Enregistré dans:
Détails bibliographiques
Auteurs principaux: Kim, Chaeyun, Yi, Seunghoon, Kim, Yejin, Jo, Yohan, Lee, Joonseok
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:https://arxiv.org/abs/2603.17413
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866918395319943168
author Kim, Chaeyun
Yi, Seunghoon
Kim, Yejin
Jo, Yohan
Lee, Joonseok
author_facet Kim, Chaeyun
Yi, Seunghoon
Kim, Yejin
Jo, Yohan
Lee, Joonseok
contents Referring Image Segmentation (RIS) requires identifying objects from images based on textual descriptions. We observe that existing methods significantly underperform on motion-related queries compared to appearance-based ones. To address this, we first introduce an efficient data augmentation scheme that extracts motion-centric phrases from original captions, exposing models to more motion expressions without additional annotations. Second, since the same object can be described differently depending on the context, we propose Multimodal Radial Contrastive Learning (MRaCL), performed on fused image-text embeddings rather than unimodal representations. For comprehensive evaluation, we introduce a new test split focusing on motion-centric queries, and introduce a new benchmark called M-Bench, where objects are distinguished primarily by actions. Extensive experiments show our method substantially improves performance on motion-centric queries across multiple RIS models, maintaining competitive results on appearance-based descriptions. Codes are available at https://github.com/snuviplab/MRaCL
format Preprint
id arxiv_https___arxiv_org_abs_2603_17413
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Towards Motion-aware Referring Image Segmentation
Kim, Chaeyun
Yi, Seunghoon
Kim, Yejin
Jo, Yohan
Lee, Joonseok
Computer Vision and Pattern Recognition
Referring Image Segmentation (RIS) requires identifying objects from images based on textual descriptions. We observe that existing methods significantly underperform on motion-related queries compared to appearance-based ones. To address this, we first introduce an efficient data augmentation scheme that extracts motion-centric phrases from original captions, exposing models to more motion expressions without additional annotations. Second, since the same object can be described differently depending on the context, we propose Multimodal Radial Contrastive Learning (MRaCL), performed on fused image-text embeddings rather than unimodal representations. For comprehensive evaluation, we introduce a new test split focusing on motion-centric queries, and introduce a new benchmark called M-Bench, where objects are distinguished primarily by actions. Extensive experiments show our method substantially improves performance on motion-centric queries across multiple RIS models, maintaining competitive results on appearance-based descriptions. Codes are available at https://github.com/snuviplab/MRaCL
title Towards Motion-aware Referring Image Segmentation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.17413