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 31–40 of 364 papers

TitleStatusHype
Exploring Spatial Language Grounding Through Referring Expressions—0
RefDrone: A Challenging Benchmark for Referring Expression Comprehension in Drone ScenesCode1
NAVER: A Neuro-Symbolic Compositional Automaton for Visual Grounding with Explicit Logic ReasoningCode1
Implicit Causality-biases in humans and LLMs as a tool for benchmarking LLM discourse capabilities—0
FLORA: Formal Language Model Enables Robust Training-free Zero-shot Object Referring Analysis—0
Omni-RGPT: Unifying Image and Video Region-level Understanding via Token Marks—0
Multi-task Visual Grounding with Coarse-to-Fine Consistency ConstraintsCode1
IPDN: Image-enhanced Prompt Decoding Network for 3D Referring Expression SegmentationCode1
Hierarchical Alignment-enhanced Adaptive Grounding Network for Generalized Referring Expression Comprehension—0
Exploring Contextual Attribute Density in Referring Expression CountingCode1
Show:102550
← PrevPage 4 of 37Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1RandomAcc@0.5m14.6—Unverified