Related papers: Eliminating Exposure Bias and Loss-Evaluation Mism…
Recent Multiple Object Tracking (MOT) methods have gradually attempted to integrate object detection and instance re-identification (Re-ID) into a united network to form a one-stage solution. Typically, these methods use two separated…
Multiple object tracking (MOT) is a crucial task in computer vision society. However, most tracking-by-detection MOT methods, with available detected bounding boxes, cannot effectively handle static, slow-moving and fast-moving camera…
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…
Recent progresses in model-free single object tracking (SOT) algorithms have largely inspired applying SOT to \emph{multi-object tracking} (MOT) to improve the robustness as well as relieving dependency on external detector. However, SOT…
The recent trend in 2D multiple object tracking (MOT) is jointly solving detection and tracking, where object detection and appearance feature (or motion) are learned simultaneously. Despite competitive performance, in crowded scenes, joint…
Multi-Object Tracking (MOT) has been notoriously difficult to evaluate. Previous metrics overemphasize the importance of either detection or association. To address this, we present a novel MOT evaluation metric, HOTA (Higher Order Tracking…
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…
Multi-object tracking (MOT) aims at estimating bounding boxes and identities of objects in videos. Most methods obtain identities by associating detection boxes whose scores are higher than a threshold. The objects with low detection…
In this paper, we propose the methods to handle temporal errors during multi-object tracking. Temporal error occurs when objects are occluded or noisy detections appear near the object. In those situations, tracking may fail and various…
Standardized benchmarks are crucial for the majority of computer vision applications. Although leaderboards and ranking tables should not be over-claimed, benchmarks often provide the most objective measure of performance and are therefore…
Tracking by detection paradigm is one of the most popular object tracking methods. However, it is very dependent on the performance of the detector. When the detector has a behavior of missing detection, the tracking result will be directly…
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…
Online multi-object tracking (MOT) is extremely important for high-level spatial reasoning and path planning for autonomous and highly-automated vehicles. In this paper, we present a modular framework for tracking multiple objects…
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…
Multi-object tracking (MOT) is an important and practical task related to both surveillance systems and moving camera applications, such as autonomous driving and robotic vision. However, due to unreliable detection, occlusion and fast…
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…
Effective tracking of surrounding traffic participants allows for an accurate state estimation as a necessary ingredient for prediction of future behavior and therefore adequate planning of the ego vehicle trajectory. One approach for…
We propose a novel meta-learning framework for real-time object tracking with efficient model adaptation and channel pruning. Given an object tracker, our framework learns to fine-tune its model parameters in only a few iterations of…
Multiple object tracking (MOT) is a fundamental component of perception systems for autonomous driving, and its robustness to unseen conditions is a requirement to avoid life-critical failures. Despite the urge of safety in driving systems,…
Automatically detecting, labeling, and tracking objects in videos depends first and foremost on accurate category-level object detectors. These might, however, not always be available in practice, as acquiring high-quality large scale…