https://github.com/svip-lab/IVOS-W
공식 코드Learning to Recommend Frame for Interactive Video Object Segmentation in the Wild
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
Video object segmentation is a binary labeling problem aiming to separate foreground object(s) from the background region of a video.
For leaderboards please refer to the different subtasks.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Learning to Recommend Frame for Interactive Video Object Segmentation in the Wild
Proposal, Tracking and Segmentation (PTS): A Cascaded Network for Video Object Segmentation
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation
Motion-Attentive Transition for Zero-Shot Video Object Segmentation
LiVOS: Light Video Object Segmentation with Gated Linear Matching
Flexible visual prompts for in-context learning in computer vision
Fast Interactive Video Object Segmentation with Graph Neural Networks
Self-supervised Object Tracking with Cycle-consistent Siamese Networks
Boosting Video Object Segmentation via Space-time Correspondence Learning
Global Spectral Filter Memory Network for Video Object Segmentation
Learning Quality-aware Dynamic Memory for Video Object Segmentation
OnlineRefer: A Simple Online Baseline for Referring Video Object Segmentation
Multi-Source Fusion and Automatic Predictor Selection for Zero-Shot Video Object Segmentation
Online Unsupervised Video Object Segmentation via Contrastive Motion Clustering
Implicit Motion-Compensated Network for Unsupervised Video Object Segmentation
Video Object Segmentation with Adaptive Feature Bank and Uncertain-Region Refinement
Rethinking Self-supervised Correspondence Learning: A Video Frame-level Similarity Perspective
Video Shadow Detection via Spatio-Temporal Interpolation Consistency Training
Scalable Video Object Segmentation with Identification Mechanism
Integrating Boxes and Masks: A Multi-Object Framework for Unified Visual Tracking and Segmentation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.