Related papers: TF-SASM: Training-free Spatial-aware Sparse Memory…
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…
Most existing Multi-Object Tracking (MOT) approaches follow the Tracking-by-Detection paradigm and the data association framework where objects are firstly detected and then associated. Although deep-learning based method can noticeably…
Matching-based networks have achieved state-of-the-art performance for video object segmentation (VOS) tasks by storing every-k frames in an external memory bank for future inference. Storing the intermediate frames' predictions provides…
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…
Multi-object tracking (MOT) is the task of estimating the state trajectories of an unknown and time-varying number of objects over a certain time window. Several algorithms have been proposed to tackle the multi-object smoothing task, where…
In this paper, we propose a novel concept of path consistency to learn robust object matching without using manual object identity supervision. Our key idea is that, to track a object through frames, we can obtain multiple different…
Multiple Object Tracking (MOT) aims to find bounding boxes and identities of targeted objects in consecutive video frames. While fully-supervised MOT methods have achieved high accuracy on existing datasets, they cannot generalize well on a…
The Segment Anything Model 2 (SAM 2) has demonstrated strong performance in object segmentation tasks but faces challenges in visual object tracking, particularly when managing crowded scenes with fast-moving or self-occluding objects.…
In this paper we present a robust tracker to solve the multiple object tracking (MOT) problem, under the framework of tracking-by-detection. As the first contribution, we innovatively combine single object tracking (SOT) algorithms with…
Recently, template-based trackers have become the leading tracking algorithms with promising performance in terms of efficiency and accuracy. However, the correlation operation between query feature and the given template only exploits…
The task of 3D single object tracking (SOT) with LiDAR point clouds is crucial for various applications, such as autonomous driving and robotics. However, existing approaches have primarily relied on appearance matching or motion modeling…
Deep learning models have enjoyed great success for image related computer vision tasks like image classification and object detection. For video related tasks like human action recognition, however, the advancements are not as significant…
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…
Recently, several studies have shown that utilizing contextual information to perceive target states is crucial for object tracking. They typically capture context by incorporating multiple video frames. However, these naive frame-context…
Multi-object tracking (MOT) is a fundamental problem in computer vision with numerous applications, such as intelligent surveillance and automated driving. Despite the significant progress made in MOT, pedestrian attributes, such as gender,…
The research on multi-object tracking (MOT) is essentially to solve for the data association assignment, the core of which is to design the association cost as discriminative as possible. Generally speaking, the match ambiguities caused by…
Recent works have shown that combining object detection and tracking tasks, in the case of video data, results in higher performance for both tasks, but they require a high frame-rate as a strict requirement for performance. This is…
This paper proposes an online visual multi-object tracking (MOT) algorithm that resolves object appearance-reappearance and occlusion. Our solution is based on the labeled random finite set (LRFS) filtering approach, which in principle,…
We propose a novel memory-based tracker via part-level dense memory and voting-based retrieval, called DMV. Since deep learning techniques have been introduced to the tracking field, Siamese trackers have attracted many researchers due to…
We propose a method for multi-object tracking and segmentation (MOTS) that does not require fine-tuning or per benchmark hyperparameter selection. The proposed method addresses particularly the data association problem. Indeed, the recently…