awesome-referring-image-segmentation

Learning From Box Annotations for Referring Image Segmentation

Adaptive Selection based Referring Image Segmentation

Bilateral Knowledge Interaction Network for Referring Image Segmentation

Bi-directional Relationship Inferring Network for Referring Image Segmentation

Bottom-Up Shift and Reasoning for Referring Image Segmentation

CARIS: Context-Aware Referring Image Segmentation

CVPR 2024 Workshop: Pixel-level Video Understanding in the Wild

3D-GRES: Generalized 3D Referring Expression Segmentation

3D-STMN: Dependency-Driven Superpoint-Text Matching Network for End-to-End 3D Referring Expression Segmentation

InstanceRefer: Cooperative Holistic Understanding for Visual Grounding on Point Clouds through Instance Multi-level Contextual Referring

RefMask3D: Language-Guided Transformer for 3D Referring Segmentation

SegPoint: Segment Any Point Cloud via Large Language Model

X-RefSeg3D: Enhancing Referring 3D Instance Segmentation via Structured Cross-Modal Graph Neural Networks

CLEVR-Ref+: Diagnosing Visual Reasoning with Referring Expressions

ClevrTex: A Texture-Rich Benchmark for Unsupervised Multi-Object Segmentation

Generation and comprehension of unambiguous object descriptions

Referit game: Referring to objects in photographs of natural scenes

ScanRefer: 3D Object Localization in RGB-D Scans using Natural Language

Modeling context in referring expressions

Decoupling Static and Hierarchical Motion Perception for Referring Video Segmentation

HTML: Hybrid Temporal-scale Multimodal Learning Framework for Referring Video Object Segmentation

Language-Bridged Spatial-Temporal Interaction for Referring Video Object Segmentation

MeViS: A Large-scale Benchmark for Video Segmentation with Motion Expressions

Local-Global Context Aware Transformer for Language-Guided Video Segmentation

LoSh: Long-Short Text Joint Prediction Network for Referring Video Object Segmentation

RIS-LAD: A Benchmark and Model for Referring Low-Altitude Drone Image Segmentation

RS2-SAM2: Customized SAM2 for Referring Remote Sensing Image Segmentation

Where It Moves, It Matters: Referring Surgical Instrument Segmentation via Motion