Related papers: Visual Tracking via Dynamic Memory Networks

How to make a good trade-off between performance and computational cost is crucial for a tracker. However, current famous methods typically focus on complicated and time-consuming learning that combining temporal and appearance information…

With the wide applications of deep neural network models in various computer vision tasks, more and more works study the model vulnerability to adversarial examples. For data-free black box attack scenario, existing methods are inspired by…

A robot operating in a household makes observations of multiple objects as it moves around over the course of days or weeks. The objects may be moved by inhabitants, but not completely at random. The robot may be called upon later to…

The rich spatio-temporal information is crucial to capture the complicated target appearance variations in visual tracking. However, most top-performing tracking algorithms rely on many hand-crafted components for spatio-temporal…

Tracking-by-detection algorithms are widely used for visual tracking, where the problem is treated as a classification task where an object model is updated over time using online learning techniques. In challenging conditions where an…

In this paper, we propose and study a novel visual object tracking approach based on convolutional networks and recurrent networks. The proposed approach is distinct from the existing approaches to visual object tracking, such as…

Continual learning on sequential data is critical for many machine learning (ML) deployments. Unfortunately, LSTM networks, which are commonly used to learn on sequential data, suffer from catastrophic forgetting and are limited in their…

Motion blur caused by the moving of the object or camera during the exposure can be a key challenge for visual object tracking, affecting tracking accuracy significantly. In this work, we explore the robustness of visual object trackers…

Neural network architectures with memory and attention mechanisms exhibit certain reasoning capabilities required for question answering. One such architecture, the dynamic memory network (DMN), obtained high accuracy on a variety of…

Recently, several studies have shown that utilizing contextual information to perceive target states is crucial for object tracking. They typically capture context by incorporating multiple video frames. However, these naive frame-context…

Models trained in the context of continual learning (CL) should be able to learn from a stream of data over an undefined period of time. The main challenges herein are: 1) maintaining old knowledge while simultaneously benefiting from it…

In recent years, anchor-free object detection models combined with matching algorithms are used to achieve real-time muti-object tracking and also ensure high tracking accuracy. However, there are still great challenges in multi-object…

Online Multi-Object Tracking (MOT) from videos is a challenging computer vision task which has been extensively studied for decades. Most of the existing MOT algorithms are based on the Tracking-by-Detection (TBD) paradigm combined with…

Tracking tasks based on deep neural networks have greatly improved with the emergence of Siamese trackers. However, the appearance of targets often changes during tracking, which can reduce the robustness of the tracker when facing…

We introduce Spatial-Temporal Memory Networks for video object detection. At its core, a novel Spatial-Temporal Memory module (STMM) serves as the recurrent computation unit to model long-term temporal appearance and motion dynamics. The…

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…

Successful video analysis relies on accurate recognition of pixels across frames, and frame reconstruction methods based on video correspondence learning are popular due to their efficiency. Existing frame reconstruction methods, while…

In this thesis, we propose a pioneering work on sparse keypoints tracking across images using transformer networks. While deep learning-based keypoints matching have been widely investigated using graph neural networks - and more recently…

Neural networks have achieved success in a wide array of perceptual tasks but often fail at tasks involving both perception and higher-level reasoning. On these more challenging tasks, bespoke approaches (such as modular symbolic…

This paper investigates trajectory prediction for robotics, to improve the interaction of robots with moving targets, such as catching a bouncing ball. Unexpected, highly-non-linear trajectories cannot easily be predicted with…