Track-Anything is a flexible and interactive tool for video object tracking and segmentation, based on Segment Anything, XMem, and E2FGVI.

A curated list of awesome video object segmentation works since 2022.

[CVPR 2021] Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion. Semi-supervised VOS as well!

[ECCV 2022] XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model

An open-source project dedicated to tracking and segmenting any objects in videos, either automatically or interactively. The primary algorithms utilized include the Segment Anything Model (SAM) for key-frame segmentation and Associating Objects with Transformers (AOT) for efficient tracking and propagation purposes.

Self-supervised learning of Video Object Segmentation using DINOSAUR and SAVi

Characterize Anything: A Wondrous Chemical Reaction between vision models and AI Characters

[AAAI22 Oral] Reliable Propagation-Correction Modulation for Video Object Segmentation

Conversion of MOVi tfrecord datasets to PyTorch-friendly format, and FG-ARI & mIoU evaluation code.

Tracking through Containers and Occluders in the Wild (CVPR 2023) - Official Implementation

Associating Objects with Transformers for Video Object Segmentation

Official website for "Video Polyp Segmentation: A Deep Learning Perspective (MIR 2022)"

Datasets and Papers (with codes) discussed in "Deep Learning for Video Object Segmentation: A Review", Artificial Intelligence Review, 2023.

[ACM MM22] Towards Robust Video Object Segmentation with Adaptive Object Calibration, ACM Multimedia 2022

[CVPR'23] Universal Instance Perception as Object Discovery and Retrieval

Implementation of "Efficient Regional Memory Network for Video Object Segmentation". (Xie et al., CVPR 2021)

The official repo for [AAAI'23] "Learning to Learn Better for Video Object Segmentation"

The official implementation of CFBI(+): Collaborative Video Object Segmentation by (Multi-scale) Foreground-Background Integration.

2021-MICCAI-Progressively Normalized Self-Attention Network for Video Polyp Segmentation

Full-Duplex Strategy for Video Object Segmentation, ICCV, 2021.

Video Object Segmentation requiring only a bounding box

[WACV 2023] A Simple and Powerful Global Optimization for Unsupervised Video Object Segmentation

Learning Unsupervised Video Object Segmentation through Visual Attention (CVPR19, PAMI20)

Implementation of our paper entitiled FAMINet: Learning Real-time Semi-supervised Video Object Segmentation with Steepest Optimized Optical Flow published in TIM.

Fast Video Object Segmentation by Pixel-Wise Feature Comparison (PiWiVOS), presented as my final degree thesis, is a proposal to solve Video Object Segmentation both accurately and fast.

Motion-Attentive Transition for Zero-Shot Video Object Segmentation (AAAI2020&TIP2021)

[ECCV'22 Oral] Towards Grand Unification of Object Tracking

[CVPR'21] Learning to Recommend Frame for Interactive Video Object Segmentation in the Wild

Zero-shot Video Object Segmentation via Attentive Graph Neural Networks (ICCV2019 Oral)