Related papers: CHASE: Robust Visual Tracking via Cell-Level Diffe…

This survey presents a deep analysis of the learning and inference capabilities in nine popular trackers. It is neither intended to study the whole literature nor is it an attempt to review all kinds of neural networks proposed for visual…

In this paper, we propose a novel on-line visual tracking framework based on the Siamese matching network and meta-learner network, which run at real-time speeds. Conventional deep convolutional feature-based discriminative visual tracking…

The current strive towards end-to-end trainable computer vision systems imposes major challenges for the task of visual tracking. In contrast to most other vision problems, tracking requires the learning of a robust target-specific…

Robustness and discrimination power are two fundamental requirements in visual object tracking. In most tracking paradigms, we find that the features extracted by the popular Siamese-like networks cannot fully discriminatively model the…

Multiple object tracking is a critical task in autonomous driving. Existing works primarily focus on the heuristic design of neural networks to obtain high accuracy. As tracking accuracy improves, however, neural networks become…

The accurate tracking of live cells using video microscopy recordings remains a challenging task for popular state-of-the-art image processing based object tracking methods. In recent years, several existing and new applications have…

Deep learning has become in recent years a cornerstone tool fueling key innovations in the industry, such as autonomous driving. To attain good performances, the neural network architecture used for a given application must be chosen with…

Convolutional Neural Networks (CNN) have been regarded as a capable class of models for visual recognition problems. Nevertheless, it is not trivial to develop generic and powerful network architectures, which requires significant efforts…

Exploiting a general-purpose neural architecture to replace hand-wired designs or inductive biases has recently drawn extensive interest. However, existing tracking approaches rely on customized sub-modules and need prior knowledge for…

In semantic video segmentation the goal is to acquire consistent dense semantic labelling across image frames. To this end, recent approaches have been reliant on manually arranged operations applied on top of static semantic segmentation…

Siamese networks have drawn great attention in visual tracking because of their balanced accuracy and speed. However, the backbone networks used in Siamese trackers are relatively shallow, such as AlexNet [18], which does not fully take…

Visual tracking is one of the most challenging computer vision problems. In order to achieve high performance visual tracking in various negative scenarios, a novel cascaded Siamese network is proposed and developed based on two different…

Neural architecture search has been shown to hold great promise towards the automation of deep learning. However in spite of its potential, neural architecture search remains quite costly. To this point, we propose a novel gradient-based…

Siamese visual trackers have recently advanced through increasingly sophisticated fusion mechanisms built on convolutional or Transformer architectures. However, both struggle to deliver pixel-level interactions efficiently on…

Deep neural networks (DNNs) are found to be vulnerable to adversarial attacks, and various methods have been proposed for the defense. Among these methods, adversarial training has been drawing increasing attention because of its simplicity…

Architecture search is the process of automatically learning the neural model or cell structure that best suits the given task. Recently, this approach has shown promising performance improvements (on language modeling and image…

In the domain of visual tracking, most deep learning-based trackers highlight the accuracy but casting aside efficiency. Therefore, their real-world deployment on mobile platforms like the unmanned aerial vehicle (UAV) is impeded. In this…

In a recurrent setting, conventional approaches to neural architecture search find and fix a general model for all data samples and time steps. We propose a novel algorithm that can dynamically search for the structure of cells in a…

Neural architecture search (NAS) has shown promise towards automating neural network design for a given task, but it is computationally demanding due to training costs associated with evaluating a large number of architectures to find the…

Differentiable neural architecture search methods became popular in recent years, mainly due to their low search costs and flexibility in designing the search space. However, these methods suffer the difficulty in optimizing network, so…