SOTAVerified

Referring Expression

Referring expressions places a bounding box around the instance corresponding to the provided description and image.

Papers

Showing 1120 of 364 papers

TitleStatusHype
TextRegion: Text-Aligned Region Tokens from Frozen Image-Text ModelsCode2
Revisiting Referring Expression Comprehension Evaluation in the Era of Large Multimodal ModelsCode2
Elysium: Exploring Object-level Perception in Videos via MLLMCode2
NExT-Chat: An LMM for Chat, Detection and SegmentationCode2
Decoupling Static and Hierarchical Motion Perception for Referring Video SegmentationCode2
GRES: Generalized Referring Expression SegmentationCode2
GroundingSuite: Measuring Complex Multi-Granular Pixel GroundingCode2
GLaMM: Pixel Grounding Large Multimodal ModelCode2
F-LMM: Grounding Frozen Large Multimodal ModelsCode2
GREC: Generalized Referring Expression ComprehensionCode2
Show:102550
← PrevPage 2 of 37Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1RandomAcc@0.5m14.6Unverified