ReferGPT: Towards Zero-Shot Referring Multi-Object Tracking

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chamiti, Tzoulio, Di Bella, Leandro, Munteanu, Adrian, Deligiannis, Nikos
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913790802526208
author Chamiti, Tzoulio
Di Bella, Leandro
Munteanu, Adrian
Deligiannis, Nikos
author_facet Chamiti, Tzoulio
Di Bella, Leandro
Munteanu, Adrian
Deligiannis, Nikos
contents Tracking multiple objects based on textual queries is a challenging task that requires linking language understanding with object association across frames. Previous works typically train the whole process end-to-end or integrate an additional referring text module into a multi-object tracker, but they both require supervised training and potentially struggle with generalization to open-set queries. In this work, we introduce ReferGPT, a novel zero-shot referring multi-object tracking framework. We provide a multi-modal large language model (MLLM) with spatial knowledge enabling it to generate 3D-aware captions. This enhances its descriptive capabilities and supports a more flexible referring vocabulary without training. We also propose a robust query-matching strategy, leveraging CLIP-based semantic encoding and fuzzy matching to associate MLLM generated captions with user queries. Extensive experiments on Refer-KITTI, Refer-KITTIv2 and Refer-KITTI+ demonstrate that ReferGPT achieves competitive performance against trained methods, showcasing its robustness and zero-shot capabilities in autonomous driving. The codes are available on https://github.com/Tzoulio/ReferGPT
format Preprint
id arxiv_https___arxiv_org_abs_2504_09195
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ReferGPT: Towards Zero-Shot Referring Multi-Object Tracking
Chamiti, Tzoulio
Di Bella, Leandro
Munteanu, Adrian
Deligiannis, Nikos
Computer Vision and Pattern Recognition
Artificial Intelligence
Tracking multiple objects based on textual queries is a challenging task that requires linking language understanding with object association across frames. Previous works typically train the whole process end-to-end or integrate an additional referring text module into a multi-object tracker, but they both require supervised training and potentially struggle with generalization to open-set queries. In this work, we introduce ReferGPT, a novel zero-shot referring multi-object tracking framework. We provide a multi-modal large language model (MLLM) with spatial knowledge enabling it to generate 3D-aware captions. This enhances its descriptive capabilities and supports a more flexible referring vocabulary without training. We also propose a robust query-matching strategy, leveraging CLIP-based semantic encoding and fuzzy matching to associate MLLM generated captions with user queries. Extensive experiments on Refer-KITTI, Refer-KITTIv2 and Refer-KITTI+ demonstrate that ReferGPT achieves competitive performance against trained methods, showcasing its robustness and zero-shot capabilities in autonomous driving. The codes are available on https://github.com/Tzoulio/ReferGPT
title ReferGPT: Towards Zero-Shot Referring Multi-Object Tracking
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2504.09195