Related papers: NOOUGAT: Towards Unified Online and Offline Multi-…
The majority of existing solutions to the Multi-Target Tracking (MTT) problem do not combine cues in a coherent end-to-end fashion over a long period of time. However, we present an online method that encodes long-term temporal dependencies…
Data association-based multiple object tracking (MOT) involves multiple separated modules processed or optimized differently, which results in complex method design and requires non-trivial tuning of parameters. In this paper, we present an…
Multi-object tracking (MOT) is essential for sports analytics, enabling performance evaluation and tactical insights. However, tracking in sports is challenging due to fast movements, occlusions, and camera shifts. Traditional…
Multi-object tracking (MOT) aims to associate target objects across video frames in order to obtain entire moving trajectories. With the advancement of deep neural networks and the increasing demand for intelligent video analysis, MOT has…
We propose a method for multi-object tracking and segmentation based on a novel memory-based mechanism to associate tracklets. The proposed tracker, MeNToS, addresses particularly the long-term data association problem, when objects are not…
Current motion-based multiple object tracking (MOT) approaches rely heavily on Intersection-over-Union (IoU) for object association. Without using 3D features, they are ineffective in scenarios with occlusions or visually similar objects.…
Online learning has turned out to be effective for improving tracking performance. However, it could be simply applied for classification branch, but still remains challenging to adapt to regression branch due to its complex design and…
Multiple Object Tracking (MOT) has witnessed remarkable advances in recent years. However, existing studies dominantly request prior knowledge of the tracking target, and hence may not generalize well to unseen categories. In contrast,…
Multi-object tracking (MOT) aims to maintain consistent identities of objects across video frames. Associating objects in low-frame-rate videos captured by moving unmanned aerial vehicles (UAVs) in actual combat scenarios is complex due to…
Most of Multiple Object Tracking (MOT) approaches compute individual target features for two subtasks: estimating target-wise motions and conducting pair-wise Re-Identification (Re-ID). Because of the indefinite number of targets among…
Vehicular Ad-hoc Networks (VANETs) operate in highly dynamic environments characterized by high mobility, time-varying channel conditions, and frequent network disruptions. Addressing these challenges, this paper presents a novel…
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…
Multiobject tracking (MOT) is an important task in robotics, autonomous driving, and maritime surveillance. Traditional work on MOT is model-based and aims to establish algorithms in the framework of sequential Bayesian estimation. More…
Supervised trackers trained on labeled data dominate the single object tracking field for superior tracking accuracy. The labeling cost and the huge computational complexity hinder their applications on edge devices. Unsupervised learning…
Multi-modal object tracking (MMOT) is an emerging field that combines data from various modalities, \eg vision (RGB), depth, thermal infrared, event, language and audio, to estimate the state of an arbitrary object in a video sequence. It…
RGBT tracking has been widely used in various fields such as robotics, surveillance processing, and autonomous driving. Existing RGBT trackers fully explore the spatial information between the template and the search region and locate the…
A typical pipeline for multi-object tracking (MOT) is to use a detector for object localization, and following re-identification (re-ID) for object association. This pipeline is partially motivated by recent progress in both object…
Multi-Object Tracking (MOT) is one of the most fundamental computer vision tasks that contributes to various video analysis applications. Despite the recent promising progress, current MOT research is still limited to a fixed sampling frame…
Recent works have shown that convolutional networks have substantially improved the performance of multiple object tracking by simultaneously learning detection and appearance features. However, due to the local perception of the…
Visual object tracking, which is primarily based on visible light image sequences, encounters numerous challenges in complicated scenarios, such as low light conditions, high dynamic ranges, and background clutter. To address these…