Related papers: Self-Supervised Multi-Object Tracking with Cross-I…

Multi-Object Tracking (MOT) is the task that has a lot of potential for development, and there are still many problems to be solved. In the traditional tracking by detection paradigm, There has been a lot of work on feature based object…

In this paper, we propose a self-supervised RGB-T tracking method. Different from existing deep RGB-T trackers that use a large number of annotated RGB-T image pairs for training, our RGB-T tracker is trained using unlabeled RGB-T video…

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…

Unsupervised learning is a challenging task due to the lack of labels. Multiple Object Tracking (MOT), which inevitably suffers from mutual object interference, occlusion, etc., is even more difficult without label supervision. In this…

Online Multi-Object Tracking (MOT) from videos is a challenging computer vision task which has been extensively studied for decades. Most of the existing MOT algorithms are based on the Tracking-by-Detection (TBD) paradigm combined with…

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)…

Given the difficulty of manually annotating motion in video, the current best motion estimation methods are trained with synthetic data, and therefore struggle somewhat due to a train/test gap. Self-supervised methods hold the promise of…

Multi-object tracking has seen a lot of progress recently, albeit with substantial annotation costs for developing better and larger labeled datasets. In this work, we remove the need for annotated datasets by proposing an unsupervised…

In this work, we study self-supervised multiple object tracking without using any video-level association labels. We propose to cast the problem of multiple object tracking as learning the frame-wise associations between detections in…

In this paper, we propose to learn an Unsupervised Single Object Tracker (USOT) from scratch. We identify that three major challenges, i.e., moving object discovery, rich temporal variation exploitation, and online update, are the central…

Learning robust contextual knowledge from unlabeled videos is essential for advancing self-supervised tracking. However, conventional self-supervised trackers lack effective context modeling, while existing context association methods based…

Multi-object tracking (MOT) is a critical technology in computer vision, designed to detect multiple targets in video sequences and assign each target a unique ID per frame. Existed MOT methods excel at accurately tracking multiple objects…

Physical processes, camera movement, and unpredictable environmental conditions like the presence of dust can induce noise and artifacts in video feeds. We observe that popular unsupervised MOT methods are dependent on noise-free inputs. We…

Multi-Object Tracking (MOT) aims to associate multiple objects across video frames and is a challenging vision task due to inherent complexities in the tracking environment. Most existing approaches train and track within a single domain,…

Occlusion between different objects is a typical challenge in Multi-Object Tracking (MOT), which often leads to inferior tracking results due to the missing detected objects. The common practice in multi-object tracking is re-identifying…

Multi-object tracking under low-light environments is prevalent in real life. Recent years have seen rapid development in the field of multi-object tracking. However, due to the lack of datasets and the high cost of annotations,…

Self-supervised multi-object trackers have tremendous potential as they enable learning from raw domain-specific data. However, their re-identification accuracy still falls short compared to their supervised counterparts. We hypothesize…

Without manually annotated identities, unsupervised multi-object trackers are inferior to learning reliable feature embeddings. It causes the similarity-based inter-frame association stage also be error-prone, where an uncertainty problem…

Multi-sensor perception is crucial to ensure the reliability and accuracy in autonomous driving system, while multi-object tracking (MOT) improves that by tracing sequential movement of dynamic objects. Most current approaches for…