OpenMMLab Video Perception Toolbox. It supports Video Object Detection (VID), Multiple Object Tracking (MOT), Single Object Tracking (SOT), Video Instance Segmentation (VIS) with a unified framework.

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

[CVPR2024 Highlight]GLEE: General Object Foundation Model for Images and Videos at Scale

SAM-PT: Extending SAM to zero-shot video segmentation with point-based tracking.

[CVPR2021 Oral] End-to-End Video Instance Segmentation with Transformers

Next-generation Video instance recognition framework on top of Detectron2 which supports InstMove (CVPR 2023), SeqFormer(ECCV Oral), and IDOL(ECCV Oral))

[ICCV 2021] Instances as Queries

Mask-Free Video Instance Segmentation [CVPR 2023]

Prototypical Cross-Attention Networks for Multiple Object Tracking and Segmentation, NeurIPS 2021 Spotlight

[NeurIPS'21] Unified tracking framework with a single appearance model. It supports Single Object Tracking (SOT), Video Object Segmentation (VOS), Multi-Object Tracking (MOT), Multi-Object Tracking and Segmentation (MOTS), Pose Tracking, Video Instance Segmentation (VIS), and class-agnostic MOT (e.g. TAO dataset).

SeqFormer: Sequential Transformer for Video Instance Segmentation (ECCV 2022 Oral)

SipMask: Spatial Information Preservation for Fast Image and Video Instance Segmentation (ECCV2020)

Temporally Efficient Vision Transformer for Video Instance Segmentation, CVPR 2022, Oral

Learning Monocular Depth in Dynamic Scenes via Instance-Aware Projection Consistency (AAAI 2021)

Code release for "UniVS: Unified and Universal Video Segmentation with Prompts as Queries" (CVPR2024)

DVIS: Decoupled Video Instance Segmentation Framework

No description provided.

Awesome video instance segmentation papers

DeVIS: Making Deformable Transformers Work for Video Instance Segmentation

Code release for "STMask: Spatial Feature Calibration and Temporal Fusion for Effective One-stage Video Instance Segmentation"(CVPR2021)

[AAAI 2025] Open-vocabulary Video Instance Segmentation Codebase built upon Detectron2, which is really easy to use.

Learning Better Video Query with SAM for Video Instance Segmentation (TCSVT 2024)

Code release for "MDQE: Mining Discriminative Query Embeddings to Segment Occluded Instances on Challenging Videos"(CVPR2023)

Code release for "BoxVIS: Video Instance Segmentation with Box Annotation"

[CVPRW 2021] - Object Propagation via Inter-Frame Attentions for Temporally Stable Video Instance Segmentation

[CVPR 2021] Youtube-VIS 2021 3rd place, [CVPR 2020] winner DAVIS 2020. Code for mask selection based methods.

UNOFFICIAL implement of MaskTrackRCNN for video instance segmentation via mmdetection 2.11.0.

Dynamic MNIST digit sequences for video instance segmentation with optical flow data.

Implementation of joint construction of Mask/BBox heads in QDTrack-mots for joint training research

A video instance segmentation codebase based on OpenMMLab projects.