From ViT Features to Training-free Video Object Segmentation via Streaming-data Mixture Models

Roy Uziel, Or Dinari, O. Freifeld
2/12/2026

No official code found. Best implementation: BGU-CS-VIL/Training-Free-VOS (15 stars, GPL-2.0, last commit 2024-01-16).

DOISemantic Scholar

Code Implementations(1)

BGU-CS-VIL/Training-Free-VOSCommunity59%
GPL-2.0

"From ViT Features to Training-free Video Object Segmentation via Streaming-data Mixture Models" [Uziel, Dinari, and Freifeld, NeurIPS 2023]

150PythonOct 24, 20232 years agoGPL-2.0

Similar Papers

Open-Set Domain Adaptation via Joint Error Based Multi-class Positive and Unlabeled Learning

65% match2026

Clustered Federated Learning via Gradient-based Partitioning

65% match1 repo152026

Interpretable Sparse System Identification: Beyond Recent Deep Learning Techniques on Time-Series Prediction

64% match2026

PoseIRM: Enhance 3D Human Pose Estimation on Unseen Camera Settings via Invariant Risk Minimization

64% match1 repo32026

Privacy-Preserving Embedding via Look-up Table Evaluation with Fully Homomorphic Encryption

64% match2026

Protein-Ligand Interaction Prior for Binding-aware 3D Molecule Diffusion Models

64% match1 repo612026

Cite this paper

@article{uziel2026from,
  title  = {From ViT Features to Training-free Video Object Segmentation via Streaming-data Mixture Models},
  author = {Roy Uziel and Or Dinari and O. Freifeld},
  year   = {2026},
  doi    = {10.52202/075280-0485},
  url    = {https://doi.org/10.52202/075280-0485},
  journal = {NEURIPS 2023 2023}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/3d08901b872a6b741bca281baa9a4ce3529e7bda.svg)](https://codeofpaper.com/paper/3d08901b872a6b741bca281baa9a4ce3529e7bda)

Discussion