ObjEmbed: Towards Universal Multimodal Object Embeddings 文章

ArXiv CS.CV2026-06-02NEWSen作者: Shenghao Fu, Yukun Su, Fengyun Rao, Jing Lyu, Xiaohua Xie, Wei-Shi Zheng

摘要

arXiv:2602.01753v3 Announce Type: replace Abstract: Aligning objects with corresponding textual descriptions is a fundamental challenge and a realistic requirement in vision-language understanding. While recent multimodal embedding models excel at global image-text alignment, they often struggle with fine-grained alignment between image regions and specific phrases. In this work, we present ObjEmbed, a novel MLLM embedding model that decomposes the input image into multiple regional embeddings, each corresponding to an individual object, along with global embeddings. It supports a wide range of visual understanding tasks like visual grounding, local image retrieval, and global image retrieval. ObjEmbed enjoys three key properties: (1) Object-Oriented Representation: It captures both semantic and spatial aspects of objects by generating two complementary embeddings for each region: an object embedding for semantic matching and an IoU embedding that predicts localization quality.

相关事件查看全部 (1)

ObjEmbed: Towards Universal Multimodal Object Embeddings
2026-06-02PRODUCT_LAUNCH影响: MEDIUM

相关公司

暂无数据

相关人物

暂无数据