Related papers: Fully Convolutional Online Tracking
We introduce the Smoothed Online Optimization for Target Tracking (SOOTT) problem, a new framework that integrates three key objectives in online decision-making under uncertainty: (1) tracking cost for following a dynamically moving…
Visual tracking can be easily disturbed by similar surrounding objects. Such objects as hard distractors, even though being the minority among negative samples, increase the risk of target drift and model corruption, which deserve…
The complex dynamicity of open-world objects presents non-negligible challenges for multi-object tracking (MOT), often manifested as severe deformations, fast motion, and occlusions. Most methods that solely depend on coarse-grained object…
Reliable multi-object tracking (MOT) is essential for robotic systems operating in complex and dynamic environments. Despite recent advances in detection and association, online MOT methods remain vulnerable to identity switches caused by…
High resolution phenotyping at the level of individual leaves offers fine-grained insights into plant development and stress responses. However, the full potential of accurate leaf tracking over time remains largely unexplored due to the…
Deep neural networks, albeit their great success on feature learning in various computer vision tasks, are usually considered as impractical for online visual tracking because they require very long training time and a large number of…
In this paper, an online adaptive model-free tracker is proposed to track single objects in video sequences to deal with real-world tracking challenges like low-resolution, object deformation, occlusion and motion blur. The novelty lies in…
Referring multi-object tracking (RMOT) is an emerging cross-modal task that aims to localize an arbitrary number of targets based on a language expression and continuously track them in a video. This intricate task involves reasoning on…
Recently using convolutional neural networks (CNNs) has gained popularity in visual tracking, due to its robust feature representation of images. Recent methods perform online tracking by fine-tuning a pre-trained CNN model to the specific…
Discriminant Correlation Filters (DCF) based methods now become a kind of dominant approach to online object tracking. The features used in these methods, however, are either based on hand-crafted features like HoGs, or convolutional…
Motivated by the Parameter-Efficient Fine-Tuning (PEFT) in large language models, we propose LoRAT, a method that unveils the power of large ViT model for tracking within laboratory-level resources. The essence of our work lies in adapting…
Discriminative correlation filters (DCFs) have been shown to perform superiorly in visual tracking. They only need a small set of training samples from the initial frame to generate an appearance model. However, existing DCFs learn the…
Correlation filter (CF)-based trackers have gained significant attention for their computational efficiency in thermal infrared (TIR) target tracking. However, ex-isting methods struggle with challenges such as low-resolution imagery,…
Correlation filter (CF) based tracking algorithms have demonstrated favorable performance recently. Nevertheless, the top performance trackers always employ complicated optimization methods which constraint their real-time applications. How…
The long-standing division between \textit{online} and \textit{offline} Multi-Object Tracking (MOT) has led to fragmented solutions that fail to address the flexible temporal requirements of real-world deployment scenarios. Current…
We present a novel approach to online multi-target tracking based on recurrent neural networks (RNNs). Tracking multiple objects in real-world scenes involves many challenges, including a) an a-priori unknown and time-varying number of…
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…
Siamese approaches have achieved promising performance in visual object tracking recently. The key to the success of Siamese trackers is to learn appearance-invariant feature embedding functions via pair-wise offline training on large-scale…
We study online changepoint detection in the context of a linear regression model. We propose a class of heavily weighted statistics based on the CUSUM process of the regression residuals, which are specifically designed to ensure timely…
This paper proposes a novel method for online Multi-Object Tracking (MOT) using Graph Convolutional Neural Network (GCNN) based feature extraction and end-to-end feature matching for object association. The Graph based approach incorporates…