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.
[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))
Instances as Queries (ICCV 2021)
Prototypical Cross-Attention Networks for Multiple Object Tracking and Segmentation, NeurIPS 2021 Spotlight
SipMask: Spatial Information Preservation for Fast Image and Video Instance Segmentation (ECCV2020)
SeqFormer: Sequential Transformer for Video Instance Segmentation (ECCV 2022 Oral)
[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).
[CVPR'23] Universal Instance Perception as Object Discovery and Retrieval
Temporally Efficient Vision Transformer for Video Instance Segmentation, CVPR 2022, Oral
Learning Monocular Depth in Dynamic Scenes via Instance-Aware Projection Consistency (AAAI 2021)
DeVIS: Making Deformable Transformers Work for Video Instance Segmentation
[CVPR 2021] Youtube-VIS 2021 3rd place, [CVPR 2020] winner DAVIS 2020. Code for mask selection based methods.
[CVPRW 2021] - Object Propagation via Inter-Frame Attentions for Temporally Stable Video Instance Segmentation
UNOFFICIAL implement of MaskTrackRCNN for video instance segmentation via mmdetection 2.11.0.
A video instance segmentation codebase based on OpenMMLab projects.
This repository captures our work on Video Instance Segmentation, as a part of our CS 534 AI course project, under Prof. Jacob Whitehill. We describe and analyze the experimental trials performed on the baseline ([CVPRW 2021] - Object Propagation via Inter-Frame Attentions for Temporally Stable Video Instance Segmentation).
Implementation of joint construction of Mask/BBox heads in QDTrack-mots for joint training research
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."