Skip to content
Conference

Cross-Domain Adaptive Transformer Framework for Robust Object Tracking in Unconstrained Multi-Domain Environments

Sep 2026 · Automation, Control, and Information Technology · pp. 1569-1600 · 0 citations · 30 references

Abstract

Visual object tracking (VOT) in real-world scenarios necessitates a high degree of adaptability to overcome the distributions discrepancies inherent in multi-domain environments. While standard deep learning models excel in well-conditioned laboratory datasets, their performance typically degrades when encountering adverse weather, fluctuating illumination, or sensor-specific noise. This research proposes a novel Context-Aware Multi-Domain Adaptation (CAMA) framework that integrates frequency-aware visual adapters and long-term memory modules into a frozen foundation transformer backbone. By leveraging a textconditioned scenario generator for synthetic domain expansion and an optimal transport-based confidence alignment mechanism, the system bridges the gap between source and unlabeled target domains without requiring redundant model updates. Evaluation across multiple benchmarks, including trimodal (RGB, Depth, Thermal) and adverse-weather datasets, indicates that the proposed framework significantly mitigates tracking drift and identity switches. The findings suggest a robust paradigm for real-time tracking in high-stakes applications such as autonomous navigation, aerial surveillance, and intelligent manufacturing.

View source

Similar papers

Open access 2026

Encoder-Level Temporal Fusion Transformers for Robust Multi-Object Tracking

Experiments on three challenging benchmarks show that GTF improves identity association and overall tracking robustness, particularly under fast motion, appearance ambiguity, and frequent occlusions, and ablation studies further support the roles of encoder-level temporal fusion, adaptive gating, entropy regularization...

Jinho Kim, Kuk-Jin Yoon · 0 citations
Open access Sep 2026

Sampling-Free Universal Domain Adaptive Object Detection with Synergistic Optimization Alignment

Synergistic Optimization Alignment Alignment (SOA) is proposed, a sampling-free framework that tackles two challenges inherent in UniDAOD: multi-scale discriminator discrepancy and task-dominant gradient conflict.

Yuan-Fan Zheng, Jin-Lin Wu, Wu-Yang Li et al. · 0 citations

Template-Search Domain Adaptation via Multi-Stage Feature Alignment for Cross-Modal Object Tracking

Visual object tracking typically assumes that the initial template and subsequent search frames share the same sensing modality. In practice, sensor availability or operation may change over time, creating a substantial representation gap between template and search frames. Unlike conventional multi-modal tracking wher...

Fereshteh Aghaee Meibodi, Amir Mehdi Soufi Enayati, Shadi Alijani et al. · 0 citations
Preprint Oct 2026

JMT-YOLO: Multi-task Domain Adaptation via Segmentation-Guided Consistency Learning

Domain adaptive object detection (DAOD) aims to reduce performance degradation due to distribution shifts between training (source) and testing (target) datasets. However, owing to insufficient modeling of fine-grained features and limited instance-level alignment, existing approaches become less effective under comple...

Zhen-Hua Yu, Jia-Hao Zhang, Wen-Chao Zhang et al. · 0 citations
Sep 2026

When to Adapt: Multi-Signal Domain Shift Detection for Efficient Training-Free Adaptation in Open-Vocabulary Segmentation

This work proposes a multi-signal domain shift detection method for training-free continual test-time adaptation (TF-CTTA) in open-vocabulary segmentation that maintains segmentation accuracy while substantially reducing adaptations, making training-free adaptation practical and feasible for long-term, real-world robot...

Michele Antonazzi, A. C. Hernández, José Araújo et al. · 0 citations
Preprint Aug 2026

Efficient Language-to-Vision Feature Injection for Referring Single-Object Tracking

LVTrack is presented, a pure transformer framework that introduces a mode-conditioned Gated Feature Injector to adaptively regulate textual guidance and alleviate semantic drift, and directly harnesses a frozen vision-language pretrained model, greatly reducing training cost and preserving strong language understanding...

Han Wang, Yuxuan Liu, Yu-Han Sun et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.