[CVPR2024 Highlight]GLEE: General Object Foundation Model for Images and Videos at Scale
-
Updated
Jul 26, 2024 - Python
[CVPR2024 Highlight]GLEE: General Object Foundation Model for Images and Videos at Scale
Code release for "UniVS: Unified and Universal Video Segmentation with Prompts as Queries" (CVPR2024)
Mask-Free Video Instance Segmentation [CVPR 2023]
Learning Better Video Query with SAM for Video Instance Segmentation (TCSVT 2024)
DVIS: Decoupled Video Instance Segmentation Framework
Open-vocabulary Video Instance Segmentation Codebase built upon Detectron2, which is really easy to use.
Next-generation Video instance recognition framework on top of Detectron2 which supports InstMove (CVPR 2023), SeqFormer(ECCV Oral), and IDOL(ECCV Oral))
SAM-PT: Extending SAM to zero-shot video segmentation with point-based tracking.
Code release for "BoxVIS: Video Instance Segmentation with Box Annotation"
Code release for "MDQE: Mining Discriminative Query Embeddings to Segment Occluded Instances on Challenging Videos"(CVPR2023)
[ICCV 2021] Instances as Queries
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.
The repository for TLTM: Two-Level Temporal Relation Model for Online Video Instance Segmentation.
Dynamic MNIST digit sequences for video instance segmentation with optical flow data.
This repo contains fixes for MaskTrackRCNN paper to make it compatible on PyTorch 1.6+.
[CVPR'23] Universal Instance Perception as Object Discovery and Retrieval
Learning Monocular Depth in Dynamic Scenes via Instance-Aware Projection Consistency (AAAI 2021)
DeVIS: Making Deformable Transformers Work for Video Instance Segmentation
Add a description, image, and links to the video-instance-segmentation topic page so that developers can more easily learn about it.
To associate your repository with the video-instance-segmentation topic, visit your repo's landing page and select "manage topics."