Higher Performance Visual Tracking with Dual-Modal Localization

2021-03-18 · Jinghao Zhou, Bo Li, Lei Qiao, Peng Wang, Weihao Gan, Wei Wu, Junjie Yan, Wanli Ouyang

Visual Object Tracking (VOT) has synchronous needs for both robustness and accuracy. While most existing works fail to operate simultaneously on both, we investigate in this work the problem of conflicting performance between accuracy and robustness. We first conduct a systematic comparison among existing methods and analyze their restrictions in terms of accuracy and robustness. Specifically, 4 formulations-offline classification (OFC), offline regression (OFR), online classification (ONC), and online regression (ONR)-are considered, categorized by the existence of online update and the types of supervision signal. To account for the problem, we resort to the idea of ensemble and propose a dual-modal framework for target localization, consisting of robust localization suppressing distractors via ONR and the accurate localization attending to the target center precisely via OFC. To yield a final representation (i.e, bounding box), we propose a simple but effective score voting strategy to involve adjacent predictions such that the final representation does not commit to a single location. Operating beyond the real-time demand, our proposed method is further validated on 8 datasets-VOT2018, VOT2019, OTB2015, NFS, UAV123, LaSOT, TrackingNet, and GOT-10k, achieving state-of-the-art performance.

📄 PDF Abstract BibTeX arXiv:2103.10089

Code (0)

등록된 구현이 없습니다.

Tasks

Object Tracking regression Visual Object Tracking Visual Tracking

Unified Multimodal Visual Tracking with Dual Mixture-of-Experts

2026-05-05 · Lingyi Hong, Jinglun Li, Xinyu Zhou, Kaixun Jiang 외 arxiv

Multimodal visual object tracking can be divided into to several kinds of tasks (e.g. RGB and RGB+X tracking), based on the input modality. Existing methods often train separate models for each modality or rely on pretra…

Visual Object Tracking Model Compression Visual Tracking

Visual and Memory Dual Adapter for Multi-Modal Object Tracking

2025-06-30 · Boyue Xu, Ruichao Hou, Tongwei Ren, Gangshan Wu

Prompt-learning-based multi-modal trackers have achieved promising progress by employing lightweight visual adapters to incorporate auxiliary modality features into frozen foundation models. However, existing approaches …

Object Tracking Prompt Learning

Learning Target-oriented Dual Attention for Robust RGB-T Tracking

2019-08-12 · Rui Yang, Yabin Zhu, Xiao Wang, Chenglong Li 외

RGB-Thermal object tracking attempt to locate target object using complementary visual and thermal infrared data. Existing RGB-T trackers fuse different modalities by robust feature representation learning or adaptive mo…

Object Object Tracking Representation Learning Rgb-T Tracking+1

Cross-Modal Object Tracking: Modality-Aware Representations and A Unified Benchmark

2021-11-08 · Chenglong Li, Tianhao Zhu, Lei Liu, Xiaonan Si 외

In many visual systems, visual tracking often bases on RGB image sequences, in which some targets are invalid in low-light conditions, and tracking performance is thus affected significantly. Introducing other modalities…

Object Tracking Visual Tracking

Robust RGB-T Tracking via Learnable Visual Fourier Prompt Fine-tuning and Modality Fusion Prompt Generation

2025-09-24 · Hongtao Yang, Bineng Zhong, Qihua Liang, Zhiruo Zhu 외 arxiv

Recently, visual prompt tuning is introduced to RGB-Thermal (RGB-T) tracking as a parameter-efficient finetuning (PEFT) method. However, these PEFT-based RGB-T tracking methods typically rely solely on spatial domain inf…

Visual Prompt Tuning Rgb-T Tracking