vision
Track-Anything
Interactive video object tracking and segmentation that combines Segment Anything with a video memory model.
Levelmodel
Classvision
Parametersnot in the notes
Contextnot in the notes
Released24 Apr 2023
Opennessopen source
Runs onmobile or NPU
Statusactive
R&D Topics
Identity
- Developer
- Southern University of Science and Technology
- Family
- not in the notes
- Released
- 24 Apr 2023 sourcesannouncement page
- Weights published
- –
- Record checked
- 12 Oct 2026
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.
Architecture and Size
- Architecture
- dense transformer
- Total parameters
- – sources
- Active parameters
- –
- Checkpoint parameters
- –
- Context length
- not in the notes
- Input
- video
- Output
- labels and boxes
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).
Openness and Access
- Openness
- open source
- Licence
- MIT License sources
- Access routes
- open weights download
Where this comes from
The licence file governs over registry tags and aggregator labels.
Deployment
- Runs on
- mobile or NPU
- Footprint
- Edge or toolkit builds listed in: Qualcomm AI Hub.
- Runtimes
- not in the notes
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.
Indonesia
- Indonesian support
- not stated
- Regional languages
- not in the notes
- Jakarta hosting
- unknown
- Languages
- not in the notes
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.
Benchmark Results
The notes record no benchmark result for this model.
Lineage
The notes record no lineage for this model.
Industry Use Cases
No industry use case links this model.
Links
ModelTrack-AnythingSouthern University of Science and Technology, vision
Track-AnythingSouthern University of Science and Technology, visionR&D TopicsPromptable Segmentation Foundation Models (Segment Anything)Multi-Object Tracking and Re-Identification
Use CasesMedical Image SegmentationHealthcareUse cases of models in the same R&D topic; none is recorded for this model itself.
Who Runs Itnone recordedDeployments of these use cases; none names this model.
R&D topics 2
Multi-Object Tracking and Re-IdentificationFollowing people, vehicles or animals across video frames and cameras and recognising the…produced byPromptable Segmentation Foundation Models (Segment Anything)Models that cut out any object from a point, box or text prompt, trained on very large ma…produced by
Sources
- arxiv.org/abs/2304.11968 https://arxiv.org/abs/2304.11968
- github.com/gaomingqi/Track-Anything https://github.com/gaomingqi/Track-Anything
- aihub.qualcomm.com/models/track_anything https://aihub.qualcomm.com/models/track_anything
- arxiv.org/html/2304.11968 https://arxiv.org/html/2304.11968
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "Track-Anything", https://aurion.semai.id/models/track-anything/, records of October 2026.