Related papers: Split and Connect: A Universal Tracklet Booster fo…
Recently, Multi-Object Tracking (MOT) has attracted rising attention, and accordingly, remarkable progresses have been achieved. However, the existing methods tend to use various basic models (e.g, detector and embedding model), and…
Most online multi-object trackers perform object detection stand-alone in a neural net without any input from tracking. In this paper, we present a new online joint detection and tracking model, TraDeS (TRAck to DEtect and Segment),…
Continual learning allows a model to learn multiple tasks sequentially while retaining the old knowledge without the training data of the preceding tasks. This paper extends the scope of continual learning research to class-incremental…
In multi-object tracking, the tracker maintains in its memory the appearance and motion information for each object in the scene. This memory is utilized for finding matches between tracks and detections and is updated based on the matching…
Robust multi-object tracking (MOT) is a prerequisite fora safe deployment of self-driving cars. Tracking objects, however, remains a highly challenging problem, especially in cluttered autonomous driving scenes in which objects tend to…
Recently, Minimum Cost Multicut Formulations have been proposed and proven to be successful in both motion trajectory segmentation and multi-target tracking scenarios. Both tasks benefit from decomposing a graphical model into an optimal…
The goal of multi-object tracking (MOT) is detecting and tracking all the objects in a scene, while keeping a unique identifier for each object. In this paper, we present a new robust state-of-the-art tracker, which can combine the…
Transformer-based multi-object tracking (MOT) methods have captured the attention of many researchers in recent years. However, these models often suffer from slow inference speeds due to their structure or other issues. To address this…
Multi-object tracking (MOT) is a fundamental task in computer vision with critical applications in autonomous driving and robotics. Multimodal MOT that integrates visible light and thermal infrared information is particularly essential for…
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…
The purpose of multi-object tracking (MOT) is to continuously track and identify objects detected in videos. Currently, most methods for multi-object tracking model the motion information and combine it with appearance information to…
Accurately distinguishing each object is a fundamental goal of Multi-object tracking (MOT) algorithms. However, achieving this goal still remains challenging, primarily due to: (i) For crowded scenes with occluded objects, the high overlap…
In recent years, the joint detection-and-tracking paradigm has been a very popular way of tackling the multi-object tracking (MOT) task. Many of the methods following this paradigm use the object center keypoint for detection. However, we…
In this work, we consider data association problems involving multi-object tracking (MOT). In particular, we address the challenges arising from object occlusions. We propose a framework called approximate dynamic programming track…
Multiple Object Tracking (MOT) is a core capability in modern computer vision, essential to autonomous driving, surveillance, sports analytics, robotics, and biomedical imaging. Persistent identity assignment across frames remains…
Object tracking and 3D reconstruction are often performed together, with tracking used as input for reconstruction. However, the obtained reconstructions also provide useful information for improving tracking. We propose a novel method that…
Feature tracking is the building block of many applications such as visual odometry, augmented reality, and target tracking. Unfortunately, the state-of-the-art vision-based tracking algorithms fail in surgical images due to the challenges…
Transformer networks have been a focus of research in many fields in recent years, being able to surpass the state-of-the-art performance in different computer vision tasks. However, in the task of Multiple Object Tracking (MOT), leveraging…
The aim of in-trawl catch monitoring for use in fishing operations is to detect, track and classify fish targets in real-time from video footage. Information gathered could be used to release unwanted bycatch in real-time. However,…
Estimating the target extent poses a fundamental challenge in visual object tracking. Typically, trackers are box-centric and fully rely on a bounding box to define the target in the scene. In practice, objects often have complex shapes and…