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 51–75 of 364 papers

TitleStatusHype
GSVA: Generalized Segmentation via Multimodal Large Language ModelsCode1
Unveiling Parts Beyond Objects:Towards Finer-Granularity Referring Expression SegmentationCode1
Zero-shot Referring Expression Comprehension via Structural Similarity Between Images and CaptionsCode1
GENOME: GenerativE Neuro-symbOlic visual reasoning by growing and reusing ModulEsCode1
Pink: Unveiling the Power of Referential Comprehension for Multi-modal LLMsCode1
3D-STMN: Dependency-Driven Superpoint-Text Matching Network for End-to-End 3D Referring Expression SegmentationCode1
A Unified Framework for 3D Point Cloud Visual GroundingCode1
RefEgo: Referring Expression Comprehension Dataset from First-Person Perception of Ego4DCode1
March in Chat: Interactive Prompting for Remote Embodied Referring ExpressionCode1
Described Object Detection: Liberating Object Detection with Flexible ExpressionsCode1
RefSAM: Efficiently Adapting Segmenting Anything Model for Referring Video Object SegmentationCode1
Kosmos-2: Grounding Multimodal Large Language Models to the WorldCode1
Advancing Referring Expression Segmentation Beyond Single ImageCode1
Zero-shot Referring Image Segmentation with Global-Local Context FeaturesCode1
NS3D: Neuro-Symbolic Grounding of 3D Objects and RelationsCode1
Layout-aware Dreamer for Embodied Referring Expression GroundingCode1
TOIST: Task Oriented Instance Segmentation Transformer with Noun-Pronoun DistillationCode1
SQA3D: Situated Question Answering in 3D ScenesCode1
VoLTA: Vision-Language Transformer with Weakly-Supervised Local-Feature AlignmentCode1
Learning to Evaluate Performance of Multi-modal Semantic LocalizationCode1
Correspondence Matters for Video Referring Expression ComprehensionCode1
Improving Visual Grounding by Encouraging Consistent Gradient-based ExplanationsCode1
PEVL: Position-enhanced Pre-training and Prompt Tuning for Vision-language ModelsCode1
GRIT: General Robust Image Task BenchmarkCode1
A Survivor in the Era of Large-Scale Pretraining: An Empirical Study of One-Stage Referring Expression ComprehensionCode1
Show:102550
← PrevPage 3 of 15Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1RandomAcc@0.5m14.6—Unverified