SOTAVerified

Generalized Referring Expression Segmentation

Generalized Referring Expression Segmentation (GRES), introduced by Liu et al in CVPR 2023, allows expressions indicating any number of target objects. GRES takes an image and a referring expression as input, and requires mask prediction of the target object(s).

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–15 of 15 papers

TitleStatusHype
PSALM: Pixelwise SegmentAtion with Large Multi-Modal ModelCode3
GRES: Generalized Referring Expression SegmentationCode2
DeRIS: Decoupling Perception and Cognition for Enhanced Referring Image Segmentation through Loopback SynergyCode1
LAVT: Language-Aware Vision Transformer for Referring Image SegmentationCode1
GSVA: Generalized Segmentation via Multimodal Large Language ModelsCode1
CoHD: A Counting-Aware Hierarchical Decoding Framework for Generalized Referring Expression SegmentationCode1
Vision-Language Transformer and Query Generation for Referring SegmentationCode1
CRIS: CLIP-Driven Referring Image SegmentationCode1
Bring Adaptive Binding Prototypes to Generalized Referring Expression SegmentationCode0
MAttNet: Modular Attention Network for Referring Expression ComprehensionCode0
Locate then Segment: A Strong Pipeline for Referring Image Segmentation—0
GROUNDHOG: Grounding Large Language Models to Holistic Segmentation—0
Hierarchical Alignment-enhanced Adaptive Grounding Network for Generalized Referring Expression Comprehension—0
Refer to Anything with Vision-Language Prompts—0
Instance-Aware Generalized Referring Expression Segmentation—0
Show:102550

No leaderboard results yet.