Related papers: DINO-Tracker: Taming DINO for Self-Supervised Poin…

Most current multi-object trackers focus on short-term tracking, and are based on deep and complex systems that do not operate in real-time, often making them impractical for video-surveillance. In this paper, we present a long-term…

How to combine the complementary capabilities of an ensemble of different algorithms has been of central interest in visual object tracking. A significant progress on such a problem has been achieved, but considering short-term tracking…

The practicality of a video surveillance system is adversely limited by the amount of queries that can be placed on human resources and their vigilance in response. To transcend this limitation, a major effort under way is to include…

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…

Many techniques have been developed, such as model compression, to make Deep Neural Networks (DNNs) inference more efficiently. Nevertheless, DNNs still lack excellent run-time dynamic inference capability to enable users trade-off accuracy…

Neural networks for multi-domain learning empowers an effective combination of information from different domains by sharing and co-learning the parameters. In visual tracking, the emerging features in shared layers of a multi-domain…

This paper deals with the problem of 3D tracking, i.e., to find dense correspondences in a sequence of time-varying 3D shapes. Despite deep learning approaches have achieved promising performance for pairwise dense 3D shapes matching, it is…

Driven by the emergence of Controllable Video Diffusion, existing Sim2Real methods for autonomous driving video generation typically rely on explicit intermediate representations to bridge the domain gap. However, these modalities face a…

Tracking-by-detection methods have demonstrated competitive performance in recent years. In these approaches, the tracking model heavily relies on the quality of the training set. Due to the limited amount of labeled training data,…

Machine learning techniques are often used in computer vision due to their ability to leverage large amounts of training data to improve performance. Unfortunately, most generic object trackers are still trained from scratch online and do…

Surround-view depth estimation is a crucial task aims to acquire the depth maps of the surrounding views. It has many applications in real world scenarios such as autonomous driving, AR/VR and 3D reconstruction, etc. However, given that…

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…

Video inpainting aims to fill spatio-temporal holes with plausible content in a video. Despite tremendous progress of deep neural networks for image inpainting, it is challenging to extend these methods to the video domain due to the…

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…

In this paper, the main task we aim to tackle is the multi-instance semi-supervised video object segmentation across a sequence of frames where only the first-frame box-level ground-truth is provided. Detection-based algorithms are widely…

Object-centric understanding is fundamental to human vision and required for complex reasoning. Traditional methods define slot-based bottlenecks to learn object properties explicitly, while recent self-supervised vision models like DINO…

We introduce a prediction driven method for visual tracking and segmentation in videos. Instead of solely relying on matching with appearance cues for tracking, we build a predictive model which guides finding more accurate tracking regions…

Deep neural networks, albeit their great success on feature learning in various computer vision tasks, are usually considered as impractical for online visual tracking because they require very long training time and a large number of…

Most state-of-the-art point trackers are trained on synthetic data due to the difficulty of annotating real videos for this task. However, this can result in suboptimal performance due to the statistical gap between synthetic and real…

Identifying unusual driving behaviors exhibited by drivers during driving is essential for understanding driver behavior and the underlying causes of crashes. Previous studies have primarily approached this problem as a classification task,…