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 171–180 of 364 papers

TitleStatusHype
Entity-enhanced Adaptive Reconstruction Network for Weakly Supervised Referring Expression GroundingCode0
Improving Visual Grounding by Encouraging Consistent Gradient-based ExplanationsCode1
Unified-IO: A Unified Model for Vision, Language, and Multi-Modal Tasks—0
RefCrowd: Grounding the Target in Crowd with Referring Expressions—0
Constructing Distributions of Variation in Referring Expression Type from Corpora for Model Evaluation—0
PEVL: Position-enhanced Pre-training and Prompt Tuning for Vision-language ModelsCode1
Referring Expressions with Rational Speech Act Framework: A Probabilistic Approach—0
Weakly-supervised segmentation of referring expressions—0
HOLM: Hallucinating Objects with Language Models for Referring Expression Recognition in Partially-Observed Scenes—0
GRIT: General Robust Image Task BenchmarkCode1
Show:102550
← PrevPage 18 of 37Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1RandomAcc@0.5m14.6—Unverified