Lune

CVPR Findings2026

GOVTrack: Towards Generative Open-Vocabulary Multi-Object Tracking

Zekun Qian, Ruize Han, Zhixiang Wang, Liang Wan, Wei Feng

Abstract

We study a novel yet practical problem of generative openvocabulary multi-object tracking (GOVMOT), which extends the MOT to localize, associate, and recognize genericcategory objects from both seen (base) and unseen (novel) classes as a generative problem. This overcomes the limitations of previous open-set MOT problems, which either fail to classify novel classes or require a predefined list of category texts as prompts. To study this problem, the top priority is to build a benchmark. In this work, we build GOVTrackB, a large-scale and comprehensive benchmark, to provide a standard evaluation platform for the GOVMOT problem. Compared to previous datasets, GOVTrackB has more abundant and balanced base/novel classes, along with corresponding samples for evaluation with less bias. We also propose a new multi-granularity recognition metric to better evaluate the generative object recognition in GOVMOT. We further develop GOVTracker as a baseline method, featuring a consistency-aware focal loss that enhances object association by jointly modeling appearance and semantic consistency. Through extensive benchmark evaluations, we report and analyze the results of various state-of-the-art methods, which demonstrate the rationale of GOVMOT, as well as the usefulness and advantages of GOVTrackB.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • TrackFormer: Multi-Object Tracking with Transformers cites Tracking Without Bells and Whistles
  • TrackFormer: Multi-Object Tracking with Transformers cites Deformable DETR: Deformable Transformers for End-to-End Object Detection
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on29

  1. Learning Transferable Visual Models From Natural Language SupervisionAlec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh et al.ICML 2021 · 47,906 citations
  2. Deformable DETR: Deformable Transformers for End-to-End Object DetectionXizhou Zhu, Weijie Su, Lewei Lu, Bin Li et al.ICLR 2021 · 7,353 citations
  3. Grounding Multimodal Large Language Models to the WorldZhiliang Peng, Wenhui Wang, Li Dong, Yaru Hao et al.ICLR 2024 · 1,170 citations
  4. Tracking Without Bells and WhistlesPhilipp Bergmann, Tim Meinhardt, Laura Leal-TaixéICCV 2019 · 1,030 citations
  5. TrackFormer: Multi-Object Tracking with TransformersTim Meinhardt, Alexander Kirillov, Laura Leal-Taixé, Christoph FeichtenhoferCVPR 2022 · 927 citations

Related papers

  1. VOVTrack: Exploring the Potentiality in Raw Videos for Open-Vocabulary Multi-Object TrackingZekun Qian, Ruize Han, Junhui Hou, Linqi Song et al.ICCV 2025 · 3 citations
  2. COVTrack: Continuous Open-Vocabulary Tracking via Adaptive Multi-Cue FusionZekun Qian, Ruize Han, Zhixiang Wang, Junhui Hou et al.ICCV 2025 · 1 citation
  3. OVTrack: Open-Vocabulary Multiple Object TrackingSiyuan Li, Tobias Fischer, Lei Ke, Henghui Ding et al.CVPR 2023
  4. DOVTrack: Data-Efficient Open-Vocabulary TrackingZekun Qian, Ruize Han, Zhixiang Wang, Junhui Hou et al.NeurIPS 2025 · 1 citation
  5. GLATrack: Global and Local Awareness for Open-Vocabulary Multiple Object TrackingGuangyao Li, Yajun Jian, Yan Yan, Hanzi WangACM MM 2024 · 3 citations
Dusk over the sea between two cliffs drawn in fine vertical lines