Alternatives and similar repositories for AutoTrackAnything:

Users that are interested in AutoTrackAnything are comparing it to the libraries listed below

• TripleJoy / SAM2MOT
  ☆74Updated 3 weeks ago
• zhang-tao-whu / DVIS_Plus
  ☆117Updated 10 months ago
• jinyanglii / OVTR
  🏄 [ICLR 2025] OVTR: End-to-End Open-Vocabulary Multiple Object Tracking with Transformer
  ☆55Updated last month
• VlSomers / keypoint_promptable_reidentification
  [ECCV24] Keypoint Promptable Re-Identification: SOTA ReID method robust to occlusions and multi-person ambiguity
  ☆126Updated 3 months ago
• George-Zhuang / NetTrack
  Official code for NetTrack [CVPR 2024]
  ☆91Updated last year
• zhang-tao-whu / DVIS
  DVIS: Decoupled Video Instance Segmentation Framework
  ☆146Updated last year
• MCG-NJU / MixSort
  [ICCV2023] MixSort: The Customized Tracker in SportsMOT
  ☆80Updated last year
• Curt-Park / yolo-world-with-efficientvit-sam
  YOLO-World + EfficientViT SAM
  ☆97Updated last year
• XuM007 / MITracker
  Official Code for "MITracker: Multi-View Integration for Visual Object Tracking"
  ☆63Updated last month
• SysCV / ovtrack
  OVTrack: Open-Vocabulary Multiple Object Tracking [CVPR 2023]
  ☆102Updated 6 months ago
• jovanavidenovic / DAM4SAM
  [CVPR 2025] "A Distractor-Aware Memory for Visual Object Tracking with SAM2"
  ☆281Updated 3 weeks ago
• sjc042 / gta-link
  ☆66Updated last month
• xushilin1 / RMP-SAM
  [ICLR 2025 oral] RMP-SAM: Towards Real-Time Multi-Purpose Segment Anything
  ☆243Updated 3 weeks ago
• chengche6230 / ReST
  [ICCV 2023] ReST: A Reconfigurable Spatial-Temporal Graph Model for Multi-Camera Multi-Object Tracking
  ☆152Updated last year
• Seung-Hun-Lee / CAVIS
  CAVIS: Context-Aware Video Instance Segmentation
  ☆86Updated 3 weeks ago
• BingfengYan / VISAM
  Combining "segment-anything" with MOT, it create the era of "MOTS"
  ☆154Updated last year
• WesleyHsieh0806 / TAO-Amodal
  Official Code for Tracking Any Object Amodally
  ☆117Updated 9 months ago
• autodistill / autodistill-grounded-sam-2
  Use Segment Anything 2, grounded with Florence-2, to auto-label data for use in training vision models.
  ☆121Updated 9 months ago
• hustvl / SparseTrack
  Official PyTorch implementation of SparseTrack
  ☆148Updated 2 months ago
• autodistill / autodistill-dinov2
  DINOv2 module for use with Autodistill.
  ☆13Updated last year
• SysCV / tet
  Implementation of Tracking Every Thing in the Wild, ECCV 2022
  ☆94Updated 6 months ago
• MCG-NJU / MeMOTR
  [ICCV 2023] MeMOTR: Long-Term Memory-Augmented Transformer for Multi-Object Tracking
  ☆184Updated 11 months ago
• patrick-tssn / Streaming-Grounded-SAM-2
  Grounded Tracking for Streaming Videos
  ☆101Updated 6 months ago
• qinzheng2000 / GeneralTrack
  ☆24Updated last year
• MCG-NJU / MOTIP
  [CVPR 2025] Multiple Object Tracking as ID Prediction
  ☆208Updated 2 weeks ago
• Ali2500 / BURST-benchmark
  ☆78Updated last year
• amazon-science / tracking-dataset
  ☆58Updated last year
• BingfengYan / CO-MOT
  CO-MOT: Bridging the Gap Between End-to-end and Non-End-to-end Multi-Object Tracking
  ☆79Updated 3 weeks ago
• dvl-tum / SUSHI
  [CVPR 2023] Unifying Short and Long-Term Tracking with Graph Hierarchies
  ☆125Updated 4 months ago
• Aimol-l / SAM2Export
  try to export sam2 to onnx.
  ☆49Updated this week