Research map / Detection and segmentation / Tracking
DOVTrack: Data-Efficient Open-Vocabulary Tracking
Zekun Qian, Ruize Han, Zhixiang Wang, Junhui Hou, Wei Feng
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Trains an open-vocabulary multi-object tracker using only limited, sparsely annotated video data, aiming to make OVMOT data-efficient.
Problem
Open-vocabulary multi-object tracking (OVMOT) must detect and track seen and unseen categories, but large-scale annotated video data for training is lacking.
Approach
Train the open-vocabulary tracker effectively using only the existing limited and sparsely annotated video data rather than requiring new large-scale annotations.
Closest papers by meaning
- VOVTrack: Exploring the Potentiality in Raw Videos for Open-Vocabulary Multi-Object Tracking (ICCV 2025 · similarity 0.94)
- OVT-B: A New Large-Scale Benchmark for Open-Vocabulary Multi-Object Tracking (NeurIPS 2024 · similarity 0.92)
- OVTR: End-to-End Open-Vocabulary Multiple Object Tracking with Transformer (ICLR 2025 · similarity 0.92)
- VastTrack: Vast Category Visual Object Tracking (NeurIPS 2024 · similarity 0.88)
- Multiple Object Tracking as ID Prediction (CVPR 2025 · similarity 0.87)
- OpenVIS: Open-vocabulary Video Instance Segmentation (AAAI 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
