Alternatives and similar repositories for AutoTrackAnything

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

• BingfengYan / VISAM
  Combining "segment-anything" with MOT, it create the era of "MOTS"
  ☆156Updated 2 years ago
• jinyanglii / OVTR
  🏄 [ICLR 2025] OVTR: End-to-End Open-Vocabulary Multiple Object Tracking with Transformer
  ☆87Updated 6 months ago
• XuM007 / MITracker
  Official Code for "MITracker: Multi-View Integration for Visual Object Tracking"
  ☆124Updated 7 months ago
• TripleJoy / SAM2MOT
  [AAAI 2026] Code for "SAM2MOT: A Novel Paradigm of Multi-Object Tracking by Segmentation".
  ☆159Updated 2 months ago
• SysCV / ovtrack
  OVTrack: Open-Vocabulary Multiple Object Tracking [CVPR 2023]
  ☆112Updated last year
• George-Zhuang / NetTrack
  Official code for NetTrack [CVPR 2024]
  ☆111Updated last year
• xushilin1 / RMP-SAM
  [ICLR 2025 oral] RMP-SAM: Towards Real-Time Multi-Purpose Segment Anything
  ☆268Updated 9 months ago
• jovanavidenovic / DAM4SAM
  [CVPR 2025] "A Distractor-Aware Memory for Visual Object Tracking with SAM2"
  ☆457Updated 3 months ago
• VlSomers / keypoint_promptable_reidentification
  [ECCV24] Keypoint Promptable Re-Identification: SOTA ReID method robust to occlusions and multi-person ambiguity
  ☆199Updated 7 months ago
• IDEA-Research / RexSeek
  [ICCV2025] Referring any person or objects given a natural language description. Code base for RexSeek and HumanRef Benchmark
  ☆177Updated 3 months ago
• Curt-Park / yolo-world-with-efficientvit-sam
  YOLO-World + EfficientViT SAM
  ☆106Updated last year
• niki-amini-naieni / CountVid
  Includes the VideoCount dataset and CountVid code for the paper Open-World Object Counting in Videos.
  ☆86Updated last month
• WesleyHsieh0806 / TAO-Amodal
  Official Code for Tracking Any Object Amodally
  ☆120Updated last year
• zhang-tao-whu / DVIS
  DVIS: Decoupled Video Instance Segmentation Framework
  ☆158Updated last year
• MCG-NJU / MixSort
  [ICCV2023] MixSort: The Customized Tracker in SportsMOT
  ☆90Updated 2 years ago
• kamkyu94 / TrackTrack
  Focusing on Tracks for Online Multi-Object Tracking
  ☆91Updated 4 months ago
• TrackingLaboratory / CAMELTrack
  Official implementation of 🐫 CAMELTrack: Context-Aware Multi-cue ExpLoitation for Online Multi-Object Tracking 🐫
  ☆112Updated 2 weeks ago
• orhir / PoseAnything
  A Graph-Based Approach for Category-Agnostic Pose Estimation [ECCV 2024]
  ☆384Updated last year
• autodistill / autodistill-grounded-sam-2
  Use Segment Anything 2, grounded with Florence-2, to auto-label data for use in training vision models.
  ☆134Updated last year
• OPPOMKLab / recognize-anything
  Codebase for the Recognize Anything Model (RAM)
  ☆88Updated 2 years ago
• AssafSinger94 / dino-tracker
  Official Pytorch Implementation for “DINO-Tracker: Taming DINO for Self-Supervised Point Tracking in a Single Video” (ECCV 2024)
  ☆549Updated last year
• zhang-tao-whu / DVIS_Plus
  ☆134Updated last year
• chengche6230 / ReST
  [ICCV 2023] ReST: A Reconfigurable Spatial-Temporal Graph Model for Multi-Camera Multi-Object Tracking
  ☆165Updated last year
• IDEA-Research / TAPTR
  [ECCV 2024 & NeurIPS 2024 & ICLR 2026] Official implementation of the paper TAPTR & TAPTRv2 & TAPTRv3
  ☆270Updated last week
• niki-amini-naieni / CountGD
  Includes the code for training and testing the CountGD model from the paper CountGD: Multi-Modal Open-World Counting.
  ☆301Updated 7 months ago
• sjc042 / gta-link
  ☆83Updated last month
• Seung-Hun-Lee / CAVIS
  Official code for CAVIS: Context-Aware Video Instance Segmentation
  ☆95Updated 4 months ago
• akashAD98 / YOLOV8_SAM
  yolov8 model with SAM meta
  ☆143Updated 2 years ago
• SysCV / tet
  Implementation of Tracking Every Thing in the Wild, ECCV 2022
  ☆96Updated last year
• SebastianJanampa / DETRPose
  DETRPose: Real-time end-to-end transformer model for multi-person pose estimation
  ☆68Updated last month