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 81–90 of 364 papers

TitleStatusHype
Talk2Radar: Bridging Natural Language with 4D mmWave Radar for 3D Referring Expression ComprehensionCode1
Adversarial Robustness for Visual Grounding of Multimodal Large Language ModelsCode0
Transcrib3D: 3D Referring Expression Resolution through Large Language Models—0
Resilience through Scene Context in Visual Referring Expression GenerationCode0
Decoupling Static and Hierarchical Motion Perception for Referring Video SegmentationCode2
Text-driven Affordance Learning from Egocentric Vision—0
SUGAR: Pre-training 3D Visual Representations for Robotics—0
PropTest: Automatic Property Testing for Improved Visual Programming—0
Elysium: Exploring Object-level Perception in Videos via MLLMCode2
PSALM: Pixelwise SegmentAtion with Large Multi-Modal ModelCode3
Show:102550
← PrevPage 9 of 37Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1RandomAcc@0.5m14.6—Unverified