Serial Over Parallel: Learning Continual Unification for Multi-Modal Visual Object Tracking and Benchmarking

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Tang, Zhangyong, Xu, Tianyang, Zhu, Xuefeng, Cheng, Chunyang, Zhou, Tao, Wu, Xiaojun, Kittler, Josef
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911105586036736
author Tang, Zhangyong
Xu, Tianyang
Zhu, Xuefeng
Cheng, Chunyang
Zhou, Tao
Wu, Xiaojun
Kittler, Josef
author_facet Tang, Zhangyong
Xu, Tianyang
Zhu, Xuefeng
Cheng, Chunyang
Zhou, Tao
Wu, Xiaojun
Kittler, Josef
contents Unifying multiple multi-modal visual object tracking (MMVOT) tasks draws increasing attention due to the complementary nature of different modalities in building robust tracking systems. Existing practices mix all data sensor types in a single training procedure, structuring a parallel paradigm from the data-centric perspective and aiming for a global optimum on the joint distribution of the involved tasks. However, the absence of a unified benchmark where all types of data coexist forces evaluations on separated benchmarks, causing \textit{inconsistency} between training and testing, thus leading to performance \textit{degradation}. To address these issues, this work advances in two aspects: \ding{182} A unified benchmark, coined as UniBench300, is introduced to bridge the inconsistency by incorporating multiple task data, reducing inference passes from three to one and cutting time consumption by 27\%. \ding{183} The unification process is reformulated in a serial format, progressively integrating new tasks. In this way, the performance degradation can be specified as knowledge forgetting of previous tasks, which naturally aligns with the philosophy of continual learning (CL), motivating further exploration of injecting CL into the unification process. Extensive experiments conducted on two baselines and four benchmarks demonstrate the significance of UniBench300 and the superiority of CL in supporting a stable unification process. Moreover, while conducting dedicated analyses, the performance degradation is found to be negatively correlated with network capacity. Additionally, modality discrepancies contribute to varying degradation levels across tasks (RGBT > RGBD > RGBE in MMVOT), offering valuable insights for future multi-modal vision research. Source codes and the proposed benchmark is available at \textit{https://github.com/Zhangyong-Tang/UniBench300}.
format Preprint
id arxiv_https___arxiv_org_abs_2508_10655
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Serial Over Parallel: Learning Continual Unification for Multi-Modal Visual Object Tracking and Benchmarking
Tang, Zhangyong
Xu, Tianyang
Zhu, Xuefeng
Cheng, Chunyang
Zhou, Tao
Wu, Xiaojun
Kittler, Josef
Computer Vision and Pattern Recognition
Artificial Intelligence
Unifying multiple multi-modal visual object tracking (MMVOT) tasks draws increasing attention due to the complementary nature of different modalities in building robust tracking systems. Existing practices mix all data sensor types in a single training procedure, structuring a parallel paradigm from the data-centric perspective and aiming for a global optimum on the joint distribution of the involved tasks. However, the absence of a unified benchmark where all types of data coexist forces evaluations on separated benchmarks, causing \textit{inconsistency} between training and testing, thus leading to performance \textit{degradation}. To address these issues, this work advances in two aspects: \ding{182} A unified benchmark, coined as UniBench300, is introduced to bridge the inconsistency by incorporating multiple task data, reducing inference passes from three to one and cutting time consumption by 27\%. \ding{183} The unification process is reformulated in a serial format, progressively integrating new tasks. In this way, the performance degradation can be specified as knowledge forgetting of previous tasks, which naturally aligns with the philosophy of continual learning (CL), motivating further exploration of injecting CL into the unification process. Extensive experiments conducted on two baselines and four benchmarks demonstrate the significance of UniBench300 and the superiority of CL in supporting a stable unification process. Moreover, while conducting dedicated analyses, the performance degradation is found to be negatively correlated with network capacity. Additionally, modality discrepancies contribute to varying degradation levels across tasks (RGBT > RGBD > RGBE in MMVOT), offering valuable insights for future multi-modal vision research. Source codes and the proposed benchmark is available at \textit{https://github.com/Zhangyong-Tang/UniBench300}.
title Serial Over Parallel: Learning Continual Unification for Multi-Modal Visual Object Tracking and Benchmarking
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2508.10655