licksylick / AutoTrackAnything
AutoTrackAnything is a universal, flexible and interactive tool for insane automatic object tracking over thousands of frames. It is developed upon XMem, Yolov8 and MobileSAM (Segment Anything), can track anything which detect Yolov8.
☆79Updated 11 months ago
Alternatives and similar repositories for AutoTrackAnything:
Users that are interested in AutoTrackAnything are comparing it to the libraries listed below
- YOLO-World + EfficientViT SAM☆92Updated last year
- Official code for NetTrack [CVPR 2024]☆89Updated last year
- [CVPR 2025] "A Distractor-Aware Memory for Visual Object Tracking with SAM2"☆253Updated 2 weeks ago
- 🏄 [ICLR 2025] OVTR: End-to-End Open-Vocabulary Multiple Object Tracking with Transformer☆42Updated last week
- [ECCV24] Keypoint Promptable Re-Identification: SOTA ReID method robust to occlusions and multi-person ambiguity☆116Updated last month
- ☆57Updated 3 months ago
- Official Code for "MITracker: Multi-View Integration for Visual Object Tracking"☆49Updated last week
- [ICCV2023] MixSort: The Customized Tracker in SportsMOT☆78Updated last year
- [CVPR 2025] Multiple Object Tracking as ID Prediction☆169Updated last week
- OVTrack: Open-Vocabulary Multiple Object Tracking [CVPR 2023]☆98Updated 5 months ago
- A Graph-Based Approach for Category-Agnostic Pose Estimation [ECCV 2024]☆354Updated 4 months ago
- ☆115Updated 8 months ago
- DVIS: Decoupled Video Instance Segmentation Framework☆145Updated 11 months ago
- [ICLR 2025 oral] RMP-SAM: Towards Real-Time Multi-Purpose Segment Anything☆236Updated last month
- Combining "segment-anything" with MOT, it create the era of "MOTS"☆153Updated last year
- Official Pytorch Implementation for “DINO-Tracker: Taming DINO for Self-Supervised Point Tracking in a Single Video” (ECCV 2024)☆474Updated 4 months ago
- Use Segment Anything 2, grounded with Florence-2, to auto-label data for use in training vision models.☆116Updated 7 months ago
- try to export sam2 to onnx.☆44Updated 5 months ago
- [ICCV 2023] ReST: A Reconfigurable Spatial-Temporal Graph Model for Multi-Camera Multi-Object Tracking☆149Updated last year
- Implementation of Tracking Every Thing in the Wild, ECCV 2022☆93Updated 5 months ago
- Mamba-YOLO-World: Marrying YOLO-World with Mamba for Open-Vocabulary Detection☆75Updated 2 weeks ago
- [ICCV 2023] MeMOTR: Long-Term Memory-Augmented Transformer for Multi-Object Tracking☆181Updated 10 months ago
- CAVIS: Context-Aware Video Instance Segmentation☆84Updated 3 months ago
- Official PyTorch implementation of SparseTrack☆147Updated 3 weeks ago
- https://arxiv.org/abs/2302.11813☆205Updated last year
- Includes the code for training and testing the CountGD model from the paper CountGD: Multi-Modal Open-World Counting.☆175Updated 2 weeks ago
- Codebase for the Recognize Anything Model (RAM)☆76Updated last year
- [CVPR2023] MOTRv2: Bootstrapping End-to-End Multi-Object Tracking by Pretrained Object Detectors☆403Updated 2 years ago
- Official Code for Tracking Any Object Amodally☆116Updated 8 months ago
- An official implementation of "Hulk: A Universal Knowledge Translator for Human-Centric Tasks"☆122Updated 3 months ago