Related papers: HIPTrack: Visual Tracking with Historical Prompts

The problem of arbitrary object tracking has traditionally been tackled by learning a model of the object's appearance exclusively online, using as sole training data the video itself. Despite the success of these methods, their online-only…

Self-supervised learning for visual object tracking possesses valuable advantages compared to supervised learning, such as the non-necessity of laborious human annotations and online training. In this work, we exploit an end-to-end Siamese…

Recently, we have seen a rapid development of Deep Neural Network (DNN) based visual tracking solutions. Some trackers combine the DNN-based solutions with Discriminative Correlation Filters (DCF) to extract semantic features and…

While remarkable progress has been made in robust visual tracking, accurate target state estimation still remains a highly challenging problem. In this paper, we argue that this issue is closely related to the prevalent bounding box…

Template-matching methods for visual tracking have gained popularity recently due to their comparable performance and fast speed. However, they lack effective ways to adapt to changes in the target object's appearance, making their tracking…

Visible-modal object tracking gives rise to a series of downstream multi-modal tracking tributaries. To inherit the powerful representations of the foundation model, a natural modus operandi for multi-modal tracking is full fine-tuning on…

In this paper, we address various challenges in multi-pedestrian and vehicle tracking in high-resolution aerial imagery by intensive evaluation of a number of traditional and Deep Learning based Single- and Multi-Object Tracking methods. We…

Most of the existing single object trackers track the target in a unitary local search window, making them particularly vulnerable to challenging factors such as heavy occlusions and out-of-view movements. Despite the attempts to further…

Maintaining the identity of multiple objects in real-time video is a challenging task, as it is not always feasible to run a detector on every frame. Thus, motion estimation systems are often employed, which either do not scale well with…

Visual tracking is challenging due to image variations caused by various factors, such as object deformation, scale change, illumination change and occlusion. Given the superior tracking performance of human visual system (HVS), an ideal…

The current Siamese network based on region proposal network (RPN) has attracted great attention in visual tracking due to its excellent accuracy and high efficiency. However, the design of the RPN involves the selection of the number,…

We propose a novel online multi-target visual tracker based on the recently developed Hypothesized and Independent Stochastic Population (HISP) filter. The HISP filter combines advantages of traditional tracking approaches like MHT and…

The deployment of transformers for visual object tracking has shown state-of-the-art results on several benchmarks. However, the transformer-based models are under-utilized for Siamese lightweight tracking due to the computational…

In this work, we present a method for landmark retrieval that utilizes global and local features. A Siamese network is used for global feature extraction and metric learning, which gives an initial ranking of the landmark search. We utilize…

Time series pre-training has recently garnered wide attention for its potential to reduce labeling expenses and benefit various downstream tasks. Prior methods are mainly based on pre-training techniques well-acknowledged in vision or…

We present Siam R-CNN, a Siamese re-detection architecture which unleashes the full power of two-stage object detection approaches for visual object tracking. We combine this with a novel tracklet-based dynamic programming algorithm, which…

The ability to detect and track the dynamic objects in different scenes is fundamental to real-world applications, e.g., autonomous driving and robot navigation. However, traditional Multi-Object Tracking (MOT) is limited to tracking…

Most thermal infrared (TIR) tracking methods are discriminative, treating the tracking problem as a classification task. However, the objective of the classifier (label prediction) is not coupled to the objective of the tracker (location…

Test-time prompt tuning, which learns prompts online with unlabelled test samples during the inference stage, has demonstrated great potential by learning effective prompts on-the-fly without requiring any task-specific annotations.…

Although data-free incremental learning methods are memory-friendly, accurately estimating and counteracting representation shifts is challenging in the absence of historical data. This paper addresses this thorny problem by proposing a…