Related papers: Object-Adaptive LSTM Network for Real-time Visual …

Most existing Multi-Object Tracking (MOT) approaches follow the Tracking-by-Detection paradigm and the data association framework where objects are firstly detected and then associated. Although deep-learning based method can noticeably…

Deep learning has recently started being applied to visual tracking of generic objects in video streams. For the purposes of robotics applications, it is very important for a target tracker to recover its track if it is lost due to heavy or…

Siamese network based trackers formulate tracking as convolutional feature cross-correlation between target template and searching region. However, Siamese trackers still have accuracy gap compared with state-of-the-art algorithms and they…

Robust online multi-person tracking requires the correct associations of online detection responses with existing trajectories. We address this problem by developing a novel appearance modeling approach to provide accurate appearance…

The rapid proliferation of digital content and the ever-growing need for precise object recognition and segmentation have driven the advancement of cutting-edge techniques in the field of object classification and segmentation. This paper…

Recently, some correlation filter based trackers with detection proposals have achieved state-of-the-art tracking results. However, a large number of redundant proposals given by the proposal generator may degrade the performance and speed…

Existing visual tracking methods usually localize a target object with a bounding box, in which the performance of the foreground object trackers or detectors is often affected by the inclusion of background clutter. To handle this problem,…

The aim of this research is to detect small objects with low resolution and noise. The existing real time object detection algorithm is based on the deep neural network of convolution need to perform multilevel convolution and pooling…

Training a neural network (NN) typically relies on some type of curve-following method, such as gradient descent (GD) (and stochastic gradient descent (SGD)), ADADELTA, ADAM or limited memory algorithms. Convergence for these algorithms…

We study active object tracking, where a tracker takes as input the visual observation (i.e., frame sequence) and produces the camera control signal (e.g., move forward, turn left, etc.). Conventional methods tackle the tracking and the…

Object trackers based on Convolution Neural Network (CNN) have achieved state-of-the-art performance on recent tracking benchmarks, while they suffer from slow computational speed. The high computational load arises from the extraction of…

During the recent years, correlation filters have shown dominant and spectacular results for visual object tracking. The types of the features that are employed in these family of trackers significantly affect the performance of visual…

As the computational needs of Large Vision-Language Models (LVLMs) increase, visual token pruning has proven effective in improving inference speed and memory efficiency. Traditional pruning methods in LVLMs predominantly focus on attention…

With efficient appearance learning models, Discriminative Correlation Filter (DCF) has been proven to be very successful in recent video object tracking benchmarks and competitions. However, the existing DCF paradigm suffers from two major…

Visual object tracking aims to estimate the location of an arbitrary target in a video sequence given its initial bounding box. By utilizing offline feature learning, the siamese paradigm has recently been the leading framework for high…

During the last years, deep learning trackers achieved stimulating results while bringing interesting ideas to solve the tracking problem. This progress is mainly due to the use of learned deep features obtained by training deep…

Deep Imitation Learning requires a large number of expert demonstrations, which are not always easy to obtain, especially for complex tasks. A way to overcome this shortage of labels is through data augmentation. However, this cannot be…

Augmented Reality (AR) applications often require robust real-time tracking of objects in the user's environment to correctly overlay virtual content. Recent advances in computer vision have produced highly accurate deep learning-based…

Object tracking based on hyperspectral video attracts increasing attention to the rich material and motion information in the hyperspectral videos. The prevailing hyperspectral methods adapt pretrained RGB-based object tracking networks for…

Self-supervised VO methods have shown great success in jointly estimating camera pose and depth from videos. However, like most data-driven methods, existing VO networks suffer from a notable decrease in performance when confronted with…