paper-with-me

홈 › Papers

OVTrack: Open-Vocabulary Multiple Object Tracking

2023-04-17 · CVPR 2023 1 · Siyuan Li, Tobias Fischer, Lei Ke, Henghui Ding, Martin Danelljan, Fisher Yu

The ability to recognize, localize and track dynamic objects in a scene is fundamental to many real-world applications, such as self-driving and robotic systems. Yet, traditional multiple object tracking (MOT) benchmarks rely only on a few object categories that hardly represent the multitude of possible objects that are encountered in the real world. This leaves contemporary MOT methods limited to a small set of pre-defined object categories. In this paper, we address this limitation by tackling a novel task, open-vocabulary MOT, that aims to evaluate tracking beyond pre-defined training categories. We further develop OVTrack, an open-vocabulary tracker that is capable of tracking arbitrary object classes. Its design is based on two key ingredients: First, leveraging vision-language models for both classification and association via knowledge distillation; second, a data hallucination strategy for robust appearance feature learning from denoising diffusion probabilistic models. The result is an extremely data-efficient open-vocabulary tracker that sets a new state-of-the-art on the large-scale, large-vocabulary TAO benchmark, while being trained solely on static images. Project page: https://www.vis.xyz/pub/ovtrack/

📄 PDF Abstract BibTeX arXiv:2304.08408

Code (1)

syscv/ovtrack jax

Tasks

DenoisingHallucinationKnowledge DistillationMulti-Object TrackingMultiple Object TrackingObjectObject Tracking

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

VOVTrack: Exploring the Potentiality in Videos for Open-Vocabulary Object Tracking

2024-10-11 · Zekun Qian, Ruize Han, Junhui Hou, Linqi Song 외

Open-vocabulary multi-object tracking (OVMOT) represents a critical new challenge involving the detection and tracking of diverse object categories in videos, encompassing both seen categories (base classes) and unseen c…

Multi-Object TrackingObjectobject-detectionObject Detection+4

COVTrack++: Learning Open-Vocabulary Multi-Object Tracking from Continuous Videos via a Synergistic Paradigm

2026-03-25 · Zekun Qian, Wei Feng, Ruize Han, Junhui Hou arxiv

Multi-Object Tracking (MOT) has traditionally focused on a few specific categories, restricting its applicability to real-world scenarios involving diverse objects. Open-Vocabulary Multi-Object Tracking (OVMOT) addresses…

Zero-shot GeneralizationMulti-Object Tracking

Open3DTrack: Towards Open-Vocabulary 3D Multi-Object Tracking

2024-10-02 · Ayesha Ishaq, Mohamed El Amine Boudjoghra, Jean Lahoud, Fahad Shahbaz Khan 외

3D multi-object tracking plays a critical role in autonomous driving by enabling the real-time monitoring and prediction of multiple objects' movements. Traditional 3D tracking systems are typically constrained by predef…

3D Multi-Object TrackingAutonomous DrivingMulti-Object TrackingObject+1

OVTR: End-to-End Open-Vocabulary Multiple Object Tracking with Transformer

2025-03-13 · Jinyang Li, En Yu, Sijia Chen, Wenbing Tao

Open-vocabulary multiple object tracking aims to generalize trackers to unseen categories during training, enabling their application across a variety of real-world scenarios. However, the existing open-vocabulary tracke…

Decodermultimodal interactionMultiple Object TrackingMultiple Object Tracking with Transformer+1

SLAck: Semantic, Location, and Appearance Aware Open-Vocabulary Tracking

2024-09-17 · Siyuan Li, Lei Ke, Yung-Hsu Yang, Luigi Piccinelli 외

Open-vocabulary Multiple Object Tracking (MOT) aims to generalize trackers to novel categories not in the training set. Currently, the best-performing methods are mainly based on pure appearance matching. Due to the comp…

Multiple Object TrackingObject Tracking