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 51–60 of 364 papers

TitleStatusHype
LLM-wrapper: Black-Box Semantic-Aware Adaptation of Vision-Language Models for Referring Expression ComprehensionCode1
MDETR -- Modulated Detection for End-to-End Multi-Modal UnderstandingCode1
DetToolChain: A New Prompting Paradigm to Unleash Detection Ability of MLLMCode1
Graph-Structured Referring Expression Reasoning in The WildCode1
Discriminative Triad Matching and Reconstruction for Weakly Referring Expression GroundingCode1
Kosmos-2: Grounding Multimodal Large Language Models to the WorldCode1
Relationship-Embedded Representation Learning for Grounding Referring ExpressionsCode1
Airbert: In-domain Pretraining for Vision-and-Language NavigationCode1
GSVA: Generalized Segmentation via Multimodal Large Language ModelsCode1
Iterative Shrinking for Referring Expression Grounding Using Deep Reinforcement LearningCode1
Show:102550
← PrevPage 6 of 37Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1RandomAcc@0.5m14.6—Unverified