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.
☆66Updated 5 months ago
Related projects: ⓘ
- An official implementation of "Hulk: A Universal Knowledge Translator for Human-Centric Tasks"☆83Updated 3 months ago
- ☆87Updated 2 months ago
- DVIS: Decoupled Video Instance Segmentation Framework☆124Updated 5 months ago
- Combining "segment-anything" with MOT, it create the era of "MOTS"☆144Updated last year
- [ECCV24] Keypoint Promptable Re-Identification: SOTA ReID method robust to occlusions and multi-person ambiguity☆53Updated last week
- Official Code for Tracking Any Object Amodally☆112Updated 2 months ago
- ☆207Updated 2 months ago
- A Graph-Based Approach for Category-Agnostic Pose Estimation [ECCV 2024]☆302Updated 2 months ago
- ☆143Updated this week
- Multiple Object Tracking as ID Prediction☆84Updated last month
- [ICCV2023] MixSort: The Customized Tracker in SportsMOT☆69Updated last year
- Grounded-SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and …☆34Updated last year
- Official implementation of OV-DINO: Unified Open-Vocabulary Detection with Language-Aware Selective Fusion☆207Updated last week
- Implementation of Tracking Every Thing in the Wild, ECCV 2022☆93Updated 3 months ago
- [NeurIPS 2022 Spotlight] VideoMAE for Action Detection☆48Updated last year
- [ICCV 2023] ReST: A Reconfigurable Spatial-Temporal Graph Model for Multi-Camera Multi-Object Tracking☆135Updated 5 months ago
- Includes the code for training and testing the CountGD model from the paper CountGD: Multi-Modal Open-World Counting.☆52Updated 2 months ago
- Official Implementation of our WACV2023 paper: “Holistic Interaction Transformer Network for Action Detection”☆54Updated 7 months ago
- CAVIS: Context-Aware Video Instance Segmentation☆53Updated 2 months ago
- OVTrack: Open-Vocabulary Multiple Object Tracking [CVPR 2023]☆79Updated 7 months ago
- [ICCV2023] Segment Every Reference Object in Spatial and Temporal Spaces☆235Updated 8 months ago
- Use Segment Anything 2, grounded with Florence-2, to auto-label data for use in training vision models.☆80Updated last month
- Official PyTorch implementation of Unifying Short and Long-Term Tracking with Graph Hierarchies (CVPR 2023)☆107Updated last year
- The suite of modeling video with Mamba☆216Updated 4 months ago
- The second generation of YOWO action detector.☆204Updated 4 months ago
- Official PyTorch implementation of UniHCP☆147Updated last year
- The official repo for ECCV'22 paper: Pose for Everything: Towards Category-Agnostic Pose Estimation☆196Updated 3 months ago
- [ECCV 2024] Official implementation of the paper "TAPTR: Tracking Any Point with Transformers as Detection"☆187Updated last month
- Official PyTorch implementation of SparseTrack (the new version of code will come soon)☆133Updated 9 months ago
- Code for "LocLLM: Exploiting Generalizable Human Keypoint Localization via Large Language Model", CVPR 2024 Highlight☆26Updated 3 months ago