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 1–10 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
Show:102550
← PrevPage 1 of 37Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1RandomAcc@0.5m14.6—Unverified