Saved in:
Bibliographic Details
Main Authors: Du, Chengyi, Jin, Keyan
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2504.10048
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913792407896064
author Du, Chengyi
Jin, Keyan
author_facet Du, Chengyi
Jin, Keyan
contents Multi-object grounding in 3D scenes involves localizing multiple objects based on natural language input. While previous work has primarily focused on single-object grounding, real-world scenarios often demand the localization of several objects. To tackle this challenge, we propose Hierarchical Contrastive Siamese Transformers (H-COST), which employs a Hierarchical Processing strategy to progressively refine object localization, enhancing the understanding of complex language instructions. Additionally, we introduce a Contrastive Siamese Transformer framework, where two networks with the identical structure are used: one auxiliary network processes robust object relations from ground-truth labels to guide and enhance the second network, the reference network, which operates on segmented point-cloud data. This contrastive mechanism strengthens the model' s semantic understanding and significantly enhances its ability to process complex point-cloud data. Our approach outperforms previous state-of-the-art methods by 9.5% on challenging multi-object grounding benchmarks.
format Preprint
id arxiv_https___arxiv_org_abs_2504_10048
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Multi-Object Grounding via Hierarchical Contrastive Siamese Transformers
Du, Chengyi
Jin, Keyan
Computer Vision and Pattern Recognition
Multi-object grounding in 3D scenes involves localizing multiple objects based on natural language input. While previous work has primarily focused on single-object grounding, real-world scenarios often demand the localization of several objects. To tackle this challenge, we propose Hierarchical Contrastive Siamese Transformers (H-COST), which employs a Hierarchical Processing strategy to progressively refine object localization, enhancing the understanding of complex language instructions. Additionally, we introduce a Contrastive Siamese Transformer framework, where two networks with the identical structure are used: one auxiliary network processes robust object relations from ground-truth labels to guide and enhance the second network, the reference network, which operates on segmented point-cloud data. This contrastive mechanism strengthens the model' s semantic understanding and significantly enhances its ability to process complex point-cloud data. Our approach outperforms previous state-of-the-art methods by 9.5% on challenging multi-object grounding benchmarks.
title Multi-Object Grounding via Hierarchical Contrastive Siamese Transformers
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2504.10048