Related papers: eMoE-Tracker: Environmental MoE-based Transformer …
Siamese network based trackers formulate 3D single object tracking as cross-correlation learning between point features of a template and a search area. Due to the large appearance variation between the template and search area during…
Current multi-object tracking (MOT) algorithms typically overlook issues inherent in low-quality videos, leading to significant degradation in tracking performance when confronted with real-world image deterioration. Therefore, advancing…
Existing tracking algorithms typically rely on low-frame-rate RGB cameras coupled with computationally intensive deep neural network architectures to achieve effective tracking. However, such frame-based methods inherently face challenges…
As an important and challenging problem in computer vision and graphics, keypoint-based object tracking is typically formulated in a spatio-temporal statistical learning framework. However, most existing keypoint trackers are incapable of…
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…
We present a novel transformer-based architecture for global multi-object tracking. Our network takes a short sequence of frames as input and produces global trajectories for all objects. The core component is a global tracking transformer…
Event sensors offer high temporal resolution visual sensing, which makes them ideal for perceiving fast visual phenomena without suffering from motion blur. Certain applications in robotics and vision-based navigation require 3D perception…
Recently, template-based trackers have become the leading tracking algorithms with promising performance in terms of efficiency and accuracy. However, the correlation operation between query feature and the given template only exploits…
The DEtection TRansformer (DETR) opened new possibilities for object detection by modeling it as a translation task: converting image features into object-level representations. Previous works typically add expensive modules to DETR to…
End-to-end transformer architectures have driven significant progress in multi-object tracking by unifying detection and association into a single, heuristic-free framework. Despite these benefits, poor detection performance and the…
Most existing multi-object tracking methods typically learn visual tracking features via maximizing dis-similarities of different instances and minimizing similarities of the same instance. While such a feature learning scheme achieves…
Multiple object tracking (MOT) is the task containing detection and association. Plenty of trackers have achieved competitive performance. Unfortunately, for the lack of informative exchange on these subtasks, they are often biased toward…
Event cameras have higher temporal resolution, and require less storage and bandwidth compared to traditional RGB cameras. However, due to relatively lagging performance of event-based approaches, event cameras have not yet replace…
Mixture of Experts (MoE) models based on Transformer architecture are pushing the boundaries of language and vision tasks. The allure of these models lies in their ability to substantially increase the parameter count without a…
This project addresses the challenge of human motion prediction, a critical area for applications such as au- tonomous vehicle movement detection. Previous works have emphasized the need for low inference times to provide real time…
Multi-modal data in Earth Observation (EO) presents a huge opportunity for improving transfer learning capabilities when pre-training deep learning models. Unlike prior work that often overlooks multi-modal EO data, recent methods have…
Many Multi-Object Tracking (MOT) approaches exploit motion information to associate all the detected objects across frames. However, many methods that rely on filtering-based algorithms, such as the Kalman Filter, often work well in linear…
Multiple Object Tracking (MOT) has rapidly progressed in recent years. Existing works tend to design a single tracking algorithm to perform both detection and association. Though ensemble learning has been exploited in many tasks, i.e,…
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…
The speed-precision trade-off is a critical problem for visual object tracking which usually requires low latency and deployment on constrained resources. Existing solutions for efficient tracking mainly focus on adopting light-weight…