Papers with Code 아카이브
Video Instance Segmentation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 8
- 보존된 평가 기록
- 132
The goal of video instance segmentation is simultaneous detection, segmentation and tracking of instances in videos. In words, it is the first time that the image instance segmentation problem is extended to the video domain.
To facilitate research on this new task, a large-scale benchmark called YouTube-VIS, which consists of 2,883 high-resolution YouTube videos, a 40-category label set and 131k high-quality instance masks is built.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
DVIS++: Improved Decoupled Framework for Universal Video Segmentation
General Object Foundation Model for Images and Videos at Scale
TMT-VIS: Taxonomy-aware Multi-dataset Joint Training for Video Instance Segmentation
VISAGE: Video Instance Segmentation with Appearance-Guided Enhancement
Video Instance Matting
CML-MOTS: Collaborative Multi-task Learning for Multi-Object Tracking and Segmentation
Deep Learning Techniques for Video Instance Segmentation: A Survey
TCOVIS: Temporally Consistent Online Video Instance Segmentation
NOVIS: A Case for End-to-End Near-Online Video Instance Segmentation
1st Place Solution for the 5th LSVOS Challenge: Video Instance Segmentation
VideoCutLER: Surprisingly Simple Unsupervised Video Instance Segmentation
1st Place Solution for CVPR2023 BURST Long Tail and Open World Challenges
CTVIS: Consistent Training for Online Video Instance Segmentation
Learning Dynamic Query Combinations for Transformer-based Object Detection and Segmentation
Segment Anything Meets Point Tracking
3rd Place Solution for PVUW Challenge 2023: Video Panoptic Segmentation
RefineVIS: Video Instance Segmentation with Temporal Attention Refinement
DVIS: Decoupled Video Instance Segmentation Framework
OpenVIS: Open-vocabulary Video Instance Segmentation
GRAtt-VIS: Gated Residual Attention for Auto Rectifying Video Instance Segmentation
Towards Open-Vocabulary Video Instance Segmentation
Video Instance Segmentation in an Open-World
MobileInst: Video Instance Segmentation on the Mobile
Mask-Free Video Instance Segmentation
BoxVIS: Video Instance Segmentation with Box Annotations
MDQE: Mining Discriminative Query Embeddings to Segment Occluded Instances on Challenging Videos
Tube-Link: A Flexible Cross Tube Framework for Universal Video Segmentation
Universal Instance Perception as Object Discovery and Retrieval
Offline-to-Online Knowledge Distillation for Video Instance Segmentation
Maximal Cliques on Multi-Frame Proposal Graph for Unsupervised Video Object Segmentation
Towards Robust Video Instance Segmentation with Temporal-Aware Transformer
TarViS: A Unified Approach for Target-based Video Segmentation
InsPro: Propagating Instance Query and Proposal for Online Video Instance Segmentation
Object Segmentation with Audio Context
The Runner-up Solution for YouTube-VIS Long Video Challenge 2022
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.