MedElevator Войти в исследования
← Поиск публикаций

DOI 10.1109/tip.2026.3661393

Медицинская библиотека · IEEE transactions on image processing : a publication of the IEEE Signal Processing Society · 2026

SMTrack: State-Aware Mamba for Efficient Temporal Modeling in Visual Tracking.

Ma Yinchao, Yang Dengqing, He Zhangyu, Yang Wenfei, Zhang Tianzhu

СтатьяПеревод в очереди

Аннотация

Visual tracking aims to automatically estimate the state of a target object in a video sequence, which is challenging especially in dynamic scenarios. Thus, numerous methods are proposed to introduce temporal cues to enhance tracking robustness. However, conventional CNN and Transformer architectures exhibit inherent limitations in modeling long-range temporal dependencies in visual tracking, often necessitating either complex customized modules or substantial computational costs to integrate temporal cues. Inspired by the success of the state space model, we propose a novel temporal modeling paradigm for visual tracking, termed State-aware Mamba Tracker (SMTrack), providing a neat pipeline for training and tracking without needing customized modules or substantial computational costs to build long-range temporal dependencies. It enjoys several merits. First, we propose a novel selective state-aware space model with state-wise parameters to capture more diverse temporal cues for robust tracking. Second, SMTrack facilitates long-range temporal interactions with linear computational complexity during training. Third, SMTrack enables each frame to interact with previously tracked frames via hidden state propagation and updating, which releases computational costs of handling temporal cues during tracking. Extensive experimental results demonstrate that SMTrack achieves promising performance with low computational costs.

Для цитирования: Ma Yinchao, Yang Dengqing, He Zhangyu, Yang Wenfei, Zhang Tianzhu. SMTrack: State-Aware Mamba for Efficient Temporal Modeling in Visual Tracking.. IEEE transactions on image processing : a publication of the IEEE Signal Processing Society. 2026. DOI: 10.1109/tip.2026.3661393.
Подготовка и перевод публикации
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…

История · было → стало

Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.

Тип публикации указан по данным источника. Уровень доказательности автоматически не присваивается.