Related papers: Exploring Dynamic Transformer for Efficient Object…

Optimization based tracking methods have been widely successful by integrating a target model prediction module, providing effective global reasoning by minimizing an objective function. While this inductive bias integrates valuable domain…

Temporal information is crucial for visual tracking, but existing multi-frame trackers are vulnerable to model drift caused by naively aggregating noisy historical predictions. In this paper, we introduce DTPTrack, a lightweight and…

Multi-object tracking (MOT) is a vital component of intelligent video analytics applications such as surveillance and autonomous driving. The time and storage complexity required to execute deep learning models for visual object tracking…

Fast and safe navigation of dynamical systems through a priori unknown cluttered environments is vital to many applications of autonomous systems. However, trajectory planning for autonomous systems is computationally intensive, often…

Tracking has traditionally been the art of following interest points through space and time. This changed with the rise of powerful deep networks. Nowadays, tracking is dominated by pipelines that perform object detection followed by…

In this paper, we propose a novel visual tracking framework that intelligently discovers reliable patterns from a wide range of video to resist drift error for long-term tracking tasks. First, we design a Discrete Fourier Transform (DFT)…

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…

The main challenge of Multi-Object Tracking~(MOT) lies in maintaining a continuous trajectory for each target. Existing methods often learn reliable motion patterns to match the same target between adjacent frames and discriminative…

Transformers have proven superior performance for a wide variety of tasks since they were introduced. In recent years, they have drawn attention from the vision community in tasks such as image classification and object detection. Despite…

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…

Tracking transforming objects holds significant importance in various fields due to the dynamic nature of many real-world scenarios. By enabling systems accurately represent transforming objects over time, tracking transforming objects…

LiDAR-based 3D single object tracking is a challenging issue in robotics and autonomous driving. Currently, existing approaches usually suffer from the problem that objects at long distance often have very sparse or partially-occluded point…

Dense 3D tracking from monocular video is fundamental to dynamic scene understanding. While recent 3D foundation models provide reliable per-frame geometry, recovering object motion in this geometry remains challenging and benefits from…

Deep trackers have proven success in visual tracking. Typically, these trackers employ optimally pre-trained deep networks to represent all diverse objects with multi-channel features from some fixed layers. The deep networks employed are…

In this paper, we consider the problem of long-term point tracking, which requires consistent identification of points across multiple frames in a video, despite changes in appearance, lighting, perspective, and occlusions. We target online…

Dynamic neural network is an emerging research topic in deep learning. With adaptive inference, dynamic models can achieve remarkable accuracy and computational efficiency. However, it is challenging to design a powerful dynamic detector,…

3D multi-object tracking (MOT) is a key problem for autonomous vehicles, required to perform well-informed motion planning in dynamic environments. Particularly for densely occupied scenes, associating existing tracks to new detections…

Diffusion Transformers (DiT) have emerged as a widely adopted backbone for high-fidelity image and video generation, yet their iterative denoising process incurs high computational costs. Existing training-free acceleration methods rely on…

Diffusion Transformer (DiT), an emerging diffusion model for image generation, has demonstrated superior performance but suffers from substantial computational costs. Our investigations reveal that these costs stem from the static inference…

Event cameras provide superior temporal resolution, dynamic range, power efficiency, and pixel bandwidth. Spiking Neural Networks (SNNs) naturally complement event data through discrete spike signals, making them ideal for event-based…