Related papers: Benchmarking EfficientTAM on FMO datasets
Multi-object tracking (MOT) has profound applications in a variety of fields, including surveillance, sports analytics, self-driving, and cooperative robotics. Despite considerable advancements, existing MOT methodologies tend to falter…
Current prevailing Video Object Segmentation methods follow the pipeline of extraction-then-matching, which first extracts features on current and reference frames independently, and then performs dense matching between them. This decoupled…
Homogenization is a fundamental technique for estimating the macroscopic properties of materials with microscale heterogeneity. Among Homogenization methods, the FFT-based Homogenization algorithm has become widely used due to its…
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…
Maintaining the identity of multiple objects in real-time video is a challenging task, as it is not always feasible to run a detector on every frame. Thus, motion estimation systems are often employed, which either do not scale well with…
Modern multiple object tracking (MOT) systems usually follow the \emph{tracking-by-detection} paradigm. It has 1) a detection model for target localization and 2) an appearance embedding model for data association. Having the two models…
Existing event stream based trackers undergo evaluation on short-term tracking datasets, however, the tracking of real-world scenarios involves long-term tracking, and the performance of existing tracking algorithms in these scenarios…
Multi-object tracking (MOT) is one of the most important problems in computer vision and a key component of any vision-based perception system used in advanced autonomous mobile robotics. Therefore, its implementation on low-power and…
Accurate moving object segmentation is an essential task for autonomous driving. It can provide effective information for many downstream tasks, such as collision avoidance, path planning, and static map construction. How to effectively…
Recently, action recognition has been dominated by transformer-based methods, thanks to their spatiotemporal contextual aggregation capacities. However, despite the significant progress achieved on scene-related datasets, they do not…
Few-shot object detection~(FSOD), which aims to detect novel objects with limited annotated instances, has made significant progress in recent years. However, existing methods still suffer from biased representations, especially for novel…
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…
Few-Shot Object Detection (FSOD) methods are mainly designed and evaluated on natural image datasets such as Pascal VOC and MS COCO. However, it is not clear whether the best methods for natural images are also the best for aerial images.…
Compute and memory demands of state-of-the-art deep learning methods are still a shortcoming that must be addressed to make them useful at IoT end-nodes. In particular, recent results depict a hopeful prospect for image processing using…
The recent advancements in transformer-based visual trackers have led to significant progress, attributed to their strong modeling capabilities. However, as performance improves, running latency correspondingly increases, presenting a…
Current multi-modal image fusion methods typically rely on task-specific models, leading to high training costs and limited scalability. While generative methods provide a unified modeling perspective, they often suffer from slow inference…
Benchmarking multi-object tracking and object detection model performance is an essential step in machine learning model development, as it allows researchers to evaluate model detection and tracker performance on human-generated 'test'…
Analysis of state-of-the-art VO/VSLAM system exposes a gap in balancing performance (accuracy & robustness) and efficiency (latency). Feature-based systems exhibit good performance, yet have higher latency due to explicit data association;…
Constantly locating moving objects, i.e., geospatial tracking, is essential for autonomous building infrastructure. Accurate and robust geospatial tracking often leverages multimodal sensor fusion algorithms, which require large datasets…
Object detectors used in autonomous vehicles can have high memory and computational overheads. In this paper, we introduce a novel semi-structured pruning framework called R-TOSS that overcomes the shortcomings of state-of-the-art model…