Related papers: Learning to Adversarially Blur Visual Object Track…
To overcome the problem of occlusion in visual tracking, this paper proposes an occlusion-aware tracking algorithm. The proposed algorithm divides the object into discrete image patches according to the pixel distribution of the object by…
We propose a hybrid framework for consistently producing high-quality object tracks by combining an automated object tracker with little human input. The key idea is to tailor a module for each dataset to intelligently decide when an object…
Visual Language Models (VLMs) are vulnerable to adversarial attacks, especially those from adversarial images, which is however under-explored in literature. To facilitate research on this critical safety problem, we first construct a new…
Visual object tracking aims to precisely estimate the bounding box for the given target, which is a challenging problem due to factors such as deformation and occlusion. Many recent trackers adopt the multiple-stage tracking strategy to…
This work focuses on multi-target tracking in Video synthetic aperture radar. Specifically, we refer to tracking based on targets' shadows. Current methods have limited accuracy as they fail to consider shadows' characteristics and…
Memory decay makes it harder for the human brain to recognize visual objects and retain details. Consequently, recorded brain signals become weaker, uncertain, and contain poor visual context over time. This paper presents one of the first…
Although deep learning-based visual tracking methods have made significant progress, they exhibit vulnerabilities when facing carefully designed adversarial attacks, which can lead to a sharp decline in tracking performance. To address this…
In this paper we present DOT (Dynamic Object Tracking), a front-end that added to existing SLAM systems can significantly improve their robustness and accuracy in highly dynamic environments. DOT combines instance segmentation and…
In object detection, data amount and cost are a trade-off, and collecting a large amount of data in a specific domain is labor intensive. Therefore, existing large-scale datasets are used for pre-training. However, conventional transfer…
The significant advancements in embodied vision navigation have raised concerns about its susceptibility to adversarial attacks exploiting deep neural networks. Investigating the adversarial robustness of embodied vision navigation is…
The goal of multi-object tracking is to detect and track all objects in a scene while maintaining unique identifiers for each, by associating their bounding boxes across video frames. This association relies on matching motion and…
Discriminative correlation filter (DCF) based trackers have recently achieved excellent performance with great computational efficiency. However, DCF based trackers suffer boundary effects, which result in unstable performance in…
Adversarial representation learning aims to learn data representations for a target task while removing unwanted sensitive information at the same time. Existing methods learn model parameters iteratively through stochastic gradient…
Current adversarial attacks for motion estimation (optical flow) optimize small per-pixel perturbations, which are unlikely to appear in the real world. In contrast, we exploit a real-world weather phenomenon for a novel attack with…
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…
Visual-based target tracking is easily influenced by multiple factors, such as background clutter, targets fast-moving, illumination variation, object shape change, occlusion, etc. These factors influence the tracking accuracy of a target…
Multi-Object Tracking, also known as Multi-Target Tracking, is a significant area of computer vision that has many uses in a variety of settings. The development of deep learning, which has encouraged researchers to propose more and more…
One of the major challenges of model-free visual tracking problem has been the difficulty originating from the unpredictable and drastic changes in the appearance of objects we target to track. Existing methods tackle this problem by…
It is infeasible to encompass all possible disturbances within the training dataset. This raises a critical question regarding the robustness of Vision-Language-Action (VLA) models when encountering unseen real-world visual disturbances,…
Research into adversarial examples (AE) has developed rapidly, yet static adversarial patches are still the main technique for conducting attacks in the real world, despite being obvious, semi-permanent and unmodifiable once deployed. In…