the goal is to predict the corresponding object masks in another perspective (e.g., exo view). To tackle this task, we propose a multimodal condition fusion module that enhances object localization by leveraging both visual masks and textual descriptions as segmentation conditions. Furthermore, to address the visual domain gap between ego and exo views, we introduce a cross-view object alignment module that enforces object-level consistency across perspectives, thereby improving the model's robustness to viewpoint changes. Our proposed method ranked second on the leaderboard of the large-scale Ego-Exo4D object correspondence benchmark. Code will be made available at https://github.com/lovelyqian/ObjectRelator.