Paper Reading AI Learner

ORMOT: A Dataset and Framework for Omnidirectional Referring Multi-Object Tracking

2026-03-05 17:15:01
Sijia Chen, Zihan Zhou, Yanqiu Yu, En Yu, Wenbing Tao

Abstract

Multi-Object Tracking (MOT) is a fundamental task in computer vision, aiming to track targets across video frames. Existing MOT methods perform well in general visual scenes, but face significant challenges and limitations when extended to visual-language settings. To bridge this gap, the task of Referring Multi-Object Tracking (RMOT) has recently been proposed, which aims to track objects that correspond to language descriptions. However, current RMOT methods are primarily developed on datasets captured by conventional cameras, which suffer from limited field of view. This constraint often causes targets to move out of the frame, leading to fragmented tracking and loss of contextual information. In this work, we propose a novel task, called Omnidirectional Referring Multi-Object Tracking (ORMOT), which extends RMOT to omnidirectional imagery, aiming to overcome the field-of-view (FoV) limitation of conventional datasets and improve the model's ability to understand long-horizon language descriptions. To advance the ORMOT task, we construct ORSet, an Omnidirectional Referring Multi-Object Tracking dataset, which contains 27 diverse omnidirectional scenes, 848 language descriptions, and 3,401 annotated objects, providing rich visual, temporal, and language information. Furthermore, we propose ORTrack, a Large Vision-Language Model (LVLM)-driven framework tailored for Omnidirectional Referring Multi-Object Tracking. Extensive experiments on the ORSet dataset demonstrate the effectiveness of our ORTrack framework. The dataset and code will be open-sourced at this https URL.

Abstract (translated)

多目标跟踪(MOT)是计算机视觉中的一个基本任务,旨在追踪视频帧中目标的位置。现有的MOT方法在一般的视觉场景下表现良好,但在扩展到涉及视觉和语言的设置时遇到了显著的挑战和限制。为了解决这一差距,最近提出了引用多对象跟踪(RMOT)的任务,其目的是根据语言描述来追踪物体。然而,目前的RMOT方法主要是在传统摄像机捕获的数据集上开发的,这些数据集视野有限。这种局限性常常导致目标移出画面范围,造成碎片化的追踪和上下文信息丢失。 为克服这一问题,在这项工作中,我们提出了一项新的任务——全向引用多对象跟踪(ORMOT),该任务扩展了RMOT至全向图像领域,旨在超越传统数据集的视野限制,并提升模型理解长跨度语言描述的能力。为了推动ORMOT的研究进展,我们构建了ORSet这一全向引用多目标追踪数据集,包含了27种多样化的全向场景、848条语言描述和3,401个标注对象,提供了丰富的视觉、时间以及语言信息。 此外,我们提出了ORTrack框架,这是一个针对全向引用多对象跟踪任务量身定制的大规模视觉-语言模型(LVLM)驱动的解决方案。在ORSet数据集上的广泛实验验证了我们的ORTrack框架的有效性。该数据集和代码将通过以下链接开放源码:[此URL]。 请注意,原文中提到的具体链接("this https URL")应替换为实际可访问的数据集和代码发布页面地址。

URL

https://arxiv.org/abs/2603.05384

PDF

https://arxiv.org/pdf/2603.05384.pdf


Tags
3D Action Action_Localization Action_Recognition Activity Adversarial Agent Attention Autonomous Bert Boundary_Detection Caption Chat Classification CNN Compressive_Sensing Contour Contrastive_Learning Deep_Learning Denoising Detection Dialog Diffusion Drone Dynamic_Memory_Network Edge_Detection Embedding Embodied Emotion Enhancement Face Face_Detection Face_Recognition Facial_Landmark Few-Shot Gait_Recognition GAN Gaze_Estimation Gesture Gradient_Descent Handwriting Human_Parsing Image_Caption Image_Classification Image_Compression Image_Enhancement Image_Generation Image_Matting Image_Retrieval Inference Inpainting Intelligent_Chip Knowledge Knowledge_Graph Language_Model LLM Matching Medical Memory_Networks Multi_Modal Multi_Task NAS NMT Object_Detection Object_Tracking OCR Ontology Optical_Character Optical_Flow Optimization Person_Re-identification Point_Cloud Portrait_Generation Pose Pose_Estimation Prediction QA Quantitative Quantitative_Finance Quantization Re-identification Recognition Recommendation Reconstruction Regularization Reinforcement_Learning Relation Relation_Extraction Represenation Represenation_Learning Restoration Review RNN Robot Salient Scene_Classification Scene_Generation Scene_Parsing Scene_Text Segmentation Self-Supervised Semantic_Instance_Segmentation Semantic_Segmentation Semi_Global Semi_Supervised Sence_graph Sentiment Sentiment_Classification Sketch SLAM Sparse Speech Speech_Recognition Style_Transfer Summarization Super_Resolution Surveillance Survey Text_Classification Text_Generation Time_Series Tracking Transfer_Learning Transformer Unsupervised Video_Caption Video_Classification Video_Indexing Video_Prediction Video_Retrieval Visual_Relation VQA Weakly_Supervised Zero-Shot