Related papers: MOTRv3: Release-Fetch Supervision for End-to-End M…

In the recent past, the computer vision community has developed centralized benchmarks for the performance evaluation of a variety of tasks, including generic object and pedestrian detection, 3D reconstruction, optical flow, single-object…

Unsupervised object-centric learning methods allow the partitioning of scenes into entities without additional localization information and are excellent candidates for reducing the annotation burden of multiple-object tracking (MOT)…

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,…

Standardized benchmarks have been crucial in pushing the performance of computer vision algorithms, especially since the advent of deep learning. Although leaderboards should not be over-claimed, they often provide the most objective…

Tracking a time-varying indefinite number of objects in a video sequence over time remains a challenge despite recent advances in the field. Most existing approaches are not able to properly handle multi-object tracking challenges such as…

Multi-object Tracking (MOT) generally can be split into two sub-tasks, i.e., detection and association. Many previous methods follow the tracking by detection paradigm, which first obtain detections at each frame and then associate them…

We consider the challenging problem of tracking multiple objects using a distributed network of sensors. In the practical setting of nodes with limited field of views (FoVs), computing power and communication resources, we develop a novel…

Multi-object tracking (MOT) is a challenging vision task that aims to detect individual objects within a single frame and associate them across multiple frames. Recent MOT approaches can be categorized into two-stage tracking-by-detection…

Traditional multiple object tracking methods divide the task into two parts: affinity learning and data association. The separation of the task requires to define a hand-crafted training goal in affinity learning stage and a hand-crafted…

Many real-world applications adopt multi-label data streams as the need for algorithms to deal with rapidly changing data increases. Changes in data distribution, also known as concept drift, cause the existing classification models to…

The tracking-by-detection paradigm is the mainstream in multi-object tracking, associating tracks to the predictions of an object detector. Although exhibiting uncertainty through a confidence score, these predictions do not capture the…

Tracking specific targets, such as pedestrians and vehicles, has been the focus of recent vision-based multitarget tracking studies. However, in some real-world scenarios, unseen categories often challenge existing methods due to…

This paper introduces a novel multi-object tracking (MOT) method, dubbed GenTrack, whose main contributions include: a hybrid tracking approach employing both stochastic and deterministic manners to robustly handle unknown and time-varying…

Multi-object tracking (MOT) aims at estimating bounding boxes and identities of objects across video frames. Detection boxes serve as the basis of both 2D and 3D MOT. The inevitable changing of detection scores leads to object missing after…

Supervised 3D Object Detection models have been displaying increasingly better performance in single-domain cases where the training data comes from the same environment and sensor as the testing data. However, in real-world scenarios data…

Classifiers deployed in the real world operate in a dynamic environment, where the data distribution can change over time. These changes, referred to as concept drift, can cause the predictive performance of the classifier to drop over…

Multi-camera tracking plays a pivotal role in various real-world applications. While end-to-end methods have gained significant interest in single-camera tracking, multi-camera tracking remains predominantly reliant on heuristic techniques.…

Data association across frames is at the core of Multiple Object Tracking (MOT) task. This problem is usually solved by a traditional graph-based optimization or directly learned via deep learning. Despite their popularity, we find some…

Multi-label text classification (MLTC) aims to assign multiple labels to each sample in the dataset. The labels usually have internal correlations. However, traditional methods tend to ignore the correlations between labels. In order to…

In the existing literature, most 3D multi-object tracking algorithms based on the tracking-by-detection framework employed deterministic tracks and detections for similarity calculation in the data association stage. Namely, the inherent…