SOTAVerified

Referring Expression

Referring expressions places a bounding box around the instance corresponding to the provided description and image.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–25 of 364 papers

TitleStatusHype
Mask-aware Text-to-Image Retrieval: Referring Expression Segmentation Meets Cross-modal Retrieval—0
Detecting Referring Expressions in Visually Grounded Dialogue with Autoregressive Language ModelsCode0
Referring Expression Instance Retrieval and A Strong End-to-End Baseline—0
Gondola: Grounded Vision Language Planning for Generalizable Robotic Manipulation—0
Synthetic Visual Genome—0
Refer to Anything with Vision-Language Prompts—0
From Objects to Anywhere: A Holistic Benchmark for Multi-level Visual Grounding in 3D Scenes—0
Rex-Thinker: Grounded Object Referring via Chain-of-Thought Reasoning—0
RefEdit: A Benchmark and Method for Improving Instruction-based Image Editing Model on Referring Expressions—0
TextRegion: Text-Aligned Region Tokens from Frozen Image-Text ModelsCode2
Improving Contrastive Learning for Referring Expression CountingCode0
Deformable Attentive Visual Enhancement for Referring Segmentation Using Vision-Language Model—0
WeakMCN: Multi-task Collaborative Network for Weakly Supervised Referring Expression Comprehension and SegmentationCode0
RemoteSAM: Towards Segment Anything for Earth ObservationCode3
Learning to Reason and Navigate: Parameter Efficient Action Planning with Large Language Models—0
RESAnything: Attribute Prompting for Arbitrary Referring Segmentation—0
Vision-Language Models Are Not Pragmatically Competent in Referring Expression GenerationCode0
LGD: Leveraging Generative Descriptions for Zero-Shot Referring Image Segmentation—0
3DResT: A Strong Baseline for Semi-Supervised 3D Referring Expression Segmentation—0
Towards Unified Referring Expression Segmentation Across Omni-Level Visual Target GranularitiesCode0
4th PVUW MeViS 3rd Place Report: Sa2VACode5
MB-ORES: A Multi-Branch Object Reasoner for Visual Grounding in Remote SensingCode0
Beyond Object Categories: Multi-Attribute Reference Understanding for Visual Grounding—0
Exploring Contextual Attribute Density in Referring Expression CountingCode1
GeoRSMLLM: A Multimodal Large Language Model for Vision-Language Tasks in Geoscience and Remote Sensing—0
Show:102550
← PrevPage 1 of 15Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1RandomAcc@0.5m14.6—Unverified