https://github.com/0liliulei/mask-vos
공식 코드Unified Mask Embedding and Correspondence Learning for Self-Supervised Video Segmentation
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.
Unified Mask Embedding and Correspondence Learning for Self-Supervised Video Segmentation
Contrastive Transformation for Self-supervised Correspondence Learning
End-to-End Semi-Supervised Learning for Video Action Detection
Stable Mean Teacher for Semi-supervised Video Action Detection
HODOR: High-level Object Descriptors for Object Re-segmentation in Video Learned from Static Images
TarViS: A Unified Approach for Target-based Video Segmentation
ViTAE: Vision Transformer Advanced by Exploring Intrinsic Inductive Bias
General Object Foundation Model for Images and Videos at Scale
Wandering around: A bioinspired approach to visual attention through object motion sensitivity
Adaptive Temporal Encoding Network for Video Instance-level Human Parsing
Learning Dynamic Network Using a Reuse Gate Function in Semi-supervised Video Object Segmentation
Physarum Powered Differentiable Linear Programming Layers and Applications
Boosting Video Object Segmentation based on Scale Inconsistency
Unsupervised Video Object Segmentation via Prototype Memory Network
Fast and Accurate Online Video Object Segmentation via Tracking Parts
SegFlow: Joint Learning for Video Object Segmentation and Optical Flow
CapsuleVOS: Semi-Supervised Video Object Segmentation Using Capsule Routing
Joint-task Self-supervised Learning for Temporal Correspondence
MixFormer: End-to-End Tracking with Iterative Mixed Attention
Alpha-Refine: Boosting Tracking Performance by Precise Bounding Box Estimation
Universal Instance Perception as Object Discovery and Retrieval
Hierarchical Feature Alignment Network for Unsupervised Video Object Segmentation
Depth-aware Test-Time Training for Zero-shot Video Object Segmentation
SOC: Semantic-Assisted Object Cluster for Referring Video Object Segmentation
MSN: Efficient Online Mask Selection Network for Video Instance Segmentation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.