Roboflow
Products
Solutions
Resources
Pricing
Docs
Blog
Toggle theme
Sign In
Playground
Arena
Rankings
Arena Rankings
Vision Evals
Models
Explore
Compare
© 2026 Roboflow
•
Terms
Filter
Playground Demo
By Task
All Models
3D Reconstruction
Captioning
Chart Question Answering
Classification
Depth Estimation
Document Question Answering
Image Embedding
Image Similarity
Image Tagging
Instance Segmentation
Keypoint Detection
Multi-Label Classification
Object Detection
OCR
Open Prompt
Open Vocabulary Object Detection
Phrase Grounding
Pose Estimation
Promptable Concept Segmentation
Promptable Concept Segmentation
Region Proposal
Semantic Segmentation
Video Classification
Video Object Tracking
Vision Language
Visual Question Answering
Zero Shot Segmentation
By Feature
Foundation Vision
LLMs with Vision Capabilities
Multimodal Vision
Real-Time Vision
Zero-shot Detection
By Modality
All
Vision
Multimodal
By Organization
By Access Type
All
Open
Closed
Top Video Object Tracking Models
Models that track objects across frames in video.
Filters
Sort by:
Newest
Meta
SAM 3
Released on November 19th, 2025, Segment Anything 3 (SAM 3) is a zero-shot image segmentation model that “detects, segments, and tracks objects in images and videos based on concept prompts.” This model was developed by Meta as the third model in the Segment Anything series.
Unlike its previous SAM models (Segment Anything and Segment Anything 2), you can provide SAM 3 with the prompt “shipping container” and it will generate precise segmentation masks for all shipping containers in an image. SAM 3 generates segmentation masks that correspond to the location of the objects found with a text prompt.
ByteDance
ByteTrack
ByteTrack is a multi-object tracking algorithm developed by ByteDance, released in October 2021. It addresses a core limitation of earlier tracking methods by associating every detection box — not just high-confidence ones — with tracklets using a two-stage matching process. Low-score detection boxes, which typically correspond to occluded or blurry objects, are retained in a secondary matching step against unmatched tracklets, significantly reducing the number of lost tracks.ByteTrack achieves strong performance on the MOT17 and MOT20 benchmarks at the time of release, operating in real time on standard GPU hardware. It is architecture-agnostic and can be paired with any object detector, making it straightforward to integrate into existing detection pipelines for video analytics, surveillance, and sports tracking applications.